From patchwork Fri Dec 9 15:33:53 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marc Zyngier X-Patchwork-Id: 130408 Return-Path: X-Original-To: incoming-imx@patchwork.ozlabs.org Delivered-To: patchwork-incoming-imx@bilbo.ozlabs.org Received: from merlin.infradead.org (merlin.infradead.org [IPv6:2001:4978:20e::2]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id 47A7D1007D7 for ; Sat, 10 Dec 2011 02:37:11 +1100 (EST) Received: from localhost ([::1] helo=merlin.infradead.org) by merlin.infradead.org with esmtp (Exim 4.76 #1 (Red Hat Linux)) id 1RZ2Sm-0001Y6-Rd; Fri, 09 Dec 2011 15:34:16 +0000 Received: from service87.mimecast.com ([91.220.42.44]) by merlin.infradead.org with esmtp (Exim 4.76 #1 (Red Hat Linux)) id 1RZ2Sg-0001XN-Vb for linux-arm-kernel@lists.infradead.org; Fri, 09 Dec 2011 15:34:13 +0000 Received: from cam-owa1.Emea.Arm.com (fw-tnat.cambridge.arm.com [217.140.96.21]) by service87.mimecast.com; Fri, 09 Dec 2011 15:34:02 +0000 Received: from localhost.localdomain ([10.1.255.212]) by cam-owa1.Emea.Arm.com with Microsoft SMTPSVC(6.0.3790.0); Fri, 9 Dec 2011 15:33:56 +0000 From: Marc Zyngier To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v4] ARM: sched_clock: allow sched_clock to be selected at runtime Date: Fri, 9 Dec 2011 15:33:53 +0000 Message-Id: <1323444833-10587-1-git-send-email-marc.zyngier@arm.com> X-Mailer: git-send-email 1.7.0.4 X-OriginalArrivalTime: 09 Dec 2011 15:33:56.0676 (UTC) FILETIME=[F6F17040:01CCB687] X-MC-Unique: 111120915340205001 X-Spam-Note: CRM114 invocation failed X-Spam-Score: -2.6 (--) X-Spam-Report: SpamAssassin version 3.3.2 on merlin.infradead.org summary: Content analysis details: (-2.6 points) pts rule name description ---- ---------------------- -------------------------------------------------- -0.7 RCVD_IN_DNSWL_LOW RBL: Sender listed at http://www.dnswl.org/, low trust [91.220.42.44 listed in list.dnswl.org] -0.0 SPF_PASS SPF: sender matches SPF record -1.9 BAYES_00 BODY: Bayes spam probability is 0 to 1% [score: 0.0000] Cc: Alessandro Rubini , Kukjin Kim , Eric Miao , Linus Walleij , Erik Gilling , Nicolas Pitre , Tony Lindgren , STEricsson , Sascha Hauer , Colin Cross , Olof Johansson , Jamie Iles , Imre Kaloz , Lennert Buytenhek , Ben Dooks , Krzysztof Halasa X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.14 Precedence: list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: linux-arm-kernel-bounces@lists.infradead.org Errors-To: linux-arm-kernel-bounces+incoming-imx=patchwork.ozlabs.org@lists.infradead.org List-Id: linux-imx-kernel.lists.patchwork.ozlabs.org sched_clock() is yet another blocker on the road to the single image. This patch implements an idea by Russell King: http://www.spinics.net/lists/linux-omap/msg49561.html Instead of asking the platform to implement both sched_clock() itself and the rollover callback, simply register a read() function, and let the ARM code care about sched_clock() itself, the conversion to ns and the rollover. sched_clock() uses this read() function as an indirection to the platform code. If the platform doesn't provide a read(), the code falls back to the jiffy counter (just like the default sched_clock). This allow some simplifications and possibly some footprint gain when multiple platforms are compiled in. Among the drawbacks, the removal of the *_fixed_sched_clock optimization which could negatively impact some platforms (sa1100, tegra, versatile and omap). Tested on 11MPCore, OMAP4 and Tegra. Cc: Imre Kaloz Cc: Krzysztof Halasa Cc: Tony Lindgren Cc: Eric Miao Cc: Colin Cross Cc: Erik Gilling Cc: Olof Johansson Cc: Linus Walleij Cc: Sascha Hauer Cc: Alessandro Rubini Cc: STEricsson Cc: Lennert Buytenhek Cc: Nicolas Pitre Cc: Ben Dooks Cc: Kukjin Kim Cc: Jamie Iles Tested-by: Jamie Iles Acked-by: Linus Walleij Signed-off-by: Marc Zyngier Acked-by: Nicolas Pitre Tested-by: Tony Lindgren Tested-by: Kyungmin Park Acked-By: Krzysztof Halasa Acked-by: Shawn Guo Acked-by: Kukjin Kim --- I'm reposting this patch with the hope that it (or Russell's alternative patch http://patchwork.ozlabs.org/patch/115961/) will get merged in 3.3. It doesn't look intrusive enough to be left on the side of the road for yet another cycle... Based on RMK's devel-stable as of Dec 9th. >From v3: - Converted picoxcell - Some minor cleanup >From v2: - Removed the read_sched_clock test from sched_clock() and move the jiffies code to its own function, as suggested by Nicolas Pitre. WARN_ON are added to ensure that setup_sched_clock() is not called in an unsafe context and that we only override the default once. >From v1: - Added 'notrace' to all _read_sched_lock() functions, fixing the ftrace problem reported by Jamie Iles - Removed useless #include from touched files - Made omap_32k_read_sched_clock() static arch/arm/include/asm/sched_clock.h | 108 +--------------------------- arch/arm/kernel/sched_clock.c | 118 ++++++++++++++++++++++++++--- arch/arm/mach-ixp4xx/common.c | 16 +--- arch/arm/mach-mmp/time.c | 16 +--- arch/arm/mach-omap1/time.c | 58 +-------------- arch/arm/mach-omap2/timer.c | 20 +---- arch/arm/mach-picoxcell/time.c | 17 +---- arch/arm/mach-pxa/time.c | 15 +--- arch/arm/mach-sa1100/time.c | 28 +------ arch/arm/mach-tegra/timer.c | 24 +----- arch/arm/mach-u300/timer.c | 15 +--- arch/arm/plat-iop/time.c | 16 +--- arch/arm/plat-mxc/time.c | 15 +--- arch/arm/plat-nomadik/timer.c | 20 +---- arch/arm/plat-omap/counter_32k.c | 40 +--------- arch/arm/plat-omap/include/plat/common.h | 1 - arch/arm/plat-orion/time.c | 21 +----- arch/arm/plat-s5p/s5p-time.c | 19 +---- arch/arm/plat-versatile/sched-clock.c | 29 ++------ 19 files changed, 161 insertions(+), 435 deletions(-) diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h index c8e6ddf..e3f7572 100644 --- a/arch/arm/include/asm/sched_clock.h +++ b/arch/arm/include/asm/sched_clock.h @@ -8,113 +8,7 @@ #ifndef ASM_SCHED_CLOCK #define ASM_SCHED_CLOCK -#include -#include - -struct clock_data { - u64 epoch_ns; - u32 epoch_cyc; - u32 epoch_cyc_copy; - u32 mult; - u32 shift; -}; - -#define DEFINE_CLOCK_DATA(name) struct clock_data name - -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) -{ - return (cyc * mult) >> shift; -} - -/* - * Atomically update the sched_clock epoch. Your update callback will - * be called from a timer before the counter wraps - read the current - * counter value, and call this function to safely move the epochs - * forward. Only use this from the update callback. - */ -static inline void update_sched_clock(struct clock_data *cd, u32 cyc, u32 mask) -{ - unsigned long flags; - u64 ns = cd->epoch_ns + - cyc_to_ns((cyc - cd->epoch_cyc) & mask, cd->mult, cd->shift); - - /* - * Write epoch_cyc and epoch_ns in a way that the update is - * detectable in cyc_to_fixed_sched_clock(). - */ - raw_local_irq_save(flags); - cd->epoch_cyc = cyc; - smp_wmb(); - cd->epoch_ns = ns; - smp_wmb(); - cd->epoch_cyc_copy = cyc; - raw_local_irq_restore(flags); -} - -/* - * If your clock rate is known at compile time, using this will allow - * you to optimize the mult/shift loads away. This is paired with - * init_fixed_sched_clock() to ensure that your mult/shift are correct. - */ -static inline unsigned long long cyc_to_fixed_sched_clock(struct clock_data *cd, - u32 cyc, u32 mask, u32 mult, u32 shift) -{ - u64 epoch_ns; - u32 epoch_cyc; - - /* - * Load the epoch_cyc and epoch_ns atomically. We do this by - * ensuring that we always write epoch_cyc, epoch_ns and - * epoch_cyc_copy in strict order, and read them in strict order. - * If epoch_cyc and epoch_cyc_copy are not equal, then we're in - * the middle of an update, and we should repeat the load. - */ - do { - epoch_cyc = cd->epoch_cyc; - smp_rmb(); - epoch_ns = cd->epoch_ns; - smp_rmb(); - } while (epoch_cyc != cd->epoch_cyc_copy); - - return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, mult, shift); -} - -/* - * Otherwise, you need to use this, which will obtain the mult/shift - * from the clock_data structure. Use init_sched_clock() with this. - */ -static inline unsigned long long cyc_to_sched_clock(struct clock_data *cd, - u32 cyc, u32 mask) -{ - return cyc_to_fixed_sched_clock(cd, cyc, mask, cd->mult, cd->shift); -} - -/* - * Initialize the clock data - calculate the appropriate multiplier - * and shift. Also setup a timer to ensure that the epoch is refreshed - * at the appropriate time interval, which will call your update - * handler. - */ -void init_sched_clock(struct clock_data *, void (*)(void), - unsigned int, unsigned long); - -/* - * Use this initialization function rather than init_sched_clock() if - * you're using cyc_to_fixed_sched_clock, which will warn if your - * constants are incorrect. - */ -static inline void init_fixed_sched_clock(struct clock_data *cd, - void (*update)(void), unsigned int bits, unsigned long rate, - u32 mult, u32 shift) -{ - init_sched_clock(cd, update, bits, rate); - if (cd->mult != mult || cd->shift != shift) { - pr_crit("sched_clock: wrong multiply/shift: %u>>%u vs calculated %u>>%u\n" - "sched_clock: fix multiply/shift to avoid scheduler hiccups\n", - mult, shift, cd->mult, cd->shift); - } -} - extern void sched_clock_postinit(void); +extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate); #endif diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index 9a46370..12ab17f 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -14,61 +14,153 @@ #include +struct clock_data { + u64 epoch_ns; + u32 epoch_cyc; + u32 epoch_cyc_copy; + u32 mult; + u32 shift; +}; + static void sched_clock_poll(unsigned long wrap_ticks); static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0); -static void (*sched_clock_update_fn)(void); + +static struct clock_data cd = { + .mult = NSEC_PER_SEC / HZ, +}; + +static u32 __read_mostly sched_clock_mask = 0xffffffff; + +static u32 notrace jiffy_sched_clock_read(void) +{ + return (u32)(jiffies - INITIAL_JIFFIES); +} + +static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; + +static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +{ + return (cyc * mult) >> shift; +} + +static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +{ + u64 epoch_ns; + u32 epoch_cyc; + + /* + * Load the epoch_cyc and epoch_ns atomically. We do this by + * ensuring that we always write epoch_cyc, epoch_ns and + * epoch_cyc_copy in strict order, and read them in strict order. + * If epoch_cyc and epoch_cyc_copy are not equal, then we're in + * the middle of an update, and we should repeat the load. + */ + do { + epoch_cyc = cd.epoch_cyc; + smp_rmb(); + epoch_ns = cd.epoch_ns; + smp_rmb(); + } while (epoch_cyc != cd.epoch_cyc_copy); + + return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift); +} + +/* + * Atomically update the sched_clock epoch. + */ +static void notrace update_sched_clock(void) +{ + unsigned long flags; + u32 cyc; + u64 ns; + + cyc = read_sched_clock(); + ns = cd.epoch_ns + + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, + cd.mult, cd.shift); + /* + * Write epoch_cyc and epoch_ns in a way that the update is + * detectable in cyc_to_fixed_sched_clock(). + */ + raw_local_irq_save(flags); + cd.epoch_cyc = cyc; + smp_wmb(); + cd.epoch_ns = ns; + smp_wmb(); + cd.epoch_cyc_copy = cyc; + raw_local_irq_restore(flags); +} static void sched_clock_poll(unsigned long wrap_ticks) { mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks)); - sched_clock_update_fn(); + update_sched_clock(); } -void __init init_sched_clock(struct clock_data *cd, void (*update)(void), - unsigned int clock_bits, unsigned long rate) +void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) { unsigned long r, w; u64 res, wrap; char r_unit; - sched_clock_update_fn = update; + BUG_ON(bits > 32); + WARN_ON(!irqs_disabled()); + WARN_ON(read_sched_clock != jiffy_sched_clock_read); + read_sched_clock = read; + sched_clock_mask = (1 << bits) - 1; /* calculate the mult/shift to convert counter ticks to ns. */ - clocks_calc_mult_shift(&cd->mult, &cd->shift, rate, NSEC_PER_SEC, 0); + clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0); r = rate; if (r >= 4000000) { r /= 1000000; r_unit = 'M'; - } else { + } else if (r >= 1000) { r /= 1000; r_unit = 'k'; - } + } else + r_unit = ' '; /* calculate how many ns until we wrap */ - wrap = cyc_to_ns((1ULL << clock_bits) - 1, cd->mult, cd->shift); + wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift); do_div(wrap, NSEC_PER_MSEC); w = wrap; /* calculate the ns resolution of this counter */ - res = cyc_to_ns(1ULL, cd->mult, cd->shift); + res = cyc_to_ns(1ULL, cd.mult, cd.shift); pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n", - clock_bits, r, r_unit, res, w); + bits, r, r_unit, res, w); /* * Start the timer to keep sched_clock() properly updated and * sets the initial epoch. */ sched_clock_timer.data = msecs_to_jiffies(w - (w / 10)); - update(); + update_sched_clock(); /* * Ensure that sched_clock() starts off at 0ns */ - cd->epoch_ns = 0; + cd.epoch_ns = 0; + + pr_debug("Registered %pF as sched_clock source\n", read); +} + +unsigned long long notrace sched_clock(void) +{ + u32 cyc = read_sched_clock(); + return cyc_to_sched_clock(cyc, sched_clock_mask); } void __init sched_clock_postinit(void) { + /* + * If no sched_clock function has been provided at that point, + * make it the final one one. + */ + if (read_sched_clock == jiffy_sched_clock_read) + setup_sched_clock(jiffy_sched_clock_read, 32, HZ); + sched_clock_poll(sched_clock_timer.data); } diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c index b86a005..c1b12f9 100644 --- a/arch/arm/mach-ixp4xx/common.c +++ b/arch/arm/mach-ixp4xx/common.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -403,18 +402,9 @@ void __init ixp4xx_sys_init(void) /* * sched_clock() */ -static DEFINE_CLOCK_DATA(cd); - -unsigned long long notrace sched_clock(void) +static u32 notrace ixp4xx_read_sched_clock(void) { - u32 cyc = *IXP4XX_OSTS; - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace ixp4xx_update_sched_clock(void) -{ - u32 cyc = *IXP4XX_OSTS; - update_sched_clock(&cd, cyc, (u32)~0); + return *IXP4XX_OSTS; } /* @@ -430,7 +420,7 @@ unsigned long ixp4xx_timer_freq = IXP4XX_TIMER_FREQ; EXPORT_SYMBOL(ixp4xx_timer_freq); static void __init ixp4xx_clocksource_init(void) { - init_sched_clock(&cd, ixp4xx_update_sched_clock, 32, ixp4xx_timer_freq); + setup_sched_clock(ixp4xx_read_sched_clock, 32, ixp4xx_timer_freq); clocksource_mmio_init(NULL, "OSTS", ixp4xx_timer_freq, 200, 32, ixp4xx_clocksource_read); diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c index 4e91ee6..71fc4ee 100644 --- a/arch/arm/mach-mmp/time.c +++ b/arch/arm/mach-mmp/time.c @@ -25,7 +25,6 @@ #include #include -#include #include #include @@ -42,8 +41,6 @@ #define MAX_DELTA (0xfffffffe) #define MIN_DELTA (16) -static DEFINE_CLOCK_DATA(cd); - /* * FIXME: the timer needs some delay to stablize the counter capture */ @@ -59,16 +56,9 @@ static inline uint32_t timer_read(void) return __raw_readl(TIMERS_VIRT_BASE + TMR_CVWR(1)); } -unsigned long long notrace sched_clock(void) +static u32 notrace mmp_read_sched_clock(void) { - u32 cyc = timer_read(); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace mmp_update_sched_clock(void) -{ - u32 cyc = timer_read(); - update_sched_clock(&cd, cyc, (u32)~0); + return timer_read(); } static irqreturn_t timer_interrupt(int irq, void *dev_id) @@ -201,7 +191,7 @@ void __init timer_init(int irq) { timer_config(); - init_sched_clock(&cd, mmp_update_sched_clock, 32, CLOCK_TICK_RATE); + setup_sched_clock(mmp_read_sched_clock, 32, CLOCK_TICK_RATE); ckevt.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, ckevt.shift); ckevt.max_delta_ns = clockevent_delta2ns(MAX_DELTA, &ckevt); diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c index 485a21d..b8faffa 100644 --- a/arch/arm/mach-omap1/time.c +++ b/arch/arm/mach-omap1/time.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -190,30 +189,9 @@ static __init void omap_init_mpu_timer(unsigned long rate) * --------------------------------------------------------------------------- */ -static DEFINE_CLOCK_DATA(cd); - -static inline unsigned long long notrace _omap_mpu_sched_clock(void) -{ - u32 cyc = ~omap_mpu_timer_read(1); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -#ifndef CONFIG_OMAP_32K_TIMER -unsigned long long notrace sched_clock(void) -{ - return _omap_mpu_sched_clock(); -} -#else -static unsigned long long notrace omap_mpu_sched_clock(void) -{ - return _omap_mpu_sched_clock(); -} -#endif - -static void notrace mpu_update_sched_clock(void) +static u32 notrace omap_mpu_read_sched_clock(void) { - u32 cyc = ~omap_mpu_timer_read(1); - update_sched_clock(&cd, cyc, (u32)~0); + return ~omap_mpu_timer_read(1); } static void __init omap_init_clocksource(unsigned long rate) @@ -223,7 +201,7 @@ static void __init omap_init_clocksource(unsigned long rate) "%s: can't register clocksource!\n"; omap_mpu_timer_start(1, ~0, 1); - init_sched_clock(&cd, mpu_update_sched_clock, 32, rate); + setup_sched_clock(omap_mpu_read_sched_clock, 32, rate); if (clocksource_mmio_init(&timer->read_tim, "mpu_timer2", rate, 300, 32, clocksource_mmio_readl_down)) @@ -254,30 +232,6 @@ static inline void omap_mpu_timer_init(void) } #endif /* CONFIG_OMAP_MPU_TIMER */ -#if defined(CONFIG_OMAP_MPU_TIMER) && defined(CONFIG_OMAP_32K_TIMER) -static unsigned long long (*preferred_sched_clock)(void); - -unsigned long long notrace sched_clock(void) -{ - if (!preferred_sched_clock) - return 0; - - return preferred_sched_clock(); -} - -static inline void preferred_sched_clock_init(bool use_32k_sched_clock) -{ - if (use_32k_sched_clock) - preferred_sched_clock = omap_32k_sched_clock; - else - preferred_sched_clock = omap_mpu_sched_clock; -} -#else -static inline void preferred_sched_clock_init(bool use_32k_sched_clcok) -{ -} -#endif - static inline int omap_32k_timer_usable(void) { int res = false; @@ -299,12 +253,8 @@ static inline int omap_32k_timer_usable(void) */ static void __init omap1_timer_init(void) { - if (omap_32k_timer_usable()) { - preferred_sched_clock_init(1); - } else { + if (!omap_32k_timer_usable()) omap_mpu_timer_init(); - preferred_sched_clock_init(0); - } } struct sys_timer omap1_timer = { diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 9edcd52..6eeff0e 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -254,7 +254,6 @@ static struct omap_dm_timer clksrc; /* * clocksource */ -static DEFINE_CLOCK_DATA(cd); static cycle_t clocksource_read_cycles(struct clocksource *cs) { return (cycle_t)__omap_dm_timer_read_counter(&clksrc, 1); @@ -268,23 +267,12 @@ static struct clocksource clocksource_gpt = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void notrace dmtimer_update_sched_clock(void) +static u32 notrace dmtimer_read_sched_clock(void) { - u32 cyc; - - cyc = __omap_dm_timer_read_counter(&clksrc, 1); - - update_sched_clock(&cd, cyc, (u32)~0); -} - -unsigned long long notrace sched_clock(void) -{ - u32 cyc = 0; - if (clksrc.reserved) - cyc = __omap_dm_timer_read_counter(&clksrc, 1); + return __omap_dm_timer_read_counter(clksrc.io_base, 1); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); + return 0; } /* Setup free-running counter for clocksource */ @@ -301,7 +289,7 @@ static void __init omap2_gp_clocksource_init(int gptimer_id, __omap_dm_timer_load_start(&clksrc, OMAP_TIMER_CTRL_ST | OMAP_TIMER_CTRL_AR, 0, 1); - init_sched_clock(&cd, dmtimer_update_sched_clock, 32, clksrc.rate); + setup_sched_clock(dmtimer_read_sched_clock, 32, clksrc.rate); if (clocksource_register_hz(&clocksource_gpt, clksrc.rate)) pr_err("Could not register clocksource %s\n", diff --git a/arch/arm/mach-picoxcell/time.c b/arch/arm/mach-picoxcell/time.c index 90a554f..6c89cf8 100644 --- a/arch/arm/mach-picoxcell/time.c +++ b/arch/arm/mach-picoxcell/time.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -66,21 +65,11 @@ static void picoxcell_add_clocksource(struct device_node *source_timer) dw_apb_clocksource_register(cs); } -static DEFINE_CLOCK_DATA(cd); static void __iomem *sched_io_base; -unsigned long long notrace sched_clock(void) +unsigned u32 notrace picoxcell_read_sched_clock(void) { - cycle_t cyc = sched_io_base ? __raw_readl(sched_io_base) : 0; - - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace picoxcell_update_sched_clock(void) -{ - cycle_t cyc = sched_io_base ? __raw_readl(sched_io_base) : 0; - - update_sched_clock(&cd, cyc, (u32)~0); + return __raw_readl(sched_io_base); } static const struct of_device_id picoxcell_rtc_ids[] __initconst = { @@ -100,7 +89,7 @@ static void picoxcell_init_sched_clock(void) timer_get_base_and_rate(sched_timer, &sched_io_base, &rate); of_node_put(sched_timer); - init_sched_clock(&cd, picoxcell_update_sched_clock, 32, rate); + setup_sched_clock(picoxcell_read_sched_clock, 32, rate); } static const struct of_device_id picoxcell_timer_ids[] __initconst = { diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c index de68470..b503049 100644 --- a/arch/arm/mach-pxa/time.c +++ b/arch/arm/mach-pxa/time.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -32,18 +31,10 @@ * long as there is always less than 582 seconds between successive * calls to sched_clock() which should always be the case in practice. */ -static DEFINE_CLOCK_DATA(cd); -unsigned long long notrace sched_clock(void) +static u32 notrace pxa_read_sched_clock(void) { - u32 cyc = OSCR; - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace pxa_update_sched_clock(void) -{ - u32 cyc = OSCR; - update_sched_clock(&cd, cyc, (u32)~0); + return OSCR; } @@ -119,7 +110,7 @@ static void __init pxa_timer_init(void) OIER = 0; OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3; - init_sched_clock(&cd, pxa_update_sched_clock, 32, clock_tick_rate); + setup_sched_clock(pxa_read_sched_clock, 32, clock_tick_rate); clockevents_calc_mult_shift(&ckevt_pxa_osmr0, clock_tick_rate, 4); ckevt_pxa_osmr0.max_delta_ns = diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c index fa66024..1ee6d4c 100644 --- a/arch/arm/mach-sa1100/time.c +++ b/arch/arm/mach-sa1100/time.c @@ -12,7 +12,6 @@ #include #include #include -#include /* just for sched_clock() - funny that */ #include #include @@ -20,29 +19,9 @@ #include #include -/* - * This is the SA11x0 sched_clock implementation. - */ -static DEFINE_CLOCK_DATA(cd); - -/* - * Constants generated by clocks_calc_mult_shift(m, s, 3.6864MHz, - * NSEC_PER_SEC, 60). - * This gives a resolution of about 271ns and a wrap period of about 19min. - */ -#define SC_MULT 2275555556u -#define SC_SHIFT 23 - -unsigned long long notrace sched_clock(void) -{ - u32 cyc = OSCR; - return cyc_to_fixed_sched_clock(&cd, cyc, (u32)~0, SC_MULT, SC_SHIFT); -} - -static void notrace sa1100_update_sched_clock(void) +static u32 notrace sa100_read_sched_clock(void) { - u32 cyc = OSCR; - update_sched_clock(&cd, cyc, (u32)~0); + return OSCR; } #define MIN_OSCR_DELTA 2 @@ -109,8 +88,7 @@ static void __init sa1100_timer_init(void) OIER = 0; OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3; - init_fixed_sched_clock(&cd, sa1100_update_sched_clock, 32, - 3686400, SC_MULT, SC_SHIFT); + setup_sched_clock(sa1100_read_sched_clock, 32, 3686400); clockevents_calc_mult_shift(&ckevt_sa1100_osmr0, 3686400, 4); ckevt_sa1100_osmr0.max_delta_ns = diff --git a/arch/arm/mach-tegra/timer.c b/arch/arm/mach-tegra/timer.c index e2272d2..732c724 100644 --- a/arch/arm/mach-tegra/timer.c +++ b/arch/arm/mach-tegra/timer.c @@ -19,7 +19,6 @@ #include #include -#include #include #include #include @@ -106,25 +105,9 @@ static struct clock_event_device tegra_clockevent = { .set_mode = tegra_timer_set_mode, }; -static DEFINE_CLOCK_DATA(cd); - -/* - * Constants generated by clocks_calc_mult_shift(m, s, 1MHz, NSEC_PER_SEC, 60). - * This gives a resolution of about 1us and a wrap period of about 1h11min. - */ -#define SC_MULT 4194304000u -#define SC_SHIFT 22 - -unsigned long long notrace sched_clock(void) -{ - u32 cyc = timer_readl(TIMERUS_CNTR_1US); - return cyc_to_fixed_sched_clock(&cd, cyc, (u32)~0, SC_MULT, SC_SHIFT); -} - -static void notrace tegra_update_sched_clock(void) +static u32 notrace tegra_read_sched_clock(void) { - u32 cyc = timer_readl(TIMERUS_CNTR_1US); - update_sched_clock(&cd, cyc, (u32)~0); + return timer_readl(TIMERUS_CNTR_1US); } /* @@ -218,8 +201,7 @@ static void __init tegra_init_timer(void) WARN(1, "Unknown clock rate"); } - init_fixed_sched_clock(&cd, tegra_update_sched_clock, 32, - 1000000, SC_MULT, SC_SHIFT); + setup_sched_clock(tegra_read_sched_clock, 32, 1000000); if (clocksource_mmio_init(timer_reg_base + TIMERUS_CNTR_1US, "timer_us", 1000000, 300, 32, clocksource_mmio_readl_up)) { diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c index 5f51bde..bc1c789 100644 --- a/arch/arm/mach-u300/timer.c +++ b/arch/arm/mach-u300/timer.c @@ -9,7 +9,6 @@ * Author: Linus Walleij */ #include -#include #include #include #include @@ -337,18 +336,10 @@ static struct irqaction u300_timer_irq = { * this wraps around for now, since it is just a relative time * stamp. (Inspired by OMAP implementation.) */ -static DEFINE_CLOCK_DATA(cd); -unsigned long long notrace sched_clock(void) +static u32 notrace u300_read_sched_clock(void) { - u32 cyc = readl(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace u300_update_sched_clock(void) -{ - u32 cyc = readl(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC); - update_sched_clock(&cd, cyc, (u32)~0); + return readl(U300_TIMER_APP_VBASE + U300_TIMER_APP_GPT2CC); } @@ -366,7 +357,7 @@ static void __init u300_timer_init(void) clk_enable(clk); rate = clk_get_rate(clk); - init_sched_clock(&cd, u300_update_sched_clock, 32, rate); + setup_sched_clock(u300_read_sched_clock, 32, rate); /* * Disable the "OS" and "DD" timers - these are designed for Symbian! diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c index 568dd02..cbfbbe4 100644 --- a/arch/arm/plat-iop/time.c +++ b/arch/arm/plat-iop/time.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -52,21 +51,12 @@ static struct clocksource iop_clocksource = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static DEFINE_CLOCK_DATA(cd); - /* * IOP sched_clock() implementation via its clocksource. */ -unsigned long long notrace sched_clock(void) +static u32 notrace iop_read_sched_clock(void) { - u32 cyc = 0xffffffffu - read_tcr1(); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace iop_update_sched_clock(void) -{ - u32 cyc = 0xffffffffu - read_tcr1(); - update_sched_clock(&cd, cyc, (u32)~0); + return 0xffffffffu - read_tcr1(); } /* @@ -152,7 +142,7 @@ void __init iop_init_time(unsigned long tick_rate) { u32 timer_ctl; - init_sched_clock(&cd, iop_update_sched_clock, 32, tick_rate); + setup_sched_clock(iop_read_sched_clock, 32, tick_rate); ticks_per_jiffy = DIV_ROUND_CLOSEST(tick_rate, HZ); iop_tick_rate = tick_rate; diff --git a/arch/arm/plat-mxc/time.c b/arch/arm/plat-mxc/time.c index 4b0fe28..1c96cdb 100644 --- a/arch/arm/plat-mxc/time.c +++ b/arch/arm/plat-mxc/time.c @@ -108,18 +108,9 @@ static void gpt_irq_acknowledge(void) static void __iomem *sched_clock_reg; -static DEFINE_CLOCK_DATA(cd); -unsigned long long notrace sched_clock(void) +static u32 notrace mxc_read_sched_clock(void) { - cycle_t cyc = sched_clock_reg ? __raw_readl(sched_clock_reg) : 0; - - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace mxc_update_sched_clock(void) -{ - cycle_t cyc = sched_clock_reg ? __raw_readl(sched_clock_reg) : 0; - update_sched_clock(&cd, cyc, (u32)~0); + return sched_clock_reg ? __raw_readl(sched_clock_reg) : 0; } static int __init mxc_clocksource_init(struct clk *timer_clk) @@ -129,7 +120,7 @@ static int __init mxc_clocksource_init(struct clk *timer_clk) sched_clock_reg = reg; - init_sched_clock(&cd, mxc_update_sched_clock, 32, c); + setup_sched_clock(mxc_read_sched_clock, 32, c); return clocksource_mmio_init(reg, "mxc_timer1", c, 200, 32, clocksource_mmio_readl_up); } diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c index 30b6433..ad1b45b 100644 --- a/arch/arm/plat-nomadik/timer.c +++ b/arch/arm/plat-nomadik/timer.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include @@ -79,23 +78,12 @@ void __iomem *mtu_base; /* Assigned by machine code */ * local implementation which uses the clocksource to get some * better resolution when scheduling the kernel. */ -static DEFINE_CLOCK_DATA(cd); - -unsigned long long notrace sched_clock(void) +static u32 notrace nomadik_read_sched_clock(void) { - u32 cyc; - if (unlikely(!mtu_base)) return 0; - cyc = -readl(mtu_base + MTU_VAL(0)); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - -static void notrace nomadik_update_sched_clock(void) -{ - u32 cyc = -readl(mtu_base + MTU_VAL(0)); - update_sched_clock(&cd, cyc, (u32)~0); + return -readl(mtu_base + MTU_VAL(0)); } #endif @@ -231,9 +219,11 @@ void __init nmdk_timer_init(void) rate, 200, 32, clocksource_mmio_readl_down)) pr_err("timer: failed to initialize clock source %s\n", "mtu_0"); + #ifdef CONFIG_NOMADIK_MTU_SCHED_CLOCK - init_sched_clock(&cd, nomadik_update_sched_clock, 32, rate); + setup_sched_clock(nomadik_read_sched_clock, 32, rate); #endif + /* Timer 1 is used for events */ clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE); diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c index a6cbb71..5f0f229 100644 --- a/arch/arm/plat-omap/counter_32k.c +++ b/arch/arm/plat-omap/counter_32k.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include @@ -37,41 +36,9 @@ static void __iomem *timer_32k_base; #define OMAP16XX_TIMER_32K_SYNCHRONIZED 0xfffbc410 -/* - * Returns current time from boot in nsecs. It's OK for this to wrap - * around for now, as it's just a relative time stamp. - */ -static DEFINE_CLOCK_DATA(cd); - -/* - * Constants generated by clocks_calc_mult_shift(m, s, 32768, NSEC_PER_SEC, 60). - * This gives a resolution of about 30us and a wrap period of about 36hrs. - */ -#define SC_MULT 4000000000u -#define SC_SHIFT 17 - -static inline unsigned long long notrace _omap_32k_sched_clock(void) -{ - u32 cyc = timer_32k_base ? __raw_readl(timer_32k_base) : 0; - return cyc_to_fixed_sched_clock(&cd, cyc, (u32)~0, SC_MULT, SC_SHIFT); -} - -#if defined(CONFIG_OMAP_32K_TIMER) && !defined(CONFIG_OMAP_MPU_TIMER) -unsigned long long notrace sched_clock(void) -{ - return _omap_32k_sched_clock(); -} -#else -unsigned long long notrace omap_32k_sched_clock(void) -{ - return _omap_32k_sched_clock(); -} -#endif - -static void notrace omap_update_sched_clock(void) +static u32 notrace omap_32k_read_sched_clock(void) { - u32 cyc = timer_32k_base ? __raw_readl(timer_32k_base) : 0; - update_sched_clock(&cd, cyc, (u32)~0); + return timer_32k_base ? __raw_readl(timer_32k_base) : 0; } /** @@ -147,8 +114,7 @@ int __init omap_init_clocksource_32k(void) clocksource_mmio_readl_up)) printk(err, "32k_counter"); - init_fixed_sched_clock(&cd, omap_update_sched_clock, 32, - 32768, SC_MULT, SC_SHIFT); + setup_sched_clock(omap_32k_read_sched_clock, 32, 32768); } return 0; } diff --git a/arch/arm/plat-omap/include/plat/common.h b/arch/arm/plat-omap/include/plat/common.h index 257f977..b4d7ec3 100644 --- a/arch/arm/plat-omap/include/plat/common.h +++ b/arch/arm/plat-omap/include/plat/common.h @@ -31,7 +31,6 @@ #include extern int __init omap_init_clocksource_32k(void); -extern unsigned long long notrace omap_32k_sched_clock(void); extern void omap_reserve(void); extern int omap_dss_reset(struct omap_hwmod *); diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c index 69a6136..1ed8d13 100644 --- a/arch/arm/plat-orion/time.c +++ b/arch/arm/plat-orion/time.c @@ -12,7 +12,6 @@ */ #include -#include #include #include #include @@ -60,24 +59,10 @@ static u32 ticks_per_jiffy; * Orion's sched_clock implementation. It has a resolution of * at least 7.5ns (133MHz TCLK). */ -static DEFINE_CLOCK_DATA(cd); -unsigned long long notrace sched_clock(void) +static u32 notrace orion_read_sched_clock(void) { - u32 cyc = ~readl(timer_base + TIMER0_VAL_OFF); - return cyc_to_sched_clock(&cd, cyc, (u32)~0); -} - - -static void notrace orion_update_sched_clock(void) -{ - u32 cyc = ~readl(timer_base + TIMER0_VAL_OFF); - update_sched_clock(&cd, cyc, (u32)~0); -} - -static void __init setup_sched_clock(unsigned long tclk) -{ - init_sched_clock(&cd, orion_update_sched_clock, 32, tclk); + return ~readl(timer_base + TIMER0_VAL_OFF); } /* @@ -217,7 +202,7 @@ orion_time_init(u32 _bridge_base, u32 _bridge_timer1_clr_mask, /* * Set scale and timer for sched_clock. */ - setup_sched_clock(tclk); + setup_sched_clock(orion_read_sched_clock, 32, tclk); /* * Setup free-running clocksource timer (interrupts diff --git a/arch/arm/plat-s5p/s5p-time.c b/arch/arm/plat-s5p/s5p-time.c index c833e7b..566341b 100644 --- a/arch/arm/plat-s5p/s5p-time.c +++ b/arch/arm/plat-s5p/s5p-time.c @@ -10,7 +10,6 @@ * published by the Free Software Foundation. */ -#include #include #include #include @@ -321,26 +320,14 @@ static void __iomem *s5p_timer_reg(void) * this wraps around for now, since it is just a relative time * stamp. (Inspired by U300 implementation.) */ -static DEFINE_CLOCK_DATA(cd); - -unsigned long long notrace sched_clock(void) -{ - void __iomem *reg = s5p_timer_reg(); - - if (!reg) - return 0; - - return cyc_to_sched_clock(&cd, ~__raw_readl(reg), (u32)~0); -} - -static void notrace s5p_update_sched_clock(void) +static u32 notrace s5p_read_sched_clock(void) { void __iomem *reg = s5p_timer_reg(); if (!reg) return; - update_sched_clock(&cd, ~__raw_readl(reg), (u32)~0); + return ~__raw_readl(reg); } static void __init s5p_clocksource_init(void) @@ -358,7 +345,7 @@ static void __init s5p_clocksource_init(void) s5p_time_setup(timer_source.source_id, TCNT_MAX); s5p_time_start(timer_source.source_id, PERIODIC); - init_sched_clock(&cd, s5p_update_sched_clock, 32, clock_rate); + setup_sched_clock(s5p_read_sched_clock, 32, clock_rate); if (clocksource_mmio_init(s5p_timer_reg(), "s5p_clocksource_timer", clock_rate, 250, 32, clocksource_mmio_readl_down)) diff --git a/arch/arm/plat-versatile/sched-clock.c b/arch/arm/plat-versatile/sched-clock.c index 3d6a4c2..b33b74c 100644 --- a/arch/arm/plat-versatile/sched-clock.c +++ b/arch/arm/plat-versatile/sched-clock.c @@ -18,41 +18,24 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include #include -#include #include #include -static DEFINE_CLOCK_DATA(cd); static void __iomem *ctr; -/* - * Constants generated by clocks_calc_mult_shift(m, s, 24MHz, NSEC_PER_SEC, 60). - * This gives a resolution of about 41ns and a wrap period of about 178s. - */ -#define SC_MULT 2796202667u -#define SC_SHIFT 26 - -unsigned long long notrace sched_clock(void) +static u32 notrace versatile_read_sched_clock(void) { - if (ctr) { - u32 cyc = readl(ctr); - return cyc_to_fixed_sched_clock(&cd, cyc, (u32)~0, - SC_MULT, SC_SHIFT); - } else - return 0; -} + if (ctr) + return readl(ctr); -static void notrace versatile_update_sched_clock(void) -{ - u32 cyc = readl(ctr); - update_sched_clock(&cd, cyc, (u32)~0); + return 0; } void __init versatile_sched_clock_init(void __iomem *reg, unsigned long rate) { ctr = reg; - init_fixed_sched_clock(&cd, versatile_update_sched_clock, - 32, rate, SC_MULT, SC_SHIFT); + setup_sched_clock(versatile_read_sched_clock, 32, rate); }