From 334ef7a7ab8f80b689a2be95d5e62d2167900865 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 12 May 2008 21:21:13 +0200 Subject: x86: use performance variant for_each_cpu_mask_nr Change references from for_each_cpu_mask to for_each_cpu_mask_nr where appropriate Reviewed-by: Paul Jackson Reviewed-by: Christoph Lameter Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner commit 2d474871e2fb092eb46a0930aba5442e10eb96cc Author: Mike Travis Date: Mon May 12 21:21:13 2008 +0200 --- include/asm-x86/ipi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h index ecc80f341f37..5f7310aa3efd 100644 --- a/include/asm-x86/ipi.h +++ b/include/asm-x86/ipi.h @@ -121,7 +121,7 @@ static inline void send_IPI_mask_sequence(cpumask_t mask, int vector) * - mbligh */ local_irq_save(flags); - for_each_cpu_mask(query_cpu, mask) { + for_each_cpu_mask_nr(query_cpu, mask) { __send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu), vector, APIC_DEST_PHYSICAL); } -- cgit v1.2.3 From 94a1e869c7b96a9d30e260084866383a145fd8ae Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 18 Jul 2008 18:11:31 -0700 Subject: NR_CPUS: Replace per_cpu(..., smp_processor_id()) with __get_cpu_var * Slight optimization when getting one's own cpu_info percpu data. Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/asm-x86/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h index 55402d2ab938..f92315ed68e1 100644 --- a/include/asm-x86/processor.h +++ b/include/asm-x86/processor.h @@ -134,7 +134,7 @@ extern __u32 cleared_cpu_caps[NCAPINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) -#define current_cpu_data cpu_data(smp_processor_id()) +#define current_cpu_data __get_cpu_var(cpu_info) #else #define cpu_data(cpu) boot_cpu_data #define current_cpu_data boot_cpu_data -- cgit v1.2.3 From 31656519e132f6612584815f128c83976a9aaaef Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 18 Jul 2008 18:01:23 +0200 Subject: sched, x86: clean up hrtick implementation random uvesafb failures were reported against Gentoo: http://bugs.gentoo.org/show_bug.cgi?id=222799 and Mihai Moldovan bisected it back to: > 8f4d37ec073c17e2d4aa8851df5837d798606d6f is first bad commit > commit 8f4d37ec073c17e2d4aa8851df5837d798606d6f > Author: Peter Zijlstra > Date: Fri Jan 25 21:08:29 2008 +0100 > > sched: high-res preemption tick Linus suspected it to be hrtick + vm86 interaction and observed: > Btw, Peter, Ingo: I think that commit is doing bad things. They aren't > _incorrect_ per se, but they are definitely bad. > > Why? > > Using random _TIF_WORK_MASK flags is really impolite for doing > "scheduling" work. There's a reason that arch/x86/kernel/entry_32.S > special-cases the _TIF_NEED_RESCHED flag: we don't want to exit out of > vm86 mode unnecessarily. > > See the "work_notifysig_v86" label, and how it does that > "save_v86_state()" thing etc etc. Right, I never liked having to fiddle with those TIF flags. Initially I needed it because the hrtimer base lock could not nest in the rq lock. That however is fixed these days. Currently the only reason left to fiddle with the TIF flags is remote wakeups. We cannot program a remote cpu's hrtimer. I've been thinking about using the new and improved IPI function call stuff to implement hrtimer_start_on(). However that does require that smp_call_function_single(.wait=0) works from interrupt context - /me looks at the latest series from Jens - Yes that does seem to be supported, good. Here's a stab at cleaning this stuff up ... Mihai reported test success as well. Signed-off-by: Peter Zijlstra Tested-by: Mihai Moldovan Cc: Michal Januszewski Cc: Antonino Daplas Signed-off-by: Ingo Molnar --- arch/x86/kernel/signal_32.c | 3 - arch/x86/kernel/signal_64.c | 3 - include/asm-x86/thread_info.h | 4 +- kernel/Kconfig.hz | 2 +- kernel/sched.c | 202 +++++++++++++----------------------------- kernel/sched_fair.c | 5 +- 6 files changed, 64 insertions(+), 155 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index d92373630963..e1fc7bd57bfe 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -667,8 +667,5 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); - if (thread_info_flags & _TIF_HRTICK_RESCHED) - hrtick_resched(); - clear_thread_flag(TIF_IRET); } diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index e53b267662e7..88023fcc7049 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -502,9 +502,6 @@ void do_notify_resume(struct pt_regs *regs, void *unused, /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); - - if (thread_info_flags & _TIF_HRTICK_RESCHED) - hrtick_resched(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h index 895339d2bc0b..d7012634ace4 100644 --- a/include/asm-x86/thread_info.h +++ b/include/asm-x86/thread_info.h @@ -81,7 +81,6 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ -#define TIF_HRTICK_RESCHED 11 /* reprogram hrtick timer */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ @@ -108,7 +107,6 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) -#define _TIF_HRTICK_RESCHED (1 << TIF_HRTICK_RESCHED) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) @@ -132,7 +130,7 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED) + (_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz index 526128a2e622..2a202a846757 100644 --- a/kernel/Kconfig.hz +++ b/kernel/Kconfig.hz @@ -55,4 +55,4 @@ config HZ default 1000 if HZ_1000 config SCHED_HRTICK - def_bool HIGH_RES_TIMERS && X86 + def_bool HIGH_RES_TIMERS diff --git a/kernel/sched.c b/kernel/sched.c index 1ee18dbb4516..c13c75e9f9f7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -571,8 +571,10 @@ struct rq { #endif #ifdef CONFIG_SCHED_HRTICK - unsigned long hrtick_flags; - ktime_t hrtick_expire; +#ifdef CONFIG_SMP + int hrtick_csd_pending; + struct call_single_data hrtick_csd; +#endif struct hrtimer hrtick_timer; #endif @@ -983,13 +985,6 @@ static struct rq *this_rq_lock(void) return rq; } -static void __resched_task(struct task_struct *p, int tif_bit); - -static inline void resched_task(struct task_struct *p) -{ - __resched_task(p, TIF_NEED_RESCHED); -} - #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -1001,25 +996,6 @@ static inline void resched_task(struct task_struct *p) * When we get rescheduled we reprogram the hrtick_timer outside of the * rq->lock. */ -static inline void resched_hrt(struct task_struct *p) -{ - __resched_task(p, TIF_HRTICK_RESCHED); -} - -static inline void resched_rq(struct rq *rq) -{ - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - resched_task(rq->curr); - spin_unlock_irqrestore(&rq->lock, flags); -} - -enum { - HRTICK_SET, /* re-programm hrtick_timer */ - HRTICK_RESET, /* not a new slice */ - HRTICK_BLOCK, /* stop hrtick operations */ -}; /* * Use hrtick when: @@ -1030,72 +1006,17 @@ static inline int hrtick_enabled(struct rq *rq) { if (!sched_feat(HRTICK)) return 0; - if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags))) + if (!cpu_online(cpu_of(rq))) return 0; return hrtimer_is_hres_active(&rq->hrtick_timer); } -/* - * Called to set the hrtick timer state. - * - * called with rq->lock held and irqs disabled - */ -static void hrtick_start(struct rq *rq, u64 delay, int reset) -{ - assert_spin_locked(&rq->lock); - - /* - * preempt at: now + delay - */ - rq->hrtick_expire = - ktime_add_ns(rq->hrtick_timer.base->get_time(), delay); - /* - * indicate we need to program the timer - */ - __set_bit(HRTICK_SET, &rq->hrtick_flags); - if (reset) - __set_bit(HRTICK_RESET, &rq->hrtick_flags); - - /* - * New slices are called from the schedule path and don't need a - * forced reschedule. - */ - if (reset) - resched_hrt(rq->curr); -} - static void hrtick_clear(struct rq *rq) { if (hrtimer_active(&rq->hrtick_timer)) hrtimer_cancel(&rq->hrtick_timer); } -/* - * Update the timer from the possible pending state. - */ -static void hrtick_set(struct rq *rq) -{ - ktime_t time; - int set, reset; - unsigned long flags; - - WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); - - spin_lock_irqsave(&rq->lock, flags); - set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags); - reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags); - time = rq->hrtick_expire; - clear_thread_flag(TIF_HRTICK_RESCHED); - spin_unlock_irqrestore(&rq->lock, flags); - - if (set) { - hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS); - if (reset && !hrtimer_active(&rq->hrtick_timer)) - resched_rq(rq); - } else - hrtick_clear(rq); -} - /* * High-resolution timer tick. * Runs from hardirq context with interrupts disabled. @@ -1115,27 +1036,37 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) } #ifdef CONFIG_SMP -static void hotplug_hrtick_disable(int cpu) +/* + * called from hardirq (IPI) context + */ +static void __hrtick_start(void *arg) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - rq->hrtick_flags = 0; - __set_bit(HRTICK_BLOCK, &rq->hrtick_flags); - spin_unlock_irqrestore(&rq->lock, flags); + struct rq *rq = arg; - hrtick_clear(rq); + spin_lock(&rq->lock); + hrtimer_restart(&rq->hrtick_timer); + rq->hrtick_csd_pending = 0; + spin_unlock(&rq->lock); } -static void hotplug_hrtick_enable(int cpu) +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +static void hrtick_start(struct rq *rq, u64 delay) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = ktime_add_ns(timer->base->get_time(), delay); - spin_lock_irqsave(&rq->lock, flags); - __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags); - spin_unlock_irqrestore(&rq->lock, flags); + timer->expires = time; + + if (rq == this_rq()) { + hrtimer_restart(timer); + } else if (!rq->hrtick_csd_pending) { + __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd); + rq->hrtick_csd_pending = 1; + } } static int @@ -1150,16 +1081,7 @@ hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DOWN_PREPARE_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - hotplug_hrtick_disable(cpu); - return NOTIFY_OK; - - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - hotplug_hrtick_enable(cpu); + hrtick_clear(cpu_rq(cpu)); return NOTIFY_OK; } @@ -1170,46 +1092,45 @@ static void init_hrtick(void) { hotcpu_notifier(hotplug_hrtick, 0); } -#endif /* CONFIG_SMP */ +#else +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +static void hrtick_start(struct rq *rq, u64 delay) +{ + hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL); +} -static void init_rq_hrtick(struct rq *rq) +static void init_hrtick(void) { - rq->hrtick_flags = 0; - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rq->hrtick_timer.function = hrtick; - rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } +#endif /* CONFIG_SMP */ -void hrtick_resched(void) +static void init_rq_hrtick(struct rq *rq) { - struct rq *rq; - unsigned long flags; +#ifdef CONFIG_SMP + rq->hrtick_csd_pending = 0; - if (!test_thread_flag(TIF_HRTICK_RESCHED)) - return; + rq->hrtick_csd.flags = 0; + rq->hrtick_csd.func = __hrtick_start; + rq->hrtick_csd.info = rq; +#endif - local_irq_save(flags); - rq = cpu_rq(smp_processor_id()); - hrtick_set(rq); - local_irq_restore(flags); + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; + rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } #else static inline void hrtick_clear(struct rq *rq) { } -static inline void hrtick_set(struct rq *rq) -{ -} - static inline void init_rq_hrtick(struct rq *rq) { } -void hrtick_resched(void) -{ -} - static inline void init_hrtick(void) { } @@ -1228,16 +1149,16 @@ static inline void init_hrtick(void) #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) #endif -static void __resched_task(struct task_struct *p, int tif_bit) +static void resched_task(struct task_struct *p) { int cpu; assert_spin_locked(&task_rq(p)->lock); - if (unlikely(test_tsk_thread_flag(p, tif_bit))) + if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) return; - set_tsk_thread_flag(p, tif_bit); + set_tsk_thread_flag(p, TIF_NEED_RESCHED); cpu = task_cpu(p); if (cpu == smp_processor_id()) @@ -1303,10 +1224,10 @@ void wake_up_idle_cpu(int cpu) #endif /* CONFIG_NO_HZ */ #else /* !CONFIG_SMP */ -static void __resched_task(struct task_struct *p, int tif_bit) +static void resched_task(struct task_struct *p) { assert_spin_locked(&task_rq(p)->lock); - set_tsk_thread_flag(p, tif_bit); + set_tsk_need_resched(p); } #endif /* CONFIG_SMP */ @@ -4395,7 +4316,7 @@ asmlinkage void __sched schedule(void) struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; - int cpu, hrtick = sched_feat(HRTICK); + int cpu; need_resched: preempt_disable(); @@ -4410,7 +4331,7 @@ need_resched_nonpreemptible: schedule_debug(prev); - if (hrtick) + if (sched_feat(HRTICK)) hrtick_clear(rq); /* @@ -4457,9 +4378,6 @@ need_resched_nonpreemptible: } else spin_unlock_irq(&rq->lock); - if (hrtick) - hrtick_set(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) goto need_resched_nonpreemptible; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f2aa987027d6..6893b3ed65fe 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -878,7 +878,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) #ifdef CONFIG_SCHED_HRTICK static void hrtick_start_fair(struct rq *rq, struct task_struct *p) { - int requeue = rq->curr == p; struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -899,10 +898,10 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) * Don't schedule slices shorter than 10000ns, that just * doesn't make sense. Rely on vruntime for fairness. */ - if (!requeue) + if (rq->curr != p) delta = max(10000LL, delta); - hrtick_start(rq, delta, requeue); + hrtick_start(rq, delta); } } #else /* !CONFIG_SCHED_HRTICK */ -- cgit v1.2.3 From c2e3277f875b83e5adc34e96989d6d87ec5f80f7 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 22 Jul 2008 15:40:46 +1000 Subject: x86: fix pte_flags() to only return flags, fix lguest (updated) (Jeremy said: rusty: use PTE_MASK rusty: use PTE_MASK rusty: use PTE_MASK When I asked: jsgf: does that include the NX flag? He responded eloquently: rusty: use PTE_MASK rusty: use PTE_MASK yes, it's the official constant of masking flags out of ptes ) Change a15af1c9ea2750a9ff01e51615c45950bad8221b 'x86/paravirt: add pte_flags to just get pte flags' removed lguest's private pte_flags() in favor of a generic one. Unfortunately, the generic one doesn't filter out the non-flags bits: this results in lguest creating corrupt shadow page tables and blowing up host memory. Since noone is supposed to use the pfn part of pte_flags(), it seems safest to always do the filtering. Signed-off-by: Rusty Russell Acked-by: Jeremy Fitzhardinge Signed-off-and-morning-tea-spilled-by: Ingo Molnar --- arch/x86/kernel/paravirt.c | 2 +- include/asm-x86/page.h | 7 ++++++- include/asm-x86/paravirt.h | 3 +++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 097d8a6797fa..94da4d52d798 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -443,7 +443,7 @@ struct pv_mmu_ops pv_mmu_ops = { #endif /* PAGETABLE_LEVELS >= 3 */ .pte_val = native_pte_val, - .pte_flags = native_pte_val, + .pte_flags = native_pte_flags, .pgd_val = native_pgd_val, .make_pte = native_make_pte, diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 28d7b4533b1a..05d9bea2bfd5 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -144,6 +144,11 @@ static inline pteval_t native_pte_val(pte_t pte) return pte.pte; } +static inline pteval_t native_pte_flags(pte_t pte) +{ + return native_pte_val(pte) & ~PTE_MASK; +} + #define pgprot_val(x) ((x).pgprot) #define __pgprot(x) ((pgprot_t) { (x) } ) @@ -165,7 +170,7 @@ static inline pteval_t native_pte_val(pte_t pte) #endif #define pte_val(x) native_pte_val(x) -#define pte_flags(x) native_pte_val(x) +#define pte_flags(x) native_pte_flags(x) #define __pte(x) native_make_pte(x) #endif /* CONFIG_PARAVIRT */ diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h index aec9767836b6..5ca4639dc7dd 100644 --- a/include/asm-x86/paravirt.h +++ b/include/asm-x86/paravirt.h @@ -1088,6 +1088,9 @@ static inline pteval_t pte_flags(pte_t pte) ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags, pte.pte); +#ifdef CONFIG_PARAVIRT_DEBUG + BUG_ON(ret & PTE_MASK); +#endif return ret; } -- cgit v1.2.3 From 59438c9fc4f7a92c808c9049bc6b396f98bf954c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 21 Jul 2008 22:59:42 -0700 Subject: x86: rename PTE_MASK to PTE_PFN_MASK Rusty, in his peevish way, complained that macros defining constants should have a name which somewhat accurately reflects the actual purpose of the constant. Aside from the fact that PTE_MASK gives no clue as to what's actually being masked, and is misleadingly similar to the functionally entirely different PMD_MASK, PUD_MASK and PGD_MASK, I don't really see what the problem is. But if this patch silences the incessent noise, then it will have achieved its goal (TODO: write test-case). Signed-off-by: Jeremy Fitzhardinge Cc: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/mm/dump_pagetables.c | 10 +++++----- arch/x86/xen/enlighten.c | 2 +- arch/x86/xen/mmu.c | 8 ++++---- include/asm-x86/page.h | 6 +++--- include/asm-x86/paravirt.h | 2 +- include/asm-x86/pgtable-3level.h | 8 ++++---- include/asm-x86/pgtable.h | 4 ++-- include/asm-x86/pgtable_32.h | 4 ++-- include/asm-x86/pgtable_64.h | 10 +++++----- include/asm-x86/xen/page.h | 2 +- 10 files changed, 28 insertions(+), 28 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0bb0caed8971..cc174fc412bc 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -148,8 +148,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot) & ~(PTE_MASK); - cur = pgprot_val(st->current_prot) & ~(PTE_MASK); + prot = pgprot_val(new_prot) & ~(PTE_PFN_MASK); + cur = pgprot_val(st->current_prot) & ~(PTE_PFN_MASK); if (!st->level) { /* First entry */ @@ -221,7 +221,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & ~PTE_MASK; + pgprotval_t prot = pmd_val(*start) & ~PTE_PFN_MASK; if (pmd_large(*start) || !pmd_present(*start)) note_page(m, st, __pgprot(prot), 3); @@ -253,7 +253,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & ~PTE_MASK; + pgprotval_t prot = pud_val(*start) & ~PTE_PFN_MASK; if (pud_large(*start) || !pud_present(*start)) note_page(m, st, __pgprot(prot), 2); @@ -288,7 +288,7 @@ static void walk_pgd_level(struct seq_file *m) for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & ~PTE_MASK; + pgprotval_t prot = pgd_val(*start) & ~PTE_PFN_MASK; if (pgd_large(*start) || !pgd_present(*start)) note_page(m, &st, __pgprot(prot), 1); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 194bbd6e3241..9ff6e3cbf08f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1435,7 +1435,7 @@ static unsigned long m2p(phys_addr_t maddr) { phys_addr_t paddr; - maddr &= PTE_MASK; + maddr &= PTE_PFN_MASK; paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT; return paddr; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index a44d56e38bd1..0db6912395ed 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -343,8 +343,8 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { - unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT; - pteval_t flags = val & ~PTE_MASK; + unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_PFN_MASK; val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; } @@ -354,8 +354,8 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) static pteval_t pte_pfn_to_mfn(pteval_t val) { if (val & _PAGE_PRESENT) { - unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT; - pteval_t flags = val & ~PTE_MASK; + unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_PFN_MASK; val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags; } diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 05d9bea2bfd5..e99fb9fe6f8a 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -18,8 +18,8 @@ (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) -/* PTE_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ -#define PTE_MASK ((pteval_t)PHYSICAL_PAGE_MASK) +/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ +#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) #define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) @@ -146,7 +146,7 @@ static inline pteval_t native_pte_val(pte_t pte) static inline pteval_t native_pte_flags(pte_t pte) { - return native_pte_val(pte) & ~PTE_MASK; + return native_pte_val(pte) & ~PTE_PFN_MASK; } #define pgprot_val(x) ((x).pgprot) diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h index 5ca4639dc7dd..fbbde93f12d6 100644 --- a/include/asm-x86/paravirt.h +++ b/include/asm-x86/paravirt.h @@ -1089,7 +1089,7 @@ static inline pteval_t pte_flags(pte_t pte) pte.pte); #ifdef CONFIG_PARAVIRT_DEBUG - BUG_ON(ret & PTE_MASK); + BUG_ON(ret & PTE_PFN_MASK); #endif return ret; } diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h index c93dbb6c2624..105057f34032 100644 --- a/include/asm-x86/pgtable-3level.h +++ b/include/asm-x86/pgtable-3level.h @@ -25,7 +25,7 @@ static inline int pud_none(pud_t pud) static inline int pud_bad(pud_t pud) { - return (pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0; + return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0; } static inline int pud_present(pud_t pud) @@ -120,9 +120,9 @@ static inline void pud_clear(pud_t *pudp) write_cr3(pgd); } -#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_MASK)) +#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK)) -#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_MASK)) +#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK)) /* Find an entry in the second-level page table.. */ @@ -160,7 +160,7 @@ static inline int pte_none(pte_t pte) static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) & PTE_MASK) >> PAGE_SHIFT; + return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT; } /* diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index 96aa76e691d8..2b1746c92370 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -53,7 +53,7 @@ _PAGE_DIRTY) /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_PCD | _PAGE_PWT | \ +#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_ACCESSED | _PAGE_DIRTY) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) @@ -286,7 +286,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) return __pgprot(preservebits | addbits); } -#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_MASK) +#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_PFN_MASK) #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h index 0611abf96a5e..525b53e65b44 100644 --- a/include/asm-x86/pgtable_32.h +++ b/include/asm-x86/pgtable_32.h @@ -88,7 +88,7 @@ extern unsigned long pg0[]; /* To avoid harmful races, pmd_none(x) should check only the lower when PAE */ #define pmd_none(x) (!(unsigned long)pmd_val((x))) #define pmd_present(x) (pmd_val((x)) & _PAGE_PRESENT) -#define pmd_bad(x) ((pmd_val(x) & (~PTE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) +#define pmd_bad(x) ((pmd_val(x) & (~PTE_PFN_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) #define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) @@ -139,7 +139,7 @@ static inline int pud_large(pud_t pud) { return 0; } #define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT)) #define pmd_page_vaddr(pmd) \ - ((unsigned long)__va(pmd_val((pmd)) & PTE_MASK)) + ((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK)) #if defined(CONFIG_HIGHPTE) #define pte_offset_map(dir, address) \ diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h index 805d3128bfc4..ac5fff4cc58a 100644 --- a/include/asm-x86/pgtable_64.h +++ b/include/asm-x86/pgtable_64.h @@ -158,17 +158,17 @@ static inline void native_pgd_clear(pgd_t *pgd) static inline int pgd_bad(pgd_t pgd) { - return (pgd_val(pgd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE; + return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE; } static inline int pud_bad(pud_t pud) { - return (pud_val(pud) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE; + return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE; } static inline int pmd_bad(pmd_t pmd) { - return (pmd_val(pmd) & ~(PTE_MASK | _PAGE_USER)) != _KERNPG_TABLE; + return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE; } #define pte_none(x) (!pte_val((x))) @@ -193,7 +193,7 @@ static inline int pmd_bad(pmd_t pmd) * Level 4 access. */ #define pgd_page_vaddr(pgd) \ - ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_MASK)) + ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK)) #define pgd_page(pgd) (pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT)) #define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT) static inline int pgd_large(pgd_t pgd) { return 0; } @@ -216,7 +216,7 @@ static inline int pud_large(pud_t pte) } /* PMD - Level 2 access */ -#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_MASK)) +#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK)) #define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h index 05e678a86628..7b3835d3b77d 100644 --- a/include/asm-x86/xen/page.h +++ b/include/asm-x86/xen/page.h @@ -124,7 +124,7 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) static inline unsigned long pte_mfn(pte_t pte) { - return (pte.pte & PTE_MASK) >> PAGE_SHIFT; + return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) -- cgit v1.2.3 From 77be1fabd024b37423d12f832b1fbdb95dbdf494 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 21 Jul 2008 22:59:56 -0700 Subject: x86: add PTE_FLAGS_MASK PTE_PFN_MASK was getting lonely, so I made it a friend. Signed-off-by: Jeremy Fitzhardinge Cc: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/mm/dump_pagetables.c | 6 +++--- arch/x86/xen/mmu.c | 4 ++-- include/asm-x86/page.h | 5 ++++- include/asm-x86/pgtable.h | 2 +- include/asm-x86/pgtable_32.h | 2 +- 5 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index cc174fc412bc..a20d1fa64b4e 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -221,7 +221,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & ~PTE_PFN_MASK; + pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK; if (pmd_large(*start) || !pmd_present(*start)) note_page(m, st, __pgprot(prot), 3); @@ -253,7 +253,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & ~PTE_PFN_MASK; + pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK; if (pud_large(*start) || !pud_present(*start)) note_page(m, st, __pgprot(prot), 2); @@ -288,7 +288,7 @@ static void walk_pgd_level(struct seq_file *m) for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & ~PTE_PFN_MASK; + pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK; if (pgd_large(*start) || !pgd_present(*start)) note_page(m, &st, __pgprot(prot), 1); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 0db6912395ed..aa37469da696 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -344,7 +344,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; - pteval_t flags = val & ~PTE_PFN_MASK; + pteval_t flags = val & PTE_FLAGS_MASK; val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; } @@ -355,7 +355,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) { if (val & _PAGE_PRESENT) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; - pteval_t flags = val & ~PTE_PFN_MASK; + pteval_t flags = val & PTE_FLAGS_MASK; val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags; } diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index e99fb9fe6f8a..6c846228948d 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -21,6 +21,9 @@ /* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ #define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) +/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */ +#define PTE_FLAGS_MASK (~PTE_PFN_MASK) + #define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) @@ -146,7 +149,7 @@ static inline pteval_t native_pte_val(pte_t pte) static inline pteval_t native_pte_flags(pte_t pte) { - return native_pte_val(pte) & ~PTE_PFN_MASK; + return native_pte_val(pte) & PTE_FLAGS_MASK; } #define pgprot_val(x) ((x).pgprot) diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index 2b1746c92370..3e5dbc4195f4 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -286,7 +286,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) return __pgprot(preservebits | addbits); } -#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_PFN_MASK) +#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK) #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h index 525b53e65b44..5c3b26567a95 100644 --- a/include/asm-x86/pgtable_32.h +++ b/include/asm-x86/pgtable_32.h @@ -88,7 +88,7 @@ extern unsigned long pg0[]; /* To avoid harmful races, pmd_none(x) should check only the lower when PAE */ #define pmd_none(x) (!(unsigned long)pmd_val((x))) #define pmd_present(x) (pmd_val((x)) & _PAGE_PRESENT) -#define pmd_bad(x) ((pmd_val(x) & (~PTE_PFN_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) +#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) #define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) -- cgit v1.2.3 From 04bbe430f73c6c31bbd067349c029e907e153a8d Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Mon, 21 Jul 2008 15:06:35 +0200 Subject: x86: fix header export, asm-x86/processor-flags.h, CONFIG_* leaks Apparently, commit 6330a30a76c1e62d4b4ec238368957f8febf9113 Author: Vegard Nossum Date: Wed May 28 09:46:19 2008 +0200 x86: break mutual header inclusion introduced some CONFIG names to processor-flags.h, which was exported in commit 6093015db2bd9e70cf20cdd23be1a50733baafdd Author: Ingo Molnar Date: Sun Mar 30 11:45:23 2008 +0200 x86: cleanup replace most vm86 flags with flags from processor-flags.h, fix Fix it by wrapping the CONFIG parts in __KERNEL__. Reported-by: Olaf Hering Signed-off-by: Vegard Nossum Cc: Adrian Bunk Cc: Olaf Hering Signed-off-by: Ingo Molnar --- include/asm-x86/processor-flags.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h index 092b39b3a7e6..eff2ecd7fff0 100644 --- a/include/asm-x86/processor-flags.h +++ b/include/asm-x86/processor-flags.h @@ -88,10 +88,12 @@ #define CX86_ARR_BASE 0xc4 #define CX86_RCR_BASE 0xdc +#ifdef __KERNEL__ #ifdef CONFIG_VM86 #define X86_VM_MASK X86_EFLAGS_VM #else #define X86_VM_MASK 0 /* No VM86 support */ #endif +#endif #endif /* __ASM_I386_PROCESSOR_FLAGS_H */ -- cgit v1.2.3 From 2351ec533ed0dd56052ab96988d2161d5ecc8ed9 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 24 Jul 2008 08:09:32 -0400 Subject: Remove asm/semaphore.h All users have now been converted to linux/semaphore.h and we don't need to keep these files around any longer. Signed-off-by: Matthew Wilcox --- Documentation/feature-removal-schedule.txt | 8 -------- include/asm-alpha/semaphore.h | 1 - include/asm-arm/semaphore.h | 1 - include/asm-avr32/semaphore.h | 1 - include/asm-blackfin/semaphore.h | 1 - include/asm-cris/semaphore.h | 1 - include/asm-frv/semaphore.h | 1 - include/asm-h8300/semaphore.h | 1 - include/asm-ia64/semaphore.h | 1 - include/asm-m32r/semaphore.h | 1 - include/asm-m68k/semaphore.h | 1 - include/asm-m68knommu/semaphore.h | 1 - include/asm-mips/semaphore.h | 1 - include/asm-mn10300/semaphore.h | 1 - include/asm-parisc/semaphore.h | 1 - include/asm-powerpc/semaphore.h | 1 - include/asm-s390/semaphore.h | 1 - include/asm-sh/semaphore.h | 1 - include/asm-sparc/semaphore.h | 1 - include/asm-sparc64/semaphore.h | 1 - include/asm-um/semaphore.h | 1 - include/asm-v850/semaphore.h | 1 - include/asm-x86/semaphore.h | 1 - include/asm-xtensa/semaphore.h | 1 - 24 files changed, 31 deletions(-) delete mode 100644 include/asm-alpha/semaphore.h delete mode 100644 include/asm-arm/semaphore.h delete mode 100644 include/asm-avr32/semaphore.h delete mode 100644 include/asm-blackfin/semaphore.h delete mode 100644 include/asm-cris/semaphore.h delete mode 100644 include/asm-frv/semaphore.h delete mode 100644 include/asm-h8300/semaphore.h delete mode 100644 include/asm-ia64/semaphore.h delete mode 100644 include/asm-m32r/semaphore.h delete mode 100644 include/asm-m68k/semaphore.h delete mode 100644 include/asm-m68knommu/semaphore.h delete mode 100644 include/asm-mips/semaphore.h delete mode 100644 include/asm-mn10300/semaphore.h delete mode 100644 include/asm-parisc/semaphore.h delete mode 100644 include/asm-powerpc/semaphore.h delete mode 100644 include/asm-s390/semaphore.h delete mode 100644 include/asm-sh/semaphore.h delete mode 100644 include/asm-sparc/semaphore.h delete mode 100644 include/asm-sparc64/semaphore.h delete mode 100644 include/asm-um/semaphore.h delete mode 100644 include/asm-v850/semaphore.h delete mode 100644 include/asm-x86/semaphore.h delete mode 100644 include/asm-xtensa/semaphore.h (limited to 'include/asm-x86') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 9f73587219e8..09c4a1efb8e3 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -300,14 +300,6 @@ Who: ocfs2-devel@oss.oracle.com --------------------------- -What: asm/semaphore.h -When: 2.6.26 -Why: Implementation became generic; users should now include - linux/semaphore.h instead. -Who: Matthew Wilcox - ---------------------------- - What: SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD, SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD When: June 2009 diff --git a/include/asm-alpha/semaphore.h b/include/asm-alpha/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-alpha/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-arm/semaphore.h b/include/asm-arm/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-arm/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-avr32/semaphore.h b/include/asm-avr32/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-avr32/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-blackfin/semaphore.h b/include/asm-blackfin/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-blackfin/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-cris/semaphore.h b/include/asm-cris/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-cris/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-frv/semaphore.h b/include/asm-frv/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-frv/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-h8300/semaphore.h b/include/asm-h8300/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-h8300/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-ia64/semaphore.h b/include/asm-ia64/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-ia64/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m32r/semaphore.h b/include/asm-m32r/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m32r/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m68k/semaphore.h b/include/asm-m68k/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m68k/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m68knommu/semaphore.h b/include/asm-m68knommu/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m68knommu/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mips/semaphore.h b/include/asm-mips/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-mips/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mn10300/semaphore.h b/include/asm-mn10300/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-mn10300/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-parisc/semaphore.h b/include/asm-parisc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-parisc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-powerpc/semaphore.h b/include/asm-powerpc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-powerpc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-s390/semaphore.h b/include/asm-s390/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-s390/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sh/semaphore.h b/include/asm-sh/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-sh/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sparc/semaphore.h b/include/asm-sparc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-sparc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sparc64/semaphore.h b/include/asm-sparc64/semaphore.h deleted file mode 100644 index 39362afde5fe..000000000000 --- a/include/asm-sparc64/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-um/semaphore.h b/include/asm-um/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-um/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-v850/semaphore.h b/include/asm-v850/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-v850/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-x86/semaphore.h b/include/asm-x86/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-x86/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-xtensa/semaphore.h b/include/asm-xtensa/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-xtensa/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include -- cgit v1.2.3 From 28b2ee20c7cba812b6f2ccf6d722cf86d00a84dc Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: access_process_vm device memory infrastructure In order to be able to debug things like the X server and programs using the PPC Cell SPUs, the debugger needs to be able to access device memory through ptrace and /proc/pid/mem. This patch: Add the generic_access_phys access function and put the hooks in place to allow access_process_vm to access device or PPC Cell SPU memory. [riel@redhat.com: Add documentation for the vm_ops->access function] Signed-off-by: Rik van Riel Signed-off-by: Benjamin Herrensmidt Cc: Dave Airlie Cc: Hugh Dickins Cc: Paul Mackerras Cc: Arnd Bergmann Acked-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 7 ++ arch/Kconfig | 3 + arch/x86/Kconfig | 1 + arch/x86/mm/ioremap.c | 8 +++ include/asm-x86/io_32.h | 2 + include/asm-x86/io_64.h | 2 + include/linux/mm.h | 8 +++ mm/memory.c | 131 ++++++++++++++++++++++++++++++++------ 8 files changed, 144 insertions(+), 18 deletions(-) (limited to 'include/asm-x86') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8b22d7d8b991..680fb566b928 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -510,6 +510,7 @@ prototypes: void (*close)(struct vm_area_struct*); int (*fault)(struct vm_area_struct*, struct vm_fault *); int (*page_mkwrite)(struct vm_area_struct *, struct page *); + int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); locking rules: BKL mmap_sem PageLocked(page) @@ -517,6 +518,7 @@ open: no yes close: no yes fault: no yes page_mkwrite: no yes no +access: no yes ->page_mkwrite() is called when a previously read-only page is about to become writeable. The file system is responsible for @@ -525,6 +527,11 @@ taking to lock out truncate, the page range should be verified to be within i_size. The page mapping should also be checked that it is not NULL. + ->access() is called when get_user_pages() fails in +acces_process_vm(), typically used to debug a process through +/proc/pid/mem or ptrace. This function is needed only for +VM_IO | VM_PFNMAP VMAs. + ================================================================================ Dubious stuff diff --git a/arch/Kconfig b/arch/Kconfig index 4d5ebbc1e72b..6093c0be58b0 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -31,6 +31,9 @@ config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES +config HAVE_IOREMAP_PROT + def_bool n + config HAVE_KPROBES def_bool n diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 03980cb04291..b2ddfcf01728 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,6 +21,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24c1d3c30186..016f335bbeea 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, return (void __iomem *)ret; } +void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_prot); + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h index 4df44ed54077..e876d89ac156 100644 --- a/include/asm-x86/io_32.h +++ b/include/asm-x86/io_32.h @@ -110,6 +110,8 @@ static inline void *phys_to_virt(unsigned long address) */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, + unsigned long prot_val); /* * The default ioremap() behavior is non-cached: diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h index ddd8058a5026..22995c5c5adc 100644 --- a/include/asm-x86/io_64.h +++ b/include/asm-x86/io_64.h @@ -175,6 +175,8 @@ extern void early_iounmap(void *addr, unsigned long size); */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, + unsigned long prot_val); /* * The default ioremap() behavior is non-cached: diff --git a/include/linux/mm.h b/include/linux/mm.h index eb815cfc1b35..5c7f8f64f70e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,12 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy @@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) diff --git a/mm/memory.c b/mm/memory.c index 46dbed4b7446..87350321e66f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2751,6 +2751,86 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ +#ifdef CONFIG_HAVE_IOREMAP_PROT +static resource_size_t follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + resource_size_t phys_addr = 0; + struct mm_struct *mm = vma->vm_mm; + + VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP))); + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto no_page_table; + + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto no_page_table; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto no_page_table; + + /* We cannot handle huge page PFN maps. Luckily they don't exist. */ + if (pmd_huge(*pmd)) + goto no_page_table; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!ptep) + goto out; + + pte = *ptep; + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + phys_addr = pte_pfn(pte); + phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ + + *prot = pgprot_val(pte_pgprot(pte)); + +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return phys_addr; +no_page_table: + return 0; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; + + phys_addr = follow_phys(vma, addr, write, &prot); + + if (!phys_addr) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +#endif + /* * Access another process' address space. * Source/target buffer must be kernel space, @@ -2760,7 +2840,6 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in { struct mm_struct *mm; struct vm_area_struct *vma; - struct page *page; void *old_buf = buf; mm = get_task_mm(tsk); @@ -2772,28 +2851,44 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in while (len) { int bytes, ret, offset; void *maddr; + struct page *page = NULL; ret = get_user_pages(tsk, mm, addr, 1, write, 1, &page, &vma); - if (ret <= 0) - break; - - bytes = len; - offset = addr & (PAGE_SIZE-1); - if (bytes > PAGE_SIZE-offset) - bytes = PAGE_SIZE-offset; - - maddr = kmap(page); - if (write) { - copy_to_user_page(vma, page, addr, - maddr + offset, buf, bytes); - set_page_dirty_lock(page); + if (ret <= 0) { + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ +#ifdef CONFIG_HAVE_IOREMAP_PROT + vma = find_vma(mm, addr); + if (!vma) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) +#endif + break; + bytes = ret; } else { - copy_from_user_page(vma, page, addr, - buf, maddr + offset, bytes); + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); } - kunmap(page); - page_cache_release(page); len -= bytes; buf += bytes; addr += bytes; -- cgit v1.2.3 From 42b7772812d15b86543a23b82bd6070eef9a08b1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 23 Jul 2008 21:27:10 -0700 Subject: mm: remove double indirection on tlb parameter to free_pgd_range() & Co The double indirection here is not needed anywhere and hence (at least) confusing. Signed-off-by: Jan Beulich Cc: Hugh Dickins Cc: Nick Piggin Cc: Christoph Lameter Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Luck, Tony" Cc: Paul Mundt Cc: "David S. Miller" Acked-by: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/hugetlbpage.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 8 ++++---- fs/exec.c | 4 ++-- include/asm-ia64/hugetlb.h | 2 +- include/asm-powerpc/hugetlb.h | 2 +- include/asm-sh/hugetlb.h | 2 +- include/asm-sparc/hugetlb.h | 2 +- include/asm-x86/hugetlb.h | 2 +- include/linux/mm.h | 4 +--- mm/internal.h | 3 +++ mm/memory.c | 10 ++++++---- mm/mmap.c | 6 ++++-- 12 files changed, 26 insertions(+), 21 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index d3ce8f3bcaa6..cd49e2860eef 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -112,7 +112,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int wri return NULL; } -void hugetlb_free_pgd_range(struct mmu_gather **tlb, +void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 0d12fba31bc5..1a96cc891cf5 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -255,7 +255,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, * * Must be called with pagetable lock held. */ -void hugetlb_free_pgd_range(struct mmu_gather **tlb, +void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -315,13 +315,13 @@ void hugetlb_free_pgd_range(struct mmu_gather **tlb, return; start = addr; - pgd = pgd_offset((*tlb)->mm, addr); + pgd = pgd_offset(tlb->mm, addr); do { - BUG_ON(get_slice_psize((*tlb)->mm, addr) != mmu_huge_psize); + BUG_ON(get_slice_psize(tlb->mm, addr) != mmu_huge_psize); next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - hugetlb_free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } diff --git a/fs/exec.c b/fs/exec.c index fd9234379e8d..190ed1f92774 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -541,7 +541,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * when the old and new regions overlap clear from new_end. */ - free_pgd_range(&tlb, new_end, old_end, new_end, + free_pgd_range(tlb, new_end, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : 0); } else { /* @@ -550,7 +550,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * have constraints on va-space that make this illegal (IA64) - * for the others its just a little faster. */ - free_pgd_range(&tlb, old_start, old_end, new_end, + free_pgd_range(tlb, old_start, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : 0); } tlb_finish_mmu(tlb, new_end, old_end); diff --git a/include/asm-ia64/hugetlb.h b/include/asm-ia64/hugetlb.h index f28a9701f1cf..e9d1e5e2382d 100644 --- a/include/asm-ia64/hugetlb.h +++ b/include/asm-ia64/hugetlb.h @@ -4,7 +4,7 @@ #include -void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h index be32ff02f4a0..0a37aa5ecaa5 100644 --- a/include/asm-powerpc/hugetlb.h +++ b/include/asm-powerpc/hugetlb.h @@ -7,7 +7,7 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len); -void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); diff --git a/include/asm-sh/hugetlb.h b/include/asm-sh/hugetlb.h index 02402303d89b..fb30018938c7 100644 --- a/include/asm-sh/hugetlb.h +++ b/include/asm-sh/hugetlb.h @@ -26,7 +26,7 @@ static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) { } -static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb, +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) diff --git a/include/asm-sparc/hugetlb.h b/include/asm-sparc/hugetlb.h index 412af58926a0..aeb92374ca3d 100644 --- a/include/asm-sparc/hugetlb.h +++ b/include/asm-sparc/hugetlb.h @@ -31,7 +31,7 @@ static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) return 0; } -static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb, +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h index 14171a4924f6..7eed6e0883bf 100644 --- a/include/asm-x86/hugetlb.h +++ b/include/asm-x86/hugetlb.h @@ -26,7 +26,7 @@ static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) { } -static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb, +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c7f8f64f70e..f8071097302a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -769,10 +769,8 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); -void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, - unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, diff --git a/mm/internal.h b/mm/internal.h index 50807e12490e..858ad01864dc 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -13,6 +13,9 @@ #include +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, + unsigned long floor, unsigned long ceiling); + static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_count, v); diff --git a/mm/memory.c b/mm/memory.c index 87350321e66f..82f3f1c5cf17 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -61,6 +61,8 @@ #include #include +#include "internal.h" + #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; @@ -211,7 +213,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, * * Must be called with pagetable lock held. */ -void free_pgd_range(struct mmu_gather **tlb, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -262,16 +264,16 @@ void free_pgd_range(struct mmu_gather **tlb, return; start = addr; - pgd = pgd_offset((*tlb)->mm, addr); + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + free_pud_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { diff --git a/mm/mmap.c b/mm/mmap.c index 1d102b956fd8..75e0d0673d78 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -32,6 +32,8 @@ #include #include +#include "internal.h" + #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif @@ -1763,7 +1765,7 @@ static void unmap_region(struct mm_struct *mm, update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); - free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS, + free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS, next? next->vm_start: 0); tlb_finish_mmu(tlb, start, end); } @@ -2063,7 +2065,7 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); - free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); + free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0); tlb_finish_mmu(tlb, 0, end); /* -- cgit v1.2.3 From a5516438959d90b071ff0a484ce4f3f523dc3152 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:41 -0700 Subject: hugetlb: modular state for hugetlb page size The goal of this patchset is to support multiple hugetlb page sizes. This is achieved by introducing a new struct hstate structure, which encapsulates the important hugetlb state and constants (eg. huge page size, number of huge pages currently allocated, etc). The hstate structure is then passed around the code which requires these fields, they will do the right thing regardless of the exact hstate they are operating on. This patch adds the hstate structure, with a single global instance of it (default_hstate), and does the basic work of converting hugetlb to use the hstate. Future patches will add more hstate structures to allow for different hugetlbfs mounts to have different page sizes. [akpm@linux-foundation.org: coding-style fixes] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/hugetlbpage.c | 7 +- arch/powerpc/mm/hugetlbpage.c | 3 +- arch/s390/mm/hugetlbpage.c | 3 +- arch/sh/mm/hugetlbpage.c | 3 +- arch/sparc64/mm/hugetlbpage.c | 5 +- arch/x86/mm/hugetlbpage.c | 5 +- fs/hugetlbfs/inode.c | 52 +++--- include/asm-ia64/hugetlb.h | 3 +- include/asm-powerpc/hugetlb.h | 3 +- include/asm-s390/hugetlb.h | 3 +- include/asm-sh/hugetlb.h | 3 +- include/asm-sparc/hugetlb.h | 3 +- include/asm-x86/hugetlb.h | 8 +- include/linux/hugetlb.h | 88 +++++++++- ipc/shm.c | 3 +- mm/hugetlb.c | 368 +++++++++++++++++++++++------------------- mm/memory.c | 2 +- mm/mempolicy.c | 9 +- mm/mmap.c | 3 +- 19 files changed, 356 insertions(+), 218 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index cd49e2860eef..6170f097d255 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -24,7 +24,7 @@ unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT; pte_t * -huge_pte_alloc (struct mm_struct *mm, unsigned long addr) +huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { unsigned long taddr = htlbpage_to_page(addr); pgd_t *pgd; @@ -75,7 +75,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) * Don't actually need to do any preparation, but need to make sure * the address is in the right region. */ -int prepare_hugepage_range(unsigned long addr, unsigned long len) +int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; @@ -149,7 +150,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, u /* Handle MAP_FIXED */ if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a96cc891cf5..c94dc71af989 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -128,7 +128,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return NULL; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pg; pud_t *pu; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index f4b6124fdb75..9162dc84f77f 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -72,7 +72,8 @@ void arch_release_hugepage(struct page *page) page[1].index = 0; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgdp; pud_t *pudp; diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index ae8c321d6e2a..2f9dbe0ef4ac 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -22,7 +22,8 @@ #include #include -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c index ebefd2a14375..1307b23f6a76 100644 --- a/arch/sparc64/mm/hugetlbpage.c +++ b/arch/sparc64/mm/hugetlbpage.c @@ -175,7 +175,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } @@ -195,7 +195,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, pgoff, flags); } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 0b3d567e686d..52476fde8996 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 1; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; @@ -368,7 +369,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 428eff5b73f3..516c581b5371 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -80,6 +80,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) struct inode *inode = file->f_path.dentry->d_inode; loff_t len, vma_len; int ret; + struct hstate *h = hstate_file(file); /* * vma address alignment (but not the pgoff alignment) has @@ -92,7 +93,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_RESERVED; vma->vm_ops = &hugetlb_vm_ops; - if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT)) + if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); @@ -104,8 +105,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); if (hugetlb_reserve_pages(inode, - vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT), - len >> HPAGE_SHIFT, vma)) + vma->vm_pgoff >> huge_page_order(h), + len >> huge_page_shift(h), vma)) goto out; ret = 0; @@ -130,20 +131,21 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; + struct hstate *h = hstate_file(file); - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -156,7 +158,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, start_addr = TASK_UNMAPPED_BASE; full_search: - addr = ALIGN(start_addr, HPAGE_SIZE); + addr = ALIGN(start_addr, huge_page_size(h)); for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -174,7 +176,7 @@ full_search: if (!vma || addr + len <= vma->vm_start) return addr; - addr = ALIGN(vma->vm_end, HPAGE_SIZE); + addr = ALIGN(vma->vm_end, huge_page_size(h)); } } #endif @@ -225,10 +227,11 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset, static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { + struct hstate *h = hstate_file(filp); struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; - unsigned long index = *ppos >> HPAGE_SHIFT; - unsigned long offset = *ppos & ~HPAGE_MASK; + unsigned long index = *ppos >> huge_page_shift(h); + unsigned long offset = *ppos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; @@ -243,17 +246,17 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, if (!isize) goto out; - end_index = (isize - 1) >> HPAGE_SHIFT; + end_index = (isize - 1) >> huge_page_shift(h); for (;;) { struct page *page; - int nr, ret; + unsigned long nr, ret; /* nr is the maximum number of bytes to copy from this page */ - nr = HPAGE_SIZE; + nr = huge_page_size(h); if (index >= end_index) { if (index > end_index) goto out; - nr = ((isize - 1) & ~HPAGE_MASK) + 1; + nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) { goto out; } @@ -287,8 +290,8 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, offset += ret; retval += ret; len -= ret; - index += offset >> HPAGE_SHIFT; - offset &= ~HPAGE_MASK; + index += offset >> huge_page_shift(h); + offset &= ~huge_page_mask(h); if (page) page_cache_release(page); @@ -298,7 +301,7 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, break; } out: - *ppos = ((loff_t)index << HPAGE_SHIFT) + offset; + *ppos = ((loff_t)index << huge_page_shift(h)) + offset; mutex_unlock(&inode->i_mutex); return retval; } @@ -339,8 +342,9 @@ static void truncate_huge_page(struct page *page) static void truncate_hugepages(struct inode *inode, loff_t lstart) { + struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; - const pgoff_t start = lstart >> HPAGE_SHIFT; + const pgoff_t start = lstart >> huge_page_shift(h); struct pagevec pvec; pgoff_t next; int i, freed = 0; @@ -449,8 +453,9 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; + struct hstate *h = hstate_inode(inode); - BUG_ON(offset & ~HPAGE_MASK); + BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; i_size_write(inode, offset); @@ -465,6 +470,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; + struct hstate *h = hstate_inode(inode); int error; unsigned int ia_valid = attr->ia_valid; @@ -476,7 +482,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) if (ia_valid & ATTR_SIZE) { error = -EINVAL; - if (!(attr->ia_size & ~HPAGE_MASK)) + if (!(attr->ia_size & ~huge_page_mask(h))) error = hugetlb_vmtruncate(inode, attr->ia_size); if (error) goto out; @@ -610,9 +616,10 @@ static int hugetlbfs_set_page_dirty(struct page *page) static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); + struct hstate *h = hstate_inode(dentry->d_inode); buf->f_type = HUGETLBFS_MAGIC; - buf->f_bsize = HPAGE_SIZE; + buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 for max/free/used @@ -942,7 +949,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size) goto out_dentry; error = -ENOMEM; - if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT, NULL)) + if (hugetlb_reserve_pages(inode, 0, + size >> huge_page_shift(hstate_inode(inode)), NULL)) goto out_inode; d_instantiate(dentry, inode); diff --git a/include/asm-ia64/hugetlb.h b/include/asm-ia64/hugetlb.h index e9d1e5e2382d..da55c63728e0 100644 --- a/include/asm-ia64/hugetlb.h +++ b/include/asm-ia64/hugetlb.h @@ -8,7 +8,8 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -int prepare_hugepage_range(unsigned long addr, unsigned long len); +int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len); static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h index 0a37aa5ecaa5..ca37c4af27b1 100644 --- a/include/asm-powerpc/hugetlb.h +++ b/include/asm-powerpc/hugetlb.h @@ -21,7 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-s390/hugetlb.h b/include/asm-s390/hugetlb.h index 600a776f8f75..670a1d1745d2 100644 --- a/include/asm-s390/hugetlb.h +++ b/include/asm-s390/hugetlb.h @@ -22,7 +22,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-sh/hugetlb.h b/include/asm-sh/hugetlb.h index fb30018938c7..967068fb79ac 100644 --- a/include/asm-sh/hugetlb.h +++ b/include/asm-sh/hugetlb.h @@ -14,7 +14,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-sparc/hugetlb.h b/include/asm-sparc/hugetlb.h index aeb92374ca3d..177061064ee6 100644 --- a/include/asm-sparc/hugetlb.h +++ b/include/asm-sparc/hugetlb.h @@ -22,7 +22,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h index 7eed6e0883bf..439a9acc132d 100644 --- a/include/asm-x86/hugetlb.h +++ b/include/asm-x86/hugetlb.h @@ -14,11 +14,13 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index abbc187193a1..ad2271e11f9b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,7 +8,6 @@ #include #include #include -#include struct ctl_table; @@ -45,7 +44,8 @@ extern int sysctl_hugetlb_shm_group; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -80,7 +80,7 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL -#define prepare_hugepage_range(addr,len) (-EINVAL) +#define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) @@ -134,8 +134,6 @@ struct file *hugetlb_file_setup(const char *name, size_t); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); -#define BLOCKS_PER_HUGEPAGE (HPAGE_SIZE / 512) - static inline int is_file_hugepages(struct file *file) { if (file->f_op == &hugetlbfs_file_operations) @@ -164,4 +162,84 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +#ifdef CONFIG_HUGETLB_PAGE + +/* Defines one hugetlb page size */ +struct hstate { + int hugetlb_next_nid; + unsigned int order; + unsigned long mask; + unsigned long max_huge_pages; + unsigned long nr_huge_pages; + unsigned long free_huge_pages; + unsigned long resv_huge_pages; + unsigned long surplus_huge_pages; + unsigned long nr_overcommit_huge_pages; + struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int nr_huge_pages_node[MAX_NUMNODES]; + unsigned int free_huge_pages_node[MAX_NUMNODES]; + unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +}; + +extern struct hstate default_hstate; + +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_file(struct file *f) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_inode(struct inode *i) +{ + return &default_hstate; +} + +static inline unsigned long huge_page_size(struct hstate *h) +{ + return (unsigned long)PAGE_SIZE << h->order; +} + +static inline unsigned long huge_page_mask(struct hstate *h) +{ + return h->mask; +} + +static inline unsigned int huge_page_order(struct hstate *h) +{ + return h->order; +} + +static inline unsigned huge_page_shift(struct hstate *h) +{ + return h->order + PAGE_SHIFT; +} + +static inline unsigned int pages_per_huge_page(struct hstate *h) +{ + return 1 << h->order; +} + +static inline unsigned int blocks_per_huge_page(struct hstate *h) +{ + return huge_page_size(h) / 512; +} + +#include + +#else +struct hstate {}; +#define hstate_file(f) NULL +#define hstate_vma(v) NULL +#define hstate_inode(i) NULL +#define huge_page_size(h) PAGE_SIZE +#define huge_page_mask(h) PAGE_MASK +#define huge_page_order(h) 0 +#define huge_page_shift(h) PAGE_SHIFT +#define pages_per_huge_page(h) 1 +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/ipc/shm.c b/ipc/shm.c index 790240cd067f..a726aebce7d7 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -577,7 +577,8 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; - *rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages; + struct hstate *h = hstate_file(shp->shm_file); + *rss += pages_per_huge_page(h) * mapping->nrpages; } else { struct shmem_inode_info *info = SHMEM_I(inode); spin_lock(&info->lock); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 32dff4290c66..0d8153e25f09 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -22,18 +22,12 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages; -static unsigned long surplus_huge_pages; -static unsigned long nr_overcommit_huge_pages; unsigned long max_huge_pages; unsigned long sysctl_overcommit_huge_pages; -static struct list_head hugepage_freelists[MAX_NUMNODES]; -static unsigned int nr_huge_pages_node[MAX_NUMNODES]; -static unsigned int free_huge_pages_node[MAX_NUMNODES]; -static unsigned int surplus_huge_pages_node[MAX_NUMNODES]; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -static int hugetlb_next_nid; + +struct hstate default_hstate; /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages @@ -203,11 +197,11 @@ static long region_count(struct list_head *head, long f, long t) * Convert the address within this vma to the page offset within * the mapping, in pagecache page units; huge pages here. */ -static pgoff_t vma_hugecache_offset(struct vm_area_struct *vma, - unsigned long address) +static pgoff_t vma_hugecache_offset(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { - return ((address - vma->vm_start) >> HPAGE_SHIFT) + - (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + return ((address - vma->vm_start) >> huge_page_shift(h)) + + (vma->vm_pgoff >> huge_page_order(h)); } /* @@ -309,20 +303,21 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) } /* Decrement the reserved pages in the hugepage pool by one */ -static void decrement_hugepage_resv_vma(struct vm_area_struct *vma) +static void decrement_hugepage_resv_vma(struct hstate *h, + struct vm_area_struct *vma) { if (vma->vm_flags & VM_NORESERVE) return; if (vma->vm_flags & VM_SHARED) { /* Shared mappings always use reserves */ - resv_huge_pages--; + h->resv_huge_pages--; } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Only the process that called mmap() has reserves for * private mappings. */ - resv_huge_pages--; + h->resv_huge_pages--; } } @@ -344,12 +339,13 @@ static int vma_has_private_reserves(struct vm_area_struct *vma) return 1; } -static void clear_huge_page(struct page *page, unsigned long addr) +static void clear_huge_page(struct page *page, + unsigned long addr, unsigned long sz) { int i; might_sleep(); - for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) { + for (i = 0; i < sz/PAGE_SIZE; i++) { cond_resched(); clear_user_highpage(page + i, addr + i * PAGE_SIZE); } @@ -359,41 +355,43 @@ static void copy_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; + struct hstate *h = hstate_vma(vma); might_sleep(); - for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) { + for (i = 0; i < pages_per_huge_page(h); i++) { cond_resched(); copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } } -static void enqueue_huge_page(struct page *page) +static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); - list_add(&page->lru, &hugepage_freelists[nid]); - free_huge_pages++; - free_huge_pages_node[nid]++; + list_add(&page->lru, &h->hugepage_freelists[nid]); + h->free_huge_pages++; + h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page(void) +static struct page *dequeue_huge_page(struct hstate *h) { int nid; struct page *page = NULL; for (nid = 0; nid < MAX_NUMNODES; ++nid) { - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + if (!list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; break; } } return page; } -static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, +static struct page *dequeue_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, unsigned long address, int avoid_reserve) { int nid; @@ -411,26 +409,26 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, * not "stolen". The child may still get SIGKILLed */ if (!vma_has_private_reserves(vma) && - free_huge_pages - resv_huge_pages == 0) + h->free_huge_pages - h->resv_huge_pages == 0) return NULL; /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && free_huge_pages - resv_huge_pages == 0) + if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) return NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { nid = zone_to_nid(zone); if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) && - !list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + !list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; if (!avoid_reserve) - decrement_hugepage_resv_vma(vma); + decrement_hugepage_resv_vma(h, vma); break; } @@ -439,12 +437,13 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, return page; } -static void update_and_free_page(struct page *page) +static void update_and_free_page(struct hstate *h, struct page *page) { int i; - nr_huge_pages--; - nr_huge_pages_node[page_to_nid(page)]--; - for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) { + + h->nr_huge_pages--; + h->nr_huge_pages_node[page_to_nid(page)]--; + for (i = 0; i < pages_per_huge_page(h); i++) { page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1<< PG_writeback); @@ -452,11 +451,16 @@ static void update_and_free_page(struct page *page) set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(page); - __free_pages(page, HUGETLB_PAGE_ORDER); + __free_pages(page, huge_page_order(h)); } static void free_huge_page(struct page *page) { + /* + * Can't pass hstate in here because it is called from the + * compound page destructor. + */ + struct hstate *h = &default_hstate; int nid = page_to_nid(page); struct address_space *mapping; @@ -466,12 +470,12 @@ static void free_huge_page(struct page *page) INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); - if (surplus_huge_pages_node[nid]) { - update_and_free_page(page); - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; + if (h->surplus_huge_pages_node[nid]) { + update_and_free_page(h, page); + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; } else { - enqueue_huge_page(page); + enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); if (mapping) @@ -483,7 +487,7 @@ static void free_huge_page(struct page *page) * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ -static int adjust_pool_surplus(int delta) +static int adjust_pool_surplus(struct hstate *h, int delta) { static int prev_nid; int nid = prev_nid; @@ -496,15 +500,15 @@ static int adjust_pool_surplus(int delta) nid = first_node(node_online_map); /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !surplus_huge_pages_node[nid]) + if (delta < 0 && !h->surplus_huge_pages_node[nid]) continue; /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && surplus_huge_pages_node[nid] >= - nr_huge_pages_node[nid]) + if (delta > 0 && h->surplus_huge_pages_node[nid] >= + h->nr_huge_pages_node[nid]) continue; - surplus_huge_pages += delta; - surplus_huge_pages_node[nid] += delta; + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[nid] += delta; ret = 1; break; } while (nid != prev_nid); @@ -513,46 +517,46 @@ static int adjust_pool_surplus(int delta) return ret; } -static void prep_new_huge_page(struct page *page, int nid) +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); - nr_huge_pages++; - nr_huge_pages_node[nid]++; + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; spin_unlock(&hugetlb_lock); put_page(page); /* free it into the hugepage allocator */ } -static struct page *alloc_fresh_huge_page_node(int nid) +static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); if (page) { if (arch_prepare_hugepage(page)) { __free_pages(page, HUGETLB_PAGE_ORDER); return NULL; } - prep_new_huge_page(page, nid); + prep_new_huge_page(h, page, nid); } return page; } -static int alloc_fresh_huge_page(void) +static int alloc_fresh_huge_page(struct hstate *h) { struct page *page; int start_nid; int next_nid; int ret = 0; - start_nid = hugetlb_next_nid; + start_nid = h->hugetlb_next_nid; do { - page = alloc_fresh_huge_page_node(hugetlb_next_nid); + page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid); if (page) ret = 1; /* @@ -566,11 +570,11 @@ static int alloc_fresh_huge_page(void) * if we just successfully allocated a hugepage so that * the next caller gets hugepages on the next node. */ - next_nid = next_node(hugetlb_next_nid, node_online_map); + next_nid = next_node(h->hugetlb_next_nid, node_online_map); if (next_nid == MAX_NUMNODES) next_nid = first_node(node_online_map); - hugetlb_next_nid = next_nid; - } while (!page && hugetlb_next_nid != start_nid); + h->hugetlb_next_nid = next_nid; + } while (!page && h->hugetlb_next_nid != start_nid); if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -580,8 +584,8 @@ static int alloc_fresh_huge_page(void) return ret; } -static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, - unsigned long address) +static struct page *alloc_buddy_huge_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct page *page; unsigned int nid; @@ -610,18 +614,18 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * per-node value is checked there. */ spin_lock(&hugetlb_lock); - if (surplus_huge_pages >= nr_overcommit_huge_pages) { + if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { spin_unlock(&hugetlb_lock); return NULL; } else { - nr_huge_pages++; - surplus_huge_pages++; + h->nr_huge_pages++; + h->surplus_huge_pages++; } spin_unlock(&hugetlb_lock); page = alloc_pages(htlb_alloc_mask|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); spin_lock(&hugetlb_lock); if (page) { @@ -636,12 +640,12 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, /* * We incremented the global counters already */ - nr_huge_pages_node[nid]++; - surplus_huge_pages_node[nid]++; + h->nr_huge_pages_node[nid]++; + h->surplus_huge_pages_node[nid]++; __count_vm_event(HTLB_BUDDY_PGALLOC); } else { - nr_huge_pages--; - surplus_huge_pages--; + h->nr_huge_pages--; + h->surplus_huge_pages--; __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); } spin_unlock(&hugetlb_lock); @@ -653,16 +657,16 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * Increase the hugetlb pool such that it can accomodate a reservation * of size 'delta'. */ -static int gather_surplus_pages(int delta) +static int gather_surplus_pages(struct hstate *h, int delta) { struct list_head surplus_list; struct page *page, *tmp; int ret, i; int needed, allocated; - needed = (resv_huge_pages + delta) - free_huge_pages; + needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { - resv_huge_pages += delta; + h->resv_huge_pages += delta; return 0; } @@ -673,7 +677,7 @@ static int gather_surplus_pages(int delta) retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { - page = alloc_buddy_huge_page(NULL, 0); + page = alloc_buddy_huge_page(h, NULL, 0); if (!page) { /* * We were not able to allocate enough pages to @@ -694,7 +698,8 @@ retry: * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock(&hugetlb_lock); - needed = (resv_huge_pages + delta) - (free_huge_pages + allocated); + needed = (h->resv_huge_pages + delta) - + (h->free_huge_pages + allocated); if (needed > 0) goto retry; @@ -707,7 +712,7 @@ retry: * before they are reserved. */ needed += allocated; - resv_huge_pages += delta; + h->resv_huge_pages += delta; ret = 0; free: /* Free the needed pages to the hugetlb pool */ @@ -715,7 +720,7 @@ free: if ((--needed) < 0) break; list_del(&page->lru); - enqueue_huge_page(page); + enqueue_huge_page(h, page); } /* Free unnecessary surplus pages to the buddy allocator */ @@ -743,7 +748,8 @@ free: * allocated to satisfy the reservation must be explicitly freed if they were * never used. */ -static void return_unused_surplus_pages(unsigned long unused_resv_pages) +static void return_unused_surplus_pages(struct hstate *h, + unsigned long unused_resv_pages) { static int nid = -1; struct page *page; @@ -758,27 +764,27 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages) unsigned long remaining_iterations = num_online_nodes(); /* Uncommit the reservation */ - resv_huge_pages -= unused_resv_pages; + h->resv_huge_pages -= unused_resv_pages; - nr_pages = min(unused_resv_pages, surplus_huge_pages); + nr_pages = min(unused_resv_pages, h->surplus_huge_pages); while (remaining_iterations-- && nr_pages) { nid = next_node(nid, node_online_map); if (nid == MAX_NUMNODES) nid = first_node(node_online_map); - if (!surplus_huge_pages_node[nid]) + if (!h->surplus_huge_pages_node[nid]) continue; - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + if (!list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[nid]--; - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; + update_and_free_page(h, page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; nr_pages--; remaining_iterations = num_online_nodes(); } @@ -794,13 +800,14 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages) * an instantiated the change should be committed via vma_commit_reservation. * No action is required on failure. */ -static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) +static int vma_needs_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); return region_chg(&inode->i_mapping->private_list, idx, idx + 1); @@ -809,7 +816,7 @@ static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) } else { int err; - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); err = region_chg(&reservations->regions, idx, idx + 1); @@ -818,18 +825,18 @@ static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) return 0; } } -static void vma_commit_reservation(struct vm_area_struct *vma, - unsigned long addr) +static void vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); region_add(&inode->i_mapping->private_list, idx, idx + 1); } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); /* Mark this page used in the map. */ @@ -840,6 +847,7 @@ static void vma_commit_reservation(struct vm_area_struct *vma, static struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { + struct hstate *h = hstate_vma(vma); struct page *page; struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; @@ -852,7 +860,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, * MAP_NORESERVE mappings may also need pages and quota allocated * if no reserve mapping overlaps. */ - chg = vma_needs_reservation(vma, addr); + chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(chg); if (chg) @@ -860,11 +868,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(vma, addr, avoid_reserve); + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); spin_unlock(&hugetlb_lock); if (!page) { - page = alloc_buddy_huge_page(vma, addr); + page = alloc_buddy_huge_page(h, vma, addr); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); return ERR_PTR(-VM_FAULT_OOM); @@ -874,7 +882,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_refcounted(page); set_page_private(page, (unsigned long) mapping); - vma_commit_reservation(vma, addr); + vma_commit_reservation(h, vma, addr); return page; } @@ -882,21 +890,28 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, static int __init hugetlb_init(void) { unsigned long i; + struct hstate *h = &default_hstate; if (HPAGE_SHIFT == 0) return 0; + if (!h->order) { + h->order = HPAGE_SHIFT - PAGE_SHIFT; + h->mask = HPAGE_MASK; + } + for (i = 0; i < MAX_NUMNODES; ++i) - INIT_LIST_HEAD(&hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_freelists[i]); - hugetlb_next_nid = first_node(node_online_map); + h->hugetlb_next_nid = first_node(node_online_map); for (i = 0; i < max_huge_pages; ++i) { - if (!alloc_fresh_huge_page()) + if (!alloc_fresh_huge_page(h)) break; } - max_huge_pages = free_huge_pages = nr_huge_pages = i; - printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages); + max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; + printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n", + h->free_huge_pages); return 0; } module_init(hugetlb_init); @@ -922,34 +937,36 @@ static unsigned int cpuset_mems_nr(unsigned int *array) #ifdef CONFIG_SYSCTL #ifdef CONFIG_HIGHMEM -static void try_to_free_low(unsigned long count) +static void try_to_free_low(struct hstate *h, unsigned long count) { int i; for (i = 0; i < MAX_NUMNODES; ++i) { struct page *page, *next; - list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) { - if (count >= nr_huge_pages) + struct list_head *freel = &h->hugepage_freelists[i]; + list_for_each_entry_safe(page, next, freel, lru) { + if (count >= h->nr_huge_pages) return; if (PageHighMem(page)) continue; list_del(&page->lru); update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[page_to_nid(page)]--; + h->free_huge_pages--; + h->free_huge_pages_node[page_to_nid(page)]--; } } } #else -static inline void try_to_free_low(unsigned long count) +static inline void try_to_free_low(struct hstate *h, unsigned long count) { } #endif -#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages) +#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static unsigned long set_max_huge_pages(unsigned long count) { unsigned long min_count, ret; + struct hstate *h = &default_hstate; /* * Increase the pool size @@ -963,19 +980,19 @@ static unsigned long set_max_huge_pages(unsigned long count) * within all the constraints specified by the sysctls. */ spin_lock(&hugetlb_lock); - while (surplus_huge_pages && count > persistent_huge_pages) { - if (!adjust_pool_surplus(-1)) + while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, -1)) break; } - while (count > persistent_huge_pages) { + while (count > persistent_huge_pages(h)) { /* * If this allocation races such that we no longer need the * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(); + ret = alloc_fresh_huge_page(h); spin_lock(&hugetlb_lock); if (!ret) goto out; @@ -997,21 +1014,21 @@ static unsigned long set_max_huge_pages(unsigned long count) * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ - min_count = resv_huge_pages + nr_huge_pages - free_huge_pages; + min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); - try_to_free_low(min_count); - while (min_count < persistent_huge_pages) { - struct page *page = dequeue_huge_page(); + try_to_free_low(h, min_count); + while (min_count < persistent_huge_pages(h)) { + struct page *page = dequeue_huge_page(h); if (!page) break; - update_and_free_page(page); + update_and_free_page(h, page); } - while (count < persistent_huge_pages) { - if (!adjust_pool_surplus(1)) + while (count < persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, 1)) break; } out: - ret = persistent_huge_pages; + ret = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); return ret; } @@ -1041,9 +1058,10 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { + struct hstate *h = &default_hstate; proc_doulongvec_minmax(table, write, file, buffer, length, ppos); spin_lock(&hugetlb_lock); - nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; + h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; spin_unlock(&hugetlb_lock); return 0; } @@ -1052,37 +1070,40 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, int hugetlb_report_meminfo(char *buf) { + struct hstate *h = &default_hstate; return sprintf(buf, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %5lu kB\n", - nr_huge_pages, - free_huge_pages, - resv_huge_pages, - surplus_huge_pages, - HPAGE_SIZE/1024); + h->nr_huge_pages, + h->free_huge_pages, + h->resv_huge_pages, + h->surplus_huge_pages, + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); } int hugetlb_report_node_meminfo(int nid, char *buf) { + struct hstate *h = &default_hstate; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", - nid, nr_huge_pages_node[nid], - nid, free_huge_pages_node[nid], - nid, surplus_huge_pages_node[nid]); + nid, h->nr_huge_pages_node[nid], + nid, h->free_huge_pages_node[nid], + nid, h->surplus_huge_pages_node[nid]); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { - return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE); + struct hstate *h = &default_hstate; + return h->nr_huge_pages * pages_per_huge_page(h); } -static int hugetlb_acct_memory(long delta) +static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; @@ -1105,18 +1126,18 @@ static int hugetlb_acct_memory(long delta) * semantics that cpuset has. */ if (delta > 0) { - if (gather_surplus_pages(delta) < 0) + if (gather_surplus_pages(h, delta) < 0) goto out; - if (delta > cpuset_mems_nr(free_huge_pages_node)) { - return_unused_surplus_pages(delta); + if (delta > cpuset_mems_nr(h->free_huge_pages_node)) { + return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) - return_unused_surplus_pages((unsigned long) -delta); + return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock(&hugetlb_lock); @@ -1141,14 +1162,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) static void hugetlb_vm_op_close(struct vm_area_struct *vma) { + struct hstate *h = hstate_vma(vma); struct resv_map *reservations = vma_resv_map(vma); unsigned long reserve; unsigned long start; unsigned long end; if (reservations) { - start = vma_hugecache_offset(vma, vma->vm_start); - end = vma_hugecache_offset(vma, vma->vm_end); + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(&reservations->regions, start, end); @@ -1156,7 +1178,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) kref_put(&reservations->refs, resv_map_release); if (reserve) - hugetlb_acct_memory(-reserve); + hugetlb_acct_memory(h, -reserve); } } @@ -1214,14 +1236,16 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct page *ptepage; unsigned long addr; int cow; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; - for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, addr); + dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) goto nomem; @@ -1257,6 +1281,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, pte_t pte; struct page *page; struct page *tmp; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + /* * A page gathering list, protected by per file i_mmap_lock. The * lock is used to avoid list corruption from multiple unmapping @@ -1265,11 +1292,11 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, LIST_HEAD(page_list); WARN_ON(!is_vm_hugetlb_page(vma)); - BUG_ON(start & ~HPAGE_MASK); - BUG_ON(end & ~HPAGE_MASK); + BUG_ON(start & ~huge_page_mask(h)); + BUG_ON(end & ~huge_page_mask(h)); spin_lock(&mm->page_table_lock); - for (address = start; address < end; address += HPAGE_SIZE) { + for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1383,6 +1410,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, struct page *pagecache_page) { + struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; int avoidcopy; int outside_reserve = 0; @@ -1443,7 +1471,7 @@ retry_avoidcopy: __SetPageUptodate(new_page); spin_lock(&mm->page_table_lock); - ptep = huge_pte_offset(mm, address & HPAGE_MASK); + ptep = huge_pte_offset(mm, address & huge_page_mask(h)); if (likely(pte_same(huge_ptep_get(ptep), pte))) { /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); @@ -1458,14 +1486,14 @@ retry_avoidcopy: } /* Return the pagecache page at a given address within a VMA */ -static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, - unsigned long address) +static struct page *hugetlbfs_pagecache_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); return find_lock_page(mapping, idx); } @@ -1473,6 +1501,7 @@ static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, int write_access) { + struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; pgoff_t idx; unsigned long size; @@ -1493,7 +1522,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, } mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); /* * Use page lock to guard against racing truncation @@ -1502,7 +1531,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, retry: page = find_lock_page(mapping, idx); if (!page) { - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; page = alloc_huge_page(vma, address, 0); @@ -1510,7 +1539,7 @@ retry: ret = -PTR_ERR(page); goto out; } - clear_huge_page(page, address); + clear_huge_page(page, address, huge_page_size(h)); __SetPageUptodate(page); if (vma->vm_flags & VM_SHARED) { @@ -1526,14 +1555,14 @@ retry: } spin_lock(&inode->i_lock); - inode->i_blocks += BLOCKS_PER_HUGEPAGE; + inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); } else lock_page(page); } spin_lock(&mm->page_table_lock); - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto backout; @@ -1569,8 +1598,9 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_t entry; int ret; static DEFINE_MUTEX(hugetlb_instantiation_mutex); + struct hstate *h = hstate_vma(vma); - ptep = huge_pte_alloc(mm, address); + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); if (!ptep) return VM_FAULT_OOM; @@ -1594,7 +1624,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (likely(pte_same(entry, huge_ptep_get(ptep)))) if (write_access && !pte_write(entry)) { struct page *page; - page = hugetlbfs_pagecache_page(vma, address); + page = hugetlbfs_pagecache_page(h, vma, address); ret = hugetlb_cow(mm, vma, address, ptep, entry, page); if (page) { unlock_page(page); @@ -1615,6 +1645,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long pfn_offset; unsigned long vaddr = *position; int remainder = *length; + struct hstate *h = hstate_vma(vma); spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { @@ -1626,7 +1657,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * each hugepage. We have to make * sure we get the * first, for the page indexing below to work. */ - pte = huge_pte_offset(mm, vaddr & HPAGE_MASK); + pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); if (!pte || huge_pte_none(huge_ptep_get(pte)) || (write && !pte_write(huge_ptep_get(pte)))) { @@ -1644,7 +1675,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } - pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT; + pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); same_page: if (pages) { @@ -1660,7 +1691,7 @@ same_page: --remainder; ++i; if (vaddr < vma->vm_end && remainder && - pfn_offset < HPAGE_SIZE/PAGE_SIZE) { + pfn_offset < pages_per_huge_page(h)) { /* * We use pfn_offset to avoid touching the pageframes * of this compound page. @@ -1682,13 +1713,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long start = address; pte_t *ptep; pte_t pte; + struct hstate *h = hstate_vma(vma); BUG_ON(address >= end); flush_cache_range(vma, address, end); spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); spin_lock(&mm->page_table_lock); - for (; address < end; address += HPAGE_SIZE) { + for (; address < end; address += huge_page_size(h)) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1711,6 +1743,7 @@ int hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma) { long ret, chg; + struct hstate *h = hstate_inode(inode); if (vma && vma->vm_flags & VM_NORESERVE) return 0; @@ -1739,7 +1772,7 @@ int hugetlb_reserve_pages(struct inode *inode, if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; - ret = hugetlb_acct_memory(chg); + ret = hugetlb_acct_memory(h, chg); if (ret < 0) { hugetlb_put_quota(inode->i_mapping, chg); return ret; @@ -1751,12 +1784,13 @@ int hugetlb_reserve_pages(struct inode *inode, void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { + struct hstate *h = hstate_inode(inode); long chg = region_truncate(&inode->i_mapping->private_list, offset); spin_lock(&inode->i_lock); - inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed; + inode->i_blocks -= blocks_per_huge_page(h); spin_unlock(&inode->i_lock); hugetlb_put_quota(inode->i_mapping, (chg - freed)); - hugetlb_acct_memory(-(chg - freed)); + hugetlb_acct_memory(h, -(chg - freed)); } diff --git a/mm/memory.c b/mm/memory.c index 72932489a082..c1c1d6d8c22b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -903,7 +903,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (unlikely(is_vm_hugetlb_page(vma))) { unmap_hugepage_range(vma, start, end, NULL); zap_work -= (end - start) / - (HPAGE_SIZE / PAGE_SIZE); + pages_per_huge_page(hstate_vma(vma)); start = end; } else start = unmap_page_range(*tlbp, vma, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index c94e58b192c3..e550bec20582 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1481,7 +1481,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { zl = node_zonelist(interleave_nid(*mpol, vma, addr, - HPAGE_SHIFT), gfp_flags); + huge_page_shift(hstate_vma(vma))), gfp_flags); } else { zl = policy_zonelist(gfp_flags, *mpol); if ((*mpol)->mode == MPOL_BIND) @@ -2220,9 +2220,12 @@ static void check_huge_range(struct vm_area_struct *vma, { unsigned long addr; struct page *page; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); - for (addr = start; addr < end; addr += HPAGE_SIZE) { - pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK); + for (addr = start; addr < end; addr += sz) { + pte_t *ptep = huge_pte_offset(vma->vm_mm, + addr & huge_page_mask(h)); pte_t pte; if (!ptep) diff --git a/mm/mmap.c b/mm/mmap.c index 57d3b6097deb..5e0cc99e9cd5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1812,7 +1812,8 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, struct mempolicy *pol; struct vm_area_struct *new; - if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK)) + if (is_vm_hugetlb_page(vma) && (addr & + ~(huge_page_mask(hstate_vma(vma))))) return -EINVAL; if (mm->map_count >= sysctl_max_map_count) -- cgit v1.2.3 From b4718e628dbf68a2dee23b5709e2aa3190409c56 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:51 -0700 Subject: x86: add hugepagesz option on 64-bit Add an hugepagesz=... option similar to IA64, PPC etc. to x86-64. This finally allows to select GB pages for hugetlbfs in x86 now that all the infrastructure is in place. Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 11 +++++++++-- arch/x86/mm/hugetlbpage.c | 17 +++++++++++++++++ include/asm-x86/page.h | 2 ++ 3 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5e20ccb5a736..d55fd88fd0a9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -774,8 +774,15 @@ and is between 256 and 4096 characters. It is defined in the file hisax= [HW,ISDN] See Documentation/isdn/README.HiSax. - hugepages= [HW,X86-32,IA-64] Maximal number of HugeTLB pages. - hugepagesz= [HW,IA-64,PPC] The size of the HugeTLB pages. + hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot. + hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages. + On x86 this option can be specified multiple times + interleaved with hugepages= to reserve huge pages + of different sizes. Valid pages sizes on x86-64 + are 2M (when the CPU supports "pse") and 1G (when the + CPU supports the "pdpe1gb" cpuinfo flag) + Note that 1GB pages can only be allocated at boot time + using hugepages= and not freed afterwards. i8042.direct [HW] Put keyboard port into non-translated mode i8042.dumbkbd [HW] Pretend that controller can only read data from diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index b7a65a07af03..8f307d914c2e 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -425,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/ +#ifdef CONFIG_X86_64 +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE && cpu_has_gbpages) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", + ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 6c846228948d..6e02098b1605 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -32,6 +32,8 @@ #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) +#define HUGE_MAX_HSTATE 2 + /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) -- cgit v1.2.3 From 27ac792ca0b0a1e7e65f20342260650516c95864 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Wed, 23 Jul 2008 21:28:13 -0700 Subject: PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures On 32-bit architectures PAGE_ALIGN() truncates 64-bit values to the 32-bit boundary. For example: u64 val = PAGE_ALIGN(size); always returns a value < 4GB even if size is greater than 4GB. The problem resides in PAGE_MASK definition (from include/asm-x86/page.h for example): #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) ... #define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) The "~" is performed on a 32-bit value, so everything in "and" with PAGE_MASK greater than 4GB will be truncated to the 32-bit boundary. Using the ALIGN() macro seems to be the right way, because it uses typeof(addr) for the mask. Also move the PAGE_ALIGN() definitions out of include/asm-*/page.h in include/linux/mm.h. See also lkml discussion: http://lkml.org/lkml/2008/6/11/237 [akpm@linux-foundation.org: fix drivers/media/video/uvc/uvc_queue.c] [akpm@linux-foundation.org: fix v850] [akpm@linux-foundation.org: fix powerpc] [akpm@linux-foundation.org: fix arm] [akpm@linux-foundation.org: fix mips] [akpm@linux-foundation.org: fix drivers/media/video/pvrusb2/pvrusb2-dvb.c] [akpm@linux-foundation.org: fix drivers/mtd/maps/uclinux.c] [akpm@linux-foundation.org: fix powerpc] Signed-off-by: Andrea Righi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/module.c | 1 + arch/arm/plat-omap/fb.c | 1 + arch/avr32/mm/ioremap.c | 1 + arch/h8300/kernel/setup.c | 1 + arch/m68k/amiga/chipram.c | 1 + arch/m68knommu/kernel/setup.c | 1 + arch/mips/kernel/module.c | 1 + arch/mips/sgi-ip27/ip27-klnuma.c | 1 + arch/powerpc/kernel/suspend.c | 1 + arch/powerpc/lib/code-patching.c | 1 + arch/sparc64/kernel/iommu_common.h | 2 +- arch/x86/kernel/module_64.c | 1 + arch/xtensa/kernel/setup.c | 1 + drivers/char/random.c | 1 + drivers/ieee1394/iso.c | 1 + drivers/media/video/pvrusb2/pvrusb2-dvb.c | 1 + drivers/media/video/pvrusb2/pvrusb2-ioread.c | 1 + drivers/media/video/uvc/uvc_queue.c | 1 + drivers/media/video/videobuf-core.c | 1 + drivers/mtd/maps/uclinux.c | 1 + drivers/net/mlx4/eq.c | 1 + drivers/pcmcia/electra_cf.c | 1 + drivers/scsi/sun_esp.c | 1 + drivers/video/acornfb.c | 1 + drivers/video/imxfb.c | 1 + drivers/video/omap/dispc.c | 1 + drivers/video/omap/omapfb_main.c | 1 + drivers/video/pxafb.c | 1 + drivers/video/sa1100fb.c | 1 + include/asm-alpha/page.h | 3 --- include/asm-arm/page-nommu.h | 4 +--- include/asm-arm/page.h | 3 --- include/asm-avr32/page.h | 3 --- include/asm-blackfin/page.h | 3 --- include/asm-cris/page.h | 3 --- include/asm-frv/page.h | 3 --- include/asm-h8300/page.h | 3 --- include/asm-ia64/page.h | 1 - include/asm-m32r/page.h | 3 --- include/asm-m68k/dvma.h | 2 +- include/asm-m68k/page.h | 3 --- include/asm-m68knommu/page.h | 3 --- include/asm-mips/page.h | 3 --- include/asm-mips/processor.h | 2 +- include/asm-mn10300/page.h | 3 --- include/asm-parisc/page.h | 4 ---- include/asm-powerpc/page.h | 3 --- include/asm-s390/page.h | 3 --- include/asm-sh/page.h | 3 --- include/asm-sparc/page_32.h | 3 --- include/asm-sparc/page_64.h | 3 --- include/asm-um/page.h | 3 --- include/asm-v850/page.h | 4 ---- include/asm-x86/page.h | 3 --- include/asm-xtensa/page.h | 2 -- include/linux/mm.h | 3 +++ sound/core/info.c | 1 + 57 files changed, 36 insertions(+), 74 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 79b7e5cf5416..a68259a0cccd 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/arm/plat-omap/fb.c b/arch/arm/plat-omap/fb.c index 96d6f0619733..5d107520e6b9 100644 --- a/arch/arm/plat-omap/fb.c +++ b/arch/arm/plat-omap/fb.c @@ -23,6 +23,7 @@ #include #include +#include #include #include #include diff --git a/arch/avr32/mm/ioremap.c b/arch/avr32/mm/ioremap.c index 3437c82434ac..f03b79f0e0ab 100644 --- a/arch/avr32/mm/ioremap.c +++ b/arch/avr32/mm/ioremap.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ #include +#include #include #include diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index b1f25c20a5db..7fda657110eb 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/m68k/amiga/chipram.c b/arch/m68k/amiga/chipram.c index cbe36538af47..61df1d33c050 100644 --- a/arch/m68k/amiga/chipram.c +++ b/arch/m68k/amiga/chipram.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c index 03f4fe6a2fc0..5985f1989021 100644 --- a/arch/m68knommu/kernel/setup.c +++ b/arch/m68knommu/kernel/setup.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index e7ed0ac48537..1f60e27523d9 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c index 48932ce1d730..d9c79d8be81d 100644 --- a/arch/mips/sgi-ip27/ip27-klnuma.c +++ b/arch/mips/sgi-ip27/ip27-klnuma.c @@ -4,6 +4,7 @@ * Copyright 2000 - 2001 Kanoj Sarcar (kanoj@sgi.com) */ #include +#include #include #include #include diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c index 8cee57107541..6fc6328dc626 100644 --- a/arch/powerpc/kernel/suspend.c +++ b/arch/powerpc/kernel/suspend.c @@ -7,6 +7,7 @@ * Copyright (c) 2001 Patrick Mochel */ +#include #include /* References to section boundaries */ diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 0559fe086eb4..7c975d43e3f3 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include diff --git a/arch/sparc64/kernel/iommu_common.h b/arch/sparc64/kernel/iommu_common.h index f3575a614fa2..53b19c8231a9 100644 --- a/arch/sparc64/kernel/iommu_common.h +++ b/arch/sparc64/kernel/iommu_common.h @@ -23,7 +23,7 @@ #define IO_PAGE_SHIFT 13 #define IO_PAGE_SIZE (1UL << IO_PAGE_SHIFT) #define IO_PAGE_MASK (~(IO_PAGE_SIZE-1)) -#define IO_PAGE_ALIGN(addr) (((addr)+IO_PAGE_SIZE-1)&IO_PAGE_MASK) +#define IO_PAGE_ALIGN(addr) ALIGN(addr, IO_PAGE_SIZE) #define IO_TSB_ENTRIES (128*1024) #define IO_TSB_SIZE (IO_TSB_ENTRIES * 8) diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c index 0e867676b5a5..6ba87830d4b1 100644 --- a/arch/x86/kernel/module_64.c +++ b/arch/x86/kernel/module_64.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 5e6d75c9f92b..a00359e8f7a8 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include diff --git a/drivers/char/random.c b/drivers/char/random.c index 0cf98bd4f2d2..e0d0e371909c 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -236,6 +236,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/ieee1394/iso.c b/drivers/ieee1394/iso.c index 07ca35c98f96..1cf6487b65ba 100644 --- a/drivers/ieee1394/iso.c +++ b/drivers/ieee1394/iso.c @@ -11,6 +11,7 @@ #include #include +#include #include #include "hosts.h" diff --git a/drivers/media/video/pvrusb2/pvrusb2-dvb.c b/drivers/media/video/pvrusb2/pvrusb2-dvb.c index 6ec4bf81fc7f..77b3c3385066 100644 --- a/drivers/media/video/pvrusb2/pvrusb2-dvb.c +++ b/drivers/media/video/pvrusb2/pvrusb2-dvb.c @@ -20,6 +20,7 @@ #include #include +#include #include "dvbdev.h" #include "pvrusb2-debug.h" #include "pvrusb2-hdw-internal.h" diff --git a/drivers/media/video/pvrusb2/pvrusb2-ioread.c b/drivers/media/video/pvrusb2/pvrusb2-ioread.c index 05a1376405e7..b4824782d858 100644 --- a/drivers/media/video/pvrusb2/pvrusb2-ioread.c +++ b/drivers/media/video/pvrusb2/pvrusb2-ioread.c @@ -22,6 +22,7 @@ #include "pvrusb2-debug.h" #include #include +#include #include #include #include diff --git a/drivers/media/video/uvc/uvc_queue.c b/drivers/media/video/uvc/uvc_queue.c index 7388d0cee3d4..5646a6a32939 100644 --- a/drivers/media/video/uvc/uvc_queue.c +++ b/drivers/media/video/uvc/uvc_queue.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include diff --git a/drivers/media/video/videobuf-core.c b/drivers/media/video/videobuf-core.c index 0a88c44ace00..b7b05842cf28 100644 --- a/drivers/media/video/videobuf-core.c +++ b/drivers/media/video/videobuf-core.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include diff --git a/drivers/mtd/maps/uclinux.c b/drivers/mtd/maps/uclinux.c index c42f4b83f686..3fcf92130aa4 100644 --- a/drivers/mtd/maps/uclinux.c +++ b/drivers/mtd/maps/uclinux.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c index e141a1513f07..ea3a09aaa844 100644 --- a/drivers/net/mlx4/eq.c +++ b/drivers/net/mlx4/eq.c @@ -33,6 +33,7 @@ #include #include +#include #include #include diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c index c21f9a9c3e3f..a34284b1482a 100644 --- a/drivers/pcmcia/electra_cf.c +++ b/drivers/pcmcia/electra_cf.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include diff --git a/drivers/scsi/sun_esp.c b/drivers/scsi/sun_esp.c index 2c87db98cdfb..f9cf70151366 100644 --- a/drivers/scsi/sun_esp.c +++ b/drivers/scsi/sun_esp.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include diff --git a/drivers/video/acornfb.c b/drivers/video/acornfb.c index eedb8285e32f..017233d0c481 100644 --- a/drivers/video/acornfb.c +++ b/drivers/video/acornfb.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c index 94e4d3ac1a05..0c5a475c1cae 100644 --- a/drivers/video/imxfb.c +++ b/drivers/video/imxfb.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/video/omap/dispc.c b/drivers/video/omap/dispc.c index ab32ceb06178..ab77c51fe9d6 100644 --- a/drivers/video/omap/dispc.c +++ b/drivers/video/omap/dispc.c @@ -20,6 +20,7 @@ */ #include #include +#include #include #include #include diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c index 14d0f7a11145..f85af5c4fa68 100644 --- a/drivers/video/omap/omapfb_main.c +++ b/drivers/video/omap/omapfb_main.c @@ -25,6 +25,7 @@ * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ #include +#include #include #include diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c index bb2514369507..5e8a140399fc 100644 --- a/drivers/video/pxafb.c +++ b/drivers/video/pxafb.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c index ab2b2110478b..4a9f7e121807 100644 --- a/drivers/video/sa1100fb.c +++ b/drivers/video/sa1100fb.c @@ -167,6 +167,7 @@ #include #include #include +#include #include #include #include diff --git a/include/asm-alpha/page.h b/include/asm-alpha/page.h index 22ff9762d17b..0995f9d13417 100644 --- a/include/asm-alpha/page.h +++ b/include/asm-alpha/page.h @@ -80,9 +80,6 @@ typedef struct page *pgtable_t; #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #define __pa(x) ((unsigned long) (x) - PAGE_OFFSET) #define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET)) #ifndef CONFIG_DISCONTIGMEM diff --git a/include/asm-arm/page-nommu.h b/include/asm-arm/page-nommu.h index a1bcad060480..ea1cde84f500 100644 --- a/include/asm-arm/page-nommu.h +++ b/include/asm-arm/page-nommu.h @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #ifndef _ASMARM_PAGE_NOMMU_H #define _ASMARM_PAGE_NOMMU_H @@ -42,9 +43,6 @@ typedef unsigned long pgprot_t; #define __pmd(x) (x) #define __pgprot(x) (x) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - extern unsigned long memory_start; extern unsigned long memory_end; diff --git a/include/asm-arm/page.h b/include/asm-arm/page.h index 8e05bdb5f12f..7c5fc5582e5d 100644 --- a/include/asm-arm/page.h +++ b/include/asm-arm/page.h @@ -15,9 +15,6 @@ #define PAGE_SIZE (1UL << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #ifndef __ASSEMBLY__ #ifndef CONFIG_MMU diff --git a/include/asm-avr32/page.h b/include/asm-avr32/page.h index cbbc5ca9728b..f805d1cb11bc 100644 --- a/include/asm-avr32/page.h +++ b/include/asm-avr32/page.h @@ -57,9 +57,6 @@ static inline int get_order(unsigned long size) #endif /* !__ASSEMBLY__ */ -/* Align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - /* * The hardware maps the virtual addresses 0x80000000 -> 0x9fffffff * permanently to the physical addresses 0x00000000 -> 0x1fffffff when diff --git a/include/asm-blackfin/page.h b/include/asm-blackfin/page.h index c7db0220fbd6..344f6a8c1f22 100644 --- a/include/asm-blackfin/page.h +++ b/include/asm-blackfin/page.h @@ -51,9 +51,6 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - extern unsigned long memory_start; extern unsigned long memory_end; diff --git a/include/asm-cris/page.h b/include/asm-cris/page.h index c45bb1ef397c..d19272ba6b69 100644 --- a/include/asm-cris/page.h +++ b/include/asm-cris/page.h @@ -60,9 +60,6 @@ typedef struct page *pgtable_t; #define page_to_phys(page) __pa((((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #ifndef __ASSEMBLY__ #endif /* __ASSEMBLY__ */ diff --git a/include/asm-frv/page.h b/include/asm-frv/page.h index c2c1e89e747d..bd9c220094c7 100644 --- a/include/asm-frv/page.h +++ b/include/asm-frv/page.h @@ -40,9 +40,6 @@ typedef struct page *pgtable_t; #define __pgprot(x) ((pgprot_t) { (x) } ) #define PTE_MASK PAGE_MASK -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - #define devmem_is_allowed(pfn) 1 #define __pa(vaddr) virt_to_phys((void *) (unsigned long) (vaddr)) diff --git a/include/asm-h8300/page.h b/include/asm-h8300/page.h index d6a3eaf3b27e..0b6acf0b03aa 100644 --- a/include/asm-h8300/page.h +++ b/include/asm-h8300/page.h @@ -43,9 +43,6 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - extern unsigned long memory_start; extern unsigned long memory_end; diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h index 36f39321b768..5f271bc712ee 100644 --- a/include/asm-ia64/page.h +++ b/include/asm-ia64/page.h @@ -40,7 +40,6 @@ #define PAGE_SIZE (__IA64_UL_CONST(1) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE - 1)) -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) #define PERCPU_PAGE_SHIFT 16 /* log2() of max. size of per-CPU area */ #define PERCPU_PAGE_SIZE (__IA64_UL_CONST(1) << PERCPU_PAGE_SHIFT) diff --git a/include/asm-m32r/page.h b/include/asm-m32r/page.h index 8a677f3fca68..c9333089fe11 100644 --- a/include/asm-m32r/page.h +++ b/include/asm-m32r/page.h @@ -41,9 +41,6 @@ typedef struct page *pgtable_t; #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - /* * This handles the memory map.. We could make this a config * option, but too many people screw it up, and too few need diff --git a/include/asm-m68k/dvma.h b/include/asm-m68k/dvma.h index 4fff408d0150..890bbf7e7758 100644 --- a/include/asm-m68k/dvma.h +++ b/include/asm-m68k/dvma.h @@ -13,7 +13,7 @@ #define DVMA_PAGE_SHIFT 13 #define DVMA_PAGE_SIZE (1UL << DVMA_PAGE_SHIFT) #define DVMA_PAGE_MASK (~(DVMA_PAGE_SIZE-1)) -#define DVMA_PAGE_ALIGN(addr) (((addr)+DVMA_PAGE_SIZE-1)&DVMA_PAGE_MASK) +#define DVMA_PAGE_ALIGN(addr) ALIGN(addr, DVMA_PAGE_SIZE) extern void dvma_init(void); extern int dvma_map_iommu(unsigned long kaddr, unsigned long baddr, diff --git a/include/asm-m68k/page.h b/include/asm-m68k/page.h index 880c2cbff8a6..a34b8bad7847 100644 --- a/include/asm-m68k/page.h +++ b/include/asm-m68k/page.h @@ -103,9 +103,6 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #endif /* !__ASSEMBLY__ */ #include diff --git a/include/asm-m68knommu/page.h b/include/asm-m68knommu/page.h index 1e82ebb7d644..3a1ede4544cb 100644 --- a/include/asm-m68knommu/page.h +++ b/include/asm-m68knommu/page.h @@ -43,9 +43,6 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - extern unsigned long memory_start; extern unsigned long memory_end; diff --git a/include/asm-mips/page.h b/include/asm-mips/page.h index 494f00ba9541..fe7a88ea066e 100644 --- a/include/asm-mips/page.h +++ b/include/asm-mips/page.h @@ -137,9 +137,6 @@ typedef struct { unsigned long pgprot; } pgprot_t; #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - /* * __pa()/__va() should be used only during mem init. */ diff --git a/include/asm-mips/processor.h b/include/asm-mips/processor.h index 58cbac5a64e4..a1e4453469f9 100644 --- a/include/asm-mips/processor.h +++ b/include/asm-mips/processor.h @@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count; * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) +#define TASK_UNMAPPED_BASE ((TASK_SIZE / 3) & ~(PAGE_SIZE)) #endif #ifdef CONFIG_64BIT diff --git a/include/asm-mn10300/page.h b/include/asm-mn10300/page.h index 124971b9fb9b..8288e124165b 100644 --- a/include/asm-mn10300/page.h +++ b/include/asm-mn10300/page.h @@ -61,9 +61,6 @@ typedef struct page *pgtable_t; #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - /* * This handles the memory map.. We could make this a config * option, but too many people screw it up, and too few need diff --git a/include/asm-parisc/page.h b/include/asm-parisc/page.h index 27d50b859541..c3941f09a878 100644 --- a/include/asm-parisc/page.h +++ b/include/asm-parisc/page.h @@ -119,10 +119,6 @@ extern int npmem_ranges; #define PMD_ENTRY_SIZE (1UL << BITS_PER_PMD_ENTRY) #define PTE_ENTRY_SIZE (1UL << BITS_PER_PTE_ENTRY) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - - #define LINUX_GATEWAY_SPACE 0 /* This governs the relationship between virtual and physical addresses. diff --git a/include/asm-powerpc/page.h b/include/asm-powerpc/page.h index cffdf0eb0df6..e088545cb3f5 100644 --- a/include/asm-powerpc/page.h +++ b/include/asm-powerpc/page.h @@ -119,9 +119,6 @@ extern phys_addr_t kernstart_addr; /* align addr on a size boundary - adjust address up if needed */ #define _ALIGN(addr,size) _ALIGN_UP(addr,size) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE) - /* * Don't compare things with KERNELBASE or PAGE_OFFSET to test for * "kernelness", use is_kernel_addr() - it should do what you want. diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h index 12fd9c4f0f15..991ba939408c 100644 --- a/include/asm-s390/page.h +++ b/include/asm-s390/page.h @@ -138,9 +138,6 @@ void arch_alloc_page(struct page *page, int order); #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #define __PAGE_OFFSET 0x0UL #define PAGE_OFFSET 0x0UL #define __pa(x) (unsigned long)(x) diff --git a/include/asm-sh/page.h b/include/asm-sh/page.h index 304c30b5d947..5dc01d2fcc4c 100644 --- a/include/asm-sh/page.h +++ b/include/asm-sh/page.h @@ -22,9 +22,6 @@ #define PAGE_MASK (~(PAGE_SIZE-1)) #define PTE_MASK PAGE_MASK -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #if defined(CONFIG_HUGETLB_PAGE_SIZE_64K) #define HPAGE_SHIFT 16 #elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K) diff --git a/include/asm-sparc/page_32.h b/include/asm-sparc/page_32.h index 14de518cc38f..cf5fb70ca1c1 100644 --- a/include/asm-sparc/page_32.h +++ b/include/asm-sparc/page_32.h @@ -134,9 +134,6 @@ BTFIXUPDEF_SETHI(sparc_unmapped_base) #endif /* !(__ASSEMBLY__) */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #define PAGE_OFFSET 0xf0000000 #ifndef __ASSEMBLY__ extern unsigned long phys_base; diff --git a/include/asm-sparc/page_64.h b/include/asm-sparc/page_64.h index a8a2bba032c1..b579b910ef51 100644 --- a/include/asm-sparc/page_64.h +++ b/include/asm-sparc/page_64.h @@ -106,9 +106,6 @@ typedef struct page *pgtable_t; #endif /* !(__ASSEMBLY__) */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - /* We used to stick this into a hard-coded global register (%g4) * but that does not make sense anymore. */ diff --git a/include/asm-um/page.h b/include/asm-um/page.h index 916e1a61999f..335c57383c02 100644 --- a/include/asm-um/page.h +++ b/include/asm-um/page.h @@ -92,9 +92,6 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - extern unsigned long uml_physmem; #define PAGE_OFFSET (uml_physmem) diff --git a/include/asm-v850/page.h b/include/asm-v850/page.h index 74a539a9bd59..f9de35d873fa 100644 --- a/include/asm-v850/page.h +++ b/include/asm-v850/page.h @@ -94,10 +94,6 @@ typedef unsigned long pgprot_t; #endif /* !__ASSEMBLY__ */ -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK) - - /* No current v850 processor has virtual memory. */ #define __virt_to_phys(addr) (addr) #define __phys_to_virt(addr) (addr) diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 6e02098b1605..49982110e4d9 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -34,9 +34,6 @@ #define HUGE_MAX_HSTATE 2 -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - #ifndef __ASSEMBLY__ #include #endif diff --git a/include/asm-xtensa/page.h b/include/asm-xtensa/page.h index 80a6ae0dd259..11f7dc2dbec7 100644 --- a/include/asm-xtensa/page.h +++ b/include/asm-xtensa/page.h @@ -26,13 +26,11 @@ /* * PAGE_SHIFT determines the page size - * PAGE_ALIGN(x) aligns the pointer to the (next) page boundary */ #define PAGE_SHIFT 12 #define PAGE_SIZE (__XTENSA_UL_CONST(1) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE - 1) & PAGE_MASK) #define PAGE_OFFSET XCHAL_KSEG_CACHED_VADDR #define MAX_MEM_PFN XCHAL_KSEG_SIZE diff --git a/include/linux/mm.h b/include/linux/mm.h index df322fb4df31..d87a5a5fe87d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,9 @@ extern unsigned long mmap_min_addr; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) + /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way diff --git a/sound/core/info.c b/sound/core/info.c index cb5ead3e202d..c67773ad9298 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -21,6 +21,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From aaca0bdca573f3f51ea03139f9c7289541e7bca3 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:20 -0700 Subject: flag parameters: paccept This patch is by far the most complex in the series. It adds a new syscall paccept. This syscall differs from accept in that it adds (at the userlevel) two additional parameters: - a signal mask - a flags value The flags parameter can be used to set flag like SOCK_CLOEXEC. This is imlpemented here as well. Some people argued that this is a property which should be inherited from the file desriptor for the server but this is against POSIX. Additionally, we really want the signal mask parameter as well (similar to pselect, ppoll, etc). So an interface change in inevitable. The flag value is the same as for socket and socketpair. I think diverging here will only create confusion. Similar to the filesystem interfaces where the use of the O_* constants differs, it is acceptable here. The signal mask is handled as for pselect etc. The mask is temporarily installed for the thread and removed before the call returns. I modeled the code after pselect. If there is a problem it's likely also in pselect. For architectures which use socketcall I maintained this interface instead of adding a system call. The symmetry shouldn't be broken. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #include #include #include #include #ifndef __NR_paccept # ifdef __x86_64__ # define __NR_paccept 288 # elif defined __i386__ # define SYS_PACCEPT 18 # define USE_SOCKETCALL 1 # else # error "need __NR_paccept" # endif #endif #ifdef USE_SOCKETCALL # define paccept(fd, addr, addrlen, mask, flags) \ ({ long args[6] = { \ (long) fd, (long) addr, (long) addrlen, (long) mask, 8, (long) flags }; \ syscall (__NR_socketcall, SYS_PACCEPT, args); }) #else # define paccept(fd, addr, addrlen, mask, flags) \ syscall (__NR_paccept, fd, addr, addrlen, mask, 8, flags) #endif #define PORT 57392 #define SOCK_CLOEXEC O_CLOEXEC static pthread_barrier_t b; static void * tf (void *arg) { pthread_barrier_wait (&b); int s = socket (AF_INET, SOCK_STREAM, 0); struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); s = socket (AF_INET, SOCK_STREAM, 0); sin.sin_port = htons (PORT); connect (s, (const struct sockaddr *) &sin, sizeof (sin)); close (s); pthread_barrier_wait (&b); pthread_barrier_wait (&b); sleep (2); pthread_kill ((pthread_t) arg, SIGUSR1); return NULL; } static void handler (int s) { } int main (void) { pthread_barrier_init (&b, NULL, 2); struct sockaddr_in sin; pthread_t th; if (pthread_create (&th, NULL, tf, (void *) pthread_self ()) != 0) { puts ("pthread_create failed"); return 1; } int s = socket (AF_INET, SOCK_STREAM, 0); int reuse = 1; setsockopt (s, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof (reuse)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = htonl (INADDR_LOOPBACK); sin.sin_port = htons (PORT); bind (s, (struct sockaddr *) &sin, sizeof (sin)); listen (s, SOMAXCONN); pthread_barrier_wait (&b); int s2 = paccept (s, NULL, 0, NULL, 0); if (s2 < 0) { puts ("paccept(0) failed"); return 1; } int coe = fcntl (s2, F_GETFD); if (coe & FD_CLOEXEC) { puts ("paccept(0) set close-on-exec-flag"); return 1; } close (s2); pthread_barrier_wait (&b); s2 = paccept (s, NULL, 0, NULL, SOCK_CLOEXEC); if (s2 < 0) { puts ("paccept(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (s2, F_GETFD); if ((coe & FD_CLOEXEC) == 0) { puts ("paccept(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (s2); pthread_barrier_wait (&b); struct sigaction sa; sa.sa_handler = handler; sa.sa_flags = 0; sigemptyset (&sa.sa_mask); sigaction (SIGUSR1, &sa, NULL); sigset_t ss; pthread_sigmask (SIG_SETMASK, NULL, &ss); sigaddset (&ss, SIGUSR1); pthread_sigmask (SIG_SETMASK, &ss, NULL); sigdelset (&ss, SIGUSR1); alarm (4); pthread_barrier_wait (&b); errno = 0 ; s2 = paccept (s, NULL, 0, &ss, 0); if (s2 != -1 || errno != EINTR) { puts ("paccept did not fail with EINTR"); return 1; } close (s); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: make it compile] [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Cc: "David S. Miller" Cc: Roland McGrath Cc: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-alpha/socket.h | 5 +++ include/asm-parisc/socket.h | 5 +++ include/asm-x86/unistd_64.h | 2 ++ include/linux/net.h | 3 ++ include/linux/syscalls.h | 2 ++ kernel/sys_ni.c | 1 + net/compat.c | 52 ++++++++++++++++++++++++++--- net/socket.c | 81 ++++++++++++++++++++++++++++++++++++++++----- 8 files changed, 139 insertions(+), 12 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-alpha/socket.h b/include/asm-alpha/socket.h index 08c979319929..a1057c2d95e7 100644 --- a/include/asm-alpha/socket.h +++ b/include/asm-alpha/socket.h @@ -62,4 +62,9 @@ #define SO_MARK 36 +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 + #endif /* _ASM_SOCKET_H */ diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h index 69a7a0d30b02..fba402c95ac2 100644 --- a/include/asm-parisc/socket.h +++ b/include/asm-parisc/socket.h @@ -54,4 +54,9 @@ #define SO_MARK 0x401f +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 + #endif /* _ASM_SOCKET_H */ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index 9c1a4a3470d9..e323994a370f 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -639,6 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate) __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) #define __NR_timerfd_gettime 287 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) +#define __NR_paccept 288 +__SYSCALL(__NR_paccept, sys_paccept) #ifndef __NO_STUBS diff --git a/include/linux/net.h b/include/linux/net.h index 8b5383c45b45..3a9b06d4d0fe 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -47,6 +47,7 @@ struct net; #define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */ #define SYS_SENDMSG 16 /* sys_sendmsg(2) */ #define SYS_RECVMSG 17 /* sys_recvmsg(2) */ +#define SYS_PACCEPT 18 /* sys_paccept(2) */ typedef enum { SS_FREE = 0, /* not allocated */ @@ -219,6 +220,8 @@ extern int sock_map_fd(struct socket *sock, int flags); extern struct socket *sockfd_lookup(int fd, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); +extern long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); #define net_random() random32() #define net_srandom(seed) srandom32((__force u32)seed) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4394dadff813..2a2a40af6b2c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -409,6 +409,8 @@ asmlinkage long sys_getsockopt(int fd, int level, int optname, asmlinkage long sys_bind(int, struct sockaddr __user *, int); asmlinkage long sys_connect(int, struct sockaddr __user *, int); asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_paccept(int, struct sockaddr __user *, int __user *, + const sigset_t *, size_t, int); asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); asmlinkage long sys_send(int, void __user *, size_t, unsigned); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 0fea0ee12da9..2f0b8a2e600f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -31,6 +31,7 @@ cond_syscall(sys_socketpair); cond_syscall(sys_bind); cond_syscall(sys_listen); cond_syscall(sys_accept); +cond_syscall(sys_paccept); cond_syscall(sys_connect); cond_syscall(sys_getsockname); cond_syscall(sys_getpeername); diff --git a/net/compat.c b/net/compat.c index 6e1b03b51933..67fb6a3834a3 100644 --- a/net/compat.c +++ b/net/compat.c @@ -722,9 +722,10 @@ EXPORT_SYMBOL(compat_mc_getsockopt); /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) -static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), +static unsigned char nas[19]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)}; + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) @@ -737,13 +738,52 @@ asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, uns return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } +asmlinkage long compat_sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret == -ERESTARTNOHAND) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; u32 a[6]; u32 a0, a1; - if (call < SYS_SOCKET || call > SYS_RECVMSG) + if (call < SYS_SOCKET || call > SYS_PACCEPT) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -764,7 +804,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) ret = sys_listen(a0, a1); break; case SYS_ACCEPT: - ret = sys_accept(a0, compat_ptr(a1), compat_ptr(a[2])); + ret = do_accept(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETSOCKNAME: ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2])); @@ -804,6 +844,10 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; + case SYS_PACCEPT: + ret = compat_sys_paccept(a0, compat_ptr(a1), compat_ptr(a[2]), + compat_ptr(a[3]), a[4], a[5]); + break; default: ret = -EINVAL; break; diff --git a/net/socket.c b/net/socket.c index 64601f900352..a0ce8ad72252 100644 --- a/net/socket.c +++ b/net/socket.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1225,6 +1226,9 @@ asmlinkage long sys_socket(int family, int type, int protocol) return -EINVAL; type &= SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + retval = sock_create(family, type, protocol, &sock); if (retval < 0) goto out; @@ -1259,6 +1263,9 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, return -EINVAL; type &= SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. @@ -1413,14 +1420,20 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen) +long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; struct sockaddr_storage address; + if (flags & ~SOCK_CLOEXEC) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1438,7 +1451,7 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, */ __module_get(newsock->ops->owner); - newfd = sock_alloc_fd(&newfile, 0); + newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); @@ -1491,6 +1504,50 @@ out_fd: goto out_put; } +asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const sigset_t __user *sigmask, + size_t sigsetsize, int flags) +{ + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) + return -EFAULT; + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret < 0 && signal_pending(current)) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + +asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen) +{ + return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0); +} + /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. @@ -2011,10 +2068,11 @@ out: /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[18]={ +static const unsigned char nargs[19]={ AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3) + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6) }; #undef AL @@ -2033,7 +2091,7 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) unsigned long a0, a1; int err; - if (call < 1 || call > SYS_RECVMSG) + if (call < 1 || call > SYS_PACCEPT) return -EINVAL; /* copy_from_user should be SMP safe. */ @@ -2062,8 +2120,8 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) break; case SYS_ACCEPT: err = - sys_accept(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + do_accept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = @@ -2110,6 +2168,13 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_PACCEPT: + err = + sys_paccept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], + (const sigset_t __user *) a[3], + a[4], a[5]); + break; default: err = -EINVAL; break; -- cgit v1.2.3 From 9deb27baedb79759c3ab9435a7d8b841842d56e9 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:24 -0700 Subject: flag parameters: signalfd This patch adds the new signalfd4 syscall. It extends the old signalfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is SFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name SFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_CLOEXEC O_CLOEXEC int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("signalfd4(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC); if (fd == -1) { puts ("signalfd4(SFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/compat.c | 14 ++++++++++---- fs/signalfd.c | 14 ++++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/signalfd.h | 5 +++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 9 files changed, 34 insertions(+), 6 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 021d71bc69b5..c308128b9251 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -826,4 +826,5 @@ ia32_sys_call_table: .quad sys32_fallocate .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime + .quad compat_sys_signalfd4 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index adff5562f5fd..c12a36c9fd51 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -326,3 +326,4 @@ ENTRY(sys_call_table) .long sys_fallocate .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime + .long sys_signalfd4 diff --git a/fs/compat.c b/fs/compat.c index b46604281766..106eba28ec5a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -2131,9 +2131,9 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, #ifdef CONFIG_SIGNALFD -asmlinkage long compat_sys_signalfd(int ufd, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize) +asmlinkage long compat_sys_signalfd4(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) { compat_sigset_t ss32; sigset_t tmp; @@ -2148,9 +2148,15 @@ asmlinkage long compat_sys_signalfd(int ufd, if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) return -EFAULT; - return sys_signalfd(ufd, ksigmask, sizeof(sigset_t)); + return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); } +asmlinkage long compat_sys_signalfd(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); +} #endif /* CONFIG_SIGNALFD */ #ifdef CONFIG_TIMERFD diff --git a/fs/signalfd.c b/fs/signalfd.c index ddb328b74bde..c8609fa51a13 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -205,11 +205,15 @@ static const struct file_operations signalfd_fops = { .read = signalfd_read, }; -asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask) +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, + size_t sizemask, int flags) { sigset_t sigmask; struct signalfd_ctx *ctx; + if (flags & ~SFD_CLOEXEC) + return -EINVAL; + if (sizemask != sizeof(sigset_t) || copy_from_user(&sigmask, user_mask, sizeof(sigmask))) return -EINVAL; @@ -228,7 +232,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas * anon_inode_getfd() will install the fd. */ ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx, - 0); + flags & O_CLOEXEC); if (ufd < 0) kfree(ctx); } else { @@ -250,3 +254,9 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas return ufd; } + +asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, + size_t sizemask) +{ + return sys_signalfd4(ufd, user_mask, sizemask, 0); +} diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index 8317d94771d3..c310371f5613 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -332,6 +332,7 @@ #define __NR_fallocate 324 #define __NR_timerfd_settime 325 #define __NR_timerfd_gettime 326 +#define __NR_signalfd4 327 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index e323994a370f..e0a9b45b2346 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -641,6 +641,8 @@ __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) #define __NR_paccept 288 __SYSCALL(__NR_paccept, sys_paccept) +#define __NR_signalfd4 289 +__SYSCALL(__NR_signalfd4, sys_signalfd4) #ifndef __NO_STUBS diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index ea037f28df91..8b3f7b7420a1 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -8,6 +8,11 @@ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H +/* For O_CLOEXEC */ +#include + +/* Flags for signalfd4. */ +#define SFD_CLOEXEC O_CLOEXEC struct signalfd_siginfo { __u32 ssi_signo; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2a2a40af6b2c..1c2707797845 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,6 +610,7 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, const struct itimerspec __user *utmr, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 2f0b8a2e600f..8627c89ae9e8 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -156,6 +156,7 @@ cond_syscall(sys_ioprio_get); /* New file descriptors */ cond_syscall(sys_signalfd); +cond_syscall(sys_signalfd4); cond_syscall(compat_sys_signalfd); cond_syscall(sys_timerfd_create); cond_syscall(sys_timerfd_settime); -- cgit v1.2.3 From b087498eb5605673b0f260a7620d91818cd72304 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:25 -0700 Subject: flag parameters: eventfd This patch adds the new eventfd2 syscall. It extends the old eventfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EFD_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("eventfd2(0) sets close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC); if (fd == -1) { puts ("eventfd2(EFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/eventfd.c | 13 +++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/eventfd.h | 6 ++++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 8 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index c308128b9251..cf0eb31745ca 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -827,4 +827,5 @@ ia32_sys_call_table: .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 + .quad sys_eventfd2 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index c12a36c9fd51..cf112cb11c37 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -327,3 +327,4 @@ ENTRY(sys_call_table) .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime .long sys_signalfd4 + .long sys_eventfd2 diff --git a/fs/eventfd.c b/fs/eventfd.c index 6094265ca409..bd420e6478ad 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -198,11 +198,14 @@ struct file *eventfd_fget(int fd) return file; } -asmlinkage long sys_eventfd(unsigned int count) +asmlinkage long sys_eventfd2(unsigned int count, int flags) { int fd; struct eventfd_ctx *ctx; + if (flags & ~EFD_CLOEXEC) + return -EINVAL; + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -214,9 +217,15 @@ asmlinkage long sys_eventfd(unsigned int count) * When we call this, the initialization must be complete, since * anon_inode_getfd() will install the fd. */ - fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, 0); + fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, + flags & O_CLOEXEC); if (fd < 0) kfree(ctx); return fd; } +asmlinkage long sys_eventfd(unsigned int count) +{ + return sys_eventfd2(count, 0); +} + diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index c310371f5613..edbd8723c939 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -333,6 +333,7 @@ #define __NR_timerfd_settime 325 #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 +#define __NR_eventfd2 328 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index e0a9b45b2346..fb059a6feeb1 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -643,6 +643,8 @@ __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) __SYSCALL(__NR_paccept, sys_paccept) #define __NR_signalfd4 289 __SYSCALL(__NR_signalfd4, sys_signalfd4) +#define __NR_eventfd2 290 +__SYSCALL(__NR_eventfd2, sys_eventfd2) #ifndef __NO_STUBS diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index a701399b7fed..a6c0eaedb1b0 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -10,6 +10,12 @@ #ifdef CONFIG_EVENTFD +/* For O_CLOEXEC */ +#include + +/* Flags for eventfd2. */ +#define EFD_CLOEXEC O_CLOEXEC + struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, int n); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1c2707797845..9ab09926a7f2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -617,6 +617,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, struct itimerspec __user *otmr); asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_eventfd2(unsigned int count, int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 8627c89ae9e8..2a361ccdc7ca 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -164,3 +164,4 @@ cond_syscall(sys_timerfd_gettime); cond_syscall(compat_sys_timerfd_settime); cond_syscall(compat_sys_timerfd_gettime); cond_syscall(sys_eventfd); +cond_syscall(sys_eventfd2); -- cgit v1.2.3 From a0998b50c3f0b8fdd265c63e0032f86ebe377dbf Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:27 -0700 Subject: flag parameters: epoll_create This patch adds the new epoll_create2 syscall. It extends the old epoll_create syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EPOLL_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 1, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/eventpoll.c | 13 +++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/eventpoll.h | 4 ++++ include/linux/syscalls.h | 1 + 7 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index cf0eb31745ca..04366f08f424 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,4 +828,5 @@ ia32_sys_call_table: .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 .quad sys_eventfd2 + .quad sys_epoll_create2 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index cf112cb11c37..4d7007ca263d 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -328,3 +328,4 @@ ENTRY(sys_call_table) .long sys_timerfd_gettime .long sys_signalfd4 .long sys_eventfd2 + .long sys_epoll_create2 diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9392dd968125..3fd4014f3c5a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1046,11 +1046,14 @@ retry: * RB tree. With the current implementation, the "size" parameter is ignored * (besides sanity checks). */ -asmlinkage long sys_epoll_create(int size) +asmlinkage long sys_epoll_create2(int size, int flags) { int error, fd = -1; struct eventpoll *ep; + if (flags & ~EPOLL_CLOEXEC) + return -EINVAL; + DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n", current, size)); @@ -1068,7 +1071,8 @@ asmlinkage long sys_epoll_create(int size) * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ - fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep, 0); + fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep, + flags & O_CLOEXEC); if (fd < 0) ep_free(ep); @@ -1079,6 +1083,11 @@ error_return: return fd; } +asmlinkage long sys_epoll_create(int size) +{ + return sys_epoll_create2(size, 0); +} + /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index edbd8723c939..a37d6b0c4e1e 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -334,6 +334,7 @@ #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 #define __NR_eventfd2 328 +#define __NR_epoll_create2 329 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index fb059a6feeb1..a1a4a5b6e5ee 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -645,6 +645,8 @@ __SYSCALL(__NR_paccept, sys_paccept) __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 __SYSCALL(__NR_eventfd2, sys_eventfd2) +#define __NR_epoll_create2 291 +__SYSCALL(__NR_epoll_create2, sys_epoll_create2) #ifndef __NO_STUBS diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index cf79853967ff..1cfaa40059c8 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,8 +14,12 @@ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H +/* For O_CLOEXEC */ +#include #include +/* Flags for epoll_create2. */ +#define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ #define EPOLL_CTL_ADD 1 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 9ab09926a7f2..85953240f28c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -430,6 +430,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); +asmlinkage long sys_epoll_create2(int size, int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3 From 336dd1f70ff62d7dd8655228caed4c5bfc818c56 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:29 -0700 Subject: flag parameters: dup2 This patch adds the new dup3 syscall. It extends the old dup2 syscall by one parameter which is meant to hold a flag value. Support for the O_CLOEXEC flag is added in this patch. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_dup3 # ifdef __x86_64__ # define __NR_dup3 292 # elif defined __i386__ # define __NR_dup3 330 # else # error "need __NR_dup3" # endif #endif int main (void) { int fd = syscall (__NR_dup3, 1, 4, 0); if (fd == -1) { puts ("dup3(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("dup3(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_dup3, 1, 4, O_CLOEXEC); if (fd == -1) { puts ("dup3(O_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("dup3(O_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/fcntl.c | 15 +++++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/syscalls.h | 1 + 6 files changed, 19 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 04366f08f424..5614a8f7bed4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -829,4 +829,5 @@ ia32_sys_call_table: .quad compat_sys_signalfd4 .quad sys_eventfd2 .quad sys_epoll_create2 + .quad sys_dup3 /* 330 */ ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 4d7007ca263d..24a3f1ea6a0e 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -329,3 +329,4 @@ ENTRY(sys_call_table) .long sys_signalfd4 .long sys_eventfd2 .long sys_epoll_create2 + .long sys_dup3 /* 330 */ diff --git a/fs/fcntl.c b/fs/fcntl.c index 330a7d782591..9679fcbdeaa0 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -125,13 +125,16 @@ static int dupfd(struct file *file, unsigned int start, int cloexec) return fd; } -asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) +asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file * file, *tofree; struct files_struct * files = current->files; struct fdtable *fdt; + if ((flags & ~O_CLOEXEC) != 0) + return -EINVAL; + spin_lock(&files->file_lock); if (!(file = fcheck(oldfd))) goto out_unlock; @@ -163,7 +166,10 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) rcu_assign_pointer(fdt->fd[newfd], file); FD_SET(newfd, fdt->open_fds); - FD_CLR(newfd, fdt->close_on_exec); + if (flags & O_CLOEXEC) + FD_SET(newfd, fdt->close_on_exec); + else + FD_CLR(newfd, fdt->close_on_exec); spin_unlock(&files->file_lock); if (tofree) @@ -181,6 +187,11 @@ out_fput: goto out; } +asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) +{ + return sys_dup3(oldfd, newfd, 0); +} + asmlinkage long sys_dup(unsigned int fildes) { int ret = -EBADF; diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index a37d6b0c4e1e..a1f6383bf695 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -335,6 +335,7 @@ #define __NR_signalfd4 327 #define __NR_eventfd2 328 #define __NR_epoll_create2 329 +#define __NR_dup3 330 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index a1a4a5b6e5ee..f0fb2bd40cdb 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -647,6 +647,8 @@ __SYSCALL(__NR_signalfd4, sys_signalfd4) __SYSCALL(__NR_eventfd2, sys_eventfd2) #define __NR_epoll_create2 291 __SYSCALL(__NR_epoll_create2, sys_epoll_create2) +#define __NR_dup3 292 +__SYSCALL(__NR_dup3, sys_dup3) #ifndef __NO_STUBS diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 85953240f28c..034d3358549e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -305,6 +305,7 @@ asmlinkage long sys_fcntl64(unsigned int fd, #endif asmlinkage long sys_dup(unsigned int fildes); asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); +asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From ed8cae8ba01348bfd83333f4648dd807b04d7f08 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:30 -0700 Subject: flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/ia32/sys_ia32.c | 2 +- arch/ia64/kernel/sys_ia64.c | 2 +- arch/mips/kernel/syscall.c | 2 +- arch/parisc/hpux/sys_hpux.c | 2 +- arch/sh/kernel/sys_sh32.c | 2 +- arch/sparc/kernel/sys_sparc.c | 2 +- arch/sparc64/kernel/sys_sparc.c | 2 +- arch/x86/ia32/ia32entry.S | 1 + arch/x86/ia32/sys_ia32.c | 2 +- arch/x86/kernel/syscall_table_32.S | 1 + arch/xtensa/kernel/syscall.c | 2 +- fs/pipe.c | 23 ++++++++++++++++++----- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/fs.h | 1 + 15 files changed, 33 insertions(+), 14 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 7e028ceb93ba..465116aecb85 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1139,7 +1139,7 @@ sys32_pipe (int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index 1eda194b9559..bcbb6d8792d3 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -160,7 +160,7 @@ sys_pipe (void) int fd[2]; int retval; - retval = do_pipe(fd); + retval = do_pipe_flags(fd, 0); if (retval) goto out; retval = fd[0]; diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3523c8d12eda..343015a2f418 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -52,7 +52,7 @@ asmlinkage int sysm_pipe(nabi_no_regargs volatile struct pt_regs regs) int fd[2]; int error, res; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) { res = error; goto out; diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c index 0c5b9dabb475..be255ebb609c 100644 --- a/arch/parisc/hpux/sys_hpux.c +++ b/arch/parisc/hpux/sys_hpux.c @@ -448,7 +448,7 @@ int hpux_pipe(int *kstack_fildes) int error; lock_kernel(); - error = do_pipe(kstack_fildes); + error = do_pipe_flags(kstack_fildes, 0); unlock_kernel(); return error; } diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 125e493ead82..f0aa5c398656 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -29,7 +29,7 @@ asmlinkage int sys_pipe(unsigned long r4, unsigned long r5, int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (!error) { regs->regs[1] = fd[1]; return fd[0]; diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c index 3c6b49a53ae8..4d73421559c3 100644 --- a/arch/sparc/kernel/sys_sparc.c +++ b/arch/sparc/kernel/sys_sparc.c @@ -97,7 +97,7 @@ asmlinkage int sparc_pipe(struct pt_regs *regs) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) goto out; regs->u_regs[UREG_I1] = fd[1]; diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c index e1f4eba2e576..39749e32dc7e 100644 --- a/arch/sparc64/kernel/sys_sparc.c +++ b/arch/sparc64/kernel/sys_sparc.c @@ -418,7 +418,7 @@ asmlinkage long sparc_pipe(struct pt_regs *regs) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) goto out; regs->u_regs[UREG_I1] = fd[1]; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 5614a8f7bed4..18808b164570 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -830,4 +830,5 @@ ia32_sys_call_table: .quad sys_eventfd2 .quad sys_epoll_create2 .quad sys_dup3 /* 330 */ + .quad sys_pipe2 ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f00afdf61e67..d3c64088b981 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -238,7 +238,7 @@ asmlinkage long sys32_pipe(int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 24a3f1ea6a0e..66154769d52f 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -330,3 +330,4 @@ ENTRY(sys_call_table) .long sys_eventfd2 .long sys_epoll_create2 .long sys_dup3 /* 330 */ + .long sys_pipe2 diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index f3e16efcd47a..ac15ecbdf919 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -49,7 +49,7 @@ asmlinkage long xtensa_pipe(int __user *userfds) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (!error) { if (copy_to_user(userfds, fd, 2 * sizeof(int))) error = -EFAULT; diff --git a/fs/pipe.c b/fs/pipe.c index 700f4e0d9572..68e82061070c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1027,12 +1027,15 @@ struct file *create_read_pipe(struct file *wrf) return f; } -int do_pipe(int *fd) +int do_pipe_flags(int *fd, int flags) { struct file *fw, *fr; int error; int fdw, fdr; + if (flags & ~O_CLOEXEC) + return -EINVAL; + fw = create_write_pipe(); if (IS_ERR(fw)) return PTR_ERR(fw); @@ -1041,12 +1044,12 @@ int do_pipe(int *fd) if (IS_ERR(fr)) goto err_write_pipe; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; @@ -1074,16 +1077,21 @@ int do_pipe(int *fd) return error; } +int do_pipe(int *fd) +{ + return do_pipe_flags(fd, 0); +} + /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ -asmlinkage long __weak sys_pipe(int __user *fildes) +asmlinkage long __weak sys_pipe2(int __user *fildes, int flags) { int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, flags); if (!error) { if (copy_to_user(fildes, fd, sizeof(fd))) { sys_close(fd[0]); @@ -1094,6 +1102,11 @@ asmlinkage long __weak sys_pipe(int __user *fildes) return error; } +asmlinkage long __weak sys_pipe(int __user *fildes) +{ + return sys_pipe2(fildes, 0); +} + /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index a1f6383bf695..748a05c77da4 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -336,6 +336,7 @@ #define __NR_eventfd2 328 #define __NR_epoll_create2 329 #define __NR_dup3 330 +#define __NR_pipe2 331 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index f0fb2bd40cdb..d2284b43ad58 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -649,6 +649,8 @@ __SYSCALL(__NR_eventfd2, sys_eventfd2) __SYSCALL(__NR_epoll_create2, sys_epoll_create2) #define __NR_dup3 292 __SYSCALL(__NR_dup3, sys_dup3) +#define __NR_pipe2 293 +__SYSCALL(__NR_pipe2, sys_pipe2) #ifndef __NO_STUBS diff --git a/include/linux/fs.h b/include/linux/fs.h index e5e6a244096c..0e80cd717d32 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,6 +1777,7 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern int do_pipe_flags(int *, int); extern struct file *create_read_pipe(struct file *f); extern struct file *create_write_pipe(void); extern void free_write_pipe(struct file *); -- cgit v1.2.3 From 4006553b06306b34054529477b06b68a1c66249b Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:32 -0700 Subject: flag parameters: inotify_init This patch introduces the new syscall inotify_init1 (note: the 1 stands for the one parameter the syscall takes, as opposed to no parameter before). The values accepted for this parameter are function-specific and defined in the inotify.h header. Here the values must match the O_* flags, though. In this patch CLOEXEC support is introduced. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("inotify_init1(0) set close-on-exit"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_CLOEXEC); if (fd == -1) { puts ("inotify_init1(IN_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/inotify_user.c | 12 ++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/inotify.h | 5 +++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + 8 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 18808b164570..4541073dd837 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -831,4 +831,5 @@ ia32_sys_call_table: .quad sys_epoll_create2 .quad sys_dup3 /* 330 */ .quad sys_pipe2 + .quad sys_inotify_init1 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 66154769d52f..f59aba5ff0f0 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -331,3 +331,4 @@ ENTRY(sys_call_table) .long sys_epoll_create2 .long sys_dup3 /* 330 */ .long sys_pipe2 + .long sys_inotify_init1 diff --git a/fs/inotify_user.c b/fs/inotify_user.c index 6676c06bb7c1..851005998cd4 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -566,7 +566,7 @@ static const struct inotify_operations inotify_user_ops = { .destroy_watch = free_inotify_user_watch, }; -asmlinkage long sys_inotify_init(void) +asmlinkage long sys_inotify_init1(int flags) { struct inotify_device *dev; struct inotify_handle *ih; @@ -574,7 +574,10 @@ asmlinkage long sys_inotify_init(void) struct file *filp; int fd, ret; - fd = get_unused_fd(); + if (flags & ~IN_CLOEXEC) + return -EINVAL; + + fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; @@ -638,6 +641,11 @@ out_put_fd: return ret; } +asmlinkage long sys_inotify_init(void) +{ + return sys_inotify_init1(0); +} + asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask) { struct inode *inode; diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index 748a05c77da4..b3daf503ab93 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -337,6 +337,7 @@ #define __NR_epoll_create2 329 #define __NR_dup3 330 #define __NR_pipe2 331 +#define __NR_inotify_init1 332 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index d2284b43ad58..c8cb88d70c6b 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -651,6 +651,8 @@ __SYSCALL(__NR_epoll_create2, sys_epoll_create2) __SYSCALL(__NR_dup3, sys_dup3) #define __NR_pipe2 293 __SYSCALL(__NR_pipe2, sys_pipe2) +#define __NR_inotify_init1 294 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) #ifndef __NO_STUBS diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 742b917e7d1b..72ef82120512 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,6 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H +/* For O_CLOEXEC */ +#include #include /* @@ -63,6 +65,9 @@ struct inotify_event { IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF | \ IN_MOVE_SELF) +/* Flags for sys_inotify_init1. */ +#define IN_CLOEXEC O_CLOEXEC + #ifdef __KERNEL__ #include diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 034d3358549e..93a7e7f017a6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -547,6 +547,7 @@ asmlinkage long sys_get_mempolicy(int __user *policy, unsigned long addr, unsigned long flags); asmlinkage long sys_inotify_init(void); +asmlinkage long sys_inotify_init1(int flags); asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask); asmlinkage long sys_inotify_rm_watch(int fd, u32 wd); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 2a361ccdc7ca..bd66ac5406f3 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -96,6 +96,7 @@ cond_syscall(sys_keyctl); cond_syscall(compat_sys_keyctl); cond_syscall(compat_sys_socketcall); cond_syscall(sys_inotify_init); +cond_syscall(sys_inotify_init1); cond_syscall(sys_inotify_add_watch); cond_syscall(sys_inotify_rm_watch); cond_syscall(sys_migrate_pages); -- cgit v1.2.3 From 9fe5ad9c8cef9ad5873d8ee55d1cf00d9b607df0 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:43 -0700 Subject: flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 2 +- arch/x86/kernel/syscall_table_32.S | 2 +- fs/eventpoll.c | 18 ++++++++++-------- include/asm-x86/unistd_32.h | 2 +- include/asm-x86/unistd_64.h | 4 ++-- include/linux/eventpoll.h | 2 +- include/linux/syscalls.h | 2 +- 7 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4541073dd837..e4bd1793a5e4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,7 +828,7 @@ ia32_sys_call_table: .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 .quad sys_eventfd2 - .quad sys_epoll_create2 + .quad sys_epoll_create1 .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index f59aba5ff0f0..d44395ff34c3 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -328,7 +328,7 @@ ENTRY(sys_call_table) .long sys_timerfd_gettime .long sys_signalfd4 .long sys_eventfd2 - .long sys_epoll_create2 + .long sys_epoll_create1 .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 2fdad4204044..0c87474f7917 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1046,7 +1046,7 @@ retry: * RB tree. With the current implementation, the "size" parameter is ignored * (besides sanity checks). */ -asmlinkage long sys_epoll_create2(int size, int flags) +asmlinkage long sys_epoll_create1(int flags) { int error, fd = -1; struct eventpoll *ep; @@ -1058,14 +1058,13 @@ asmlinkage long sys_epoll_create2(int size, int flags) return -EINVAL; DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n", - current, size)); + current, flags)); /* - * Sanity check on the size parameter, and create the internal data - * structure ( "struct eventpoll" ). + * Create the internal data structure ( "struct eventpoll" ). */ - error = -EINVAL; - if (size <= 0 || (error = ep_alloc(&ep)) < 0) { + error = ep_alloc(&ep); + if (error < 0) { fd = error; goto error_return; } @@ -1081,14 +1080,17 @@ asmlinkage long sys_epoll_create2(int size, int flags) error_return: DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n", - current, size, fd)); + current, flags, fd)); return fd; } asmlinkage long sys_epoll_create(int size) { - return sys_epoll_create2(size, 0); + if (size < 0) + return -EINVAL; + + return sys_epoll_create1(0); } /* diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index b3daf503ab93..d7394673b772 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -334,7 +334,7 @@ #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 #define __NR_eventfd2 328 -#define __NR_epoll_create2 329 +#define __NR_epoll_create1 329 #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index c8cb88d70c6b..3a341d791792 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -645,8 +645,8 @@ __SYSCALL(__NR_paccept, sys_paccept) __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 __SYSCALL(__NR_eventfd2, sys_eventfd2) -#define __NR_epoll_create2 291 -__SYSCALL(__NR_epoll_create2, sys_epoll_create2) +#define __NR_epoll_create1 291 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) #define __NR_dup3 292 __SYSCALL(__NR_dup3, sys_dup3) #define __NR_pipe2 293 diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 1cfaa40059c8..f1e1d3c47125 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -18,7 +18,7 @@ #include #include -/* Flags for epoll_create2. */ +/* Flags for epoll_create1. */ #define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 93a7e7f017a6..06f2bf76c030 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,7 +431,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); -asmlinkage long sys_epoll_create2(int size, int flags); +asmlinkage long sys_epoll_create1(int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3 From b6cd7da5be2522b62bbc48d41b36c828b88e02fe Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:28 +0200 Subject: ide-generic: remove "no_pci_devices()" quirk from ide_default_io_base() Since the decision to probe for ISA ide2-6 is now left to the user "no_pci_devices()" quirk is no longer needed and may be removed. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/asm-mips/mach-generic/ide.h | 18 ++++-------------- include/asm-x86/ide.h | 18 ++++-------------- 2 files changed, 8 insertions(+), 28 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-mips/mach-generic/ide.h b/include/asm-mips/mach-generic/ide.h index 71a01c5aec16..f34740ee6775 100644 --- a/include/asm-mips/mach-generic/ide.h +++ b/include/asm-mips/mach-generic/ide.h @@ -72,23 +72,13 @@ static __inline__ int ide_default_irq(unsigned long base) static __inline__ unsigned long ide_default_io_base(int index) { - /* - * If PCI is present then it is not safe to poke around - * the other legacy IDE ports. Only 0x1f0 and 0x170 are - * defined compatibility mode ports for PCI. A user can - * override this using ide= but we must default safe. - */ - if (no_pci_devices()) { - switch (index) { - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; - } - } switch (index) { case 0: return 0x1f0; case 1: return 0x170; + case 2: return 0x1e8; + case 3: return 0x168; + case 4: return 0x1e0; + case 5: return 0x160; default: return 0; } diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h index cf9c98e5bdb5..34050747f38c 100644 --- a/include/asm-x86/ide.h +++ b/include/asm-x86/ide.h @@ -36,23 +36,13 @@ static __inline__ int ide_default_irq(unsigned long base) static __inline__ unsigned long ide_default_io_base(int index) { - /* - * If PCI is present then it is not safe to poke around - * the other legacy IDE ports. Only 0x1f0 and 0x170 are - * defined compatibility mode ports for PCI. A user can - * override this using ide= but we must default safe. - */ - if (no_pci_devices()) { - switch(index) { - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; - } - } switch (index) { case 0: return 0x1f0; case 1: return 0x170; + case 2: return 0x1e8; + case 3: return 0x168; + case 4: return 0x1e0; + case 5: return 0x160; default: return 0; } -- cgit v1.2.3 From d83b8b85cd56a083d30df73f3fd5e4714591b910 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:30 +0200 Subject: ide: define MAX_HWIFS in * Now that ide_hwif_t instances are allocated dynamically the difference between MAX_HWIFS == 2 and MAX_HWIFS == 10 is ~100 bytes (x86-32) so use MAX_HWIFS == 10 on all archs except these ones that use MAX_HWIFS == 1. * Define MAX_HWIFS in instead of . [ Please note that avr32/cris/v850 have no and alpha/ia64/sh always define CONFIG_IDE_MAX_HWIFS. ] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/asm-arm/ide.h | 4 ---- include/asm-blackfin/ide.h | 2 -- include/asm-frv/ide.h | 4 ---- include/asm-h8300/ide.h | 2 -- include/asm-m32r/ide.h | 8 -------- include/asm-m68k/ide.h | 4 ---- include/asm-mips/mach-generic/ide.h | 8 -------- include/asm-mn10300/ide.h | 4 ---- include/asm-parisc/ide.h | 4 ---- include/asm-powerpc/ide.h | 8 -------- include/asm-sparc/ide.h | 3 --- include/asm-x86/ide.h | 9 --------- include/asm-xtensa/ide.h | 5 ----- include/linux/ide.h | 8 ++++++++ 14 files changed, 8 insertions(+), 65 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-arm/ide.h b/include/asm-arm/ide.h index 88f4d231ce4f..a48019f99d08 100644 --- a/include/asm-arm/ide.h +++ b/include/asm-arm/ide.h @@ -13,10 +13,6 @@ #ifdef __KERNEL__ -#ifndef MAX_HWIFS -#define MAX_HWIFS 4 -#endif - #define __ide_mm_insw(port,addr,len) readsw(port,addr,len) #define __ide_mm_insl(port,addr,len) readsl(port,addr,len) #define __ide_mm_outsw(port,addr,len) writesw(port,addr,len) diff --git a/include/asm-blackfin/ide.h b/include/asm-blackfin/ide.h index 5b88de115bf4..90bc50bd22e9 100644 --- a/include/asm-blackfin/ide.h +++ b/include/asm-blackfin/ide.h @@ -17,8 +17,6 @@ #ifdef __KERNEL__ /****************************************************************************/ -#define MAX_HWIFS 1 - #include /****************************************************************************/ diff --git a/include/asm-frv/ide.h b/include/asm-frv/ide.h index 8c9a540d4344..7ebcc56a2229 100644 --- a/include/asm-frv/ide.h +++ b/include/asm-frv/ide.h @@ -18,10 +18,6 @@ #include #include -#ifndef MAX_HWIFS -#define MAX_HWIFS 8 -#endif - /****************************************************************************/ /* * some bits needed for parts of the IDE subsystem to compile diff --git a/include/asm-h8300/ide.h b/include/asm-h8300/ide.h index f8535ce7476e..8f79ba2ff929 100644 --- a/include/asm-h8300/ide.h +++ b/include/asm-h8300/ide.h @@ -16,8 +16,6 @@ #ifdef __KERNEL__ /****************************************************************************/ -#define MAX_HWIFS 1 - #include /****************************************************************************/ diff --git a/include/asm-m32r/ide.h b/include/asm-m32r/ide.h index 72798d624221..d755d41b9931 100644 --- a/include/asm-m32r/ide.h +++ b/include/asm-m32r/ide.h @@ -15,14 +15,6 @@ #include -#ifndef MAX_HWIFS -# ifdef CONFIG_BLK_DEV_IDEPCI -#define MAX_HWIFS 10 -# else -#define MAX_HWIFS 2 -# endif -#endif - static __inline__ int ide_default_irq(unsigned long base) { switch (base) { diff --git a/include/asm-m68k/ide.h b/include/asm-m68k/ide.h index 909c6dfd3851..1daf6cbdd9f0 100644 --- a/include/asm-m68k/ide.h +++ b/include/asm-m68k/ide.h @@ -45,10 +45,6 @@ #include #endif -#ifndef MAX_HWIFS -#define MAX_HWIFS 4 /* same as the other archs */ -#endif - /* * Get rid of defs from io.h - ide has its private and conflicting versions * Since so far no single m68k platform uses ISA/PCI I/O space for IDE, we diff --git a/include/asm-mips/mach-generic/ide.h b/include/asm-mips/mach-generic/ide.h index f34740ee6775..8ee6bff030d9 100644 --- a/include/asm-mips/mach-generic/ide.h +++ b/include/asm-mips/mach-generic/ide.h @@ -19,14 +19,6 @@ #include #include -#ifndef MAX_HWIFS -# ifdef CONFIG_BLK_DEV_IDEPCI -#define MAX_HWIFS 10 -# else -#define MAX_HWIFS 6 -# endif -#endif - static __inline__ int ide_probe_legacy(void) { #ifdef CONFIG_PCI diff --git a/include/asm-mn10300/ide.h b/include/asm-mn10300/ide.h index dc235121ec42..6adcdd92e83d 100644 --- a/include/asm-mn10300/ide.h +++ b/include/asm-mn10300/ide.h @@ -23,10 +23,6 @@ #undef SUPPORT_VLB_SYNC #define SUPPORT_VLB_SYNC 0 -#ifndef MAX_HWIFS -#define MAX_HWIFS 8 -#endif - /* * some bits needed for parts of the IDE subsystem to compile */ diff --git a/include/asm-parisc/ide.h b/include/asm-parisc/ide.h index db0c94410095..c246ef75017d 100644 --- a/include/asm-parisc/ide.h +++ b/include/asm-parisc/ide.h @@ -13,10 +13,6 @@ #ifdef __KERNEL__ -#ifndef MAX_HWIFS -#define MAX_HWIFS 2 -#endif - #define ide_request_irq(irq,hand,flg,dev,id) request_irq((irq),(hand),(flg),(dev),(id)) #define ide_free_irq(irq,dev_id) free_irq((irq), (dev_id)) #define ide_request_region(from,extent,name) request_region((from), (extent), (name)) diff --git a/include/asm-powerpc/ide.h b/include/asm-powerpc/ide.h index 3d90bf7d3d73..262def6a9f0a 100644 --- a/include/asm-powerpc/ide.h +++ b/include/asm-powerpc/ide.h @@ -14,14 +14,6 @@ #endif #include -#ifndef MAX_HWIFS -#ifdef __powerpc64__ -#define MAX_HWIFS 10 -#else -#define MAX_HWIFS 8 -#endif -#endif - #define __ide_mm_insw(p, a, c) readsw((void __iomem *)(p), (a), (c)) #define __ide_mm_insl(p, a, c) readsl((void __iomem *)(p), (a), (c)) #define __ide_mm_outsw(p, a, c) writesw((void __iomem *)(p), (a), (c)) diff --git a/include/asm-sparc/ide.h b/include/asm-sparc/ide.h index 879fcec72dc1..b7af3d658239 100644 --- a/include/asm-sparc/ide.h +++ b/include/asm-sparc/ide.h @@ -21,9 +21,6 @@ #include #endif -#undef MAX_HWIFS -#define MAX_HWIFS 2 - #define __ide_insl(data_reg, buffer, wcount) \ __ide_insw(data_reg, buffer, (wcount)<<1) #define __ide_outsl(data_reg, buffer, wcount) \ diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h index 34050747f38c..bc54879daed1 100644 --- a/include/asm-x86/ide.h +++ b/include/asm-x86/ide.h @@ -11,15 +11,6 @@ #ifdef __KERNEL__ - -#ifndef MAX_HWIFS -# ifdef CONFIG_BLK_DEV_IDEPCI -#define MAX_HWIFS 10 -# else -#define MAX_HWIFS 6 -# endif -#endif - static __inline__ int ide_default_irq(unsigned long base) { switch (base) { diff --git a/include/asm-xtensa/ide.h b/include/asm-xtensa/ide.h index cb995701c42d..18342a2cc774 100644 --- a/include/asm-xtensa/ide.h +++ b/include/asm-xtensa/ide.h @@ -14,11 +14,6 @@ #ifdef __KERNEL__ - -#ifndef MAX_HWIFS -# define MAX_HWIFS 1 -#endif - #include #endif /* __KERNEL__ */ diff --git a/include/linux/ide.h b/include/linux/ide.h index dbd0aeb3a56d..76fe00b24b51 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -213,6 +213,14 @@ static inline int __ide_default_irq(unsigned long base) #include +#ifndef MAX_HWIFS +#if defined(CONFIG_BLACKFIN) || defined(CONFIG_H8300) || defined(CONFIG_XTENSA) +# define MAX_HWIFS 1 +#else +# define MAX_HWIFS 10 +#endif +#endif + #if !defined(MAX_HWIFS) || defined(CONFIG_EMBEDDED) #undef MAX_HWIFS #define MAX_HWIFS CONFIG_IDE_MAX_HWIFS -- cgit v1.2.3 From f01d35d87f39ab794ddcdefadb79c11054bcbfbc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:31 +0200 Subject: ide-generic: remove ide_default_{io_base,irq}() inlines (take 3) Replace ide_default_{io_base,irq}() inlines by legacy_{bases,irqs}[]. v2: Add missing zero-ing of hws[] (caught during testing by Borislav Petkov). v3: Fix zero-oing of hws[] for _real_ this time. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/ide/ide-generic.c | 32 +++++++++++++++++++++--- include/asm-alpha/ide.h | 24 ------------------ include/asm-ia64/ide.h | 29 --------------------- include/asm-m32r/ide.h | 50 ------------------------------------- include/asm-mips/mach-generic/ide.h | 28 --------------------- include/asm-x86/ide.h | 28 --------------------- 6 files changed, 29 insertions(+), 162 deletions(-) (limited to 'include/asm-x86') diff --git a/drivers/ide/ide-generic.c b/drivers/ide/ide-generic.c index 567fd843c7ff..8fe8b5b9cf7d 100644 --- a/drivers/ide/ide-generic.c +++ b/drivers/ide/ide-generic.c @@ -20,6 +20,11 @@ #include #include +/* FIXME: convert m32r to use ide_platform host driver */ +#ifdef CONFIG_M32R +#include +#endif + #define DRV_NAME "ide_generic" static int probe_mask = 0x03; @@ -80,6 +85,21 @@ static int __init ide_generic_sysfs_init(void) return 0; } +#if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_MAPPI2) \ + || defined(CONFIG_PLAT_OPSPUT) +static const u16 legacy_bases[] = { 0x1f0 }; +static const int legacy_irqs[] = { PLD_IRQ_CFIREQ }; +#elif defined(CONFIG_PLAT_MAPPI3) +static const u16 legacy_bases[] = { 0x1f0, 0x170 }; +static const int legacy_irqs[] = { PLD_IRQ_CFIREQ, PLD_IRQ_IDEIREQ }; +#elif defined(CONFIG_ALPHA) +static const u16 legacy_bases[] = { 0x1f0, 0x170, 0x1e8, 0x168 }; +static const int legacy_irqs[] = { 14, 15, 11, 10 }; +#else +static const u16 legacy_bases[] = { 0x1f0, 0x170, 0x1e8, 0x168, 0x1e0, 0x160 }; +static const int legacy_irqs[] = { 14, 15, 11, 10, 8, 12 }; +#endif + static int __init ide_generic_init(void) { hw_regs_t hw[MAX_HWIFS], *hws[MAX_HWIFS]; @@ -94,8 +114,10 @@ static int __init ide_generic_init(void) printk(KERN_INFO DRV_NAME ": please use \"probe_mask=0x3f\" module " "parameter for probing all legacy ISA IDE ports\n"); - for (i = 0; i < MAX_HWIFS; i++) { - io_addr = ide_default_io_base(i); + memset(hws, 0, sizeof(hw_regs_t *) * MAX_HWIFS); + + for (i = 0; i < ARRAY_SIZE(legacy_bases); i++) { + io_addr = legacy_bases[i]; hws[i] = NULL; @@ -117,7 +139,11 @@ static int __init ide_generic_init(void) memset(&hw[i], 0, sizeof(hw[i])); ide_std_init_ports(&hw[i], io_addr, io_addr + 0x206); - hw[i].irq = ide_default_irq(io_addr); +#ifdef CONFIG_IA64 + hw[i].irq = isa_irq_to_vector(legacy_irqs[i]); +#else + hw[i].irq = legacy_irqs[i]; +#endif hw[i].chipset = ide_generic; hws[i] = &hw[i]; diff --git a/include/asm-alpha/ide.h b/include/asm-alpha/ide.h index f44129abc02c..55f9f6870249 100644 --- a/include/asm-alpha/ide.h +++ b/include/asm-alpha/ide.h @@ -13,30 +13,6 @@ #ifdef __KERNEL__ -static inline int ide_default_irq(unsigned long base) -{ - switch (base) { - case 0x1f0: return 14; - case 0x170: return 15; - case 0x1e8: return 11; - case 0x168: return 10; - default: - return 0; - } -} - -static inline unsigned long ide_default_io_base(int index) -{ - switch (index) { - case 0: return 0x1f0; - case 1: return 0x170; - case 2: return 0x1e8; - case 3: return 0x168; - default: - return 0; - } -} - #include #endif /* __KERNEL__ */ diff --git a/include/asm-ia64/ide.h b/include/asm-ia64/ide.h index 8fa3f8cd067a..5a0aedea4764 100644 --- a/include/asm-ia64/ide.h +++ b/include/asm-ia64/ide.h @@ -13,37 +13,8 @@ #ifdef __KERNEL__ - #include -static inline int ide_default_irq(unsigned long base) -{ - switch (base) { - case 0x1f0: return isa_irq_to_vector(14); - case 0x170: return isa_irq_to_vector(15); - case 0x1e8: return isa_irq_to_vector(11); - case 0x168: return isa_irq_to_vector(10); - case 0x1e0: return isa_irq_to_vector(8); - case 0x160: return isa_irq_to_vector(12); - default: - return 0; - } -} - -static inline unsigned long ide_default_io_base(int index) -{ - switch (index) { - case 0: return 0x1f0; - case 1: return 0x170; - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; - default: - return 0; - } -} - #include #endif /* __KERNEL__ */ diff --git a/include/asm-m32r/ide.h b/include/asm-m32r/ide.h index d755d41b9931..0f1ec6973879 100644 --- a/include/asm-m32r/ide.h +++ b/include/asm-m32r/ide.h @@ -13,56 +13,6 @@ #ifdef __KERNEL__ -#include - -static __inline__ int ide_default_irq(unsigned long base) -{ - switch (base) { -#if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_MAPPI2) \ - || defined(CONFIG_PLAT_OPSPUT) - case 0x1f0: return PLD_IRQ_CFIREQ; - default: - return 0; -#elif defined(CONFIG_PLAT_MAPPI3) - case 0x1f0: return PLD_IRQ_CFIREQ; - case 0x170: return PLD_IRQ_IDEIREQ; - default: - return 0; -#else - case 0x1f0: return 14; - case 0x170: return 15; - case 0x1e8: return 11; - case 0x168: return 10; - case 0x1e0: return 8; - case 0x160: return 12; - default: - return 0; -#endif - } -} - -static __inline__ unsigned long ide_default_io_base(int index) -{ - switch (index) { -#if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_MAPPI2) \ - || defined(CONFIG_PLAT_OPSPUT) - case 0: return 0x1f0; -#elif defined(CONFIG_PLAT_MAPPI3) - case 0: return 0x1f0; - case 1: return 0x170; -#else - case 0: return 0x1f0; - case 1: return 0x170; - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; -#endif - default: - return 0; - } -} - #include #endif /* __KERNEL__ */ diff --git a/include/asm-mips/mach-generic/ide.h b/include/asm-mips/mach-generic/ide.h index 8ee6bff030d9..73008f7bdc93 100644 --- a/include/asm-mips/mach-generic/ide.h +++ b/include/asm-mips/mach-generic/ide.h @@ -48,34 +48,6 @@ found: #endif } -static __inline__ int ide_default_irq(unsigned long base) -{ - switch (base) { - case 0x1f0: return 14; - case 0x170: return 15; - case 0x1e8: return 11; - case 0x168: return 10; - case 0x1e0: return 8; - case 0x160: return 12; - default: - return 0; - } -} - -static __inline__ unsigned long ide_default_io_base(int index) -{ - switch (index) { - case 0: return 0x1f0; - case 1: return 0x170; - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; - default: - return 0; - } -} - /* MIPS port and memory-mapped I/O string operations. */ static inline void __ide_flush_prologue(void) { diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h index bc54879daed1..0289baf9ce0a 100644 --- a/include/asm-x86/ide.h +++ b/include/asm-x86/ide.h @@ -11,34 +11,6 @@ #ifdef __KERNEL__ -static __inline__ int ide_default_irq(unsigned long base) -{ - switch (base) { - case 0x1f0: return 14; - case 0x170: return 15; - case 0x1e8: return 11; - case 0x168: return 10; - case 0x1e0: return 8; - case 0x160: return 12; - default: - return 0; - } -} - -static __inline__ unsigned long ide_default_io_base(int index) -{ - switch (index) { - case 0: return 0x1f0; - case 1: return 0x170; - case 2: return 0x1e8; - case 3: return 0x168; - case 4: return 0x1e0; - case 5: return 0x160; - default: - return 0; - } -} - #include #endif /* __KERNEL__ */ -- cgit v1.2.3 From 2a8f7450f828eaee49d66f41f99ac2e54f1160a6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Thu, 24 Jul 2008 22:53:31 +0200 Subject: ide: remove for some archs * Remove include from ( includes which is enough). * Remove for alpha/blackfin/h8300/ia64/m32r/sh/x86/xtensa (this leaves us with arm/frv/m68k/mips/mn10300/parisc/powerpc/sparc[64]). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/asm-alpha/ide.h | 20 -------------------- include/asm-blackfin/ide.h | 25 ------------------------- include/asm-h8300/ide.h | 24 ------------------------ include/asm-ia64/ide.h | 22 ---------------------- include/asm-m32r/ide.h | 20 -------------------- include/asm-sh/ide.h | 21 --------------------- include/asm-x86/ide.h | 18 ------------------ include/asm-xtensa/ide.h | 21 --------------------- include/linux/ide.h | 6 ++++++ 9 files changed, 6 insertions(+), 171 deletions(-) delete mode 100644 include/asm-alpha/ide.h delete mode 100644 include/asm-blackfin/ide.h delete mode 100644 include/asm-h8300/ide.h delete mode 100644 include/asm-ia64/ide.h delete mode 100644 include/asm-m32r/ide.h delete mode 100644 include/asm-sh/ide.h delete mode 100644 include/asm-x86/ide.h delete mode 100644 include/asm-xtensa/ide.h (limited to 'include/asm-x86') diff --git a/include/asm-alpha/ide.h b/include/asm-alpha/ide.h deleted file mode 100644 index 55f9f6870249..000000000000 --- a/include/asm-alpha/ide.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * linux/include/asm-alpha/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - */ - -/* - * This file contains the alpha architecture specific IDE code. - */ - -#ifndef __ASMalpha_IDE_H -#define __ASMalpha_IDE_H - -#ifdef __KERNEL__ - -#include - -#endif /* __KERNEL__ */ - -#endif /* __ASMalpha_IDE_H */ diff --git a/include/asm-blackfin/ide.h b/include/asm-blackfin/ide.h deleted file mode 100644 index 90bc50bd22e9..000000000000 --- a/include/asm-blackfin/ide.h +++ /dev/null @@ -1,25 +0,0 @@ -/****************************************************************************/ - -/* - * linux/include/asm-blackfin/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - * Copyright (C) 2001 Lineo Inc., davidm@snapgear.com - * Copyright (C) 2002 Greg Ungerer (gerg@snapgear.com) - * Copyright (C) 2002 Yoshinori Sato (ysato@users.sourceforge.jp) - * Copyright (C) 2005 Hennerich Michael (hennerich@blackfin.uclinux.org) - */ - -/****************************************************************************/ -#ifndef _BLACKFIN_IDE_H -#define _BLACKFIN_IDE_H -/****************************************************************************/ -#ifdef __KERNEL__ -/****************************************************************************/ - -#include - -/****************************************************************************/ -#endif /* __KERNEL__ */ -#endif /* _BLACKFIN_IDE_H */ -/****************************************************************************/ diff --git a/include/asm-h8300/ide.h b/include/asm-h8300/ide.h deleted file mode 100644 index 8f79ba2ff929..000000000000 --- a/include/asm-h8300/ide.h +++ /dev/null @@ -1,24 +0,0 @@ -/****************************************************************************/ - -/* - * linux/include/asm-h8300/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - * Copyright (C) 2001 Lineo Inc., davidm@snapgear.com - * Copyright (C) 2002 Greg Ungerer (gerg@snapgear.com) - * Copyright (C) 2002 Yoshinori Sato (ysato@users.sourceforge.jp) - */ - -/****************************************************************************/ -#ifndef _H8300_IDE_H -#define _H8300_IDE_H -/****************************************************************************/ -#ifdef __KERNEL__ -/****************************************************************************/ - -#include - -/****************************************************************************/ -#endif /* __KERNEL__ */ -#endif /* _H8300_IDE_H */ -/****************************************************************************/ diff --git a/include/asm-ia64/ide.h b/include/asm-ia64/ide.h deleted file mode 100644 index 5a0aedea4764..000000000000 --- a/include/asm-ia64/ide.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * linux/include/asm-ia64/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - */ - -/* - * This file contains the ia64 architecture specific IDE code. - */ - -#ifndef __ASM_IA64_IDE_H -#define __ASM_IA64_IDE_H - -#ifdef __KERNEL__ - -#include - -#include - -#endif /* __KERNEL__ */ - -#endif /* __ASM_IA64_IDE_H */ diff --git a/include/asm-m32r/ide.h b/include/asm-m32r/ide.h deleted file mode 100644 index 0f1ec6973879..000000000000 --- a/include/asm-m32r/ide.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _ASM_M32R_IDE_H -#define _ASM_M32R_IDE_H - -/* - * linux/include/asm-m32r/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - */ - -/* - * This file contains the i386 architecture specific IDE code. - */ - -#ifdef __KERNEL__ - -#include - -#endif /* __KERNEL__ */ - -#endif /* _ASM_M32R_IDE_H */ diff --git a/include/asm-sh/ide.h b/include/asm-sh/ide.h deleted file mode 100644 index 58e0bdd52be4..000000000000 --- a/include/asm-sh/ide.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * linux/include/asm-sh/ide.h - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - */ - -/* - * This file contains the i386 architecture specific IDE code. - * In future, SuperH code. - */ - -#ifndef __ASM_SH_IDE_H -#define __ASM_SH_IDE_H - -#ifdef __KERNEL__ - -#include - -#endif /* __KERNEL__ */ - -#endif /* __ASM_SH_IDE_H */ diff --git a/include/asm-x86/ide.h b/include/asm-x86/ide.h deleted file mode 100644 index 0289baf9ce0a..000000000000 --- a/include/asm-x86/ide.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Copyright (C) 1994-1996 Linus Torvalds & authors - */ - -/* - * This file contains the i386 architecture specific IDE code. - */ - -#ifndef __ASMi386_IDE_H -#define __ASMi386_IDE_H - -#ifdef __KERNEL__ - -#include - -#endif /* __KERNEL__ */ - -#endif /* __ASMi386_IDE_H */ diff --git a/include/asm-xtensa/ide.h b/include/asm-xtensa/ide.h deleted file mode 100644 index 18342a2cc774..000000000000 --- a/include/asm-xtensa/ide.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * include/asm-xtensa/ide.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1994 - 1996 Linus Torvalds & authors - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - -#ifndef _XTENSA_IDE_H -#define _XTENSA_IDE_H - -#ifdef __KERNEL__ - -#include - -#endif /* __KERNEL__ */ - -#endif /* _XTENSA_IDE_H */ diff --git a/include/linux/ide.h b/include/linux/ide.h index 76fe00b24b51..fd78b401b036 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -211,7 +211,13 @@ static inline int __ide_default_irq(unsigned long base) return 0; } +#if defined(CONFIG_ARM) || defined(CONFIG_FRV) || defined(CONFIG_M68K) || \ + defined(CONFIG_MIPS) || defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ + || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || defined(CONFIG_SPARC64) #include +#else +#include +#endif #ifndef MAX_HWIFS #if defined(CONFIG_BLACKFIN) || defined(CONFIG_H8300) || defined(CONFIG_XTENSA) -- cgit v1.2.3 From b30f3ae50cd03ef2ff433a5030fbf88dd8323528 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 24 Jul 2008 15:43:44 -0700 Subject: x86-64: Clean up 'save/restore_i387()' usage Suresh Siddha wants to fix a possible FPU leakage in error conditions, but the fact that save/restore_i387() are inlines in a header file makes that harder to do than necessary. So start off with an obvious cleanup. This just moves the x86-64 version of save/restore_i387() out of the header file, and moves it to the only file that it is actually used in: arch/x86/kernel/signal_64.c. So exposing it in a header file was wrong to begin with. [ Side note: I'd like to fix up some of the games we play with the 32-bit version of these functions too, but that's a separate matter. The 32-bit versions are shared - under different names at that! - by both the native x86-32 code and the x86-64 32-bit compatibility code ] Acked-by: Suresh Siddha Signed-off-by: Linus Torvalds --- arch/x86/kernel/signal_64.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ include/asm-x86/i387.h | 54 --------------------------------------------- 2 files changed, 53 insertions(+), 54 deletions(-) (limited to 'include/asm-x86') diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 47c3d249e638..b45ef8ddd651 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, return do_sigaltstack(uss, uoss, regs->sp); } +/* + * Signal frame handlers. + */ + +static inline int save_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err = 0; + + BUILD_BUG_ON(sizeof(struct user_i387_struct) != + sizeof(tsk->thread.xstate->fxsave)); + + if ((unsigned long)buf % 16) + printk("save_i387: bad fpstate %p\n", buf); + + if (!used_math()) + return 0; + clear_used_math(); /* trigger finit */ + if (task_thread_info(tsk)->status & TS_USEDFPU) { + err = save_i387_checking((struct i387_fxsave_struct __user *) + buf); + if (err) + return err; + task_thread_info(tsk)->status &= ~TS_USEDFPU; + stts(); + } else { + if (__copy_to_user(buf, &tsk->thread.xstate->fxsave, + sizeof(struct i387_fxsave_struct))) + return -1; + } + return 1; +} + +/* + * This restores directly out of user space. Exceptions are handled. + */ +static inline int restore_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err; + + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + + if (!(task_thread_info(current)->status & TS_USEDFPU)) { + clts(); + task_thread_info(current)->status |= TS_USEDFPU; + } + return restore_fpu_checking((__force struct i387_fxsave_struct *)buf); +} /* * Do a signal return; undo the signal stack. diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h index 37672f79dcc8..96fa8449ff11 100644 --- a/include/asm-x86/i387.h +++ b/include/asm-x86/i387.h @@ -137,60 +137,6 @@ static inline void __save_init_fpu(struct task_struct *tsk) task_thread_info(tsk)->status &= ~TS_USEDFPU; } -/* - * Signal frame handlers. - */ - -static inline int save_i387(struct _fpstate __user *buf) -{ - struct task_struct *tsk = current; - int err = 0; - - BUILD_BUG_ON(sizeof(struct user_i387_struct) != - sizeof(tsk->thread.xstate->fxsave)); - - if ((unsigned long)buf % 16) - printk("save_i387: bad fpstate %p\n", buf); - - if (!used_math()) - return 0; - clear_used_math(); /* trigger finit */ - if (task_thread_info(tsk)->status & TS_USEDFPU) { - err = save_i387_checking((struct i387_fxsave_struct __user *) - buf); - if (err) - return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); - } else { - if (__copy_to_user(buf, &tsk->thread.xstate->fxsave, - sizeof(struct i387_fxsave_struct))) - return -1; - } - return 1; -} - -/* - * This restores directly out of user space. Exceptions are handled. - */ -static inline int restore_i387(struct _fpstate __user *buf) -{ - struct task_struct *tsk = current; - int err; - - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } - - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } - return restore_fpu_checking((__force struct i387_fxsave_struct *)buf); -} - #else /* CONFIG_X86_32 */ extern void finit(void); -- cgit v1.2.3 From b69c49b78457f681ecfb3147bd968434ee6559c1 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 25 Jul 2008 01:45:40 -0700 Subject: clean up duplicated alloc/free_thread_info We duplicate alloc/free_thread_info defines on many platforms (the majority uses __get_free_pages/free_pages). This patch defines common defines and removes these duplicated defines. __HAVE_ARCH_THREAD_INFO_ALLOCATOR is introduced for platforms that do something different. Signed-off-by: FUJITA Tomonori Acked-by: Russell King Cc: Pekka Enberg Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-alpha/thread_info.h | 4 +--- include/asm-arm/thread_info.h | 13 ------------- include/asm-avr32/thread_info.h | 4 ---- include/asm-blackfin/thread_info.h | 5 +---- include/asm-cris/thread_info.h | 2 ++ include/asm-frv/thread_info.h | 2 ++ include/asm-h8300/thread_info.h | 5 +---- include/asm-ia64/thread_info.h | 2 ++ include/asm-m32r/thread_info.h | 2 ++ include/asm-m68k/thread_info.h | 8 +------- include/asm-m68knommu/thread_info.h | 4 ---- include/asm-mips/thread_info.h | 2 ++ include/asm-mn10300/thread_info.h | 2 ++ include/asm-parisc/thread_info.h | 10 +++------- include/asm-powerpc/thread_info.h | 14 +++----------- include/asm-s390/thread_info.h | 5 +---- include/asm-sh/thread_info.h | 2 ++ include/asm-sparc/thread_info_32.h | 2 ++ include/asm-sparc/thread_info_64.h | 2 ++ include/asm-um/thread_info.h | 16 +--------------- include/asm-x86/thread_info.h | 2 ++ include/asm-xtensa/thread_info.h | 5 +---- kernel/fork.c | 17 +++++++++++++++++ 23 files changed, 50 insertions(+), 80 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-alpha/thread_info.h b/include/asm-alpha/thread_info.h index fb3185196298..15fda4344424 100644 --- a/include/asm-alpha/thread_info.h +++ b/include/asm-alpha/thread_info.h @@ -50,10 +50,8 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define current_thread_info() __current_thread_info /* Thread information allocation. */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (2*PAGE_SIZE) -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ diff --git a/include/asm-arm/thread_info.h b/include/asm-arm/thread_info.h index f5a664786311..d4be2d646160 100644 --- a/include/asm-arm/thread_info.h +++ b/include/asm-arm/thread_info.h @@ -97,19 +97,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)(sp & ~(THREAD_SIZE - 1)); } -/* thread information allocation */ -#ifdef CONFIG_DEBUG_STACK_USAGE -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, \ - THREAD_SIZE_ORDER)) -#else -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#endif - -#define free_thread_info(info) \ - free_pages((unsigned long)info, THREAD_SIZE_ORDER); - #define thread_saved_pc(tsk) \ ((unsigned long)(pc_pointer(task_thread_info(tsk)->cpu_context.pc))) #define thread_saved_fp(tsk) \ diff --git a/include/asm-avr32/thread_info.h b/include/asm-avr32/thread_info.h index df68631b7b27..294b25f9323d 100644 --- a/include/asm-avr32/thread_info.h +++ b/include/asm-avr32/thread_info.h @@ -61,10 +61,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)addr; } -/* thread information allocation */ -#define alloc_thread_info(ti) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long)(ti), 1) #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/include/asm-blackfin/thread_info.h b/include/asm-blackfin/thread_info.h index bc2fe5accf20..642769329d12 100644 --- a/include/asm-blackfin/thread_info.h +++ b/include/asm-blackfin/thread_info.h @@ -42,6 +42,7 @@ /* * Size of kernel stack for each process. This must be a power of 2... */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE 8192 /* 2 pages */ #ifndef __ASSEMBLY__ @@ -94,10 +95,6 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)((long)ti & ~((long)THREAD_SIZE-1)); } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, 1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ /* diff --git a/include/asm-cris/thread_info.h b/include/asm-cris/thread_info.h index 784668ab0fa2..7efe1000f99d 100644 --- a/include/asm-cris/thread_info.h +++ b/include/asm-cris/thread_info.h @@ -11,6 +11,8 @@ #ifdef __KERNEL__ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifndef __ASSEMBLY__ #include #include diff --git a/include/asm-frv/thread_info.h b/include/asm-frv/thread_info.h index 348b8f1df17e..b7ac6bf2844c 100644 --- a/include/asm-frv/thread_info.h +++ b/include/asm-frv/thread_info.h @@ -82,6 +82,8 @@ register struct thread_info *__current_thread_info asm("gr15"); #define current_thread_info() ({ __current_thread_info; }) +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ diff --git a/include/asm-h8300/thread_info.h b/include/asm-h8300/thread_info.h index 27bb95e2944c..aafd4d322ec3 100644 --- a/include/asm-h8300/thread_info.h +++ b/include/asm-h8300/thread_info.h @@ -49,6 +49,7 @@ struct thread_info { /* * Size of kernel stack for each process. This must be a power of 2... */ +#define THREAD_SIZE_ORDER 1 #define THREAD_SIZE 8192 /* 2 pages */ @@ -65,10 +66,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, 1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) #endif /* __ASSEMBLY__ */ /* diff --git a/include/asm-ia64/thread_info.h b/include/asm-ia64/thread_info.h index 2422ac61658a..7c60fcdd2efd 100644 --- a/include/asm-ia64/thread_info.h +++ b/include/asm-ia64/thread_info.h @@ -54,6 +54,8 @@ struct thread_info { }, \ } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifndef ASM_OFFSETS_C /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE)) diff --git a/include/asm-m32r/thread_info.h b/include/asm-m32r/thread_info.h index 1effcd0f5e63..8589d462df27 100644 --- a/include/asm-m32r/thread_info.h +++ b/include/asm-m32r/thread_info.h @@ -94,6 +94,8 @@ static inline struct thread_info *current_thread_info(void) return ti; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ diff --git a/include/asm-m68k/thread_info.h b/include/asm-m68k/thread_info.h index d635a3752488..abc002798a2b 100644 --- a/include/asm-m68k/thread_info.h +++ b/include/asm-m68k/thread_info.h @@ -25,13 +25,7 @@ struct thread_info { } /* THREAD_SIZE should be 8k, so handle differently for 4k and 8k machines */ -#if PAGE_SHIFT == 13 /* 8k machines */ -#define alloc_thread_info(tsk) ((struct thread_info *)__get_free_pages(GFP_KERNEL,0)) -#define free_thread_info(ti) free_pages((unsigned long)(ti),0) -#else /* otherwise assume 4k pages */ -#define alloc_thread_info(tsk) ((struct thread_info *)__get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long)(ti),1) -#endif /* PAGE_SHIFT == 13 */ +#define THREAD_SIZE_ORDER (13 - PAGE_SHIFT) #define init_thread_info (init_task.thread.info) #define init_stack (init_thread_union.stack) diff --git a/include/asm-m68knommu/thread_info.h b/include/asm-m68knommu/thread_info.h index 95996d978bed..0c9bc095f3f0 100644 --- a/include/asm-m68knommu/thread_info.h +++ b/include/asm-m68knommu/thread_info.h @@ -71,10 +71,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_SIZE_ORDER) #endif /* __ASSEMBLY__ */ #define PREEMPT_ACTIVE 0x4000000 diff --git a/include/asm-mips/thread_info.h b/include/asm-mips/thread_info.h index b2772df1a1bd..bb3060699df2 100644 --- a/include/asm-mips/thread_info.h +++ b/include/asm-mips/thread_info.h @@ -82,6 +82,8 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define THREAD_MASK (THREAD_SIZE - 1UL) +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ ({ \ diff --git a/include/asm-mn10300/thread_info.h b/include/asm-mn10300/thread_info.h index e397e7192785..78a3881f3c12 100644 --- a/include/asm-mn10300/thread_info.h +++ b/include/asm-mn10300/thread_info.h @@ -112,6 +112,8 @@ static inline unsigned long current_stack_pointer(void) return sp; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) kzalloc(THREAD_SIZE, GFP_KERNEL) diff --git a/include/asm-parisc/thread_info.h b/include/asm-parisc/thread_info.h index 2d9c7500867b..9f812741c355 100644 --- a/include/asm-parisc/thread_info.h +++ b/include/asm-parisc/thread_info.h @@ -34,15 +34,11 @@ struct thread_info { /* thread information allocation */ -#define THREAD_ORDER 2 +#define THREAD_SIZE_ORDER 2 /* Be sure to hunt all references to this down when you change the size of * the kernel stack */ -#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) -#define THREAD_SHIFT (PAGE_SHIFT + THREAD_ORDER) - -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL, THREAD_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_ORDER) +#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER) /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *)mfctl(30)) diff --git a/include/asm-powerpc/thread_info.h b/include/asm-powerpc/thread_info.h index b705c2a7651a..a9db562df69a 100644 --- a/include/asm-powerpc/thread_info.h +++ b/include/asm-powerpc/thread_info.h @@ -66,20 +66,12 @@ struct thread_info { #if THREAD_SHIFT >= PAGE_SHIFT -#define THREAD_ORDER (THREAD_SHIFT - PAGE_SHIFT) - -#ifdef CONFIG_DEBUG_STACK_USAGE -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL | \ - __GFP_ZERO, THREAD_ORDER)) -#else -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(GFP_KERNEL, THREAD_ORDER)) -#endif -#define free_thread_info(ti) free_pages((unsigned long)ti, THREAD_ORDER) +#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) #else /* THREAD_SHIFT < PAGE_SHIFT */ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + extern struct thread_info *alloc_thread_info(struct task_struct *tsk); extern void free_thread_info(struct thread_info *ti); diff --git a/include/asm-s390/thread_info.h b/include/asm-s390/thread_info.h index 99bbed99a3b2..91a8f93ad355 100644 --- a/include/asm-s390/thread_info.h +++ b/include/asm-s390/thread_info.h @@ -78,10 +78,7 @@ static inline struct thread_info *current_thread_info(void) return (struct thread_info *)((*(unsigned long *) __LC_KERNEL_STACK)-THREAD_SIZE); } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) \ - __get_free_pages(GFP_KERNEL,THREAD_ORDER)) -#define free_thread_info(ti) free_pages((unsigned long) (ti),THREAD_ORDER) +#define THREAD_SIZE_ORDER THREAD_ORDER #endif diff --git a/include/asm-sh/thread_info.h b/include/asm-sh/thread_info.h index c50e5d35fe84..5131e3907525 100644 --- a/include/asm-sh/thread_info.h +++ b/include/asm-sh/thread_info.h @@ -92,6 +92,8 @@ static inline struct thread_info *current_thread_info(void) return ti; } +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + /* thread information allocation */ #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(ti) kzalloc(THREAD_SIZE, GFP_KERNEL) diff --git a/include/asm-sparc/thread_info_32.h b/include/asm-sparc/thread_info_32.h index 91b9f5888c85..2cf9db044055 100644 --- a/include/asm-sparc/thread_info_32.h +++ b/include/asm-sparc/thread_info_32.h @@ -86,6 +86,8 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define THREAD_INFO_ORDER 1 #endif +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + BTFIXUPDEF_CALL(struct thread_info *, alloc_thread_info, void) #define alloc_thread_info(tsk) BTFIXUP_CALL(alloc_thread_info)() diff --git a/include/asm-sparc/thread_info_64.h b/include/asm-sparc/thread_info_64.h index c6d2e6c7f844..960969d5ad06 100644 --- a/include/asm-sparc/thread_info_64.h +++ b/include/asm-sparc/thread_info_64.h @@ -155,6 +155,8 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define __THREAD_INFO_ORDER 0 #endif /* PAGE_SHIFT == 13 */ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #ifdef CONFIG_DEBUG_STACK_USAGE #define alloc_thread_info(tsk) \ ({ \ diff --git a/include/asm-um/thread_info.h b/include/asm-um/thread_info.h index 356b83e2c22e..e07e72846c7a 100644 --- a/include/asm-um/thread_info.h +++ b/include/asm-um/thread_info.h @@ -53,21 +53,7 @@ static inline struct thread_info *current_thread_info(void) return ti; } -#ifdef CONFIG_DEBUG_STACK_USAGE - -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, \ - CONFIG_KERNEL_STACK_ORDER)) -#else - -/* thread information allocation */ -#define alloc_thread_info(tsk) \ - ((struct thread_info *) __get_free_pages(GFP_KERNEL, \ - CONFIG_KERNEL_STACK_ORDER)) -#endif - -#define free_thread_info(ti) \ - free_pages((unsigned long)(ti),CONFIG_KERNEL_STACK_ORDER) +#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER #endif diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h index 3f2de1050988..da0a675adf94 100644 --- a/include/asm-x86/thread_info.h +++ b/include/asm-x86/thread_info.h @@ -152,6 +152,8 @@ struct thread_info { #define THREAD_FLAGS GFP_KERNEL #endif +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR + #define alloc_thread_info(tsk) \ ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER)) diff --git a/include/asm-xtensa/thread_info.h b/include/asm-xtensa/thread_info.h index a2c640682ed9..7e4131dd546c 100644 --- a/include/asm-xtensa/thread_info.h +++ b/include/asm-xtensa/thread_info.h @@ -111,10 +111,6 @@ static inline struct thread_info *current_thread_info(void) return ti; } -/* thread information allocation */ -#define alloc_thread_info(tsk) ((struct thread_info *) __get_free_pages(GFP_KERNEL,1)) -#define free_thread_info(ti) free_pages((unsigned long) (ti), 1) - #else /* !__ASSEMBLY__ */ /* how to get the thread information struct from ASM */ @@ -160,6 +156,7 @@ static inline struct thread_info *current_thread_info(void) #define TS_USEDFPU 0x0001 /* FPU was used by this task this quantum (SMP) */ #define THREAD_SIZE 8192 //(2*PAGE_SIZE) +#define THREAD_SIZE_ORDER 1 #endif /* __KERNEL__ */ #endif /* _XTENSA_THREAD_INFO */ diff --git a/kernel/fork.c b/kernel/fork.c index 552c8d8e77ad..5a5d6fef341d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -93,6 +93,23 @@ int nr_processes(void) static struct kmem_cache *task_struct_cachep; #endif +#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR +static inline struct thread_info *alloc_thread_info(struct task_struct *tsk) +{ +#ifdef CONFIG_DEBUG_STACK_USAGE + gfp_t mask = GFP_KERNEL | __GFP_ZERO; +#else + gfp_t mask = GFP_KERNEL; +#endif + return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER); +} + +static inline void free_thread_info(struct thread_info *ti) +{ + free_pages((unsigned long)ti, THREAD_SIZE_ORDER); +} +#endif + /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; -- cgit v1.2.3 From 7444a72effa632fcd8edc566f880d96fe213c73b Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Fri, 25 Jul 2008 01:46:11 -0700 Subject: gpiolib: allow user-selection This patch adds functionality to the gpio-lib subsystem to make it possible to enable the gpio-lib code even if the architecture code didn't request to get it built in. The archtitecture code does still need to implement the gpiolib accessor functions in its asm/gpio.h file. This patch adds the implementations for x86 and PPC. With these changes it is possible to run generic GPIO expansion cards on every architecture that implements the trivial wrapper functions. Support for more architectures can easily be added. Signed-off-by: Michael Buesch Cc: Benjamin Herrenschmidt Cc: Stephen Rothwell Cc: David Brownell Cc: Russell King Cc: Haavard Skinnemoen Cc: Jesper Nilsson Cc: Ralf Baechle Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Jean Delvare Cc: Samuel Ortiz Cc: Kumar Gala Cc: Sam Ravnborg Cc: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/gpio.txt | 12 +++++++- arch/arm/Kconfig | 8 +++--- arch/avr32/Kconfig | 2 +- arch/mips/Kconfig | 2 +- arch/powerpc/Kconfig | 1 + arch/powerpc/platforms/52xx/Kconfig | 2 +- arch/powerpc/sysdev/qe_lib/Kconfig | 2 +- arch/x86/Kconfig | 1 + drivers/Makefile | 2 +- drivers/gpio/Kconfig | 33 ++++++++++++++++++--- drivers/gpio/Makefile | 2 +- drivers/i2c/chips/Kconfig | 2 +- drivers/mfd/Kconfig | 4 +-- drivers/of/Kconfig | 2 +- include/asm-generic/gpio.h | 2 +- include/asm-mips/mach-generic/gpio.h | 2 +- include/asm-powerpc/gpio.h | 4 +-- include/asm-x86/gpio.h | 56 ++++++++++++++++++++++++++++++++++++ 18 files changed, 116 insertions(+), 23 deletions(-) (limited to 'include/asm-x86') diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt index 8b69811a9642..18022e249c53 100644 --- a/Documentation/gpio.txt +++ b/Documentation/gpio.txt @@ -389,11 +389,21 @@ either NULL or the label associated with that GPIO when it was requested. Platform Support ---------------- -To support this framework, a platform's Kconfig will "select HAVE_GPIO_LIB" +To support this framework, a platform's Kconfig will "select" either +ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB and arrange that its includes and defines three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep(). They may also want to provide a custom value for ARCH_NR_GPIOS. +ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled +into the kernel on that architecture. + +ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user +can enable it and build it into the kernel optionally. + +If neither of these options are selected, the platform does not support +GPIOs through GPIO-lib and the code cannot be enabled by the user. + Trivial implementations of those functions can directly use framework code, which always dispatches through the gpio_chip: diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 6fb4f03369f2..dabb015aa40b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -268,7 +268,7 @@ config ARCH_EP93XX select GENERIC_GPIO select HAVE_CLK select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help This enables support for the Cirrus EP93xx series of CPUs. @@ -447,7 +447,7 @@ config ARCH_PXA select ARCH_MTD_XIP select GENERIC_GPIO select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_TIME select GENERIC_CLOCKEVENTS select TICK_ONESHOT @@ -479,7 +479,7 @@ config ARCH_SA1100 select GENERIC_CLOCKEVENTS select HAVE_CLK select TICK_ONESHOT - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Support for StrongARM 11x0 based boards. @@ -522,7 +522,7 @@ config ARCH_OMAP bool "TI OMAP" select GENERIC_GPIO select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_TIME select GENERIC_CLOCKEVENTS help diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index df4adefedb42..7c239a916275 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -88,7 +88,7 @@ config PLATFORM_AT32AP select SUBARCH_AVR32B select MMU select PERFORMANCE_COUNTERS - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_ALLOCATOR # diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b9c754f4070c..b4c4eaa5dd26 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -713,7 +713,7 @@ config CSRC_SB1250 config GPIO_TXX9 select GENERIC_GPIO - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB bool config CFE diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index de6b49cd6be8..fe88418167c5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -110,6 +110,7 @@ config PPC default y select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE + select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index d664b1bce381..ccbd4958412e 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -48,6 +48,6 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_GPIO bool "MPC5200 GPIO support" depends on PPC_MPC52xx - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Enable gpiolib support for mpc5200 based boards diff --git a/arch/powerpc/sysdev/qe_lib/Kconfig b/arch/powerpc/sysdev/qe_lib/Kconfig index 4bb18f57901e..1ce546462be5 100644 --- a/arch/powerpc/sysdev/qe_lib/Kconfig +++ b/arch/powerpc/sysdev/qe_lib/Kconfig @@ -29,7 +29,7 @@ config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE select GENERIC_GPIO - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Say Y here if you're going to use hardware that connects to the QE GPIOs. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 66f3ab05b18c..e3cba0b45600 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,7 @@ config X86 select HAVE_OPROFILE select HAVE_IOREMAP_PROT select HAVE_KPROBES + select ARCH_WANT_OPTIONAL_GPIOLIB if !X86_RDC321X select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE diff --git a/drivers/Makefile b/drivers/Makefile index 808e0ae66aa8..54ec5e718c0e 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -5,7 +5,7 @@ # Rewritten to use lists instead of if-statements. # -obj-$(CONFIG_HAVE_GPIO_LIB) += gpio/ +obj-y += gpio/ obj-$(CONFIG_PCI) += pci/ obj-$(CONFIG_PARISC) += parisc/ obj-$(CONFIG_RAPIDIO) += rapidio/ diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index de202dbe5300..5a355f829167 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -2,15 +2,40 @@ # GPIO infrastructure and expanders # -config HAVE_GPIO_LIB +config ARCH_WANT_OPTIONAL_GPIOLIB bool + help + Select this config option from the architecture Kconfig, if + it is possible to use gpiolib on the architecture, but let the + user decide whether to actually build it or not. + Select this instead of ARCH_REQUIRE_GPIOLIB, if your architecture does + not depend on GPIOs being available, but rather let the user + decide whether he needs it or not. + +config ARCH_REQUIRE_GPIOLIB + bool + select GPIOLIB help Platforms select gpiolib if they use this infrastructure for all their GPIOs, usually starting with ones integrated into SOC processors. + Selecting this from the architecture code will cause the gpiolib + code to always get built in. + + + +menuconfig GPIOLIB + bool "GPIO Support" + depends on ARCH_WANT_OPTIONAL_GPIOLIB || ARCH_REQUIRE_GPIOLIB + select GENERIC_GPIO + help + This enables GPIO support through the generic GPIO library. + You only need to enable this, if you also want to enable + one or more of the GPIO expansion card drivers below. + + If unsure, say N. -menu "GPIO Support" - depends on HAVE_GPIO_LIB +if GPIOLIB config DEBUG_GPIO bool "Debug GPIO calls" @@ -116,4 +141,4 @@ config GPIO_MCP23S08 SPI driver for Microchip MCP23S08 I/O expander. This provides a GPIO interface supporting inputs and outputs. -endmenu +endif diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index eeb2f2b20282..8c45948d1fe7 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -2,7 +2,7 @@ ccflags-$(CONFIG_DEBUG_GPIO) += -DDEBUG -obj-$(CONFIG_HAVE_GPIO_LIB) += gpiolib.o +obj-$(CONFIG_GPIOLIB) += gpiolib.o obj-$(CONFIG_GPIO_MAX7301) += max7301.o obj-$(CONFIG_GPIO_MCP23S08) += mcp23s08.o diff --git a/drivers/i2c/chips/Kconfig b/drivers/i2c/chips/Kconfig index 50e0a4653741..a95cb9465d65 100644 --- a/drivers/i2c/chips/Kconfig +++ b/drivers/i2c/chips/Kconfig @@ -126,7 +126,7 @@ config ISP1301_OMAP config TPS65010 tristate "TPS6501x Power Management chips" - depends on HAVE_GPIO_LIB + depends on GPIOLIB default y if MACH_OMAP_H2 || MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes here you get support for the TPS6501x series of diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index bac9e973ece0..1f57a99fd968 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -36,7 +36,7 @@ config MFD_ASIC3 config HTC_EGPIO bool "HTC EGPIO support" - depends on GENERIC_HARDIRQS && HAVE_GPIO_LIB && ARM + depends on GENERIC_HARDIRQS && GPIOLIB && ARM help This driver supports the CPLD egpio chip present on several HTC phones. It provides basic support for input @@ -52,7 +52,7 @@ config HTC_PASIC3 config MFD_TC6393XB bool "Support Toshiba TC6393XB" - depends on HAVE_GPIO_LIB + depends on GPIOLIB select MFD_CORE help Support for Toshiba Mobile IO Controller TC6393XB diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 3a7a11a75fb4..1d7ec3129349 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -4,7 +4,7 @@ config OF_DEVICE config OF_GPIO def_bool y - depends on OF && PPC_OF && HAVE_GPIO_LIB + depends on OF && PPC_OF && GPIOLIB help OpenFirmware GPIO accessors diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 1beff5166e53..a3034d20ebd5 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -3,7 +3,7 @@ #include -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB #include diff --git a/include/asm-mips/mach-generic/gpio.h b/include/asm-mips/mach-generic/gpio.h index e6b376bd9d06..b4e70208da64 100644 --- a/include/asm-mips/mach-generic/gpio.h +++ b/include/asm-mips/mach-generic/gpio.h @@ -1,7 +1,7 @@ #ifndef __ASM_MACH_GENERIC_GPIO_H #define __ASM_MACH_GENERIC_GPIO_H -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB #define gpio_get_value __gpio_get_value #define gpio_set_value __gpio_set_value #define gpio_cansleep __gpio_cansleep diff --git a/include/asm-powerpc/gpio.h b/include/asm-powerpc/gpio.h index 77ad3a890f30..ea04632399d8 100644 --- a/include/asm-powerpc/gpio.h +++ b/include/asm-powerpc/gpio.h @@ -17,7 +17,7 @@ #include #include -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB /* * We don't (yet) implement inlined/rapid versions for on-chip gpios. @@ -51,6 +51,6 @@ static inline int irq_to_gpio(unsigned int irq) return -EINVAL; } -#endif /* CONFIG_HAVE_GPIO_LIB */ +#endif /* CONFIG_GPIOLIB */ #endif /* __ASM_POWERPC_GPIO_H */ diff --git a/include/asm-x86/gpio.h b/include/asm-x86/gpio.h index ff87fca0caf9..116e9147fe66 100644 --- a/include/asm-x86/gpio.h +++ b/include/asm-x86/gpio.h @@ -1,6 +1,62 @@ +/* + * Generic GPIO API implementation for x86. + * + * Derived from the generic GPIO API for powerpc: + * + * Copyright (c) 2007-2008 MontaVista Software, Inc. + * + * Author: Anton Vorontsov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + #ifndef _ASM_I386_GPIO_H #define _ASM_I386_GPIO_H +#ifdef CONFIG_X86_RDC321X #include +#else /* CONFIG_X86_RDC321X */ + +#include + +#ifdef CONFIG_GPIOLIB + +/* + * Just call gpiolib. + */ +static inline int gpio_get_value(unsigned int gpio) +{ + return __gpio_get_value(gpio); +} + +static inline void gpio_set_value(unsigned int gpio, int value) +{ + __gpio_set_value(gpio, value); +} + +static inline int gpio_cansleep(unsigned int gpio) +{ + return __gpio_cansleep(gpio); +} + +/* + * Not implemented, yet. + */ +static inline int gpio_to_irq(unsigned int gpio) +{ + return -ENOSYS; +} + +static inline int irq_to_gpio(unsigned int irq) +{ + return -EINVAL; +} + +#endif /* CONFIG_GPIOLIB */ + +#endif /* CONFIG_X86_RDC321X */ #endif /* _ASM_I386_GPIO_H */ -- cgit v1.2.3 From f22ab814a24e654b1de24db0c5f8b57b5ab2026a Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:47:34 -0700 Subject: include/asm/ptrace.h userspace headers cleanup This patch contains the following cleanups for the asm/ptrace.h userspace headers: - include/asm-generic/Kbuild.asm already lists ptrace.h, remove the superfluous listings in the Kbuild files of the following architectures: - cris - frv - powerpc - x86 - don't expose function prototypes and macros to userspace: - arm - blackfin - cris - mn10300 - parisc - remove #ifdef CONFIG_'s around #define's: - blackfin - m68knommu - sh: AFAIK __SH5__ should work in both kernel and userspace, no need to leak CONFIG_SUPERH64 to userspace - xtensa: cosmetical change to remove empty #ifndef __ASSEMBLY__ #else #endif from the userspace headers Not changed by this patch is the fact that the following architectures have a different struct pt_regs depending on CONFIG_ variables: - h8300 - m68knommu - mips This does not work in userspace. Signed-off-by: Adrian Bunk Cc: Cc: Roland McGrath Cc: Oleg Nesterov Acked-by: Greg Ungerer Acked-by: Paul Mundt Acked-by: Grant Grundler Acked-by: Jesper Nilsson Acked-by: Chris Zankel Acked-by: David Howells Acked-by: Paul Mackerras Acked-by: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-arm/ptrace.h | 6 ++---- include/asm-blackfin/ptrace.h | 6 ++++-- include/asm-cris/arch-v10/Kbuild | 1 - include/asm-cris/arch-v10/ptrace.h | 4 ++++ include/asm-cris/arch-v32/Kbuild | 1 - include/asm-cris/arch-v32/ptrace.h | 4 ++++ include/asm-cris/ptrace.h | 4 +++- include/asm-frv/Kbuild | 1 - include/asm-m68knommu/ptrace.h | 2 -- include/asm-mn10300/ptrace.h | 8 ++++++-- include/asm-parisc/ptrace.h | 4 +++- include/asm-powerpc/Kbuild | 1 - include/asm-sh/ptrace.h | 2 +- include/asm-x86/Kbuild | 1 - include/asm-xtensa/ptrace.h | 10 +++++----- 15 files changed, 32 insertions(+), 23 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-arm/ptrace.h b/include/asm-arm/ptrace.h index 7aaa206cb54e..8382b7510f94 100644 --- a/include/asm-arm/ptrace.h +++ b/include/asm-arm/ptrace.h @@ -139,8 +139,6 @@ static inline int valid_user_regs(struct pt_regs *regs) return 0; } -#endif /* __KERNEL__ */ - #define pc_pointer(v) \ ((v) & ~PCMASK) @@ -153,10 +151,10 @@ extern unsigned long profile_pc(struct pt_regs *regs); #define profile_pc(regs) instruction_pointer(regs) #endif -#ifdef __KERNEL__ #define predicate(x) ((x) & 0xf0000000) #define PREDICATE_ALWAYS 0xe0000000 -#endif + +#endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/include/asm-blackfin/ptrace.h b/include/asm-blackfin/ptrace.h index b8346cd3a6f6..a45a80e54adc 100644 --- a/include/asm-blackfin/ptrace.h +++ b/include/asm-blackfin/ptrace.h @@ -83,14 +83,14 @@ struct pt_regs { #define PTRACE_GETREGS 12 #define PTRACE_SETREGS 13 /* ptrace signal */ -#ifdef CONFIG_BINFMT_ELF_FDPIC #define PTRACE_GETFDPIC 31 #define PTRACE_GETFDPIC_EXEC 0 #define PTRACE_GETFDPIC_INTERP 1 -#endif #define PS_S (0x0002) +#ifdef __KERNEL__ + /* user_mode returns true if only one bit is set in IPEND, other than the master interrupt enable. */ #define user_mode(regs) (!(((regs)->ipend & ~0x10) & (((regs)->ipend & ~0x10) - 1))) @@ -98,6 +98,8 @@ struct pt_regs { #define profile_pc(regs) instruction_pointer(regs) extern void show_regs(struct pt_regs *); +#endif /* __KERNEL__ */ + #endif /* __ASSEMBLY__ */ /* diff --git a/include/asm-cris/arch-v10/Kbuild b/include/asm-cris/arch-v10/Kbuild index 60e7e1b73cec..7a192e1290b1 100644 --- a/include/asm-cris/arch-v10/Kbuild +++ b/include/asm-cris/arch-v10/Kbuild @@ -1,4 +1,3 @@ -header-y += ptrace.h header-y += user.h header-y += svinto.h header-y += sv_addr_ag.h diff --git a/include/asm-cris/arch-v10/ptrace.h b/include/asm-cris/arch-v10/ptrace.h index fb14c5ee37f9..2f464eab3a51 100644 --- a/include/asm-cris/arch-v10/ptrace.h +++ b/include/asm-cris/arch-v10/ptrace.h @@ -106,10 +106,14 @@ struct switch_stack { unsigned long return_ip; /* ip that _resume will return to */ }; +#ifdef __KERNEL__ + /* bit 8 is user-mode flag */ #define user_mode(regs) (((regs)->dccr & 0x100) != 0) #define instruction_pointer(regs) ((regs)->irp) #define profile_pc(regs) instruction_pointer(regs) extern void show_regs(struct pt_regs *); +#endif /* __KERNEL__ */ + #endif diff --git a/include/asm-cris/arch-v32/Kbuild b/include/asm-cris/arch-v32/Kbuild index a0ec545e242e..35f2fc4f993e 100644 --- a/include/asm-cris/arch-v32/Kbuild +++ b/include/asm-cris/arch-v32/Kbuild @@ -1,3 +1,2 @@ -header-y += ptrace.h header-y += user.h header-y += cryptocop.h diff --git a/include/asm-cris/arch-v32/ptrace.h b/include/asm-cris/arch-v32/ptrace.h index 516cc7062d94..41f4e8662bc2 100644 --- a/include/asm-cris/arch-v32/ptrace.h +++ b/include/asm-cris/arch-v32/ptrace.h @@ -106,9 +106,13 @@ struct switch_stack { unsigned long return_ip; /* ip that _resume will return to */ }; +#ifdef __KERNEL__ + #define user_mode(regs) (((regs)->ccs & (1 << (U_CCS_BITNR + CCS_SHIFT))) != 0) #define instruction_pointer(regs) ((regs)->erp) extern void show_regs(struct pt_regs *); #define profile_pc(regs) instruction_pointer(regs) +#endif /* __KERNEL__ */ + #endif diff --git a/include/asm-cris/ptrace.h b/include/asm-cris/ptrace.h index 1ec69a7ea836..d910925e3174 100644 --- a/include/asm-cris/ptrace.h +++ b/include/asm-cris/ptrace.h @@ -4,11 +4,13 @@ #include #ifdef __KERNEL__ + /* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ #define PTRACE_GETREGS 12 #define PTRACE_SETREGS 13 -#endif #define profile_pc(regs) instruction_pointer(regs) +#endif /* __KERNEL__ */ + #endif /* _CRIS_PTRACE_H */ diff --git a/include/asm-frv/Kbuild b/include/asm-frv/Kbuild index bc3f12c5b7e0..0f8956def738 100644 --- a/include/asm-frv/Kbuild +++ b/include/asm-frv/Kbuild @@ -3,4 +3,3 @@ include include/asm-generic/Kbuild.asm header-y += registers.h unifdef-y += termios.h -unifdef-y += ptrace.h diff --git a/include/asm-m68knommu/ptrace.h b/include/asm-m68knommu/ptrace.h index 47258e86e8c4..8c9194b98548 100644 --- a/include/asm-m68knommu/ptrace.h +++ b/include/asm-m68knommu/ptrace.h @@ -68,10 +68,8 @@ struct switch_stack { /* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ #define PTRACE_GETREGS 12 #define PTRACE_SETREGS 13 -#ifdef CONFIG_FPU #define PTRACE_GETFPREGS 14 #define PTRACE_SETFPREGS 15 -#endif #ifdef __KERNEL__ diff --git a/include/asm-mn10300/ptrace.h b/include/asm-mn10300/ptrace.h index b3684689fcce..7b06cc623d8b 100644 --- a/include/asm-mn10300/ptrace.h +++ b/include/asm-mn10300/ptrace.h @@ -88,12 +88,16 @@ extern struct pt_regs *__frame; /* current frame pointer */ /* options set using PTRACE_SETOPTIONS */ #define PTRACE_O_TRACESYSGOOD 0x00000001 -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +#if defined(__KERNEL__) + +#if !defined(__ASSEMBLY__) #define user_mode(regs) (((regs)->epsw & EPSW_nSL) == EPSW_nSL) #define instruction_pointer(regs) ((regs)->pc) extern void show_regs(struct pt_regs *); -#endif +#endif /* !__ASSEMBLY */ #define profile_pc(regs) ((regs)->pc) +#endif /* __KERNEL__ */ + #endif /* _ASM_PTRACE_H */ diff --git a/include/asm-parisc/ptrace.h b/include/asm-parisc/ptrace.h index 93f990e418f1..3e94c5d85ff5 100644 --- a/include/asm-parisc/ptrace.h +++ b/include/asm-parisc/ptrace.h @@ -33,7 +33,6 @@ struct pt_regs { unsigned long ipsw; /* CR22 */ }; -#define task_regs(task) ((struct pt_regs *) ((char *)(task) + TASK_REGS)) /* * The numbers chosen here are somewhat arbitrary but absolutely MUST * not overlap with any of the number assigned in . @@ -43,8 +42,11 @@ struct pt_regs { * since we have taken branch traps too) */ #define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */ + #ifdef __KERNEL__ +#define task_regs(task) ((struct pt_regs *) ((char *)(task) + TASK_REGS)) + /* XXX should we use iaoq[1] or iaoq[0] ? */ #define user_mode(regs) (((regs)->iaoq[0] & 3) ? 1 : 0) #define user_space(regs) (((regs)->iasq[1] != 0) ? 1 : 0) diff --git a/include/asm-powerpc/Kbuild b/include/asm-powerpc/Kbuild index 04ce8f8a2ee7..5ab7d7fe198c 100644 --- a/include/asm-powerpc/Kbuild +++ b/include/asm-powerpc/Kbuild @@ -29,7 +29,6 @@ unifdef-y += elf.h unifdef-y += nvram.h unifdef-y += param.h unifdef-y += posix_types.h -unifdef-y += ptrace.h unifdef-y += seccomp.h unifdef-y += signal.h unifdef-y += spu_info.h diff --git a/include/asm-sh/ptrace.h b/include/asm-sh/ptrace.h index 8d6c92b3e770..7d36dc3bee69 100644 --- a/include/asm-sh/ptrace.h +++ b/include/asm-sh/ptrace.h @@ -5,7 +5,7 @@ * Copyright (C) 1999, 2000 Niibe Yutaka * */ -#if defined(__SH5__) || defined(CONFIG_SUPERH64) +#if defined(__SH5__) struct pt_regs { unsigned long long pc; unsigned long long sr; diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild index 1e3554596f72..00473f7dd819 100644 --- a/include/asm-x86/Kbuild +++ b/include/asm-x86/Kbuild @@ -19,7 +19,6 @@ unifdef-y += msr.h unifdef-y += mtrr.h unifdef-y += posix_types_32.h unifdef-y += posix_types_64.h -unifdef-y += ptrace.h unifdef-y += unistd_32.h unifdef-y += unistd_64.h unifdef-y += vm86.h diff --git a/include/asm-xtensa/ptrace.h b/include/asm-xtensa/ptrace.h index 422c73e26937..089b0db44816 100644 --- a/include/asm-xtensa/ptrace.h +++ b/include/asm-xtensa/ptrace.h @@ -73,10 +73,10 @@ #define PTRACE_GETXTREGS 18 #define PTRACE_SETXTREGS 19 -#ifndef __ASSEMBLY__ - #ifdef __KERNEL__ +#ifndef __ASSEMBLY__ + /* * This struct defines the way the registers are stored on the * kernel stack during a system call or other kernel entry. @@ -122,14 +122,14 @@ extern void show_regs(struct pt_regs *); # ifndef CONFIG_SMP # define profile_pc(regs) instruction_pointer(regs) # endif -#endif /* __KERNEL__ */ #else /* __ASSEMBLY__ */ -#ifdef __KERNEL__ # include #define PT_REGS_OFFSET (KERNEL_STACK_SIZE - PT_USER_SIZE) -#endif #endif /* !__ASSEMBLY__ */ + +#endif /* __KERNEL__ */ + #endif /* _XTENSA_PTRACE_H */ -- cgit v1.2.3 From 7dcf2a9fced59e58e4694cdcf15850c01fdba89b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Tue, 1 Jul 2008 19:27:16 +0300 Subject: remove dummy asm/kvm.h files This patch removes the dummy asm/kvm.h files on architectures not (yet) supporting KVM and uses the same conditional headers installation as already used for a.out.h . Also removed are superfluous install rules in the s390 and x86 Kbuild files (they are already in Kbuild.asm). Signed-off-by: Adrian Bunk Acked-by: Sam Ravnborg Signed-off-by: David Woodhouse --- include/asm-alpha/kvm.h | 6 ------ include/asm-arm/kvm.h | 6 ------ include/asm-avr32/kvm.h | 6 ------ include/asm-blackfin/kvm.h | 6 ------ include/asm-cris/kvm.h | 6 ------ include/asm-frv/kvm.h | 6 ------ include/asm-generic/Kbuild.asm | 2 ++ include/asm-h8300/kvm.h | 6 ------ include/asm-m32r/kvm.h | 6 ------ include/asm-m68k/kvm.h | 6 ------ include/asm-m68knommu/kvm.h | 6 ------ include/asm-mips/kvm.h | 6 ------ include/asm-mn10300/kvm.h | 6 ------ include/asm-parisc/kvm.h | 6 ------ include/asm-s390/Kbuild | 1 - include/asm-sh/kvm.h | 6 ------ include/asm-sparc/kvm.h | 6 ------ include/asm-sparc64/kvm.h | 1 - include/asm-um/kvm.h | 6 ------ include/asm-x86/Kbuild | 1 - include/asm-xtensa/kvm.h | 6 ------ include/linux/Kbuild | 2 ++ 22 files changed, 4 insertions(+), 105 deletions(-) delete mode 100644 include/asm-alpha/kvm.h delete mode 100644 include/asm-arm/kvm.h delete mode 100644 include/asm-avr32/kvm.h delete mode 100644 include/asm-blackfin/kvm.h delete mode 100644 include/asm-cris/kvm.h delete mode 100644 include/asm-frv/kvm.h delete mode 100644 include/asm-h8300/kvm.h delete mode 100644 include/asm-m32r/kvm.h delete mode 100644 include/asm-m68k/kvm.h delete mode 100644 include/asm-m68knommu/kvm.h delete mode 100644 include/asm-mips/kvm.h delete mode 100644 include/asm-mn10300/kvm.h delete mode 100644 include/asm-parisc/kvm.h delete mode 100644 include/asm-sh/kvm.h delete mode 100644 include/asm-sparc/kvm.h delete mode 100644 include/asm-sparc64/kvm.h delete mode 100644 include/asm-um/kvm.h delete mode 100644 include/asm-xtensa/kvm.h (limited to 'include/asm-x86') diff --git a/include/asm-alpha/kvm.h b/include/asm-alpha/kvm.h deleted file mode 100644 index b9daec429689..000000000000 --- a/include/asm-alpha/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_ALPHA_H -#define __LINUX_KVM_ALPHA_H - -/* alpha does not support KVM */ - -#endif diff --git a/include/asm-arm/kvm.h b/include/asm-arm/kvm.h deleted file mode 100644 index cb3c08cbcb9e..000000000000 --- a/include/asm-arm/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_ARM_H -#define __LINUX_KVM_ARM_H - -/* arm does not support KVM */ - -#endif diff --git a/include/asm-avr32/kvm.h b/include/asm-avr32/kvm.h deleted file mode 100644 index 8c5777020e2c..000000000000 --- a/include/asm-avr32/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_AVR32_H -#define __LINUX_KVM_AVR32_H - -/* avr32 does not support KVM */ - -#endif diff --git a/include/asm-blackfin/kvm.h b/include/asm-blackfin/kvm.h deleted file mode 100644 index e3477d77c014..000000000000 --- a/include/asm-blackfin/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_BLACKFIN_H -#define __LINUX_KVM_BLACKFIN_H - -/* blackfin does not support KVM */ - -#endif diff --git a/include/asm-cris/kvm.h b/include/asm-cris/kvm.h deleted file mode 100644 index c860f51149f0..000000000000 --- a/include/asm-cris/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_CRIS_H -#define __LINUX_KVM_CRIS_H - -/* cris does not support KVM */ - -#endif diff --git a/include/asm-frv/kvm.h b/include/asm-frv/kvm.h deleted file mode 100644 index 9c8a4f08d0a9..000000000000 --- a/include/asm-frv/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_FRV_H -#define __LINUX_KVM_FRV_H - -/* frv does not support KVM */ - -#endif diff --git a/include/asm-generic/Kbuild.asm b/include/asm-generic/Kbuild.asm index 7cd25b8e7c9a..1170dc60e638 100644 --- a/include/asm-generic/Kbuild.asm +++ b/include/asm-generic/Kbuild.asm @@ -1,4 +1,6 @@ +ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/kvm.h),) header-y += kvm.h +endif ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/a.out.h),) unifdef-y += a.out.h diff --git a/include/asm-h8300/kvm.h b/include/asm-h8300/kvm.h deleted file mode 100644 index bdbed7b987e1..000000000000 --- a/include/asm-h8300/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_H8300_H -#define __LINUX_KVM_H8300_H - -/* h8300 does not support KVM */ - -#endif diff --git a/include/asm-m32r/kvm.h b/include/asm-m32r/kvm.h deleted file mode 100644 index 99a40515b77e..000000000000 --- a/include/asm-m32r/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_M32R_H -#define __LINUX_KVM_M32R_H - -/* m32r does not support KVM */ - -#endif diff --git a/include/asm-m68k/kvm.h b/include/asm-m68k/kvm.h deleted file mode 100644 index 7ed27fce5240..000000000000 --- a/include/asm-m68k/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_M68K_H -#define __LINUX_KVM_M68K_H - -/* m68k does not support KVM */ - -#endif diff --git a/include/asm-m68knommu/kvm.h b/include/asm-m68knommu/kvm.h deleted file mode 100644 index b49d4258dabb..000000000000 --- a/include/asm-m68knommu/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_M68KNOMMU_H -#define __LINUX_KVM_M68KNOMMU_H - -/* m68knommu does not support KVM */ - -#endif diff --git a/include/asm-mips/kvm.h b/include/asm-mips/kvm.h deleted file mode 100644 index 093a5b7f796b..000000000000 --- a/include/asm-mips/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_MIPS_H -#define __LINUX_KVM_MIPS_H - -/* mips does not support KVM */ - -#endif diff --git a/include/asm-mn10300/kvm.h b/include/asm-mn10300/kvm.h deleted file mode 100644 index f6b609ff4a57..000000000000 --- a/include/asm-mn10300/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_MN10300_H -#define __LINUX_KVM_MN10300_H - -/* mn10300 does not support KVM */ - -#endif diff --git a/include/asm-parisc/kvm.h b/include/asm-parisc/kvm.h deleted file mode 100644 index 00cc45812547..000000000000 --- a/include/asm-parisc/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_PARISC_H -#define __LINUX_KVM_PARISC_H - -/* parisc does not support KVM */ - -#endif diff --git a/include/asm-s390/Kbuild b/include/asm-s390/Kbuild index bb5e9edb9825..63a23415fba6 100644 --- a/include/asm-s390/Kbuild +++ b/include/asm-s390/Kbuild @@ -7,7 +7,6 @@ header-y += tape390.h header-y += ucontext.h header-y += vtoc.h header-y += zcrypt.h -header-y += kvm.h header-y += chsc.h unifdef-y += cmb.h diff --git a/include/asm-sh/kvm.h b/include/asm-sh/kvm.h deleted file mode 100644 index 6af51dbab2d0..000000000000 --- a/include/asm-sh/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_SH_H -#define __LINUX_KVM_SH_H - -/* sh does not support KVM */ - -#endif diff --git a/include/asm-sparc/kvm.h b/include/asm-sparc/kvm.h deleted file mode 100644 index 2e5478da3819..000000000000 --- a/include/asm-sparc/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_SPARC_H -#define __LINUX_KVM_SPARC_H - -/* sparc does not support KVM */ - -#endif diff --git a/include/asm-sparc64/kvm.h b/include/asm-sparc64/kvm.h deleted file mode 100644 index 53564ad86b15..000000000000 --- a/include/asm-sparc64/kvm.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-um/kvm.h b/include/asm-um/kvm.h deleted file mode 100644 index 66aa77094551..000000000000 --- a/include/asm-um/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_UM_H -#define __LINUX_KVM_UM_H - -/* um does not support KVM */ - -#endif diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild index 1e3554596f72..811e9828ccb3 100644 --- a/include/asm-x86/Kbuild +++ b/include/asm-x86/Kbuild @@ -3,7 +3,6 @@ include include/asm-generic/Kbuild.asm header-y += boot.h header-y += bootparam.h header-y += debugreg.h -header-y += kvm.h header-y += ldt.h header-y += msr-index.h header-y += prctl.h diff --git a/include/asm-xtensa/kvm.h b/include/asm-xtensa/kvm.h deleted file mode 100644 index bda4e331e98c..000000000000 --- a/include/asm-xtensa/kvm.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __LINUX_KVM_XTENSA_H -#define __LINUX_KVM_XTENSA_H - -/* xtensa does not support KVM */ - -#endif diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 71d70d1fbce2..402c8f55d713 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -256,7 +256,9 @@ unifdef-y += kd.h unifdef-y += kernelcapi.h unifdef-y += kernel.h unifdef-y += keyboard.h +ifneq ($(wildcard $(srctree)/include/asm-$(SRCARCH)/kvm.h),) unifdef-y += kvm.h +endif unifdef-y += llc.h unifdef-y += loop.h unifdef-y += lp.h -- cgit v1.2.3