From 93a6d3ce6962044fe9badf528fed46b455d58292 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 9 Jan 2009 16:52:19 +1100 Subject: powerpc: Provide a way to defer perf counter work until interrupts are enabled Because 64-bit powerpc uses lazy (soft) interrupt disabling, it is possible for a performance monitor exception to come in when the kernel thinks interrupts are disabled (i.e. when they are soft-disabled but hard-enabled). In such a situation the performance monitor exception handler might have some processing to do (such as process wakeups) which can't be done in what is effectively an NMI handler. This provides a way to defer that work until interrupts get enabled, either in raw_local_irq_restore() or by returning from an interrupt handler to code that had interrupts enabled. We have a per-processor flag that indicates that there is work pending to do when interrupts subsequently get re-enabled. This flag is checked in the interrupt return path and in raw_local_irq_restore(), and if it is set, perf_counter_do_pending() is called to do the pending work. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/hw_irq.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index f75a5fc64d2e..e10f151c3db6 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -131,5 +131,36 @@ static inline int irqs_disabled_flags(unsigned long flags) */ struct hw_interrupt_type; +#ifdef CONFIG_PERF_COUNTERS +static inline unsigned long get_perf_counter_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, perf_counter_pending))); + return x; +} + +static inline void set_perf_counter_pending(int x) +{ + asm volatile("stb %0,%1(13)" : : + "r" (x), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +extern void perf_counter_do_pending(void); + +#else + +static inline unsigned long get_perf_counter_pending(void) +{ + return 0; +} + +static inline void set_perf_counter_pending(int x) {} +static inline void perf_counter_do_pending(void) {} +#endif /* CONFIG_PERF_COUNTERS */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ -- cgit v1.2.3 From b6c5a71da1477d261bc36254fe1f20d32b57598d Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 16 Mar 2009 21:00:00 +1100 Subject: perf_counter: abstract wakeup flag setting in core to fix powerpc build Impact: build fix for powerpc Commit bd753921015e7905 ("perf_counter: software counter event infrastructure") introduced a use of TIF_PERF_COUNTERS into the core perfcounter code. This breaks the build on powerpc because we use a flag in a per-cpu area to signal wakeups on powerpc rather than a thread_info flag, because the thread_info flags have to be manipulated with atomic operations and are thus slower than per-cpu flags. This fixes the by changing the core to use an abstracted set_perf_counter_pending() function, which is defined on x86 to set the TIF_PERF_COUNTERS flag and on powerpc to set the per-cpu flag (paca->perf_counter_pending). It changes the previous powerpc definition of set_perf_counter_pending to not take an argument and adds a clear_perf_counter_pending, so as to simplify the definition on x86. On x86, set_perf_counter_pending() is defined as a macro. Defining it as a static inline in arch/x86/include/asm/perf_counters.h causes compile failures because gets included early in , and the definitions of set_tsk_thread_flag etc. are therefore not available in . (On powerpc this problem is avoided by defining set_perf_counter_pending etc. in .) Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/hw_irq.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index b43076ff92c9..cb32d571c9c7 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -142,10 +142,17 @@ static inline unsigned long get_perf_counter_pending(void) return x; } -static inline void set_perf_counter_pending(int x) +static inline void set_perf_counter_pending(void) { asm volatile("stb %0,%1(13)" : : - "r" (x), + "r" (1), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +static inline void clear_perf_counter_pending(void) +{ + asm volatile("stb %0,%1(13)" : : + "r" (0), "i" (offsetof(struct paca_struct, perf_counter_pending))); } @@ -158,7 +165,8 @@ static inline unsigned long get_perf_counter_pending(void) return 0; } -static inline void set_perf_counter_pending(int x) {} +static inline void set_perf_counter_pending(void) {} +static inline void clear_perf_counter_pending(void) {} static inline void perf_counter_do_pending(void) {} #endif /* CONFIG_PERF_COUNTERS */ -- cgit v1.2.3 From 925d519ab82b6dd7aca9420d809ee83819c08db2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Mar 2009 19:07:02 +0200 Subject: perf_counter: unify and fix delayed counter wakeup While going over the wakeup code I noticed delayed wakeups only work for hardware counters but basically all software counters rely on them. This patch unifies and generalizes the delayed wakeup to fix this issue. Since we're dealing with NMI context bits here, use a cmpxchg() based single link list implementation to track counters that have pending wakeups. [ This should really be generic code for delayed wakeups, but since we cannot use cmpxchg()/xchg() in generic code, I've let it live in the perf_counter code. -- Eric Dumazet could use it to aggregate the network wakeups. ] Furthermore, the x86 method of using TIF flags was flawed in that its quite possible to end up setting the bit on the idle task, loosing the wakeup. The powerpc method uses per-cpu storage and does appear to be sufficient. Signed-off-by: Peter Zijlstra Acked-by: Paul Mackerras Orig-LKML-Reference: <20090330171023.153932974@chello.nl> Signed-off-by: Ingo Molnar --- arch/powerpc/include/asm/hw_irq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index cb32d571c9c7..20a44d0c9fdd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -132,7 +132,7 @@ static inline int irqs_disabled_flags(unsigned long flags) struct irq_chip; #ifdef CONFIG_PERF_COUNTERS -static inline unsigned long get_perf_counter_pending(void) +static inline unsigned long test_perf_counter_pending(void) { unsigned long x; @@ -160,7 +160,7 @@ extern void perf_counter_do_pending(void); #else -static inline unsigned long get_perf_counter_pending(void) +static inline unsigned long test_perf_counter_pending(void) { return 0; } -- cgit v1.2.3 From e14112d1bd5e193166b54be19119cf6440470560 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 12 Jun 2009 10:14:22 +1000 Subject: perfcounters: remove powerpc definitions of perf_counter_do_pending Commit 925d519ab82b6dd7aca9420d809ee83819c08db2 ("perf_counter: unify and fix delayed counter wakeup") added global definitions. Signed-off-by: Stephen Rothwell Acked-by: Paul Mackerras Acked-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/hw_irq.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 20a44d0c9fdd..53512374e1c9 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -156,8 +156,6 @@ static inline void clear_perf_counter_pending(void) "i" (offsetof(struct paca_struct, perf_counter_pending))); } -extern void perf_counter_do_pending(void); - #else static inline unsigned long test_perf_counter_pending(void) @@ -167,7 +165,6 @@ static inline unsigned long test_perf_counter_pending(void) static inline void set_perf_counter_pending(void) {} static inline void clear_perf_counter_pending(void) {} -static inline void perf_counter_do_pending(void) {} #endif /* CONFIG_PERF_COUNTERS */ #endif /* __KERNEL__ */ -- cgit v1.2.3 From 4c75f84f2c781beb230031234ed961d28771a764 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 12 Jun 2009 02:00:50 +0000 Subject: powerpc: Add compiler memory barrier to mtmsr macro On 32-bit non-Book E, local_irq_restore() turns into just mtmsr(), which doesn't currently have a compiler memory barrier. This means that accesses to memory inside a local_irq_save/restore section, or a spin_lock_irqsave/spin_unlock_irqrestore section on UP, can be reordered by the compiler to occur outside that section. To fix this, this adds a compiler memory barrier to mtmsr for both 32-bit and 64-bit. Having a compiler memory barrier in mtmsr makes sense because it will almost always be changing something about the context in which memory accesses are done, so in general we don't want memory accesses getting moved from one side of an mtmsr to the other. With the barrier in mtmsr(), some of the explicit barriers in hw_irq.h are now redundant, so this removes them. Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hw_irq.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 53512374e1c9..b7f8f4a87cc0 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -80,7 +80,7 @@ static inline void local_irq_disable(void) __asm__ __volatile__("wrteei 0": : :"memory"); #else unsigned long msr; - __asm__ __volatile__("": : :"memory"); + msr = mfmsr(); SET_MSR_EE(msr & ~MSR_EE); #endif @@ -92,7 +92,7 @@ static inline void local_irq_enable(void) __asm__ __volatile__("wrteei 1": : :"memory"); #else unsigned long msr; - __asm__ __volatile__("": : :"memory"); + msr = mfmsr(); SET_MSR_EE(msr | MSR_EE); #endif @@ -108,7 +108,6 @@ static inline void local_irq_save_ptr(unsigned long *flags) #else SET_MSR_EE(msr & ~MSR_EE); #endif - __asm__ __volatile__("": : :"memory"); } #define local_save_flags(flags) ((flags) = mfmsr()) -- cgit v1.2.3 From 9974458e2f9a11dbd2f4bd14fab5a79af4907b41 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 15 Jun 2009 21:45:16 +1000 Subject: perf_counter: Make set_perf_counter_pending() declaration common At present, every architecture that supports perf_counters has to declare set_perf_counter_pending() in its arch-specific headers. This consolidates the declarations into a single declaration in one common place, include/linux/perf_counter.h. On powerpc, we continue to provide a static inline definition of set_perf_counter_pending() in the powerpc hw_irq.h. Also, this removes from the x86 perf_counter.h the unused null definitions of {test,clear}_perf_counter_pending. Reported-by: Mike Frysinger Signed-off-by: Paul Mackerras Cc: Peter Zijlstra Cc: benh@kernel.crashing.org LKML-Reference: <18998.13388.920691.523227@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- arch/powerpc/include/asm/hw_irq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 53512374e1c9..1974cf191b03 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -163,7 +163,6 @@ static inline unsigned long test_perf_counter_pending(void) return 0; } -static inline void set_perf_counter_pending(void) {} static inline void clear_perf_counter_pending(void) {} #endif /* CONFIG_PERF_COUNTERS */ -- cgit v1.2.3 From 105988c015943e77092a6568bc5fb7e386df6ccd Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 17 Jun 2009 21:50:04 +1000 Subject: perf_counter: powerpc: Enable use of software counters on 32-bit powerpc This enables the perf_counter subsystem on 32-bit powerpc. Since we don't have any support for hardware counters on 32-bit powerpc yet, only software counters can be used. Besides selecting HAVE_PERF_COUNTERS for 32-bit powerpc as well as 64-bit, the main thing this does is add an implementation of set_perf_counter_pending(). This needs to arrange for perf_counter_do_pending() to be called when interrupts are enabled. Rather than add code to local_irq_restore as 64-bit does, the 32-bit set_perf_counter_pending() generates an interrupt by setting the decrementer to 1 so that a decrementer interrupt will become pending in 1 or 2 timebase ticks (if a decrementer interrupt isn't already pending). When interrupts are enabled, timer_interrupt() will be called, and some new code in there calls perf_counter_do_pending(). We use a per-cpu array of flags to indicate whether we need to call perf_counter_do_pending() or not. This introduces a couple of new Kconfig symbols: PPC_HAVE_PMU_SUPPORT, which is selected by processor families for which we have hardware PMU support (currently only PPC64), and PPC_PERF_CTRS, which enables the powerpc-specific perf_counter back-end. Signed-off-by: Paul Mackerras Cc: Peter Zijlstra Cc: linuxppc-dev@ozlabs.org Cc: benh@kernel.crashing.org LKML-Reference: <19000.55404.103840.393470@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- arch/powerpc/include/asm/hw_irq.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm/hw_irq.h') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 10a642df014e..867ab8ed69b3 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -131,6 +131,8 @@ static inline int irqs_disabled_flags(unsigned long flags) struct irq_chip; #ifdef CONFIG_PERF_COUNTERS + +#ifdef CONFIG_PPC64 static inline unsigned long test_perf_counter_pending(void) { unsigned long x; @@ -154,8 +156,9 @@ static inline void clear_perf_counter_pending(void) "r" (0), "i" (offsetof(struct paca_struct, perf_counter_pending))); } +#endif /* CONFIG_PPC64 */ -#else +#else /* CONFIG_PERF_COUNTERS */ static inline unsigned long test_perf_counter_pending(void) { -- cgit v1.2.3