Commit 0e285e90 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'pm-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "This time the majority of changes go to the cpufreq subsystem (and to
  the intel_pstate driver in particular) and there are some updates in
  the generic power domains framework, cpuidle, tools and a couple of
  other places.

  One thing worth mentioning is that the intel_pstate's sysfs interface
  has been reworked to be more consistent with the general expectations
  of the cpufreq core and less confusing, hopefully for the better.
  Also, we have a new cpufreq driver for Tegra186 and new hardware
  support in intel_pstata and the Mediatek cpufreq driver.

  Apart from that, the AnalyzeSuspend utility for system suspend
  profiling gets a companion called AnalyzeBoot for the analogous
  profiling of system boot and they both go into one place under
  tools/power/pm-graph/.

  The rest is mostly fixes, cleanups and code reorganization.

  Specifics:

   - Rework the intel_pstate driver's sysfs interface to make it more
     straightforward and more intuitive (Rafael Wysocki).

   - Make intel_pstate support all processors which advertise HWP
     (hardware-managed P-states) to the kernel in all operation modes
     and make it use the load-based P-state selection algorithm on a
     wider range of systems in the active mode (Rafael Wysocki).

   - Add cpufreq driver for Tegra186 (Mikko Perttunen).

   - Add support for Gemini Lake SoCs to intel_pstate (David Box).

   - Add support for MT8176 and MT817x to the Mediatek cpufreq driver
     and clean up that driver a bit (Daniel Kurtz).

   - Clean up intel_pstate and optimize it slightly (Rafael Wysocki).

   - Update the schedutil cpufreq governor, mostly to fix a couple of
     issues with it related to specific workloads, and rework its sysfs
     tunable and initialization a bit (Rafael Wysocki, Viresh Kumar).

   - Fix minor issues in the imx6q, dbx500 and qoriq cpufreq drivers
     (Christophe Jaillet, Irina Tirdea, Leonard Crestez, Viresh Kumar,
     YuanTian Tang).

   - Add file patterns for cpufreq DT bindings to MAINTAINERS (Geert
     Uytterhoeven).

   - Add support for "always on" power domains to the genpd (generic
     power domains) framework and clean up that code somewhat (Ulf
     Hansson, Lina Iyer, Viresh Kumar).

   - Fix minor issues in the powernv cpuidle driver and clean it up
     (Anton Blanchard, Gautham Shenoy).

   - Move the AnalyzeSuspend utility under tools/power/pm-graph/ and add
     an analogous boot-profiling utility called AnalyzeBoot to it (Todd
     Brandt).

   - Add rk3328 support to the rockchip-io AVS (Adaptive Voltage
     Scaling) driver (David Wu).

   - Fix minor issues in the cpuidle core, the intel_pstate_tracer
     utility, the devfreq framework and the PM core documentation
     (Chanwoo Choi, Doug Smythies, Johan Hovold, Marcin Nowakowski)"

* tag 'pm-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (56 commits)
  PM / runtime: Document autosuspend-helper side effects
  PM / runtime: Fix autosuspend documentation
  tools: power: pm-graph: Package makefile and man pages
  tools: power: pm-graph: AnalyzeBoot v2.0
  tools: power: pm-graph: AnalyzeSuspend v4.6
  cpufreq: Add Tegra186 cpufreq driver
  cpufreq: imx6q: Fix error handling code
  cpufreq: imx6q: Set max suspend_freq to avoid changes during suspend
  cpufreq: imx6q: Fix handling EPROBE_DEFER from regulator
  cpuidle: powernv: Avoid a branch in the core snooze_loop() loop
  cpuidle: powernv: Don't continually set thread priority in snooze_loop()
  cpuidle: powernv: Don't bounce between low and very low thread priority
  cpuidle: cpuidle-cps: remove unused variable
  tools/power/x86/intel_pstate_tracer: Adjust directory ownership
  cpufreq: schedutil: Use policy-dependent transition delays
  cpufreq: schedutil: Reduce frequencies slower
  PM / devfreq: Move struct devfreq_governor to devfreq directory
  PM / Domains: Ignore domain-idle-states that are not compatible
  cpufreq: intel_pstate: Add support for Gemini Lake
  powernv-cpuidle: Validate DT property array size
  ...
parents 9410091d a1d2fcfd
...@@ -31,7 +31,9 @@ Optional properties: ...@@ -31,7 +31,9 @@ Optional properties:
- domain-idle-states : A phandle of an idle-state that shall be soaked into a - domain-idle-states : A phandle of an idle-state that shall be soaked into a
generic domain power state. The idle state definitions are generic domain power state. The idle state definitions are
compatible with domain-idle-state specified in [1]. compatible with domain-idle-state specified in [1]. phandles
that are not compatible with domain-idle-state will be
ignored.
The domain-idle-state property reflects the idle state of this PM domain and The domain-idle-state property reflects the idle state of this PM domain and
not the idle states of the devices or sub-domains in the PM domain. Devices not the idle states of the devices or sub-domains in the PM domain. Devices
and sub-domains have their own idle-states independent of the parent and sub-domains have their own idle-states independent of the parent
......
...@@ -33,6 +33,7 @@ Required properties: ...@@ -33,6 +33,7 @@ Required properties:
- compatible: should be one of: - compatible: should be one of:
- "rockchip,rk3188-io-voltage-domain" for rk3188 - "rockchip,rk3188-io-voltage-domain" for rk3188
- "rockchip,rk3288-io-voltage-domain" for rk3288 - "rockchip,rk3288-io-voltage-domain" for rk3288
- "rockchip,rk3328-io-voltage-domain" for rk3328
- "rockchip,rk3368-io-voltage-domain" for rk3368 - "rockchip,rk3368-io-voltage-domain" for rk3368
- "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains - "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains
- "rockchip,rk3399-io-voltage-domain" for rk3399 - "rockchip,rk3399-io-voltage-domain" for rk3399
......
...@@ -478,15 +478,23 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: ...@@ -478,15 +478,23 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
- set the power.last_busy field to the current time - set the power.last_busy field to the current time
void pm_runtime_use_autosuspend(struct device *dev); void pm_runtime_use_autosuspend(struct device *dev);
- set the power.use_autosuspend flag, enabling autosuspend delays - set the power.use_autosuspend flag, enabling autosuspend delays; call
pm_runtime_get_sync if the flag was previously cleared and
power.autosuspend_delay is negative
void pm_runtime_dont_use_autosuspend(struct device *dev); void pm_runtime_dont_use_autosuspend(struct device *dev);
- clear the power.use_autosuspend flag, disabling autosuspend delays - clear the power.use_autosuspend flag, disabling autosuspend delays;
decrement the device's usage counter if the flag was previously set and
power.autosuspend_delay is negative; call pm_runtime_idle
void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
- set the power.autosuspend_delay value to 'delay' (expressed in - set the power.autosuspend_delay value to 'delay' (expressed in
milliseconds); if 'delay' is negative then runtime suspends are milliseconds); if 'delay' is negative then runtime suspends are
prevented prevented; if power.use_autosuspend is set, pm_runtime_get_sync may be
called or the device's usage counter may be decremented and
pm_runtime_idle called depending on if power.autosuspend_delay is
changed to or from a negative value; if power.use_autosuspend is clear,
pm_runtime_idle is called
unsigned long pm_runtime_autosuspend_expiration(struct device *dev); unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
- calculate the time when the current autosuspend delay period will expire, - calculate the time when the current autosuspend delay period will expire,
...@@ -836,9 +844,8 @@ of the non-autosuspend counterparts: ...@@ -836,9 +844,8 @@ of the non-autosuspend counterparts:
Instead of: pm_runtime_put_sync use: pm_runtime_put_sync_autosuspend. Instead of: pm_runtime_put_sync use: pm_runtime_put_sync_autosuspend.
Drivers may also continue to use the non-autosuspend helper functions; they Drivers may also continue to use the non-autosuspend helper functions; they
will behave normally, not taking the autosuspend delay into account. will behave normally, which means sometimes taking the autosuspend delay into
Similarly, if the power.use_autosuspend field isn't set then the autosuspend account (see pm_runtime_idle).
helper functions will behave just like the non-autosuspend counterparts.
Under some circumstances a driver or subsystem may want to prevent a device Under some circumstances a driver or subsystem may want to prevent a device
from autosuspending immediately, even though the usage counter is zero and the from autosuspending immediately, even though the usage counter is zero and the
......
...@@ -3471,6 +3471,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git ...@@ -3471,6 +3471,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates) T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates)
B: https://bugzilla.kernel.org B: https://bugzilla.kernel.org
F: Documentation/cpu-freq/ F: Documentation/cpu-freq/
F: Documentation/devicetree/bindings/cpufreq/
F: drivers/cpufreq/ F: drivers/cpufreq/
F: include/linux/cpufreq.h F: include/linux/cpufreq.h
F: tools/testing/selftests/cpufreq/ F: tools/testing/selftests/cpufreq/
......
...@@ -1189,11 +1189,6 @@ external-bus@50000000 { ...@@ -1189,11 +1189,6 @@ external-bus@50000000 {
status = "disabled"; status = "disabled";
}; };
cpufreq-cooling {
compatible = "stericsson,db8500-cpufreq-cooling";
status = "disabled";
};
mcde@a0350000 { mcde@a0350000 {
compatible = "stericsson,mcde"; compatible = "stericsson,mcde";
reg = <0xa0350000 0x1000>, /* MCDE */ reg = <0xa0350000 0x1000>, /* MCDE */
......
...@@ -121,7 +121,9 @@ static const struct genpd_lock_ops genpd_spin_ops = { ...@@ -121,7 +121,9 @@ static const struct genpd_lock_ops genpd_spin_ops = {
#define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) #define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p)
#define genpd_unlock(p) p->lock_ops->unlock(p) #define genpd_unlock(p) p->lock_ops->unlock(p)
#define genpd_status_on(genpd) (genpd->status == GPD_STATE_ACTIVE)
#define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) #define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE)
#define genpd_is_always_on(genpd) (genpd->flags & GENPD_FLAG_ALWAYS_ON)
static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
struct generic_pm_domain *genpd) struct generic_pm_domain *genpd)
...@@ -130,8 +132,12 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, ...@@ -130,8 +132,12 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
/* Warn once if IRQ safe dev in no sleep domain */ /*
if (ret) * Warn once if an IRQ safe device is attached to a no sleep domain, as
* to indicate a suboptimal configuration for PM. For an always on
* domain this isn't case, thus don't warn.
*/
if (ret && !genpd_is_always_on(genpd))
dev_warn_once(dev, "PM domain %s will not be powered off\n", dev_warn_once(dev, "PM domain %s will not be powered off\n",
genpd->name); genpd->name);
...@@ -296,11 +302,15 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, ...@@ -296,11 +302,15 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
* (1) The domain is already in the "power off" state. * (1) The domain is already in the "power off" state.
* (2) System suspend is in progress. * (2) System suspend is in progress.
*/ */
if (genpd->status == GPD_STATE_POWER_OFF if (!genpd_status_on(genpd) || genpd->prepared_count > 0)
|| genpd->prepared_count > 0)
return 0; return 0;
if (atomic_read(&genpd->sd_count) > 0) /*
* Abort power off for the PM domain in the following situations:
* (1) The domain is configured as always on.
* (2) When the domain has a subdomain being powered on.
*/
if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0)
return -EBUSY; return -EBUSY;
list_for_each_entry(pdd, &genpd->dev_list, list_node) { list_for_each_entry(pdd, &genpd->dev_list, list_node) {
...@@ -373,7 +383,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth) ...@@ -373,7 +383,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
struct gpd_link *link; struct gpd_link *link;
int ret = 0; int ret = 0;
if (genpd->status == GPD_STATE_ACTIVE) if (genpd_status_on(genpd))
return 0; return 0;
/* /*
...@@ -752,7 +762,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, ...@@ -752,7 +762,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
{ {
struct gpd_link *link; struct gpd_link *link;
if (genpd->status == GPD_STATE_POWER_OFF) if (!genpd_status_on(genpd) || genpd_is_always_on(genpd))
return; return;
if (genpd->suspended_count != genpd->device_count if (genpd->suspended_count != genpd->device_count
...@@ -761,7 +771,8 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, ...@@ -761,7 +771,8 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
/* Choose the deepest state when suspending */ /* Choose the deepest state when suspending */
genpd->state_idx = genpd->state_count - 1; genpd->state_idx = genpd->state_count - 1;
_genpd_power_off(genpd, false); if (_genpd_power_off(genpd, false))
return;
genpd->status = GPD_STATE_POWER_OFF; genpd->status = GPD_STATE_POWER_OFF;
...@@ -793,7 +804,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock, ...@@ -793,7 +804,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
{ {
struct gpd_link *link; struct gpd_link *link;
if (genpd->status == GPD_STATE_ACTIVE) if (genpd_status_on(genpd))
return; return;
list_for_each_entry(link, &genpd->slave_links, slave_node) { list_for_each_entry(link, &genpd->slave_links, slave_node) {
...@@ -1329,8 +1340,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, ...@@ -1329,8 +1340,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
genpd_lock(subdomain); genpd_lock(subdomain);
genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
if (genpd->status == GPD_STATE_POWER_OFF if (!genpd_status_on(genpd) && genpd_status_on(subdomain)) {
&& subdomain->status != GPD_STATE_POWER_OFF) {
ret = -EINVAL; ret = -EINVAL;
goto out; goto out;
} }
...@@ -1346,7 +1356,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, ...@@ -1346,7 +1356,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
list_add_tail(&link->master_node, &genpd->master_links); list_add_tail(&link->master_node, &genpd->master_links);
link->slave = subdomain; link->slave = subdomain;
list_add_tail(&link->slave_node, &subdomain->slave_links); list_add_tail(&link->slave_node, &subdomain->slave_links);
if (subdomain->status != GPD_STATE_POWER_OFF) if (genpd_status_on(subdomain))
genpd_sd_counter_inc(genpd); genpd_sd_counter_inc(genpd);
out: out:
...@@ -1406,7 +1416,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, ...@@ -1406,7 +1416,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
list_del(&link->master_node); list_del(&link->master_node);
list_del(&link->slave_node); list_del(&link->slave_node);
kfree(link); kfree(link);
if (subdomain->status != GPD_STATE_POWER_OFF) if (genpd_status_on(subdomain))
genpd_sd_counter_dec(genpd); genpd_sd_counter_dec(genpd);
ret = 0; ret = 0;
...@@ -1492,6 +1502,10 @@ int pm_genpd_init(struct generic_pm_domain *genpd, ...@@ -1492,6 +1502,10 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
genpd->dev_ops.start = pm_clk_resume; genpd->dev_ops.start = pm_clk_resume;
} }
/* Always-on domains must be powered on at initialization. */
if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
return -EINVAL;
/* Use only one "off" state if there were no states declared */ /* Use only one "off" state if there were no states declared */
if (genpd->state_count == 0) { if (genpd->state_count == 0) {
ret = genpd_set_default_power_state(genpd); ret = genpd_set_default_power_state(genpd);
...@@ -1700,13 +1714,13 @@ int of_genpd_add_provider_simple(struct device_node *np, ...@@ -1700,13 +1714,13 @@ int of_genpd_add_provider_simple(struct device_node *np,
mutex_lock(&gpd_list_lock); mutex_lock(&gpd_list_lock);
if (pm_genpd_present(genpd)) if (pm_genpd_present(genpd)) {
ret = genpd_add_provider(np, genpd_xlate_simple, genpd); ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
if (!ret) { if (!ret) {
genpd->provider = &np->fwnode; genpd->provider = &np->fwnode;
genpd->has_provider = true; genpd->has_provider = true;
} }
}
mutex_unlock(&gpd_list_lock); mutex_unlock(&gpd_list_lock);
...@@ -2079,11 +2093,6 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, ...@@ -2079,11 +2093,6 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state,
int err; int err;
u32 residency; u32 residency;
u32 entry_latency, exit_latency; u32 entry_latency, exit_latency;
const struct of_device_id *match_id;
match_id = of_match_node(idle_state_match, state_node);
if (!match_id)
return -EINVAL;
err = of_property_read_u32(state_node, "entry-latency-us", err = of_property_read_u32(state_node, "entry-latency-us",
&entry_latency); &entry_latency);
...@@ -2132,6 +2141,7 @@ int of_genpd_parse_idle_states(struct device_node *dn, ...@@ -2132,6 +2141,7 @@ int of_genpd_parse_idle_states(struct device_node *dn,
int err, ret; int err, ret;
int count; int count;
struct of_phandle_iterator it; struct of_phandle_iterator it;
const struct of_device_id *match_id;
count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
if (count <= 0) if (count <= 0)
...@@ -2144,6 +2154,9 @@ int of_genpd_parse_idle_states(struct device_node *dn, ...@@ -2144,6 +2154,9 @@ int of_genpd_parse_idle_states(struct device_node *dn,
/* Loop over the phandles until all the requested entry is found */ /* Loop over the phandles until all the requested entry is found */
of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
np = it.node; np = it.node;
match_id = of_match_node(idle_state_match, np);
if (!match_id)
continue;
ret = genpd_parse_state(&st[i++], np); ret = genpd_parse_state(&st[i++], np);
if (ret) { if (ret) {
pr_err pr_err
...@@ -2155,7 +2168,10 @@ int of_genpd_parse_idle_states(struct device_node *dn, ...@@ -2155,7 +2168,10 @@ int of_genpd_parse_idle_states(struct device_node *dn,
} }
} }
*n = count; *n = i;
if (!i)
kfree(st);
else
*states = st; *states = st;
return 0; return 0;
...@@ -2221,7 +2237,7 @@ static int pm_genpd_summary_one(struct seq_file *s, ...@@ -2221,7 +2237,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup))) if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
goto exit; goto exit;
if (genpd->status == GPD_STATE_POWER_OFF) if (!genpd_status_on(genpd))
snprintf(state, sizeof(state), "%s-%u", snprintf(state, sizeof(state), "%s-%u",
status_lookup[genpd->status], genpd->state_idx); status_lookup[genpd->status], genpd->state_idx);
else else
......
...@@ -247,6 +247,12 @@ config ARM_TEGRA124_CPUFREQ ...@@ -247,6 +247,12 @@ config ARM_TEGRA124_CPUFREQ
help help
This adds the CPUFreq driver support for Tegra124 SOCs. This adds the CPUFreq driver support for Tegra124 SOCs.
config ARM_TEGRA186_CPUFREQ
tristate "Tegra186 CPUFreq support"
depends on ARCH_TEGRA && TEGRA_BPMP
help
This adds the CPUFreq driver support for Tegra186 SOCs.
config ARM_TI_CPUFREQ config ARM_TI_CPUFREQ
bool "Texas Instruments CPUFreq support" bool "Texas Instruments CPUFreq support"
depends on ARCH_OMAP2PLUS depends on ARCH_OMAP2PLUS
......
...@@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ) += spear-cpufreq.o ...@@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ) += spear-cpufreq.o
obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o
obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o
obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o
obj-$(CONFIG_ARM_TEGRA186_CPUFREQ) += tegra186-cpufreq.o
obj-$(CONFIG_ARM_TI_CPUFREQ) += ti-cpufreq.o obj-$(CONFIG_ARM_TI_CPUFREQ) += ti-cpufreq.o
obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o
obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
......
...@@ -11,6 +11,7 @@ ...@@ -11,6 +11,7 @@
#include <linux/module.h> #include <linux/module.h>
#include <linux/kernel.h> #include <linux/kernel.h>
#include <linux/cpufreq.h> #include <linux/cpufreq.h>
#include <linux/cpu_cooling.h>
#include <linux/delay.h> #include <linux/delay.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/platform_device.h> #include <linux/platform_device.h>
...@@ -18,6 +19,7 @@ ...@@ -18,6 +19,7 @@
static struct cpufreq_frequency_table *freq_table; static struct cpufreq_frequency_table *freq_table;
static struct clk *armss_clk; static struct clk *armss_clk;
static struct thermal_cooling_device *cdev;
static int dbx500_cpufreq_target(struct cpufreq_policy *policy, static int dbx500_cpufreq_target(struct cpufreq_policy *policy,
unsigned int index) unsigned int index)
...@@ -32,6 +34,22 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy) ...@@ -32,6 +34,22 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy)
return cpufreq_generic_init(policy, freq_table, 20 * 1000); return cpufreq_generic_init(policy, freq_table, 20 * 1000);
} }
static int dbx500_cpufreq_exit(struct cpufreq_policy *policy)
{
if (!IS_ERR(cdev))
cpufreq_cooling_unregister(cdev);
return 0;
}
static void dbx500_cpufreq_ready(struct cpufreq_policy *policy)
{
cdev = cpufreq_cooling_register(policy->cpus);
if (IS_ERR(cdev))
pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev));
else
pr_info("Cooling device registered: %s\n", cdev->type);
}
static struct cpufreq_driver dbx500_cpufreq_driver = { static struct cpufreq_driver dbx500_cpufreq_driver = {
.flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS | .flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS |
CPUFREQ_NEED_INITIAL_FREQ_CHECK, CPUFREQ_NEED_INITIAL_FREQ_CHECK,
...@@ -39,6 +57,8 @@ static struct cpufreq_driver dbx500_cpufreq_driver = { ...@@ -39,6 +57,8 @@ static struct cpufreq_driver dbx500_cpufreq_driver = {
.target_index = dbx500_cpufreq_target, .target_index = dbx500_cpufreq_target,
.get = cpufreq_generic_get, .get = cpufreq_generic_get,
.init = dbx500_cpufreq_init, .init = dbx500_cpufreq_init,
.exit = dbx500_cpufreq_exit,
.ready = dbx500_cpufreq_ready,
.name = "DBX500", .name = "DBX500",
.attr = cpufreq_generic_attr, .attr = cpufreq_generic_attr,
}; };
......
...@@ -161,8 +161,13 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) ...@@ -161,8 +161,13 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
static int imx6q_cpufreq_init(struct cpufreq_policy *policy) static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
{ {
int ret;
policy->clk = arm_clk; policy->clk = arm_clk;
return cpufreq_generic_init(policy, freq_table, transition_latency); ret = cpufreq_generic_init(policy, freq_table, transition_latency);
policy->suspend_freq = policy->max;
return ret;
} }
static struct cpufreq_driver imx6q_cpufreq_driver = { static struct cpufreq_driver imx6q_cpufreq_driver = {
...@@ -173,6 +178,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = { ...@@ -173,6 +178,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
.init = imx6q_cpufreq_init, .init = imx6q_cpufreq_init,
.name = "imx6q-cpufreq", .name = "imx6q-cpufreq",
.attr = cpufreq_generic_attr, .attr = cpufreq_generic_attr,
.suspend = cpufreq_generic_suspend,
}; };
static int imx6q_cpufreq_probe(struct platform_device *pdev) static int imx6q_cpufreq_probe(struct platform_device *pdev)
...@@ -222,6 +228,13 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) ...@@ -222,6 +228,13 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
arm_reg = regulator_get(cpu_dev, "arm"); arm_reg = regulator_get(cpu_dev, "arm");
pu_reg = regulator_get_optional(cpu_dev, "pu"); pu_reg = regulator_get_optional(cpu_dev, "pu");
soc_reg = regulator_get(cpu_dev, "soc"); soc_reg = regulator_get(cpu_dev, "soc");
if (PTR_ERR(arm_reg) == -EPROBE_DEFER ||
PTR_ERR(soc_reg) == -EPROBE_DEFER ||
PTR_ERR(pu_reg) == -EPROBE_DEFER) {
ret = -EPROBE_DEFER;
dev_dbg(cpu_dev, "regulators not ready, defer\n");
goto put_reg;
}
if (IS_ERR(arm_reg) || IS_ERR(soc_reg)) { if (IS_ERR(arm_reg) || IS_ERR(soc_reg)) {
dev_err(cpu_dev, "failed to get regulators\n"); dev_err(cpu_dev, "failed to get regulators\n");
ret = -ENOENT; ret = -ENOENT;
...@@ -255,7 +268,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) ...@@ -255,7 +268,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
if (ret) { if (ret) {
dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
goto put_reg; goto out_free_opp;
} }
/* Make imx6_soc_volt array's size same as arm opp number */ /* Make imx6_soc_volt array's size same as arm opp number */
......
...@@ -37,7 +37,11 @@ ...@@ -37,7 +37,11 @@
#include <asm/cpufeature.h> #include <asm/cpufeature.h>
#include <asm/intel-family.h> #include <asm/intel-family.h>
#define INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL (10 * NSEC_PER_MSEC)
#define INTEL_PSTATE_HWP_SAMPLING_INTERVAL (50 * NSEC_PER_MSEC)
#define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 #define INTEL_CPUFREQ_TRANSITION_LATENCY 20000
#define INTEL_CPUFREQ_TRANSITION_DELAY 500
#ifdef CONFIG_ACPI #ifdef CONFIG_ACPI
#include <acpi/processor.h> #include <acpi/processor.h>
...@@ -74,6 +78,11 @@ static inline int ceiling_fp(int32_t x) ...@@ -74,6 +78,11 @@ static inline int ceiling_fp(int32_t x)
return ret; return ret;
} }
static inline int32_t percent_fp(int percent)
{
return div_fp(percent, 100);
}
static inline u64 mul_ext_fp(u64 x, u64 y) static inline u64 mul_ext_fp(u64 x, u64 y)
{ {
return (x * y) >> EXT_FRAC_BITS; return (x * y) >> EXT_FRAC_BITS;
...@@ -186,45 +195,22 @@ struct _pid { ...@@ -186,45 +195,22 @@ struct _pid {
}; };
/** /**
* struct perf_limits - Store user and policy limits * struct global_params - Global parameters, mostly tunable via sysfs.
* @no_turbo: User requested turbo state from intel_pstate sysfs * @no_turbo: Whether or not to use turbo P-states.
* @turbo_disabled: Platform turbo status either from msr * @turbo_disabled: Whethet or not turbo P-states are available at all,
* MSR_IA32_MISC_ENABLE or when maximum available pstate * based on the MSR_IA32_MISC_ENABLE value and whether or
* matches the maximum turbo pstate * not the maximum reported turbo P-state is different from
* @max_perf_pct: Effective maximum performance limit in percentage, this * the maximum reported non-turbo one.
* is minimum of either limits enforced by cpufreq policy * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo
* or limits from user set limits via intel_pstate sysfs * P-state capacity.
* @min_perf_pct: Effective minimum performance limit in percentage, this * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo
* is maximum of either limits enforced by cpufreq policy * P-state capacity.
* or limits from user set limits via intel_pstate sysfs
* @max_perf: This is a scaled value between 0 to 255 for max_perf_pct
* This value is used to limit max pstate
* @min_perf: This is a scaled value between 0 to 255 for min_perf_pct
* This value is used to limit min pstate
* @max_policy_pct: The maximum performance in percentage enforced by
* cpufreq setpolicy interface
* @max_sysfs_pct: The maximum performance in percentage enforced by
* intel pstate sysfs interface, unused when per cpu
* controls are enforced
* @min_policy_pct: The minimum performance in percentage enforced by
* cpufreq setpolicy interface
* @min_sysfs_pct: The minimum performance in percentage enforced by
* intel pstate sysfs interface, unused when per cpu
* controls are enforced
*
* Storage for user and policy defined limits.
*/ */
struct perf_limits { struct global_params {
int no_turbo; bool no_turbo;
int turbo_disabled; bool turbo_disabled;
int max_perf_pct; int max_perf_pct;
int min_perf_pct; int min_perf_pct;
int32_t max_perf;
int32_t min_perf;
int max_policy_pct;
int max_sysfs_pct;
int min_policy_pct;
int min_sysfs_pct;
}; };
/** /**
...@@ -245,9 +231,10 @@ struct perf_limits { ...@@ -245,9 +231,10 @@ struct perf_limits {
* @prev_cummulative_iowait: IO Wait time difference from last and * @prev_cummulative_iowait: IO Wait time difference from last and
* current sample * current sample
* @sample: Storage for storing last Sample data * @sample: Storage for storing last Sample data
* @perf_limits: Pointer to perf_limit unique to this CPU * @min_perf: Minimum capacity limit as a fraction of the maximum
* Not all field in the structure are applicable * turbo P-state capacity.
* when per cpu controls are enforced * @max_perf: Maximum capacity limit as a fraction of the maximum
* turbo P-state capacity.
* @acpi_perf_data: Stores ACPI perf information read from _PSS * @acpi_perf_data: Stores ACPI perf information read from _PSS
* @valid_pss_table: Set to true for valid ACPI _PSS entries found * @valid_pss_table: Set to true for valid ACPI _PSS entries found
* @epp_powersave: Last saved HWP energy performance preference * @epp_powersave: Last saved HWP energy performance preference
...@@ -279,7 +266,8 @@ struct cpudata { ...@@ -279,7 +266,8 @@ struct cpudata {
u64 prev_tsc; u64 prev_tsc;
u64 prev_cummulative_iowait; u64 prev_cummulative_iowait;
struct sample sample; struct sample sample;
struct perf_limits *perf_limits; int32_t min_perf;
int32_t max_perf;
#ifdef CONFIG_ACPI #ifdef CONFIG_ACPI
struct acpi_processor_performance acpi_perf_data; struct acpi_processor_performance acpi_perf_data;
bool valid_pss_table; bool valid_pss_table;
...@@ -324,7 +312,7 @@ struct pstate_adjust_policy { ...@@ -324,7 +312,7 @@ struct pstate_adjust_policy {
* @get_scaling: Callback to get frequency scaling factor * @get_scaling: Callback to get frequency scaling factor
* @get_val: Callback to convert P state to actual MSR write value * @get_val: Callback to convert P state to actual MSR write value
* @get_vid: Callback to get VID data for Atom platforms * @get_vid: Callback to get VID data for Atom platforms
* @get_target_pstate: Callback to a function to calculate next P state to use * @update_util: Active mode utilization update callback.
* *
* Core and Atom CPU models have different way to get P State limits. This * Core and Atom CPU models have different way to get P State limits. This
* structure is used to store those callbacks. * structure is used to store those callbacks.
...@@ -337,43 +325,31 @@ struct pstate_funcs { ...@@ -337,43 +325,31 @@ struct pstate_funcs {
int (*get_scaling)(void); int (*get_scaling)(void);
u64 (*get_val)(struct cpudata*, int pstate); u64 (*get_val)(struct cpudata*, int pstate);
void (*get_vid)(struct cpudata *); void (*get_vid)(struct cpudata *);
int32_t (*get_target_pstate)(struct cpudata *); void (*update_util)(struct update_util_data *data, u64 time,
unsigned int flags);
}; };
/** static struct pstate_funcs pstate_funcs __read_mostly;
* struct cpu_defaults- Per CPU model default config data static struct pstate_adjust_policy pid_params __read_mostly = {
* @pid_policy: PID config data .sample_rate_ms = 10,
* @funcs: Callback function data .sample_rate_ns = 10 * NSEC_PER_MSEC,
*/ .deadband = 0,
struct cpu_defaults { .setpoint = 97,
struct pstate_adjust_policy pid_policy; .p_gain_pct = 20,
struct pstate_funcs funcs; .d_gain_pct = 0,
.i_gain_pct = 0,
}; };
static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
static struct pstate_adjust_policy pid_params __read_mostly;
static struct pstate_funcs pstate_funcs __read_mostly;
static int hwp_active __read_mostly; static int hwp_active __read_mostly;
static bool per_cpu_limits __read_mostly; static bool per_cpu_limits __read_mostly;
static bool driver_registered __read_mostly; static struct cpufreq_driver *intel_pstate_driver __read_mostly;
#ifdef CONFIG_ACPI #ifdef CONFIG_ACPI
static bool acpi_ppc; static bool acpi_ppc;
#endif #endif
static struct perf_limits global; static struct global_params global;
static void intel_pstate_init_limits(struct perf_limits *limits)
{
memset(limits, 0, sizeof(*limits));
limits->max_perf_pct = 100;
limits->max_perf = int_ext_tofp(1);
limits->max_policy_pct = 100;
limits->max_sysfs_pct = 100;
}
static DEFINE_MUTEX(intel_pstate_driver_lock); static DEFINE_MUTEX(intel_pstate_driver_lock);
static DEFINE_MUTEX(intel_pstate_limits_lock); static DEFINE_MUTEX(intel_pstate_limits_lock);
...@@ -530,29 +506,6 @@ static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) ...@@ -530,29 +506,6 @@ static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
} }
#endif #endif
static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
int deadband, int integral) {
pid->setpoint = int_tofp(setpoint);
pid->deadband = int_tofp(deadband);
pid->integral = int_tofp(integral);
pid->last_err = int_tofp(setpoint) - int_tofp(busy);
}
static inline void pid_p_gain_set(struct _pid *pid, int percent)
{
pid->p_gain = div_fp(percent, 100);
}
static inline void pid_i_gain_set(struct _pid *pid, int percent)
{
pid->i_gain = div_fp(percent, 100);
}
static inline void pid_d_gain_set(struct _pid *pid, int percent)
{
pid->d_gain = div_fp(percent, 100);
}
static signed int pid_calc(struct _pid *pid, int32_t busy) static signed int pid_calc(struct _pid *pid, int32_t busy)
{ {
signed int result; signed int result;
...@@ -590,23 +543,17 @@ static signed int pid_calc(struct _pid *pid, int32_t busy) ...@@ -590,23 +543,17 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
return (signed int)fp_toint(result); return (signed int)fp_toint(result);
} }
static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu) static inline void intel_pstate_pid_reset(struct cpudata *cpu)
{ {
pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct); struct _pid *pid = &cpu->pid;
pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);
pid_reset(&cpu->pid, pid_params.setpoint, 100, pid_params.deadband, 0); pid->p_gain = percent_fp(pid_params.p_gain_pct);
} pid->d_gain = percent_fp(pid_params.d_gain_pct);
pid->i_gain = percent_fp(pid_params.i_gain_pct);
static inline void intel_pstate_reset_all_pid(void) pid->setpoint = int_tofp(pid_params.setpoint);
{ pid->last_err = pid->setpoint - int_tofp(100);
unsigned int cpu; pid->deadband = int_tofp(pid_params.deadband);
pid->integral = 0;
for_each_online_cpu(cpu) {
if (all_cpu_data[cpu])
intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
}
} }
static inline void update_turbo_state(void) static inline void update_turbo_state(void)
...@@ -621,6 +568,14 @@ static inline void update_turbo_state(void) ...@@ -621,6 +568,14 @@ static inline void update_turbo_state(void)
cpu->pstate.max_pstate == cpu->pstate.turbo_pstate); cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
} }
static int min_perf_pct_min(void)
{
struct cpudata *cpu = all_cpu_data[0];
return DIV_ROUND_UP(cpu->pstate.min_pstate * 100,
cpu->pstate.turbo_pstate);
}
static s16 intel_pstate_get_epb(struct cpudata *cpu_data) static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
{ {
u64 epb; u64 epb;
...@@ -838,19 +793,13 @@ static struct freq_attr *hwp_cpufreq_attrs[] = { ...@@ -838,19 +793,13 @@ static struct freq_attr *hwp_cpufreq_attrs[] = {
NULL, NULL,
}; };
static void intel_pstate_hwp_set(struct cpufreq_policy *policy) static void intel_pstate_hwp_set(unsigned int cpu)
{ {
int min, hw_min, max, hw_max, cpu;
struct perf_limits *perf_limits = &global;
u64 value, cap;
for_each_cpu(cpu, policy->cpus) {
struct cpudata *cpu_data = all_cpu_data[cpu]; struct cpudata *cpu_data = all_cpu_data[cpu];
int min, hw_min, max, hw_max;
u64 value, cap;
s16 epp; s16 epp;
if (per_cpu_limits)
perf_limits = all_cpu_data[cpu]->perf_limits;
rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
hw_min = HWP_LOWEST_PERF(cap); hw_min = HWP_LOWEST_PERF(cap);
if (global.no_turbo) if (global.no_turbo)
...@@ -858,11 +807,11 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) ...@@ -858,11 +807,11 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
else else
hw_max = HWP_HIGHEST_PERF(cap); hw_max = HWP_HIGHEST_PERF(cap);
max = fp_ext_toint(hw_max * perf_limits->max_perf); max = fp_ext_toint(hw_max * cpu_data->max_perf);
if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
min = max; min = max;
else else
min = fp_ext_toint(hw_max * perf_limits->min_perf); min = fp_ext_toint(hw_max * cpu_data->min_perf);
rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
...@@ -890,7 +839,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) ...@@ -890,7 +839,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
if (epp < 0) if (epp < 0)
goto skip_epp; goto skip_epp;
epp = 0; epp = 0;
} else { } else {
/* skip setting EPP, when saved value is invalid */ /* skip setting EPP, when saved value is invalid */
...@@ -919,15 +867,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy) ...@@ -919,15 +867,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
} }
skip_epp: skip_epp:
wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
}
}
static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
{
if (hwp_active)
intel_pstate_hwp_set(policy);
return 0;
} }
static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
...@@ -944,20 +883,17 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) ...@@ -944,20 +883,17 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
static int intel_pstate_resume(struct cpufreq_policy *policy) static int intel_pstate_resume(struct cpufreq_policy *policy)
{ {
int ret;
if (!hwp_active) if (!hwp_active)
return 0; return 0;
mutex_lock(&intel_pstate_limits_lock); mutex_lock(&intel_pstate_limits_lock);
all_cpu_data[policy->cpu]->epp_policy = 0; all_cpu_data[policy->cpu]->epp_policy = 0;
intel_pstate_hwp_set(policy->cpu);
ret = intel_pstate_hwp_set_policy(policy);
mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_limits_lock);
return ret; return 0;
} }
static void intel_pstate_update_policies(void) static void intel_pstate_update_policies(void)
...@@ -971,9 +907,14 @@ static void intel_pstate_update_policies(void) ...@@ -971,9 +907,14 @@ static void intel_pstate_update_policies(void)
/************************** debugfs begin ************************/ /************************** debugfs begin ************************/
static int pid_param_set(void *data, u64 val) static int pid_param_set(void *data, u64 val)
{ {
unsigned int cpu;
*(u32 *)data = val; *(u32 *)data = val;
pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC; pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
intel_pstate_reset_all_pid(); for_each_possible_cpu(cpu)
if (all_cpu_data[cpu])
intel_pstate_pid_reset(all_cpu_data[cpu]);
return 0; return 0;
} }
...@@ -1084,7 +1025,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj, ...@@ -1084,7 +1025,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
...@@ -1109,7 +1050,7 @@ static ssize_t show_num_pstates(struct kobject *kobj, ...@@ -1109,7 +1050,7 @@ static ssize_t show_num_pstates(struct kobject *kobj,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
...@@ -1129,7 +1070,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, ...@@ -1129,7 +1070,7 @@ static ssize_t show_no_turbo(struct kobject *kobj,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
...@@ -1157,7 +1098,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, ...@@ -1157,7 +1098,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
...@@ -1174,6 +1115,15 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, ...@@ -1174,6 +1115,15 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
global.no_turbo = clamp_t(int, input, 0, 1); global.no_turbo = clamp_t(int, input, 0, 1);
if (global.no_turbo) {
struct cpudata *cpu = all_cpu_data[0];
int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate;
/* Squash the global minimum into the permitted range. */
if (global.min_perf_pct > pct)
global.min_perf_pct = pct;
}
mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_limits_lock);
intel_pstate_update_policies(); intel_pstate_update_policies();
...@@ -1195,18 +1145,14 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, ...@@ -1195,18 +1145,14 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
mutex_lock(&intel_pstate_limits_lock); mutex_lock(&intel_pstate_limits_lock);
global.max_sysfs_pct = clamp_t(int, input, 0 , 100); global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100);
global.max_perf_pct = min(global.max_policy_pct, global.max_sysfs_pct);
global.max_perf_pct = max(global.min_policy_pct, global.max_perf_pct);
global.max_perf_pct = max(global.min_perf_pct, global.max_perf_pct);
global.max_perf = percent_ext_fp(global.max_perf_pct);
mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_limits_lock);
...@@ -1229,18 +1175,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, ...@@ -1229,18 +1175,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
if (!driver_registered) { if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN; return -EAGAIN;
} }
mutex_lock(&intel_pstate_limits_lock); mutex_lock(&intel_pstate_limits_lock);
global.min_sysfs_pct = clamp_t(int, input, 0 , 100); global.min_perf_pct = clamp_t(int, input,
global.min_perf_pct = max(global.min_policy_pct, global.min_sysfs_pct); min_perf_pct_min(), global.max_perf_pct);
global.min_perf_pct = min(global.max_policy_pct, global.min_perf_pct);
global.min_perf_pct = min(global.max_perf_pct, global.min_perf_pct);
global.min_perf = percent_ext_fp(global.min_perf_pct);
mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_limits_lock);
...@@ -1554,132 +1497,10 @@ static int knl_get_turbo_pstate(void) ...@@ -1554,132 +1497,10 @@ static int knl_get_turbo_pstate(void)
return ret; return ret;
} }
static struct cpu_defaults core_params = { static int intel_pstate_get_base_pstate(struct cpudata *cpu)
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
.setpoint = 97,
.p_gain_pct = 20,
.d_gain_pct = 0,
.i_gain_pct = 0,
},
.funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = core_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.get_target_pstate = get_target_pstate_use_performance,
},
};
static const struct cpu_defaults silvermont_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
.setpoint = 60,
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
},
.funcs = {
.get_max = atom_get_max_pstate,
.get_max_physical = atom_get_max_pstate,
.get_min = atom_get_min_pstate,
.get_turbo = atom_get_turbo_pstate,
.get_val = atom_get_val,
.get_scaling = silvermont_get_scaling,
.get_vid = atom_get_vid,
.get_target_pstate = get_target_pstate_use_cpu_load,
},
};
static const struct cpu_defaults airmont_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
.setpoint = 60,
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
},
.funcs = {
.get_max = atom_get_max_pstate,
.get_max_physical = atom_get_max_pstate,
.get_min = atom_get_min_pstate,
.get_turbo = atom_get_turbo_pstate,
.get_val = atom_get_val,
.get_scaling = airmont_get_scaling,
.get_vid = atom_get_vid,
.get_target_pstate = get_target_pstate_use_cpu_load,
},
};
static const struct cpu_defaults knl_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
.setpoint = 97,
.p_gain_pct = 20,
.d_gain_pct = 0,
.i_gain_pct = 0,
},
.funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = knl_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.get_target_pstate = get_target_pstate_use_performance,
},
};
static const struct cpu_defaults bxt_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
.setpoint = 60,
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
},
.funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = core_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.get_target_pstate = get_target_pstate_use_cpu_load,
},
};
static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
{ {
int max_perf = cpu->pstate.turbo_pstate; return global.no_turbo || global.turbo_disabled ?
int max_perf_adj; cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
int min_perf;
struct perf_limits *perf_limits = &global;
if (global.no_turbo || global.turbo_disabled)
max_perf = cpu->pstate.max_pstate;
if (per_cpu_limits)
perf_limits = cpu->perf_limits;
/*
* performance can be limited by user through sysfs, by cpufreq
* policy, or by cpu specific default values determined through
* experimentation.
*/
max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf);
*max = clamp_t(int, max_perf_adj,
cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
min_perf = fp_ext_toint(max_perf * perf_limits->min_perf);
*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
} }
static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
...@@ -1702,11 +1523,13 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) ...@@ -1702,11 +1523,13 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
static void intel_pstate_max_within_limits(struct cpudata *cpu) static void intel_pstate_max_within_limits(struct cpudata *cpu)
{ {
int min_pstate, max_pstate; int pstate;
update_turbo_state(); update_turbo_state();
intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate); pstate = intel_pstate_get_base_pstate(cpu);
intel_pstate_set_pstate(cpu, max_pstate); pstate = max(cpu->pstate.min_pstate,
fp_ext_toint(pstate * cpu->max_perf));
intel_pstate_set_pstate(cpu, pstate);
} }
static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
...@@ -1767,7 +1590,11 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) ...@@ -1767,7 +1590,11 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
* that sample.time will always be reset before setting the utilization * that sample.time will always be reset before setting the utilization
* update hook and make the caller skip the sample then. * update hook and make the caller skip the sample then.
*/ */
return !!cpu->last_sample_time; if (cpu->last_sample_time) {
intel_pstate_calc_avg_perf(cpu);
return true;
}
return false;
} }
static inline int32_t get_avg_frequency(struct cpudata *cpu) static inline int32_t get_avg_frequency(struct cpudata *cpu)
...@@ -1788,6 +1615,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) ...@@ -1788,6 +1615,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
int32_t busy_frac, boost; int32_t busy_frac, boost;
int target, avg_pstate; int target, avg_pstate;
if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
return cpu->pstate.turbo_pstate;
busy_frac = div_fp(sample->mperf, sample->tsc); busy_frac = div_fp(sample->mperf, sample->tsc);
boost = cpu->iowait_boost; boost = cpu->iowait_boost;
...@@ -1824,6 +1654,9 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) ...@@ -1824,6 +1654,9 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
int32_t perf_scaled, max_pstate, current_pstate, sample_ratio; int32_t perf_scaled, max_pstate, current_pstate, sample_ratio;
u64 duration_ns; u64 duration_ns;
if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
return cpu->pstate.turbo_pstate;
/* /*
* perf_scaled is the ratio of the average P-state during the last * perf_scaled is the ratio of the average P-state during the last
* sampling period to the P-state requested last time (in percent). * sampling period to the P-state requested last time (in percent).
...@@ -1858,11 +1691,13 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) ...@@ -1858,11 +1691,13 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
{ {
int max_perf, min_perf; int max_pstate = intel_pstate_get_base_pstate(cpu);
int min_pstate;
intel_pstate_get_min_max(cpu, &min_perf, &max_perf); min_pstate = max(cpu->pstate.min_pstate,
pstate = clamp_t(int, pstate, min_perf, max_perf); fp_ext_toint(max_pstate * cpu->min_perf));
return pstate; max_pstate = max(min_pstate, fp_ext_toint(max_pstate * cpu->max_perf));
return clamp_t(int, pstate, min_pstate, max_pstate);
} }
static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
...@@ -1874,16 +1709,11 @@ static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) ...@@ -1874,16 +1709,11 @@ static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate)); wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
} }
static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) static void intel_pstate_adjust_pstate(struct cpudata *cpu, int target_pstate)
{ {
int from, target_pstate; int from = cpu->pstate.current_pstate;
struct sample *sample; struct sample *sample;
from = cpu->pstate.current_pstate;
target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
update_turbo_state(); update_turbo_state();
target_pstate = intel_pstate_prepare_request(cpu, target_pstate); target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
...@@ -1902,13 +1732,39 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) ...@@ -1902,13 +1732,39 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
fp_toint(cpu->iowait_boost * 100)); fp_toint(cpu->iowait_boost * 100));
} }
static void intel_pstate_update_util_hwp(struct update_util_data *data,
u64 time, unsigned int flags)
{
struct cpudata *cpu = container_of(data, struct cpudata, update_util);
u64 delta_ns = time - cpu->sample.time;
if ((s64)delta_ns >= INTEL_PSTATE_HWP_SAMPLING_INTERVAL)
intel_pstate_sample(cpu, time);
}
static void intel_pstate_update_util_pid(struct update_util_data *data,
u64 time, unsigned int flags)
{
struct cpudata *cpu = container_of(data, struct cpudata, update_util);
u64 delta_ns = time - cpu->sample.time;
if ((s64)delta_ns < pid_params.sample_rate_ns)
return;
if (intel_pstate_sample(cpu, time)) {
int target_pstate;
target_pstate = get_target_pstate_use_performance(cpu);
intel_pstate_adjust_pstate(cpu, target_pstate);
}
}
static void intel_pstate_update_util(struct update_util_data *data, u64 time, static void intel_pstate_update_util(struct update_util_data *data, u64 time,
unsigned int flags) unsigned int flags)
{ {
struct cpudata *cpu = container_of(data, struct cpudata, update_util); struct cpudata *cpu = container_of(data, struct cpudata, update_util);
u64 delta_ns; u64 delta_ns;
if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) {
if (flags & SCHED_CPUFREQ_IOWAIT) { if (flags & SCHED_CPUFREQ_IOWAIT) {
cpu->iowait_boost = int_tofp(1); cpu->iowait_boost = int_tofp(1);
} else if (cpu->iowait_boost) { } else if (cpu->iowait_boost) {
...@@ -1918,60 +1774,113 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, ...@@ -1918,60 +1774,113 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
cpu->iowait_boost = 0; cpu->iowait_boost = 0;
} }
cpu->last_update = time; cpu->last_update = time;
}
delta_ns = time - cpu->sample.time; delta_ns = time - cpu->sample.time;
if ((s64)delta_ns >= pid_params.sample_rate_ns) { if ((s64)delta_ns < INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL)
bool sample_taken = intel_pstate_sample(cpu, time); return;
if (sample_taken) { if (intel_pstate_sample(cpu, time)) {
intel_pstate_calc_avg_perf(cpu); int target_pstate;
if (!hwp_active)
intel_pstate_adjust_busy_pstate(cpu); target_pstate = get_target_pstate_use_cpu_load(cpu);
} intel_pstate_adjust_pstate(cpu, target_pstate);
} }
} }
static struct pstate_funcs core_funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = core_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.update_util = intel_pstate_update_util_pid,
};
static const struct pstate_funcs silvermont_funcs = {
.get_max = atom_get_max_pstate,
.get_max_physical = atom_get_max_pstate,
.get_min = atom_get_min_pstate,
.get_turbo = atom_get_turbo_pstate,
.get_val = atom_get_val,
.get_scaling = silvermont_get_scaling,
.get_vid = atom_get_vid,
.update_util = intel_pstate_update_util,
};
static const struct pstate_funcs airmont_funcs = {
.get_max = atom_get_max_pstate,
.get_max_physical = atom_get_max_pstate,
.get_min = atom_get_min_pstate,
.get_turbo = atom_get_turbo_pstate,
.get_val = atom_get_val,
.get_scaling = airmont_get_scaling,
.get_vid = atom_get_vid,
.update_util = intel_pstate_update_util,
};
static const struct pstate_funcs knl_funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = knl_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.update_util = intel_pstate_update_util_pid,
};
static const struct pstate_funcs bxt_funcs = {
.get_max = core_get_max_pstate,
.get_max_physical = core_get_max_pstate_physical,
.get_min = core_get_min_pstate,
.get_turbo = core_get_turbo_pstate,
.get_scaling = core_get_scaling,
.get_val = core_get_val,
.update_util = intel_pstate_update_util,
};
#define ICPU(model, policy) \ #define ICPU(model, policy) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
(unsigned long)&policy } (unsigned long)&policy }
static const struct x86_cpu_id intel_pstate_cpu_ids[] = { static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(INTEL_FAM6_SANDYBRIDGE, core_params), ICPU(INTEL_FAM6_SANDYBRIDGE, core_funcs),
ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_params), ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_funcs),
ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_params), ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_funcs),
ICPU(INTEL_FAM6_IVYBRIDGE, core_params), ICPU(INTEL_FAM6_IVYBRIDGE, core_funcs),
ICPU(INTEL_FAM6_HASWELL_CORE, core_params), ICPU(INTEL_FAM6_HASWELL_CORE, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_CORE, core_params), ICPU(INTEL_FAM6_BROADWELL_CORE, core_funcs),
ICPU(INTEL_FAM6_IVYBRIDGE_X, core_params), ICPU(INTEL_FAM6_IVYBRIDGE_X, core_funcs),
ICPU(INTEL_FAM6_HASWELL_X, core_params), ICPU(INTEL_FAM6_HASWELL_X, core_funcs),
ICPU(INTEL_FAM6_HASWELL_ULT, core_params), ICPU(INTEL_FAM6_HASWELL_ULT, core_funcs),
ICPU(INTEL_FAM6_HASWELL_GT3E, core_params), ICPU(INTEL_FAM6_HASWELL_GT3E, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_GT3E, core_params), ICPU(INTEL_FAM6_BROADWELL_GT3E, core_funcs),
ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_params), ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_funcs),
ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_params), ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_X, core_params), ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_params), ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs),
ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_params), ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_funcs),
ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_params), ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_funcs),
ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_params), ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_funcs),
ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, bxt_funcs),
{} {}
}; };
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_X, core_params), ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
ICPU(INTEL_FAM6_SKYLAKE_X, core_params), ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
{} {}
}; };
static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params), ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_funcs),
{} {}
}; };
static bool pid_in_use(void);
static int intel_pstate_init_cpu(unsigned int cpunum) static int intel_pstate_init_cpu(unsigned int cpunum)
{ {
struct cpudata *cpu; struct cpudata *cpu;
...@@ -1979,18 +1888,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum) ...@@ -1979,18 +1888,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
cpu = all_cpu_data[cpunum]; cpu = all_cpu_data[cpunum];
if (!cpu) { if (!cpu) {
unsigned int size = sizeof(struct cpudata); cpu = kzalloc(sizeof(*cpu), GFP_KERNEL);
if (per_cpu_limits)
size += sizeof(struct perf_limits);
cpu = kzalloc(size, GFP_KERNEL);
if (!cpu) if (!cpu)
return -ENOMEM; return -ENOMEM;
all_cpu_data[cpunum] = cpu; all_cpu_data[cpunum] = cpu;
if (per_cpu_limits)
cpu->perf_limits = (struct perf_limits *)(cpu + 1);
cpu->epp_default = -EINVAL; cpu->epp_default = -EINVAL;
cpu->epp_powersave = -EINVAL; cpu->epp_powersave = -EINVAL;
...@@ -2009,14 +1911,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum) ...@@ -2009,14 +1911,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
intel_pstate_disable_ee(cpunum); intel_pstate_disable_ee(cpunum);
intel_pstate_hwp_enable(cpu); intel_pstate_hwp_enable(cpu);
pid_params.sample_rate_ms = 50; } else if (pid_in_use()) {
pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC; intel_pstate_pid_reset(cpu);
} }
intel_pstate_get_cpu_pstates(cpu); intel_pstate_get_cpu_pstates(cpu);
intel_pstate_busy_pid_reset(cpu);
pr_debug("controlling: cpu %d\n", cpunum); pr_debug("controlling: cpu %d\n", cpunum);
return 0; return 0;
...@@ -2039,7 +1939,7 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) ...@@ -2039,7 +1939,7 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
/* Prevent intel_pstate_update_util() from using stale data. */ /* Prevent intel_pstate_update_util() from using stale data. */
cpu->sample.time = 0; cpu->sample.time = 0;
cpufreq_add_update_util_hook(cpu_num, &cpu->update_util, cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
intel_pstate_update_util); pstate_funcs.update_util);
cpu->update_util_set = true; cpu->update_util_set = true;
} }
...@@ -2055,46 +1955,68 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu) ...@@ -2055,46 +1955,68 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu)
synchronize_sched(); synchronize_sched();
} }
static int intel_pstate_get_max_freq(struct cpudata *cpu)
{
return global.turbo_disabled || global.no_turbo ?
cpu->pstate.max_freq : cpu->pstate.turbo_freq;
}
static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
struct perf_limits *limits) struct cpudata *cpu)
{ {
int max_freq = intel_pstate_get_max_freq(cpu);
int32_t max_policy_perf, min_policy_perf; int32_t max_policy_perf, min_policy_perf;
max_policy_perf = div_ext_fp(policy->max, policy->cpuinfo.max_freq); max_policy_perf = div_ext_fp(policy->max, max_freq);
max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1)); max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1));
if (policy->max == policy->min) { if (policy->max == policy->min) {
min_policy_perf = max_policy_perf; min_policy_perf = max_policy_perf;
} else { } else {
min_policy_perf = div_ext_fp(policy->min, min_policy_perf = div_ext_fp(policy->min, max_freq);
policy->cpuinfo.max_freq);
min_policy_perf = clamp_t(int32_t, min_policy_perf, min_policy_perf = clamp_t(int32_t, min_policy_perf,
0, max_policy_perf); 0, max_policy_perf);
} }
/* Normalize user input to [min_perf, max_perf] */ /* Normalize user input to [min_perf, max_perf] */
limits->min_perf = max(min_policy_perf, if (per_cpu_limits) {
percent_ext_fp(limits->min_sysfs_pct)); cpu->min_perf = min_policy_perf;
limits->min_perf = min(limits->min_perf, max_policy_perf); cpu->max_perf = max_policy_perf;
limits->max_perf = min(max_policy_perf, } else {
percent_ext_fp(limits->max_sysfs_pct)); int32_t global_min, global_max;
limits->max_perf = max(min_policy_perf, limits->max_perf);
/* Global limits are in percent of the maximum turbo P-state. */
global_max = percent_ext_fp(global.max_perf_pct);
global_min = percent_ext_fp(global.min_perf_pct);
if (max_freq != cpu->pstate.turbo_freq) {
int32_t turbo_factor;
turbo_factor = div_ext_fp(cpu->pstate.turbo_pstate,
cpu->pstate.max_pstate);
global_min = mul_ext_fp(global_min, turbo_factor);
global_max = mul_ext_fp(global_max, turbo_factor);
}
global_min = clamp_t(int32_t, global_min, 0, global_max);
cpu->min_perf = max(min_policy_perf, global_min);
cpu->min_perf = min(cpu->min_perf, max_policy_perf);
cpu->max_perf = min(max_policy_perf, global_max);
cpu->max_perf = max(min_policy_perf, cpu->max_perf);
/* Make sure min_perf <= max_perf */ /* Make sure min_perf <= max_perf */
limits->min_perf = min(limits->min_perf, limits->max_perf); cpu->min_perf = min(cpu->min_perf, cpu->max_perf);
}
limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS); cpu->max_perf = round_up(cpu->max_perf, EXT_FRAC_BITS);
limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS); cpu->min_perf = round_up(cpu->min_perf, EXT_FRAC_BITS);
limits->max_perf_pct = fp_ext_toint(limits->max_perf * 100);
limits->min_perf_pct = fp_ext_toint(limits->min_perf * 100);
pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu, pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu,
limits->max_perf_pct, limits->min_perf_pct); fp_ext_toint(cpu->max_perf * 100),
fp_ext_toint(cpu->min_perf * 100));
} }
static int intel_pstate_set_policy(struct cpufreq_policy *policy) static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{ {
struct cpudata *cpu; struct cpudata *cpu;
struct perf_limits *perf_limits = &global;
if (!policy->cpuinfo.max_freq) if (!policy->cpuinfo.max_freq)
return -ENODEV; return -ENODEV;
...@@ -2105,19 +2027,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) ...@@ -2105,19 +2027,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
cpu = all_cpu_data[policy->cpu]; cpu = all_cpu_data[policy->cpu];
cpu->policy = policy->policy; cpu->policy = policy->policy;
if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
policy->max < policy->cpuinfo.max_freq &&
policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
pr_debug("policy->max > max non turbo frequency\n");
policy->max = policy->cpuinfo.max_freq;
}
if (per_cpu_limits)
perf_limits = cpu->perf_limits;
mutex_lock(&intel_pstate_limits_lock); mutex_lock(&intel_pstate_limits_lock);
intel_pstate_update_perf_limits(policy, perf_limits); intel_pstate_update_perf_limits(policy, cpu);
if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
/* /*
...@@ -2130,38 +2042,38 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) ...@@ -2130,38 +2042,38 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
intel_pstate_set_update_util_hook(policy->cpu); intel_pstate_set_update_util_hook(policy->cpu);
intel_pstate_hwp_set_policy(policy); if (hwp_active)
intel_pstate_hwp_set(policy->cpu);
mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_limits_lock);
return 0; return 0;
} }
static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
struct cpudata *cpu)
{
if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
policy->max < policy->cpuinfo.max_freq &&
policy->max > cpu->pstate.max_freq) {
pr_debug("policy->max > max non turbo frequency\n");
policy->max = policy->cpuinfo.max_freq;
}
}
static int intel_pstate_verify_policy(struct cpufreq_policy *policy) static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
{ {
struct cpudata *cpu = all_cpu_data[policy->cpu]; struct cpudata *cpu = all_cpu_data[policy->cpu];
update_turbo_state(); update_turbo_state();
policy->cpuinfo.max_freq = global.turbo_disabled || global.no_turbo ? cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
cpu->pstate.max_freq : intel_pstate_get_max_freq(cpu));
cpu->pstate.turbo_freq;
cpufreq_verify_within_cpu_limits(policy);
if (policy->policy != CPUFREQ_POLICY_POWERSAVE && if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
policy->policy != CPUFREQ_POLICY_PERFORMANCE) policy->policy != CPUFREQ_POLICY_PERFORMANCE)
return -EINVAL; return -EINVAL;
/* When per-CPU limits are used, sysfs limits are not used */ intel_pstate_adjust_policy_max(policy, cpu);
if (!per_cpu_limits) {
unsigned int max_freq, min_freq;
max_freq = policy->cpuinfo.max_freq *
global.max_sysfs_pct / 100;
min_freq = policy->cpuinfo.max_freq *
global.min_sysfs_pct / 100;
cpufreq_verify_within_limits(policy, min_freq, max_freq);
}
return 0; return 0;
} }
...@@ -2202,8 +2114,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) ...@@ -2202,8 +2114,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
cpu = all_cpu_data[policy->cpu]; cpu = all_cpu_data[policy->cpu];
if (per_cpu_limits) cpu->max_perf = int_ext_tofp(1);
intel_pstate_init_limits(cpu->perf_limits); cpu->min_perf = 0;
policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
...@@ -2257,10 +2169,12 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) ...@@ -2257,10 +2169,12 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
struct cpudata *cpu = all_cpu_data[policy->cpu]; struct cpudata *cpu = all_cpu_data[policy->cpu];
update_turbo_state(); update_turbo_state();
policy->cpuinfo.max_freq = global.no_turbo || global.turbo_disabled ? cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
cpu->pstate.max_freq : cpu->pstate.turbo_freq; intel_pstate_get_max_freq(cpu));
cpufreq_verify_within_cpu_limits(policy); intel_pstate_adjust_policy_max(policy, cpu);
intel_pstate_update_perf_limits(policy, cpu);
return 0; return 0;
} }
...@@ -2324,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) ...@@ -2324,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
return ret; return ret;
policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY; policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
/* This reflects the intel_pstate_get_cpu_pstates() setting. */ /* This reflects the intel_pstate_get_cpu_pstates() setting. */
policy->cur = policy->cpuinfo.min_freq; policy->cur = policy->cpuinfo.min_freq;
...@@ -2341,7 +2256,13 @@ static struct cpufreq_driver intel_cpufreq = { ...@@ -2341,7 +2256,13 @@ static struct cpufreq_driver intel_cpufreq = {
.name = "intel_cpufreq", .name = "intel_cpufreq",
}; };
static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; static struct cpufreq_driver *default_driver = &intel_pstate;
static bool pid_in_use(void)
{
return intel_pstate_driver == &intel_pstate &&
pstate_funcs.update_util == intel_pstate_update_util_pid;
}
static void intel_pstate_driver_cleanup(void) static void intel_pstate_driver_cleanup(void)
{ {
...@@ -2358,26 +2279,26 @@ static void intel_pstate_driver_cleanup(void) ...@@ -2358,26 +2279,26 @@ static void intel_pstate_driver_cleanup(void)
} }
} }
put_online_cpus(); put_online_cpus();
intel_pstate_driver = NULL;
} }
static int intel_pstate_register_driver(void) static int intel_pstate_register_driver(struct cpufreq_driver *driver)
{ {
int ret; int ret;
intel_pstate_init_limits(&global); memset(&global, 0, sizeof(global));
global.max_perf_pct = 100;
intel_pstate_driver = driver;
ret = cpufreq_register_driver(intel_pstate_driver); ret = cpufreq_register_driver(intel_pstate_driver);
if (ret) { if (ret) {
intel_pstate_driver_cleanup(); intel_pstate_driver_cleanup();
return ret; return ret;
} }
mutex_lock(&intel_pstate_limits_lock); global.min_perf_pct = min_perf_pct_min();
driver_registered = true;
mutex_unlock(&intel_pstate_limits_lock);
if (intel_pstate_driver == &intel_pstate && !hwp_active && if (pid_in_use())
pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
intel_pstate_debug_expose_params(); intel_pstate_debug_expose_params();
return 0; return 0;
...@@ -2388,14 +2309,9 @@ static int intel_pstate_unregister_driver(void) ...@@ -2388,14 +2309,9 @@ static int intel_pstate_unregister_driver(void)
if (hwp_active) if (hwp_active)
return -EBUSY; return -EBUSY;
if (intel_pstate_driver == &intel_pstate && !hwp_active && if (pid_in_use())
pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
intel_pstate_debug_hide_params(); intel_pstate_debug_hide_params();
mutex_lock(&intel_pstate_limits_lock);
driver_registered = false;
mutex_unlock(&intel_pstate_limits_lock);
cpufreq_unregister_driver(intel_pstate_driver); cpufreq_unregister_driver(intel_pstate_driver);
intel_pstate_driver_cleanup(); intel_pstate_driver_cleanup();
...@@ -2404,7 +2320,7 @@ static int intel_pstate_unregister_driver(void) ...@@ -2404,7 +2320,7 @@ static int intel_pstate_unregister_driver(void)
static ssize_t intel_pstate_show_status(char *buf) static ssize_t intel_pstate_show_status(char *buf)
{ {
if (!driver_registered) if (!intel_pstate_driver)
return sprintf(buf, "off\n"); return sprintf(buf, "off\n");
return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ? return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
...@@ -2416,11 +2332,11 @@ static int intel_pstate_update_status(const char *buf, size_t size) ...@@ -2416,11 +2332,11 @@ static int intel_pstate_update_status(const char *buf, size_t size)
int ret; int ret;
if (size == 3 && !strncmp(buf, "off", size)) if (size == 3 && !strncmp(buf, "off", size))
return driver_registered ? return intel_pstate_driver ?
intel_pstate_unregister_driver() : -EINVAL; intel_pstate_unregister_driver() : -EINVAL;
if (size == 6 && !strncmp(buf, "active", size)) { if (size == 6 && !strncmp(buf, "active", size)) {
if (driver_registered) { if (intel_pstate_driver) {
if (intel_pstate_driver == &intel_pstate) if (intel_pstate_driver == &intel_pstate)
return 0; return 0;
...@@ -2429,13 +2345,12 @@ static int intel_pstate_update_status(const char *buf, size_t size) ...@@ -2429,13 +2345,12 @@ static int intel_pstate_update_status(const char *buf, size_t size)
return ret; return ret;
} }
intel_pstate_driver = &intel_pstate; return intel_pstate_register_driver(&intel_pstate);
return intel_pstate_register_driver();
} }
if (size == 7 && !strncmp(buf, "passive", size)) { if (size == 7 && !strncmp(buf, "passive", size)) {
if (driver_registered) { if (intel_pstate_driver) {
if (intel_pstate_driver != &intel_pstate) if (intel_pstate_driver == &intel_cpufreq)
return 0; return 0;
ret = intel_pstate_unregister_driver(); ret = intel_pstate_unregister_driver();
...@@ -2443,8 +2358,7 @@ static int intel_pstate_update_status(const char *buf, size_t size) ...@@ -2443,8 +2358,7 @@ static int intel_pstate_update_status(const char *buf, size_t size)
return ret; return ret;
} }
intel_pstate_driver = &intel_cpufreq; return intel_pstate_register_driver(&intel_cpufreq);
return intel_pstate_register_driver();
} }
return -EINVAL; return -EINVAL;
...@@ -2465,23 +2379,17 @@ static int __init intel_pstate_msrs_not_valid(void) ...@@ -2465,23 +2379,17 @@ static int __init intel_pstate_msrs_not_valid(void)
return 0; return 0;
} }
static void __init copy_pid_params(struct pstate_adjust_policy *policy)
{
pid_params.sample_rate_ms = policy->sample_rate_ms;
pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
pid_params.p_gain_pct = policy->p_gain_pct;
pid_params.i_gain_pct = policy->i_gain_pct;
pid_params.d_gain_pct = policy->d_gain_pct;
pid_params.deadband = policy->deadband;
pid_params.setpoint = policy->setpoint;
}
#ifdef CONFIG_ACPI #ifdef CONFIG_ACPI
static void intel_pstate_use_acpi_profile(void) static void intel_pstate_use_acpi_profile(void)
{ {
if (acpi_gbl_FADT.preferred_profile == PM_MOBILE) switch (acpi_gbl_FADT.preferred_profile) {
pstate_funcs.get_target_pstate = case PM_MOBILE:
get_target_pstate_use_cpu_load; case PM_TABLET:
case PM_APPLIANCE_PC:
case PM_DESKTOP:
case PM_WORKSTATION:
pstate_funcs.update_util = intel_pstate_update_util;
}
} }
#else #else
static void intel_pstate_use_acpi_profile(void) static void intel_pstate_use_acpi_profile(void)
...@@ -2498,7 +2406,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) ...@@ -2498,7 +2406,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
pstate_funcs.get_scaling = funcs->get_scaling; pstate_funcs.get_scaling = funcs->get_scaling;
pstate_funcs.get_val = funcs->get_val; pstate_funcs.get_val = funcs->get_val;
pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.get_vid = funcs->get_vid;
pstate_funcs.get_target_pstate = funcs->get_target_pstate; pstate_funcs.update_util = funcs->update_util;
intel_pstate_use_acpi_profile(); intel_pstate_use_acpi_profile();
} }
...@@ -2637,28 +2545,30 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { ...@@ -2637,28 +2545,30 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = {
static int __init intel_pstate_init(void) static int __init intel_pstate_init(void)
{ {
const struct x86_cpu_id *id; int rc;
struct cpu_defaults *cpu_def;
int rc = 0;
if (no_load) if (no_load)
return -ENODEV; return -ENODEV;
if (x86_match_cpu(hwp_support_ids) && !no_hwp) { if (x86_match_cpu(hwp_support_ids)) {
copy_cpu_funcs(&core_params.funcs); copy_cpu_funcs(&core_funcs);
if (no_hwp) {
pstate_funcs.update_util = intel_pstate_update_util;
} else {
hwp_active++; hwp_active++;
intel_pstate.attr = hwp_cpufreq_attrs; intel_pstate.attr = hwp_cpufreq_attrs;
pstate_funcs.update_util = intel_pstate_update_util_hwp;
goto hwp_cpu_matched; goto hwp_cpu_matched;
} }
} else {
const struct x86_cpu_id *id;
id = x86_match_cpu(intel_pstate_cpu_ids); id = x86_match_cpu(intel_pstate_cpu_ids);
if (!id) if (!id)
return -ENODEV; return -ENODEV;
cpu_def = (struct cpu_defaults *)id->driver_data; copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
}
copy_pid_params(&cpu_def->pid_policy);
copy_cpu_funcs(&cpu_def->funcs);
if (intel_pstate_msrs_not_valid()) if (intel_pstate_msrs_not_valid())
return -ENODEV; return -ENODEV;
...@@ -2685,7 +2595,7 @@ static int __init intel_pstate_init(void) ...@@ -2685,7 +2595,7 @@ static int __init intel_pstate_init(void)
intel_pstate_sysfs_expose_params(); intel_pstate_sysfs_expose_params();
mutex_lock(&intel_pstate_driver_lock); mutex_lock(&intel_pstate_driver_lock);
rc = intel_pstate_register_driver(); rc = intel_pstate_register_driver(default_driver);
mutex_unlock(&intel_pstate_driver_lock); mutex_unlock(&intel_pstate_driver_lock);
if (rc) if (rc)
return rc; return rc;
...@@ -2706,7 +2616,7 @@ static int __init intel_pstate_setup(char *str) ...@@ -2706,7 +2616,7 @@ static int __init intel_pstate_setup(char *str)
no_load = 1; no_load = 1;
} else if (!strcmp(str, "passive")) { } else if (!strcmp(str, "passive")) {
pr_info("Passive mode enabled\n"); pr_info("Passive mode enabled\n");
intel_pstate_driver = &intel_cpufreq; default_driver = &intel_cpufreq;
no_hwp = 1; no_hwp = 1;
} }
if (!strcmp(str, "no_hwp")) { if (!strcmp(str, "no_hwp")) {
......
...@@ -573,14 +573,33 @@ static struct platform_driver mt8173_cpufreq_platdrv = { ...@@ -573,14 +573,33 @@ static struct platform_driver mt8173_cpufreq_platdrv = {
.probe = mt8173_cpufreq_probe, .probe = mt8173_cpufreq_probe,
}; };
static int mt8173_cpufreq_driver_init(void) /* List of machines supported by this driver */
static const struct of_device_id mt8173_cpufreq_machines[] __initconst = {
{ .compatible = "mediatek,mt817x", },
{ .compatible = "mediatek,mt8173", },
{ .compatible = "mediatek,mt8176", },
{ }
};
static int __init mt8173_cpufreq_driver_init(void)
{ {
struct device_node *np;
const struct of_device_id *match;
struct platform_device *pdev; struct platform_device *pdev;
int err; int err;
if (!of_machine_is_compatible("mediatek,mt8173")) np = of_find_node_by_path("/");
if (!np)
return -ENODEV; return -ENODEV;
match = of_match_node(mt8173_cpufreq_machines, np);
of_node_put(np);
if (!match) {
pr_warn("Machine is not compatible with mt8173-cpufreq\n");
return -ENODEV;
}
err = platform_driver_register(&mt8173_cpufreq_platdrv); err = platform_driver_register(&mt8173_cpufreq_platdrv);
if (err) if (err)
return err; return err;
......
...@@ -52,17 +52,27 @@ static u32 get_bus_freq(void) ...@@ -52,17 +52,27 @@ static u32 get_bus_freq(void)
{ {
struct device_node *soc; struct device_node *soc;
u32 sysfreq; u32 sysfreq;
struct clk *pltclk;
int ret;
/* get platform freq by searching bus-frequency property */
soc = of_find_node_by_type(NULL, "soc"); soc = of_find_node_by_type(NULL, "soc");
if (!soc) if (soc) {
return 0; ret = of_property_read_u32(soc, "bus-frequency", &sysfreq);
if (of_property_read_u32(soc, "bus-frequency", &sysfreq))
sysfreq = 0;
of_node_put(soc); of_node_put(soc);
if (!ret)
return sysfreq; return sysfreq;
}
/* get platform freq by its clock name */
pltclk = clk_get(NULL, "cg-pll0-div1");
if (IS_ERR(pltclk)) {
pr_err("%s: can't get bus frequency %ld\n",
__func__, PTR_ERR(pltclk));
return PTR_ERR(pltclk);
}
return clk_get_rate(pltclk);
} }
static struct clk *cpu_to_clk(int cpu) static struct clk *cpu_to_clk(int cpu)
......
/*
* Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/cpufreq.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <soc/tegra/bpmp.h>
#include <soc/tegra/bpmp-abi.h>
#define EDVD_CORE_VOLT_FREQ(core) (0x20 + (core) * 0x4)
#define EDVD_CORE_VOLT_FREQ_F_SHIFT 0
#define EDVD_CORE_VOLT_FREQ_V_SHIFT 16
struct tegra186_cpufreq_cluster_info {
unsigned long offset;
int cpus[4];
unsigned int bpmp_cluster_id;
};
#define NO_CPU -1
static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = {
/* Denver cluster */
{
.offset = SZ_64K * 7,
.cpus = { 1, 2, NO_CPU, NO_CPU },
.bpmp_cluster_id = 0,
},
/* A57 cluster */
{
.offset = SZ_64K * 6,
.cpus = { 0, 3, 4, 5 },
.bpmp_cluster_id = 1,
},
};
struct tegra186_cpufreq_cluster {
const struct tegra186_cpufreq_cluster_info *info;
struct cpufreq_frequency_table *table;
};
struct tegra186_cpufreq_data {
void __iomem *regs;
size_t num_clusters;
struct tegra186_cpufreq_cluster *clusters;
};
static int tegra186_cpufreq_init(struct cpufreq_policy *policy)
{
struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
unsigned int i;
for (i = 0; i < data->num_clusters; i++) {
struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
const struct tegra186_cpufreq_cluster_info *info =
cluster->info;
int core;
for (core = 0; core < ARRAY_SIZE(info->cpus); core++) {
if (info->cpus[core] == policy->cpu)
break;
}
if (core == ARRAY_SIZE(info->cpus))
continue;
policy->driver_data =
data->regs + info->offset + EDVD_CORE_VOLT_FREQ(core);
cpufreq_table_validate_and_show(policy, cluster->table);
}
policy->cpuinfo.transition_latency = 300 * 1000;
return 0;
}
static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy,
unsigned int index)
{
struct cpufreq_frequency_table *tbl = policy->freq_table + index;
void __iomem *edvd_reg = policy->driver_data;
u32 edvd_val = tbl->driver_data;
writel(edvd_val, edvd_reg);
return 0;
}
static struct cpufreq_driver tegra186_cpufreq_driver = {
.name = "tegra186",
.flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
.verify = cpufreq_generic_frequency_table_verify,
.target_index = tegra186_cpufreq_set_target,
.init = tegra186_cpufreq_init,
.attr = cpufreq_generic_attr,
};
static struct cpufreq_frequency_table *init_vhint_table(
struct platform_device *pdev, struct tegra_bpmp *bpmp,
unsigned int cluster_id)
{
struct cpufreq_frequency_table *table;
struct mrq_cpu_vhint_request req;
struct tegra_bpmp_message msg;
struct cpu_vhint_data *data;
int err, i, j, num_rates = 0;
dma_addr_t phys;
void *virt;
virt = dma_alloc_coherent(bpmp->dev, sizeof(*data), &phys,
GFP_KERNEL | GFP_DMA32);
if (!virt)
return ERR_PTR(-ENOMEM);
data = (struct cpu_vhint_data *)virt;
memset(&req, 0, sizeof(req));
req.addr = phys;
req.cluster_id = cluster_id;
memset(&msg, 0, sizeof(msg));
msg.mrq = MRQ_CPU_VHINT;
msg.tx.data = &req;
msg.tx.size = sizeof(req);
err = tegra_bpmp_transfer(bpmp, &msg);
if (err) {
table = ERR_PTR(err);
goto free;
}
for (i = data->vfloor; i <= data->vceil; i++) {
u16 ndiv = data->ndiv[i];
if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
continue;
/* Only store lowest voltage index for each rate */
if (i > 0 && ndiv == data->ndiv[i - 1])
continue;
num_rates++;
}
table = devm_kcalloc(&pdev->dev, num_rates + 1, sizeof(*table),
GFP_KERNEL);
if (!table) {
table = ERR_PTR(-ENOMEM);
goto free;
}
for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
struct cpufreq_frequency_table *point;
u16 ndiv = data->ndiv[i];
u32 edvd_val = 0;
if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
continue;
/* Only store lowest voltage index for each rate */
if (i > 0 && ndiv == data->ndiv[i - 1])
continue;
edvd_val |= i << EDVD_CORE_VOLT_FREQ_V_SHIFT;
edvd_val |= ndiv << EDVD_CORE_VOLT_FREQ_F_SHIFT;
point = &table[j++];
point->driver_data = edvd_val;
point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
data->mdiv / 1000;
}
table[j].frequency = CPUFREQ_TABLE_END;
free:
dma_free_coherent(bpmp->dev, sizeof(*data), virt, phys);
return table;
}
static int tegra186_cpufreq_probe(struct platform_device *pdev)
{
struct tegra186_cpufreq_data *data;
struct tegra_bpmp *bpmp;
struct resource *res;
unsigned int i = 0, err;
data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
data->clusters = devm_kcalloc(&pdev->dev, ARRAY_SIZE(tegra186_clusters),
sizeof(*data->clusters), GFP_KERNEL);
if (!data->clusters)
return -ENOMEM;
data->num_clusters = ARRAY_SIZE(tegra186_clusters);
bpmp = tegra_bpmp_get(&pdev->dev);
if (IS_ERR(bpmp))
return PTR_ERR(bpmp);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
data->regs = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(data->regs)) {
err = PTR_ERR(data->regs);
goto put_bpmp;
}
for (i = 0; i < data->num_clusters; i++) {
struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
cluster->info = &tegra186_clusters[i];
cluster->table = init_vhint_table(
pdev, bpmp, cluster->info->bpmp_cluster_id);
if (IS_ERR(cluster->table)) {
err = PTR_ERR(cluster->table);
goto put_bpmp;
}
}
tegra_bpmp_put(bpmp);
tegra186_cpufreq_driver.driver_data = data;
err = cpufreq_register_driver(&tegra186_cpufreq_driver);
if (err)
return err;
return 0;
put_bpmp:
tegra_bpmp_put(bpmp);
return err;
}
static int tegra186_cpufreq_remove(struct platform_device *pdev)
{
cpufreq_unregister_driver(&tegra186_cpufreq_driver);
return 0;
}
static const struct of_device_id tegra186_cpufreq_of_match[] = {
{ .compatible = "nvidia,tegra186-ccplex-cluster", },
{ }
};
MODULE_DEVICE_TABLE(of, tegra186_cpufreq_of_match);
static struct platform_driver tegra186_cpufreq_platform_driver = {
.driver = {
.name = "tegra186-cpufreq",
.of_match_table = tegra186_cpufreq_of_match,
},
.probe = tegra186_cpufreq_probe,
.remove = tegra186_cpufreq_remove,
};
module_platform_driver(tegra186_cpufreq_platform_driver);
MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
MODULE_DESCRIPTION("NVIDIA Tegra186 cpufreq driver");
MODULE_LICENSE("GPL v2");
...@@ -118,7 +118,7 @@ static void __init cps_cpuidle_unregister(void) ...@@ -118,7 +118,7 @@ static void __init cps_cpuidle_unregister(void)
static int __init cps_cpuidle_init(void) static int __init cps_cpuidle_init(void)
{ {
int err, cpu, core, i; int err, cpu, i;
struct cpuidle_device *device; struct cpuidle_device *device;
/* Detect supported states */ /* Detect supported states */
...@@ -160,7 +160,6 @@ static int __init cps_cpuidle_init(void) ...@@ -160,7 +160,6 @@ static int __init cps_cpuidle_init(void)
} }
for_each_possible_cpu(cpu) { for_each_possible_cpu(cpu) {
core = cpu_data[cpu].core;
device = &per_cpu(cpuidle_dev, cpu); device = &per_cpu(cpuidle_dev, cpu);
device->cpu = cpu; device->cpu = cpu;
#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
......
...@@ -56,10 +56,9 @@ static int snooze_loop(struct cpuidle_device *dev, ...@@ -56,10 +56,9 @@ static int snooze_loop(struct cpuidle_device *dev,
snooze_exit_time = get_tb() + snooze_timeout; snooze_exit_time = get_tb() + snooze_timeout;
ppc64_runlatch_off(); ppc64_runlatch_off();
while (!need_resched()) {
HMT_low();
HMT_very_low(); HMT_very_low();
if (snooze_timeout_en && get_tb() > snooze_exit_time) while (!need_resched()) {
if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time)
break; break;
} }
...@@ -215,11 +214,25 @@ static inline void add_powernv_state(int index, const char *name, ...@@ -215,11 +214,25 @@ static inline void add_powernv_state(int index, const char *name,
stop_psscr_table[index].mask = psscr_mask; stop_psscr_table[index].mask = psscr_mask;
} }
/*
* Returns 0 if prop1_len == prop2_len. Else returns -1
*/
static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
const char *prop2, int prop2_len)
{
if (prop1_len == prop2_len)
return 0;
pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
prop1, prop2);
return -1;
}
static int powernv_add_idle_states(void) static int powernv_add_idle_states(void)
{ {
struct device_node *power_mgt; struct device_node *power_mgt;
int nr_idle_states = 1; /* Snooze */ int nr_idle_states = 1; /* Snooze */
int dt_idle_states; int dt_idle_states, count;
u32 latency_ns[CPUIDLE_STATE_MAX]; u32 latency_ns[CPUIDLE_STATE_MAX];
u32 residency_ns[CPUIDLE_STATE_MAX]; u32 residency_ns[CPUIDLE_STATE_MAX];
u32 flags[CPUIDLE_STATE_MAX]; u32 flags[CPUIDLE_STATE_MAX];
...@@ -244,6 +257,21 @@ static int powernv_add_idle_states(void) ...@@ -244,6 +257,21 @@ static int powernv_add_idle_states(void)
goto out; goto out;
} }
count = of_property_count_u32_elems(power_mgt,
"ibm,cpu-idle-state-latencies-ns");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
"ibm,cpu-idle-state-latencies-ns",
count) != 0)
goto out;
count = of_property_count_strings(power_mgt,
"ibm,cpu-idle-state-names");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
"ibm,cpu-idle-state-names",
count) != 0)
goto out;
/* /*
* Since snooze is used as first idle state, max idle states allowed is * Since snooze is used as first idle state, max idle states allowed is
* CPUIDLE_STATE_MAX -1 * CPUIDLE_STATE_MAX -1
...@@ -278,6 +306,22 @@ static int powernv_add_idle_states(void) ...@@ -278,6 +306,22 @@ static int powernv_add_idle_states(void)
has_stop_states = (flags[0] & has_stop_states = (flags[0] &
(OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP)); (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
if (has_stop_states) { if (has_stop_states) {
count = of_property_count_u64_elems(power_mgt,
"ibm,cpu-idle-state-psscr");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-psscr",
count) != 0)
goto out;
count = of_property_count_u64_elems(power_mgt,
"ibm,cpu-idle-state-psscr-mask");
if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-psscr-mask",
count) != 0)
goto out;
if (of_property_read_u64_array(power_mgt, if (of_property_read_u64_array(power_mgt,
"ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) { "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
...@@ -292,8 +336,21 @@ static int powernv_add_idle_states(void) ...@@ -292,8 +336,21 @@ static int powernv_add_idle_states(void)
} }
} }
count = of_property_count_u32_elems(power_mgt,
"ibm,cpu-idle-state-residency-ns");
if (count < 0) {
rc = count;
} else if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
dt_idle_states,
"ibm,cpu-idle-state-residency-ns",
count) != 0) {
goto out;
} else {
rc = of_property_read_u32_array(power_mgt, rc = of_property_read_u32_array(power_mgt,
"ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states); "ibm,cpu-idle-state-residency-ns",
residency_ns, dt_idle_states);
}
for (i = 0; i < dt_idle_states; i++) { for (i = 0; i < dt_idle_states; i++) {
unsigned int exit_latency, target_residency; unsigned int exit_latency, target_residency;
......
...@@ -25,6 +25,35 @@ ...@@ -25,6 +25,35 @@
#define DEVFREQ_GOV_SUSPEND 0x4 #define DEVFREQ_GOV_SUSPEND 0x4
#define DEVFREQ_GOV_RESUME 0x5 #define DEVFREQ_GOV_RESUME 0x5
/**
* struct devfreq_governor - Devfreq policy governor
* @node: list node - contains registered devfreq governors
* @name: Governor's name
* @immutable: Immutable flag for governor. If the value is 1,
* this govenror is never changeable to other governor.
* @get_target_freq: Returns desired operating frequency for the device.
* Basically, get_target_freq will run
* devfreq_dev_profile.get_dev_status() to get the
* status of the device (load = busy_time / total_time).
* If no_central_polling is set, this callback is called
* only with update_devfreq() notified by OPP.
* @event_handler: Callback for devfreq core framework to notify events
* to governors. Events include per device governor
* init and exit, opp changes out of devfreq, suspend
* and resume of per device devfreq during device idle.
*
* Note that the callbacks are called with devfreq->lock locked by devfreq.
*/
struct devfreq_governor {
struct list_head node;
const char name[DEVFREQ_NAME_LEN];
const unsigned int immutable;
int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
int (*event_handler)(struct devfreq *devfreq,
unsigned int event, void *data);
};
/* Caution: devfreq->lock must be locked before calling update_devfreq */ /* Caution: devfreq->lock must be locked before calling update_devfreq */
extern int update_devfreq(struct devfreq *devfreq); extern int update_devfreq(struct devfreq *devfreq);
......
...@@ -43,6 +43,10 @@ ...@@ -43,6 +43,10 @@
#define RK3288_SOC_CON2_FLASH0 BIT(7) #define RK3288_SOC_CON2_FLASH0 BIT(7)
#define RK3288_SOC_FLASH_SUPPLY_NUM 2 #define RK3288_SOC_FLASH_SUPPLY_NUM 2
#define RK3328_SOC_CON4 0x410
#define RK3328_SOC_CON4_VCCIO2 BIT(7)
#define RK3328_SOC_VCCIO2_SUPPLY_NUM 1
#define RK3368_SOC_CON15 0x43c #define RK3368_SOC_CON15 0x43c
#define RK3368_SOC_CON15_FLASH0 BIT(14) #define RK3368_SOC_CON15_FLASH0 BIT(14)
#define RK3368_SOC_FLASH_SUPPLY_NUM 2 #define RK3368_SOC_FLASH_SUPPLY_NUM 2
...@@ -166,6 +170,25 @@ static void rk3288_iodomain_init(struct rockchip_iodomain *iod) ...@@ -166,6 +170,25 @@ static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
dev_warn(iod->dev, "couldn't update flash0 ctrl\n"); dev_warn(iod->dev, "couldn't update flash0 ctrl\n");
} }
static void rk3328_iodomain_init(struct rockchip_iodomain *iod)
{
int ret;
u32 val;
/* if no vccio2 supply we should leave things alone */
if (!iod->supplies[RK3328_SOC_VCCIO2_SUPPLY_NUM].reg)
return;
/*
* set vccio2 iodomain to also use this framework
* instead of a special gpio.
*/
val = RK3328_SOC_CON4_VCCIO2 | (RK3328_SOC_CON4_VCCIO2 << 16);
ret = regmap_write(iod->grf, RK3328_SOC_CON4, val);
if (ret < 0)
dev_warn(iod->dev, "couldn't update vccio2 vsel ctrl\n");
}
static void rk3368_iodomain_init(struct rockchip_iodomain *iod) static void rk3368_iodomain_init(struct rockchip_iodomain *iod)
{ {
int ret; int ret;
...@@ -247,6 +270,20 @@ static const struct rockchip_iodomain_soc_data soc_data_rk3288 = { ...@@ -247,6 +270,20 @@ static const struct rockchip_iodomain_soc_data soc_data_rk3288 = {
.init = rk3288_iodomain_init, .init = rk3288_iodomain_init,
}; };
static const struct rockchip_iodomain_soc_data soc_data_rk3328 = {
.grf_offset = 0x410,
.supply_names = {
"vccio1",
"vccio2",
"vccio3",
"vccio4",
"vccio5",
"vccio6",
"pmuio",
},
.init = rk3328_iodomain_init,
};
static const struct rockchip_iodomain_soc_data soc_data_rk3368 = { static const struct rockchip_iodomain_soc_data soc_data_rk3368 = {
.grf_offset = 0x900, .grf_offset = 0x900,
.supply_names = { .supply_names = {
...@@ -311,6 +348,10 @@ static const struct of_device_id rockchip_iodomain_match[] = { ...@@ -311,6 +348,10 @@ static const struct of_device_id rockchip_iodomain_match[] = {
.compatible = "rockchip,rk3288-io-voltage-domain", .compatible = "rockchip,rk3288-io-voltage-domain",
.data = (void *)&soc_data_rk3288 .data = (void *)&soc_data_rk3288
}, },
{
.compatible = "rockchip,rk3328-io-voltage-domain",
.data = (void *)&soc_data_rk3328
},
{ {
.compatible = "rockchip,rk3368-io-voltage-domain", .compatible = "rockchip,rk3368-io-voltage-domain",
.data = (void *)&soc_data_rk3368 .data = (void *)&soc_data_rk3368
......
...@@ -291,18 +291,6 @@ config ARMADA_THERMAL ...@@ -291,18 +291,6 @@ config ARMADA_THERMAL
Enable this option if you want to have support for thermal management Enable this option if you want to have support for thermal management
controller present in Armada 370 and Armada XP SoC. controller present in Armada 370 and Armada XP SoC.
config DB8500_CPUFREQ_COOLING
tristate "DB8500 cpufreq cooling"
depends on ARCH_U8500 || COMPILE_TEST
depends on HAS_IOMEM
depends on CPU_THERMAL
default y
help
Adds DB8500 cpufreq cooling devices, and these cooling devices can be
bound to thermal zone trip points. When a trip point reached, the
bound cpufreq cooling device turns active to set CPU frequency low to
cool down the CPU.
config INTEL_POWERCLAMP config INTEL_POWERCLAMP
tristate "Intel PowerClamp idle injection driver" tristate "Intel PowerClamp idle injection driver"
depends on THERMAL depends on THERMAL
......
...@@ -41,7 +41,6 @@ obj-$(CONFIG_TANGO_THERMAL) += tango_thermal.o ...@@ -41,7 +41,6 @@ obj-$(CONFIG_TANGO_THERMAL) += tango_thermal.o
obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o
obj-$(CONFIG_MAX77620_THERMAL) += max77620_thermal.o obj-$(CONFIG_MAX77620_THERMAL) += max77620_thermal.o
obj-$(CONFIG_QORIQ_THERMAL) += qoriq_thermal.o obj-$(CONFIG_QORIQ_THERMAL) += qoriq_thermal.o
obj-$(CONFIG_DB8500_CPUFREQ_COOLING) += db8500_cpufreq_cooling.o
obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o
obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o
obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE) += intel_soc_dts_iosf.o obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE) += intel_soc_dts_iosf.o
......
/*
* db8500_cpufreq_cooling.c - DB8500 cpufreq works as cooling device.
*
* Copyright (C) 2012 ST-Ericsson
* Copyright (C) 2012 Linaro Ltd.
*
* Author: Hongbo Zhang <hongbo.zhang@linaro.com>
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/cpu_cooling.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
static int db8500_cpufreq_cooling_probe(struct platform_device *pdev)
{
struct thermal_cooling_device *cdev;
cdev = cpufreq_cooling_register(cpu_present_mask);
if (IS_ERR(cdev)) {
int ret = PTR_ERR(cdev);
if (ret != -EPROBE_DEFER)
dev_err(&pdev->dev,
"Failed to register cooling device %d\n",
ret);
return ret;
}
platform_set_drvdata(pdev, cdev);
dev_info(&pdev->dev, "Cooling device registered: %s\n", cdev->type);
return 0;
}
static int db8500_cpufreq_cooling_remove(struct platform_device *pdev)
{
struct thermal_cooling_device *cdev = platform_get_drvdata(pdev);
cpufreq_cooling_unregister(cdev);
return 0;
}
static int db8500_cpufreq_cooling_suspend(struct platform_device *pdev,
pm_message_t state)
{
return -ENOSYS;
}
static int db8500_cpufreq_cooling_resume(struct platform_device *pdev)
{
return -ENOSYS;
}
#ifdef CONFIG_OF
static const struct of_device_id db8500_cpufreq_cooling_match[] = {
{ .compatible = "stericsson,db8500-cpufreq-cooling" },
{},
};
MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match);
#endif
static struct platform_driver db8500_cpufreq_cooling_driver = {
.driver = {
.name = "db8500-cpufreq-cooling",
.of_match_table = of_match_ptr(db8500_cpufreq_cooling_match),
},
.probe = db8500_cpufreq_cooling_probe,
.suspend = db8500_cpufreq_cooling_suspend,
.resume = db8500_cpufreq_cooling_resume,
.remove = db8500_cpufreq_cooling_remove,
};
static int __init db8500_cpufreq_cooling_init(void)
{
return platform_driver_register(&db8500_cpufreq_cooling_driver);
}
static void __exit db8500_cpufreq_cooling_exit(void)
{
platform_driver_unregister(&db8500_cpufreq_cooling_driver);
}
/* Should be later than db8500_cpufreq_register */
late_initcall(db8500_cpufreq_cooling_init);
module_exit(db8500_cpufreq_cooling_exit);
MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
MODULE_DESCRIPTION("DB8500 cpufreq cooling driver");
MODULE_LICENSE("GPL");
...@@ -120,6 +120,13 @@ struct cpufreq_policy { ...@@ -120,6 +120,13 @@ struct cpufreq_policy {
bool fast_switch_possible; bool fast_switch_possible;
bool fast_switch_enabled; bool fast_switch_enabled;
/*
* Preferred average time interval between consecutive invocations of
* the driver to set the frequency for this policy. To be set by the
* scaling driver (0, which is the default, means no preference).
*/
unsigned int transition_delay_us;
/* Cached frequency lookup from cpufreq_driver_resolve_freq. */ /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
unsigned int cached_target_freq; unsigned int cached_target_freq;
int cached_resolved_idx; int cached_resolved_idx;
......
...@@ -27,6 +27,7 @@ ...@@ -27,6 +27,7 @@
#define DEVFREQ_POSTCHANGE (1) #define DEVFREQ_POSTCHANGE (1)
struct devfreq; struct devfreq;
struct devfreq_governor;
/** /**
* struct devfreq_dev_status - Data given from devfreq user device to * struct devfreq_dev_status - Data given from devfreq user device to
...@@ -100,35 +101,6 @@ struct devfreq_dev_profile { ...@@ -100,35 +101,6 @@ struct devfreq_dev_profile {
unsigned int max_state; unsigned int max_state;
}; };
/**
* struct devfreq_governor - Devfreq policy governor
* @node: list node - contains registered devfreq governors
* @name: Governor's name
* @immutable: Immutable flag for governor. If the value is 1,
* this govenror is never changeable to other governor.
* @get_target_freq: Returns desired operating frequency for the device.
* Basically, get_target_freq will run
* devfreq_dev_profile.get_dev_status() to get the
* status of the device (load = busy_time / total_time).
* If no_central_polling is set, this callback is called
* only with update_devfreq() notified by OPP.
* @event_handler: Callback for devfreq core framework to notify events
* to governors. Events include per device governor
* init and exit, opp changes out of devfreq, suspend
* and resume of per device devfreq during device idle.
*
* Note that the callbacks are called with devfreq->lock locked by devfreq.
*/
struct devfreq_governor {
struct list_head node;
const char name[DEVFREQ_NAME_LEN];
const unsigned int immutable;
int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
int (*event_handler)(struct devfreq *devfreq,
unsigned int event, void *data);
};
/** /**
* struct devfreq - Device devfreq structure * struct devfreq - Device devfreq structure
* @node: list node - contains the devices with devfreq that have been * @node: list node - contains the devices with devfreq that have been
......
...@@ -20,6 +20,7 @@ ...@@ -20,6 +20,7 @@
/* Defines used for the flags field in the struct generic_pm_domain */ /* Defines used for the flags field in the struct generic_pm_domain */
#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */
#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ #define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */
#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */
enum gpd_status { enum gpd_status {
GPD_STATE_ACTIVE = 0, /* PM domain is active */ GPD_STATE_ACTIVE = 0, /* PM domain is active */
......
...@@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void); ...@@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void);
extern void tick_nohz_idle_exit(void); extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void); extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void); extern ktime_t tick_nohz_get_sleep_length(void);
extern unsigned long tick_nohz_get_idle_calls(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */ #else /* !CONFIG_NO_HZ_COMMON */
......
...@@ -61,6 +61,11 @@ struct sugov_cpu { ...@@ -61,6 +61,11 @@ struct sugov_cpu {
unsigned long util; unsigned long util;
unsigned long max; unsigned long max;
unsigned int flags; unsigned int flags;
/* The field below is for single-CPU policies only. */
#ifdef CONFIG_NO_HZ_COMMON
unsigned long saved_idle_calls;
#endif
}; };
static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu); static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
...@@ -93,22 +98,23 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, ...@@ -93,22 +98,23 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
{ {
struct cpufreq_policy *policy = sg_policy->policy; struct cpufreq_policy *policy = sg_policy->policy;
if (sg_policy->next_freq == next_freq)
return;
if (sg_policy->next_freq > next_freq)
next_freq = (sg_policy->next_freq + next_freq) >> 1;
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time; sg_policy->last_freq_update_time = time;
if (policy->fast_switch_enabled) { if (policy->fast_switch_enabled) {
if (sg_policy->next_freq == next_freq) {
trace_cpu_frequency(policy->cur, smp_processor_id());
return;
}
sg_policy->next_freq = next_freq;
next_freq = cpufreq_driver_fast_switch(policy, next_freq); next_freq = cpufreq_driver_fast_switch(policy, next_freq);
if (next_freq == CPUFREQ_ENTRY_INVALID) if (next_freq == CPUFREQ_ENTRY_INVALID)
return; return;
policy->cur = next_freq; policy->cur = next_freq;
trace_cpu_frequency(next_freq, smp_processor_id()); trace_cpu_frequency(next_freq, smp_processor_id());
} else if (sg_policy->next_freq != next_freq) { } else {
sg_policy->next_freq = next_freq;
sg_policy->work_in_progress = true; sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work); irq_work_queue(&sg_policy->irq_work);
} }
...@@ -192,6 +198,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util, ...@@ -192,6 +198,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
sg_cpu->iowait_boost >>= 1; sg_cpu->iowait_boost >>= 1;
} }
#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
unsigned long idle_calls = tick_nohz_get_idle_calls();
bool ret = idle_calls == sg_cpu->saved_idle_calls;
sg_cpu->saved_idle_calls = idle_calls;
return ret;
}
#else
static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
#endif /* CONFIG_NO_HZ_COMMON */
static void sugov_update_single(struct update_util_data *hook, u64 time, static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned int flags) unsigned int flags)
{ {
...@@ -200,6 +219,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, ...@@ -200,6 +219,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
struct cpufreq_policy *policy = sg_policy->policy; struct cpufreq_policy *policy = sg_policy->policy;
unsigned long util, max; unsigned long util, max;
unsigned int next_f; unsigned int next_f;
bool busy;
sugov_set_iowait_boost(sg_cpu, time, flags); sugov_set_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time; sg_cpu->last_update = time;
...@@ -207,40 +227,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, ...@@ -207,40 +227,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time)) if (!sugov_should_update_freq(sg_policy, time))
return; return;
busy = sugov_cpu_is_busy(sg_cpu);
if (flags & SCHED_CPUFREQ_RT_DL) { if (flags & SCHED_CPUFREQ_RT_DL) {
next_f = policy->cpuinfo.max_freq; next_f = policy->cpuinfo.max_freq;
} else { } else {
sugov_get_util(&util, &max); sugov_get_util(&util, &max);
sugov_iowait_boost(sg_cpu, &util, &max); sugov_iowait_boost(sg_cpu, &util, &max);
next_f = get_next_freq(sg_policy, util, max); next_f = get_next_freq(sg_policy, util, max);
/*
* Do not reduce the frequency if the CPU has not been idle
* recently, as the reduction is likely to be premature then.
*/
if (busy && next_f < sg_policy->next_freq)
next_f = sg_policy->next_freq;
} }
sugov_update_commit(sg_policy, time, next_f); sugov_update_commit(sg_policy, time, next_f);
} }
static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
unsigned long util, unsigned long max,
unsigned int flags)
{ {
struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy; struct cpufreq_policy *policy = sg_policy->policy;
unsigned int max_f = policy->cpuinfo.max_freq;
u64 last_freq_update_time = sg_policy->last_freq_update_time; u64 last_freq_update_time = sg_policy->last_freq_update_time;
unsigned long util = 0, max = 1;
unsigned int j; unsigned int j;
if (flags & SCHED_CPUFREQ_RT_DL)
return max_f;
sugov_iowait_boost(sg_cpu, &util, &max);
for_each_cpu(j, policy->cpus) { for_each_cpu(j, policy->cpus) {
struct sugov_cpu *j_sg_cpu; struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max; unsigned long j_util, j_max;
s64 delta_ns; s64 delta_ns;
if (j == smp_processor_id())
continue;
j_sg_cpu = &per_cpu(sugov_cpu, j);
/* /*
* If the CPU utilization was last updated before the previous * If the CPU utilization was last updated before the previous
* frequency update and the time elapsed between the last update * frequency update and the time elapsed between the last update
...@@ -254,7 +271,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, ...@@ -254,7 +271,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
continue; continue;
} }
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL) if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
return max_f; return policy->cpuinfo.max_freq;
j_util = j_sg_cpu->util; j_util = j_sg_cpu->util;
j_max = j_sg_cpu->max; j_max = j_sg_cpu->max;
...@@ -289,7 +306,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, ...@@ -289,7 +306,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
sg_cpu->last_update = time; sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) { if (sugov_should_update_freq(sg_policy, time)) {
next_f = sugov_next_freq_shared(sg_cpu, util, max, flags); if (flags & SCHED_CPUFREQ_RT_DL)
next_f = sg_policy->policy->cpuinfo.max_freq;
else
next_f = sugov_next_freq_shared(sg_cpu);
sugov_update_commit(sg_policy, time, next_f); sugov_update_commit(sg_policy, time, next_f);
} }
...@@ -473,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy) ...@@ -473,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy)
{ {
struct sugov_policy *sg_policy; struct sugov_policy *sg_policy;
struct sugov_tunables *tunables; struct sugov_tunables *tunables;
unsigned int lat;
int ret = 0; int ret = 0;
/* State should be equivalent to EXIT */ /* State should be equivalent to EXIT */
...@@ -512,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy) ...@@ -512,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy)
goto stop_kthread; goto stop_kthread;
} }
if (policy->transition_delay_us) {
tunables->rate_limit_us = policy->transition_delay_us;
} else {
unsigned int lat;
tunables->rate_limit_us = LATENCY_MULTIPLIER; tunables->rate_limit_us = LATENCY_MULTIPLIER;
lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC; lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
if (lat) if (lat)
tunables->rate_limit_us *= lat; tunables->rate_limit_us *= lat;
}
policy->governor_data = sg_policy; policy->governor_data = sg_policy;
sg_policy->tunables = tunables; sg_policy->tunables = tunables;
......
...@@ -993,6 +993,18 @@ ktime_t tick_nohz_get_sleep_length(void) ...@@ -993,6 +993,18 @@ ktime_t tick_nohz_get_sleep_length(void)
return ts->sleep_length; return ts->sleep_length;
} }
/**
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
* Called from the schedutil frequency scaling governor in scheduler context.
*/
unsigned long tick_nohz_get_idle_calls(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
return ts->idle_calls;
}
static void tick_nohz_account_idle_ticks(struct tick_sched *ts) static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
{ {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
......
PREFIX ?= /usr
DESTDIR ?=
all:
@echo "Nothing to build"
install :
install -d $(DESTDIR)$(PREFIX)/lib/pm-graph
install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph
install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph
ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py $(DESTDIR)$(PREFIX)/bin/bootgraph
ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py $(DESTDIR)$(PREFIX)/bin/sleepgraph
install -d $(DESTDIR)$(PREFIX)/share/man/man8
install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
uninstall :
rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8
rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8
rm $(DESTDIR)$(PREFIX)/bin/bootgraph
rm $(DESTDIR)$(PREFIX)/bin/sleepgraph
rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py
rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py
rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph
#!/usr/bin/python
#
# Tool for analyzing boot timing
# Copyright (c) 2013, Intel Corporation.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms and conditions of the GNU General Public License,
# version 2, as published by the Free Software Foundation.
#
# This program is distributed in the hope it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
# more details.
#
# Authors:
# Todd Brandt <todd.e.brandt@linux.intel.com>
#
# Description:
# This tool is designed to assist kernel and OS developers in optimizing
# their linux stack's boot time. It creates an html representation of
# the kernel boot timeline up to the start of the init process.
#
# ----------------- LIBRARIES --------------------
import sys
import time
import os
import string
import re
import platform
import shutil
from datetime import datetime, timedelta
from subprocess import call, Popen, PIPE
import analyze_suspend as aslib
# ----------------- CLASSES --------------------
# Class: SystemValues
# Description:
# A global, single-instance container used to
# store system values and test parameters
class SystemValues(aslib.SystemValues):
title = 'BootGraph'
version = 2.0
hostname = 'localhost'
testtime = ''
kernel = ''
dmesgfile = ''
ftracefile = ''
htmlfile = 'bootgraph.html'
outfile = ''
phoronix = False
addlogs = False
useftrace = False
usedevsrc = True
suspendmode = 'boot'
max_graph_depth = 2
graph_filter = 'do_one_initcall'
reboot = False
manual = False
iscronjob = False
timeformat = '%.6f'
def __init__(self):
if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
self.phoronix = True
self.addlogs = True
self.outfile = os.environ['LOG_FILE']
self.htmlfile = os.environ['LOG_FILE']
self.hostname = platform.node()
self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S')
if os.path.exists('/proc/version'):
fp = open('/proc/version', 'r')
val = fp.read().strip()
fp.close()
self.kernel = self.kernelVersion(val)
else:
self.kernel = 'unknown'
def kernelVersion(self, msg):
return msg.split()[2]
def kernelParams(self):
cmdline = 'initcall_debug log_buf_len=32M'
if self.useftrace:
cmdline += ' trace_buf_size=128M trace_clock=global '\
'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\
'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\
'nofuncgraph-overhead,context-info,graph-time '\
'ftrace=function_graph '\
'ftrace_graph_max_depth=%d '\
'ftrace_graph_filter=%s' % \
(self.max_graph_depth, self.graph_filter)
return cmdline
def setGraphFilter(self, val):
fp = open(self.tpath+'available_filter_functions')
master = fp.read().split('\n')
fp.close()
for i in val.split(','):
func = i.strip()
if func not in master:
doError('function "%s" not available for ftrace' % func)
self.graph_filter = val
def cronjobCmdString(self):
cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0])
args = iter(sys.argv[1:])
for arg in args:
if arg in ['-h', '-v', '-cronjob', '-reboot']:
continue
elif arg in ['-o', '-dmesg', '-ftrace', '-filter']:
args.next()
continue
cmdline += ' '+arg
if self.graph_filter != 'do_one_initcall':
cmdline += ' -filter "%s"' % self.graph_filter
cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile)
return cmdline
def manualRebootRequired(self):
cmdline = self.kernelParams()
print 'To generate a new timeline manually, follow these steps:\n'
print '1. Add the CMDLINE string to your kernel command line.'
print '2. Reboot the system.'
print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n'
print 'CMDLINE="%s"' % cmdline
sys.exit()
sysvals = SystemValues()
# Class: Data
# Description:
# The primary container for test data.
class Data(aslib.Data):
dmesg = {} # root data structure
start = 0.0 # test start
end = 0.0 # test end
dmesgtext = [] # dmesg text file in memory
testnumber = 0
idstr = ''
html_device_id = 0
valid = False
initstart = 0.0
boottime = ''
phases = ['boot']
do_one_initcall = False
def __init__(self, num):
self.testnumber = num
self.idstr = 'a'
self.dmesgtext = []
self.dmesg = {
'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'}
}
def deviceTopology(self):
return ''
def newAction(self, phase, name, start, end, ret, ulen):
# new device callback for a specific phase
self.html_device_id += 1
devid = '%s%d' % (self.idstr, self.html_device_id)
list = self.dmesg[phase]['list']
length = -1.0
if(start >= 0 and end >= 0):
length = end - start
i = 2
origname = name
while(name in list):
name = '%s[%d]' % (origname, i)
i += 1
list[name] = {'name': name, 'start': start, 'end': end,
'pid': 0, 'length': length, 'row': 0, 'id': devid,
'ret': ret, 'ulen': ulen }
return name
def deviceMatch(self, cg):
if cg.end - cg.start == 0:
return True
list = self.dmesg['boot']['list']
for devname in list:
dev = list[devname]
if cg.name == 'do_one_initcall':
if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0):
dev['ftrace'] = cg
self.do_one_initcall = True
return True
else:
if(cg.start > dev['start'] and cg.end < dev['end']):
if 'ftraces' not in dev:
dev['ftraces'] = []
dev['ftraces'].append(cg)
return True
return False
# ----------------- FUNCTIONS --------------------
# Function: loadKernelLog
# Description:
# Load a raw kernel log from dmesg
def loadKernelLog():
data = Data(0)
data.dmesg['boot']['start'] = data.start = ktime = 0.0
sysvals.stamp = {
'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'),
'host': sysvals.hostname,
'mode': 'boot', 'kernel': ''}
devtemp = dict()
if(sysvals.dmesgfile):
lf = open(sysvals.dmesgfile, 'r')
else:
lf = Popen('dmesg', stdout=PIPE).stdout
for line in lf:
line = line.replace('\r\n', '')
idx = line.find('[')
if idx > 1:
line = line[idx:]
m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
if(not m):
continue
ktime = float(m.group('ktime'))
if(ktime > 120):
break
msg = m.group('msg')
data.end = data.initstart = ktime
data.dmesgtext.append(line)
if(ktime == 0.0 and re.match('^Linux version .*', msg)):
if(not sysvals.stamp['kernel']):
sysvals.stamp['kernel'] = sysvals.kernelVersion(msg)
continue
m = re.match('.* setting system clock to (?P<t>.*) UTC.*', msg)
if(m):
bt = datetime.strptime(m.group('t'), '%Y-%m-%d %H:%M:%S')
bt = bt - timedelta(seconds=int(ktime))
data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S')
sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p')
continue
m = re.match('^calling *(?P<f>.*)\+.*', msg)
if(m):
devtemp[m.group('f')] = ktime
continue
m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg)
if(m):
data.valid = True
f, r, t = m.group('f', 'r', 't')
if(f in devtemp):
data.newAction('boot', f, devtemp[f], ktime, int(r), int(t))
data.end = ktime
del devtemp[f]
continue
if(re.match('^Freeing unused kernel memory.*', msg)):
break
data.dmesg['boot']['end'] = data.end
lf.close()
return data
# Function: loadTraceLog
# Description:
# Check if trace is available and copy to a temp file
def loadTraceLog(data):
# load the data to a temp file if none given
if not sysvals.ftracefile:
lib = aslib.sysvals
aslib.rootCheck(True)
if not lib.verifyFtrace():
doError('ftrace not available')
if lib.fgetVal('current_tracer').strip() != 'function_graph':
doError('ftrace not configured for a boot callgraph')
sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid()
call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True)
if not sysvals.ftracefile:
doError('No trace data available')
# parse the trace log
ftemp = dict()
tp = aslib.TestProps()
tp.setTracerType('function_graph')
tf = open(sysvals.ftracefile, 'r')
for line in tf:
if line[0] == '#':
continue
m = re.match(tp.ftrace_line_fmt, line.strip())
if(not m):
continue
m_time, m_proc, m_pid, m_msg, m_dur = \
m.group('time', 'proc', 'pid', 'msg', 'dur')
if float(m_time) > data.end:
break
if(m_time and m_pid and m_msg):
t = aslib.FTraceLine(m_time, m_msg, m_dur)
pid = int(m_pid)
else:
continue
if t.fevent or t.fkprobe:
continue
key = (m_proc, pid)
if(key not in ftemp):
ftemp[key] = []
ftemp[key].append(aslib.FTraceCallGraph(pid))
cg = ftemp[key][-1]
if(cg.addLine(t)):
ftemp[key].append(aslib.FTraceCallGraph(pid))
tf.close()
# add the callgraph data to the device hierarchy
for key in ftemp:
proc, pid = key
for cg in ftemp[key]:
if len(cg.list) < 1 or cg.invalid:
continue
if(not cg.postProcess()):
print('Sanity check failed for %s-%d' % (proc, pid))
continue
# match cg data to devices
if not data.deviceMatch(cg):
print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end)
# Function: colorForName
# Description:
# Generate a repeatable color from a list for a given name
def colorForName(name):
list = [
('c1', '#ec9999'),
('c2', '#ffc1a6'),
('c3', '#fff0a6'),
('c4', '#adf199'),
('c5', '#9fadea'),
('c6', '#a699c1'),
('c7', '#ad99b4'),
('c8', '#eaffea'),
('c9', '#dcecfb'),
('c10', '#ffffea')
]
i = 0
total = 0
count = len(list)
while i < len(name):
total += ord(name[i])
i += 1
return list[total % count]
def cgOverview(cg, minlen):
stats = dict()
large = []
for l in cg.list:
if l.fcall and l.depth == 1:
if l.length >= minlen:
large.append(l)
if l.name not in stats:
stats[l.name] = [0, 0.0]
stats[l.name][0] += (l.length * 1000.0)
stats[l.name][1] += 1
return (large, stats)
# Function: createBootGraph
# Description:
# Create the output html file from the resident test data
# Arguments:
# testruns: array of Data objects from parseKernelLog or parseTraceLog
# Output:
# True if the html file was created, false if it failed
def createBootGraph(data, embedded):
# html function templates
html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n'
html_timetotal = '<table class="time1">\n<tr>'\
'<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\
'</tr>\n</table>\n'
# device timeline
devtl = aslib.Timeline(100, 20)
# write the test title and general info header
devtl.createHeader(sysvals, 'noftrace')
# Generate the header for this timeline
t0 = data.start
tMax = data.end
tTotal = tMax - t0
if(tTotal == 0):
print('ERROR: No timeline data')
return False
boot_time = '%.0f'%(tTotal*1000)
devtl.html += html_timetotal.format(boot_time)
# determine the maximum number of rows we need to draw
phase = 'boot'
list = data.dmesg[phase]['list']
devlist = []
for devname in list:
d = aslib.DevItem(0, phase, list[devname])
devlist.append(d)
devtl.getPhaseRows(devlist)
devtl.calcTotalRows()
# draw the timeline background
devtl.createZoomBox()
boot = data.dmesg[phase]
length = boot['end']-boot['start']
left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal)
width = '%.3f' % ((length*100.0)/tTotal)
devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH)
devtl.html += devtl.html_phase.format('0', '100', \
'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
'white', '')
# draw the device timeline
num = 0
devstats = dict()
for devname in sorted(list):
cls, color = colorForName(devname)
dev = list[devname]
info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0,
dev['ulen']/1000.0, dev['ret'])
devstats[dev['id']] = {'info':info}
dev['color'] = color
height = devtl.phaseRowHeight(0, phase, dev['row'])
top = '%.6f' % ((dev['row']*height) + devtl.scaleH)
left = '%.6f' % (((dev['start']-t0)*100)/tTotal)
width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal)
length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
devtl.html += devtl.html_device.format(dev['id'],
devname+length+'kernel_mode', left, top, '%.3f'%height,
width, devname, ' '+cls, '')
rowtop = devtl.phaseRowTop(0, phase, dev['row'])
height = '%.6f' % (devtl.rowH / 2)
top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2))
if data.do_one_initcall:
if('ftrace' not in dev):
continue
cg = dev['ftrace']
large, stats = cgOverview(cg, 0.001)
devstats[dev['id']]['fstat'] = stats
for l in large:
left = '%f' % (((l.time-t0)*100)/tTotal)
width = '%f' % (l.length*100/tTotal)
title = '%s (%0.3fms)' % (l.name, l.length * 1000.0)
devtl.html += html_srccall.format(l.name, left,
top, height, width, title, 'x%d'%num)
num += 1
continue
if('ftraces' not in dev):
continue
for cg in dev['ftraces']:
left = '%f' % (((cg.start-t0)*100)/tTotal)
width = '%f' % ((cg.end-cg.start)*100/tTotal)
cglen = (cg.end - cg.start) * 1000.0
title = '%s (%0.3fms)' % (cg.name, cglen)
cg.id = 'x%d' % num
devtl.html += html_srccall.format(cg.name, left,
top, height, width, title, dev['id']+cg.id)
num += 1
# draw the time scale, try to make the number of labels readable
devtl.createTimeScale(t0, tMax, tTotal, phase)
devtl.html += '</div>\n'
# timeline is finished
devtl.html += '</div>\n</div>\n'
if(sysvals.outfile == sysvals.htmlfile):
hf = open(sysvals.htmlfile, 'a')
else:
hf = open(sysvals.htmlfile, 'w')
# add the css if this is not an embedded run
extra = '\
.c1 {background:rgba(209,0,0,0.4);}\n\
.c2 {background:rgba(255,102,34,0.4);}\n\
.c3 {background:rgba(255,218,33,0.4);}\n\
.c4 {background:rgba(51,221,0,0.4);}\n\
.c5 {background:rgba(17,51,204,0.4);}\n\
.c6 {background:rgba(34,0,102,0.4);}\n\
.c7 {background:rgba(51,0,68,0.4);}\n\
.c8 {background:rgba(204,255,204,0.4);}\n\
.c9 {background:rgba(169,208,245,0.4);}\n\
.c10 {background:rgba(255,255,204,0.4);}\n\
.vt {transform:rotate(-60deg);transform-origin:0 0;}\n\
table.fstat {table-layout:fixed;padding:150px 15px 0 0;font-size:10px;column-width:30px;}\n\
.fstat th {width:55px;}\n\
.fstat td {text-align:left;width:35px;}\n\
.srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
.srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n'
if(not embedded):
aslib.addCSS(hf, sysvals, 1, False, extra)
# write the device timeline
hf.write(devtl.html)
# add boot specific html
statinfo = 'var devstats = {\n'
for n in sorted(devstats):
statinfo += '\t"%s": [\n\t\t"%s",\n' % (n, devstats[n]['info'])
if 'fstat' in devstats[n]:
funcs = devstats[n]['fstat']
for f in sorted(funcs, key=funcs.get, reverse=True):
if funcs[f][0] < 0.01 and len(funcs) > 10:
break
statinfo += '\t\t"%f|%s|%d",\n' % (funcs[f][0], f, funcs[f][1])
statinfo += '\t],\n'
statinfo += '};\n'
html = \
'<div id="devicedetailtitle"></div>\n'\
'<div id="devicedetail" style="display:none;">\n'\
'<div id="devicedetail0">\n'\
'<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\
'</div>\n</div>\n'\
'<script type="text/javascript">\n'+statinfo+\
'</script>\n'
hf.write(html)
# add the callgraph html
if(sysvals.usecallgraph):
aslib.addCallgraphs(sysvals, hf, data)
# add the dmesg log as a hidden div
if sysvals.addlogs:
hf.write('<div id="dmesglog" style="display:none;">\n')
for line in data.dmesgtext:
line = line.replace('<', '&lt').replace('>', '&gt')
hf.write(line)
hf.write('</div>\n')
if(not embedded):
# write the footer and close
aslib.addScriptCode(hf, [data])
hf.write('</body>\n</html>\n')
else:
# embedded out will be loaded in a page, skip the js
hf.write('<div id=bounds style=display:none>%f,%f</div>' % \
(data.start*1000, data.initstart*1000))
hf.close()
return True
# Function: updateCron
# Description:
# (restore=False) Set the tool to run automatically on reboot
# (restore=True) Restore the original crontab
def updateCron(restore=False):
if not restore:
sysvals.rootUser(True)
crondir = '/var/spool/cron/crontabs/'
cronfile = crondir+'root'
backfile = crondir+'root-analyze_boot-backup'
if not os.path.exists(crondir):
doError('%s not found' % crondir)
out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read()
if not out:
doError('crontab not found')
# on restore: move the backup cron back into place
if restore:
if os.path.exists(backfile):
shutil.move(backfile, cronfile)
return
# backup current cron and install new one with reboot
if os.path.exists(cronfile):
shutil.move(cronfile, backfile)
else:
fp = open(backfile, 'w')
fp.close()
res = -1
try:
fp = open(backfile, 'r')
op = open(cronfile, 'w')
for line in fp:
if '@reboot' not in line:
op.write(line)
continue
fp.close()
op.write('@reboot python %s\n' % sysvals.cronjobCmdString())
op.close()
res = call('crontab %s' % cronfile, shell=True)
except Exception, e:
print 'Exception: %s' % str(e)
shutil.move(backfile, cronfile)
res = -1
if res != 0:
doError('crontab failed')
# Function: updateGrub
# Description:
# update grub.cfg for all kernels with our parameters
def updateGrub(restore=False):
# call update-grub on restore
if restore:
try:
call(['update-grub'], stderr=PIPE, stdout=PIPE,
env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'})
except Exception, e:
print 'Exception: %s\n' % str(e)
return
# verify we can do this
sysvals.rootUser(True)
grubfile = '/etc/default/grub'
if not os.path.exists(grubfile):
print 'ERROR: Unable to set the kernel parameters via grub.\n'
sysvals.manualRebootRequired()
out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read()
if not out:
print 'ERROR: Unable to set the kernel parameters via grub.\n'
sysvals.manualRebootRequired()
# extract the option and create a grub config without it
tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT'
cmdline = ''
tempfile = '/etc/default/grub.analyze_boot'
shutil.move(grubfile, tempfile)
res = -1
try:
fp = open(tempfile, 'r')
op = open(grubfile, 'w')
cont = False
for line in fp:
line = line.strip()
if len(line) == 0 or line[0] == '#':
continue
opt = line.split('=')[0].strip()
if opt == tgtopt:
cmdline = line.split('=', 1)[1].strip('\\')
if line[-1] == '\\':
cont = True
elif cont:
cmdline += line.strip('\\')
if line[-1] != '\\':
cont = False
else:
op.write('%s\n' % line)
fp.close()
# if the target option value is in quotes, strip them
sp = '"'
val = cmdline.strip()
if val[0] == '\'' or val[0] == '"':
sp = val[0]
val = val.strip(sp)
cmdline = val
# append our cmd line options
if len(cmdline) > 0:
cmdline += ' '
cmdline += sysvals.kernelParams()
# write out the updated target option
op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp))
op.close()
res = call('update-grub')
os.remove(grubfile)
except Exception, e:
print 'Exception: %s' % str(e)
res = -1
# cleanup
shutil.move(tempfile, grubfile)
if res != 0:
doError('update-grub failed')
# Function: doError
# Description:
# generic error function for catastrphic failures
# Arguments:
# msg: the error message to print
# help: True if printHelp should be called after, False otherwise
def doError(msg, help=False):
if help == True:
printHelp()
print 'ERROR: %s\n' % msg
sys.exit()
# Function: printHelp
# Description:
# print out the help text
def printHelp():
print('')
print('%s v%.1f' % (sysvals.title, sysvals.version))
print('Usage: bootgraph <options> <command>')
print('')
print('Description:')
print(' This tool reads in a dmesg log of linux kernel boot and')
print(' creates an html representation of the boot timeline up to')
print(' the start of the init process.')
print('')
print(' If no specific command is given the tool reads the current dmesg')
print(' and/or ftrace log and outputs bootgraph.html')
print('')
print('Options:')
print(' -h Print this help text')
print(' -v Print the current tool version')
print(' -addlogs Add the dmesg log to the html output')
print(' -o file Html timeline name (default: bootgraph.html)')
print(' [advanced]')
print(' -f Use ftrace to add function detail (default: disabled)')
print(' -callgraph Add callgraph detail, can be very large (default: disabled)')
print(' -maxdepth N limit the callgraph data to N call levels (default: 2)')
print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
print(' -timeprec N Number of significant digits in timestamps (0:S, 3:ms, [6:us])')
print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)')
print(' -filter list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
print(' [commands]')
print(' -reboot Reboot the machine automatically and generate a new timeline')
print(' -manual Show the requirements to generate a new timeline manually')
print(' -dmesg file Load a stored dmesg file (used with -ftrace)')
print(' -ftrace file Load a stored ftrace file (used with -dmesg)')
print(' -flistall Print all functions capable of being captured in ftrace')
print('')
return True
# ----------------- MAIN --------------------
# exec start (skipped if script is loaded as library)
if __name__ == '__main__':
# loop through the command line arguments
cmd = ''
simplecmds = ['-updategrub', '-flistall']
args = iter(sys.argv[1:])
for arg in args:
if(arg == '-h'):
printHelp()
sys.exit()
elif(arg == '-v'):
print("Version %.1f" % sysvals.version)
sys.exit()
elif(arg in simplecmds):
cmd = arg[1:]
elif(arg == '-f'):
sysvals.useftrace = True
elif(arg == '-callgraph'):
sysvals.useftrace = True
sysvals.usecallgraph = True
elif(arg == '-mincg'):
sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0)
elif(arg == '-timeprec'):
sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6))
elif(arg == '-maxdepth'):
sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000)
elif(arg == '-filter'):
try:
val = args.next()
except:
doError('No filter functions supplied', True)
aslib.rootCheck(True)
sysvals.setGraphFilter(val)
elif(arg == '-ftrace'):
try:
val = args.next()
except:
doError('No ftrace file supplied', True)
if(os.path.exists(val) == False):
doError('%s does not exist' % val)
sysvals.ftracefile = val
elif(arg == '-addlogs'):
sysvals.addlogs = True
elif(arg == '-expandcg'):
sysvals.cgexp = True
elif(arg == '-dmesg'):
try:
val = args.next()
except:
doError('No dmesg file supplied', True)
if(os.path.exists(val) == False):
doError('%s does not exist' % val)
if(sysvals.htmlfile == val or sysvals.outfile == val):
doError('Output filename collision')
sysvals.dmesgfile = val
elif(arg == '-o'):
try:
val = args.next()
except:
doError('No HTML filename supplied', True)
if(sysvals.dmesgfile == val or sysvals.ftracefile == val):
doError('Output filename collision')
sysvals.htmlfile = val
elif(arg == '-reboot'):
if sysvals.iscronjob:
doError('-reboot and -cronjob are incompatible')
sysvals.reboot = True
elif(arg == '-manual'):
sysvals.reboot = True
sysvals.manual = True
# remaining options are only for cron job use
elif(arg == '-cronjob'):
sysvals.iscronjob = True
if sysvals.reboot:
doError('-reboot and -cronjob are incompatible')
else:
doError('Invalid argument: '+arg, True)
if cmd != '':
if cmd == 'updategrub':
updateGrub()
elif cmd == 'flistall':
sysvals.getFtraceFilterFunctions(False)
sys.exit()
# update grub, setup a cronjob, and reboot
if sysvals.reboot:
if not sysvals.manual:
updateGrub()
updateCron()
call('reboot')
else:
sysvals.manualRebootRequired()
sys.exit()
# disable the cronjob
if sysvals.iscronjob:
updateCron(True)
updateGrub(True)
data = loadKernelLog()
if sysvals.useftrace:
loadTraceLog(data)
if sysvals.iscronjob:
try:
sysvals.fsetVal('0', 'tracing_on')
except:
pass
if(sysvals.outfile and sysvals.phoronix):
fp = open(sysvals.outfile, 'w')
fp.write('pass %s initstart %.3f end %.3f boot %s\n' %
(data.valid, data.initstart*1000, data.end*1000, data.boottime))
fp.close()
if(not data.valid):
if sysvals.dmesgfile:
doError('No initcall data found in %s' % sysvals.dmesgfile)
else:
doError('No initcall data found, is initcall_debug enabled?')
print(' Host: %s' % sysvals.hostname)
print(' Test time: %s' % sysvals.testtime)
print(' Boot time: %s' % data.boottime)
print('Kernel Version: %s' % sysvals.kernel)
print(' Kernel start: %.3f' % (data.start * 1000))
print(' init start: %.3f' % (data.initstart * 1000))
createBootGraph(data, sysvals.phoronix)
...@@ -12,10 +12,6 @@ ...@@ -12,10 +12,6 @@
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
# more details. # more details.
# #
# You should have received a copy of the GNU General Public License along with
# this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
#
# Authors: # Authors:
# Todd Brandt <todd.e.brandt@linux.intel.com> # Todd Brandt <todd.e.brandt@linux.intel.com>
# #
...@@ -23,7 +19,7 @@ ...@@ -23,7 +19,7 @@
# Home Page # Home Page
# https://01.org/suspendresume # https://01.org/suspendresume
# Source repo # Source repo
# https://github.com/01org/suspendresume # https://github.com/01org/pm-graph
# #
# Description: # Description:
# This tool is designed to assist kernel and OS developers in optimizing # This tool is designed to assist kernel and OS developers in optimizing
...@@ -71,14 +67,16 @@ from subprocess import call, Popen, PIPE ...@@ -71,14 +67,16 @@ from subprocess import call, Popen, PIPE
# A global, single-instance container used to # A global, single-instance container used to
# store system values and test parameters # store system values and test parameters
class SystemValues: class SystemValues:
title = 'SleepGraph'
version = '4.6'
ansi = False ansi = False
version = '4.5'
verbose = False verbose = False
addlogs = False addlogs = False
mindevlen = 0.0 mindevlen = 0.0
mincglen = 0.0 mincglen = 0.0
cgphase = '' cgphase = ''
cgtest = -1 cgtest = -1
max_graph_depth = 0
callloopmaxgap = 0.0001 callloopmaxgap = 0.0001
callloopmaxlen = 0.005 callloopmaxlen = 0.005
srgap = 0 srgap = 0
...@@ -106,8 +104,8 @@ class SystemValues: ...@@ -106,8 +104,8 @@ class SystemValues:
ftracefile = '' ftracefile = ''
htmlfile = '' htmlfile = ''
embedded = False embedded = False
rtcwake = False rtcwake = True
rtcwaketime = 10 rtcwaketime = 15
rtcpath = '' rtcpath = ''
devicefilter = [] devicefilter = []
stamp = 0 stamp = 0
...@@ -235,6 +233,12 @@ class SystemValues: ...@@ -235,6 +233,12 @@ class SystemValues:
self.rtcpath = rtc self.rtcpath = rtc
if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()): if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
self.ansi = True self.ansi = True
def rootUser(self, fatal=False):
if 'USER' in os.environ and os.environ['USER'] == 'root':
return True
if fatal:
doError('This command must be run as root')
return False
def setPrecision(self, num): def setPrecision(self, num):
if num < 0 or num > 6: if num < 0 or num > 6:
return return
...@@ -564,7 +568,7 @@ class SystemValues: ...@@ -564,7 +568,7 @@ class SystemValues:
self.fsetVal('global', 'trace_clock') self.fsetVal('global', 'trace_clock')
# set trace buffer to a huge value # set trace buffer to a huge value
self.fsetVal('nop', 'current_tracer') self.fsetVal('nop', 'current_tracer')
self.fsetVal('100000', 'buffer_size_kb') self.fsetVal('131073', 'buffer_size_kb')
# go no further if this is just a status check # go no further if this is just a status check
if testing: if testing:
return return
...@@ -583,7 +587,7 @@ class SystemValues: ...@@ -583,7 +587,7 @@ class SystemValues:
self.fsetVal('nofuncgraph-overhead', 'trace_options') self.fsetVal('nofuncgraph-overhead', 'trace_options')
self.fsetVal('context-info', 'trace_options') self.fsetVal('context-info', 'trace_options')
self.fsetVal('graph-time', 'trace_options') self.fsetVal('graph-time', 'trace_options')
self.fsetVal('0', 'max_graph_depth') self.fsetVal('%d' % self.max_graph_depth, 'max_graph_depth')
cf = ['dpm_run_callback'] cf = ['dpm_run_callback']
if(self.usetraceeventsonly): if(self.usetraceeventsonly):
cf += ['dpm_prepare', 'dpm_complete'] cf += ['dpm_prepare', 'dpm_complete']
...@@ -639,6 +643,12 @@ class SystemValues: ...@@ -639,6 +643,12 @@ class SystemValues:
return '\x1B[%d;40m%s\x1B[m' % (color, str) return '\x1B[%d;40m%s\x1B[m' % (color, str)
sysvals = SystemValues() sysvals = SystemValues()
suspendmodename = {
'freeze': 'Freeze (S0)',
'standby': 'Standby (S1)',
'mem': 'Suspend (S3)',
'disk': 'Hibernate (S4)'
}
# Class: DevProps # Class: DevProps
# Description: # Description:
...@@ -1013,6 +1023,8 @@ class Data: ...@@ -1013,6 +1023,8 @@ class Data:
tmp = dict() tmp = dict()
for devname in list: for devname in list:
dev = list[devname] dev = list[devname]
if dev['length'] == 0:
continue
tmp[dev['start']] = devname tmp[dev['start']] = devname
for t in sorted(tmp): for t in sorted(tmp):
slist.append(tmp[t]) slist.append(tmp[t])
...@@ -1477,12 +1489,14 @@ class FTraceLine: ...@@ -1477,12 +1489,14 @@ class FTraceLine:
# Each instance is tied to a single device in a single phase, and is # Each instance is tied to a single device in a single phase, and is
# comprised of an ordered list of FTraceLine objects # comprised of an ordered list of FTraceLine objects
class FTraceCallGraph: class FTraceCallGraph:
id = ''
start = -1.0 start = -1.0
end = -1.0 end = -1.0
list = [] list = []
invalid = False invalid = False
depth = 0 depth = 0
pid = 0 pid = 0
name = ''
def __init__(self, pid): def __init__(self, pid):
self.start = -1.0 self.start = -1.0
self.end = -1.0 self.end = -1.0
...@@ -1631,9 +1645,17 @@ class FTraceCallGraph: ...@@ -1631,9 +1645,17 @@ class FTraceCallGraph:
return True return True
return False return False
def postProcess(self, debug=False): def postProcess(self, debug=False):
if len(self.list) > 0:
self.name = self.list[0].name
stack = dict() stack = dict()
cnt = 0 cnt = 0
last = 0
for l in self.list: for l in self.list:
# ftrace bug: reported duration is not reliable
# check each leaf and clip it at max possible length
if(last and last.freturn and last.fcall):
if last.length > l.time - last.time:
last.length = l.time - last.time
if(l.fcall and not l.freturn): if(l.fcall and not l.freturn):
stack[l.depth] = l stack[l.depth] = l
cnt += 1 cnt += 1
...@@ -1643,11 +1665,12 @@ class FTraceCallGraph: ...@@ -1643,11 +1665,12 @@ class FTraceCallGraph:
print 'Post Process Error: Depth missing' print 'Post Process Error: Depth missing'
l.debugPrint() l.debugPrint()
return False return False
# transfer total time from return line to call line # calculate call length from call/return lines
stack[l.depth].length = l.length stack[l.depth].length = l.time - stack[l.depth].time
stack.pop(l.depth) stack.pop(l.depth)
l.length = 0 l.length = 0
cnt -= 1 cnt -= 1
last = l
if(cnt == 0): if(cnt == 0):
# trace caught the whole call tree # trace caught the whole call tree
return True return True
...@@ -1664,8 +1687,8 @@ class FTraceCallGraph: ...@@ -1664,8 +1687,8 @@ class FTraceCallGraph:
'dpm_prepare': 'suspend_prepare', 'dpm_prepare': 'suspend_prepare',
'dpm_complete': 'resume_complete' 'dpm_complete': 'resume_complete'
} }
if(self.list[0].name in borderphase): if(self.name in borderphase):
p = borderphase[self.list[0].name] p = borderphase[self.name]
list = data.dmesg[p]['list'] list = data.dmesg[p]['list']
for devname in list: for devname in list:
dev = list[devname] dev = list[devname]
...@@ -1690,7 +1713,7 @@ class FTraceCallGraph: ...@@ -1690,7 +1713,7 @@ class FTraceCallGraph:
break break
return found return found
def newActionFromFunction(self, data): def newActionFromFunction(self, data):
name = self.list[0].name name = self.name
if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']: if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']:
return return
fs = self.start fs = self.start
...@@ -1710,7 +1733,7 @@ class FTraceCallGraph: ...@@ -1710,7 +1733,7 @@ class FTraceCallGraph:
phase, myname = out phase, myname = out
data.dmesg[phase]['list'][myname]['ftrace'] = self data.dmesg[phase]['list'][myname]['ftrace'] = self
def debugPrint(self): def debugPrint(self):
print('[%f - %f] %s (%d)') % (self.start, self.end, self.list[0].name, self.pid) print('[%f - %f] %s (%d)') % (self.start, self.end, self.name, self.pid)
for l in self.list: for l in self.list:
if(l.freturn and l.fcall): if(l.freturn and l.fcall):
print('%f (%02d): %s(); (%.3f us)' % (l.time, \ print('%f (%02d): %s(); (%.3f us)' % (l.time, \
...@@ -1738,7 +1761,7 @@ class DevItem: ...@@ -1738,7 +1761,7 @@ class DevItem:
# A container for a device timeline which calculates # A container for a device timeline which calculates
# all the html properties to display it correctly # all the html properties to display it correctly
class Timeline: class Timeline:
html = {} html = ''
height = 0 # total timeline height height = 0 # total timeline height
scaleH = 20 # timescale (top) row height scaleH = 20 # timescale (top) row height
rowH = 30 # device row height rowH = 30 # device row height
...@@ -1746,14 +1769,28 @@ class Timeline: ...@@ -1746,14 +1769,28 @@ class Timeline:
rows = 0 # total timeline rows rows = 0 # total timeline rows
rowlines = dict() rowlines = dict()
rowheight = dict() rowheight = dict()
html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n'
html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
def __init__(self, rowheight, scaleheight): def __init__(self, rowheight, scaleheight):
self.rowH = rowheight self.rowH = rowheight
self.scaleH = scaleheight self.scaleH = scaleheight
self.html = { self.html = ''
'header': '', def createHeader(self, sv, suppress=''):
'timeline': '', if(not sv.stamp['time']):
'legend': '', return
} self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \
% (sv.title, sv.version)
if sv.logmsg and 'log' not in suppress:
self.html += '<button id="showtest" class="logbtn">log</button>'
if sv.addlogs and 'dmesg' not in suppress:
self.html += '<button id="showdmesg" class="logbtn">dmesg</button>'
if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress:
self.html += '<button id="showftrace" class="logbtn">ftrace</button>'
headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'],
sv.stamp['mode'], sv.stamp['time'])
# Function: getDeviceRows # Function: getDeviceRows
# Description: # Description:
# determine how may rows the device funcs will take # determine how may rows the device funcs will take
...@@ -1880,10 +1917,8 @@ class Timeline: ...@@ -1880,10 +1917,8 @@ class Timeline:
break break
top += self.rowheight[test][phase][i] top += self.rowheight[test][phase][i]
return top return top
# Function: calcTotalRows
# Description:
# Calculate the heights and offsets for the header and rows
def calcTotalRows(self): def calcTotalRows(self):
# Calculate the heights and offsets for the header and rows
maxrows = 0 maxrows = 0
standardphases = [] standardphases = []
for t in self.rowlines: for t in self.rowlines:
...@@ -1901,6 +1936,20 @@ class Timeline: ...@@ -1901,6 +1936,20 @@ class Timeline:
for t, p in standardphases: for t, p in standardphases:
for i in sorted(self.rowheight[t][p]): for i in sorted(self.rowheight[t][p]):
self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p]) self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p])
def createZoomBox(self, mode='command', testcount=1):
# Create bounding box, add buttons
html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail{0}</button>'
html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
if mode != 'command':
if testcount > 1:
self.html += html_devlist2
self.html += html_devlist1.format('1')
else:
self.html += html_devlist1.format('')
self.html += html_zoombox
self.html += html_timeline.format('dmesg', self.height)
# Function: createTimeScale # Function: createTimeScale
# Description: # Description:
# Create the timescale for a timeline block # Create the timescale for a timeline block
...@@ -1913,7 +1962,7 @@ class Timeline: ...@@ -1913,7 +1962,7 @@ class Timeline:
# The html code needed to display the time scale # The html code needed to display the time scale
def createTimeScale(self, m0, mMax, tTotal, mode): def createTimeScale(self, m0, mMax, tTotal, mode):
timescale = '<div class="t" style="right:{0}%">{1}</div>\n' timescale = '<div class="t" style="right:{0}%">{1}</div>\n'
rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">Resume</div>\n' rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">{0}</div>\n'
output = '<div class="timescale">\n' output = '<div class="timescale">\n'
# set scale for timeline # set scale for timeline
mTotal = mMax - m0 mTotal = mMax - m0
...@@ -1926,21 +1975,20 @@ class Timeline: ...@@ -1926,21 +1975,20 @@ class Timeline:
divEdge = (mTotal - tS*(divTotal-1))*100/mTotal divEdge = (mTotal - tS*(divTotal-1))*100/mTotal
for i in range(divTotal): for i in range(divTotal):
htmlline = '' htmlline = ''
if(mode == 'resume'): if(mode == 'suspend'):
pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
val = '%0.fms' % (float(i)*tS*1000)
htmlline = timescale.format(pos, val)
if(i == 0):
htmlline = rline
else:
pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge) pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge)
val = '%0.fms' % (float(i-divTotal+1)*tS*1000) val = '%0.fms' % (float(i-divTotal+1)*tS*1000)
if(i == divTotal - 1): if(i == divTotal - 1):
val = 'Suspend' val = mode
htmlline = timescale.format(pos, val) htmlline = timescale.format(pos, val)
else:
pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
val = '%0.fms' % (float(i)*tS*1000)
htmlline = timescale.format(pos, val)
if(i == 0):
htmlline = rline.format(mode)
output += htmlline output += htmlline
output += '</div>\n' self.html += output+'</div>\n'
return output
# Class: TestProps # Class: TestProps
# Description: # Description:
...@@ -2009,7 +2057,7 @@ class ProcessMonitor: ...@@ -2009,7 +2057,7 @@ class ProcessMonitor:
val['kern'] = kern val['kern'] = kern
if ujiff > 0 or kjiff > 0: if ujiff > 0 or kjiff > 0:
running[pid] = ujiff + kjiff running[pid] = ujiff + kjiff
result = process.wait() process.wait()
out = '' out = ''
for pid in running: for pid in running:
jiffies = running[pid] jiffies = running[pid]
...@@ -2071,26 +2119,6 @@ def parseStamp(line, data): ...@@ -2071,26 +2119,6 @@ def parseStamp(line, data):
if not sysvals.stamp: if not sysvals.stamp:
sysvals.stamp = data.stamp sysvals.stamp = data.stamp
# Function: diffStamp
# Description:
# compare the host, kernel, and mode fields in 3 stamps
# Arguments:
# stamp1: string array with mode, kernel, and host
# stamp2: string array with mode, kernel, and host
# Return:
# True if stamps differ, False if they're the same
def diffStamp(stamp1, stamp2):
if 'host' in stamp1 and 'host' in stamp2:
if stamp1['host'] != stamp2['host']:
return True
if 'kernel' in stamp1 and 'kernel' in stamp2:
if stamp1['kernel'] != stamp2['kernel']:
return True
if 'mode' in stamp1 and 'mode' in stamp2:
if stamp1['mode'] != stamp2['mode']:
return True
return False
# Function: doesTraceLogHaveTraceEvents # Function: doesTraceLogHaveTraceEvents
# Description: # Description:
# Quickly determine if the ftrace log has some or all of the trace events # Quickly determine if the ftrace log has some or all of the trace events
...@@ -2722,7 +2750,7 @@ def parseTraceLog(): ...@@ -2722,7 +2750,7 @@ def parseTraceLog():
# create blocks for orphan cg data # create blocks for orphan cg data
for sortkey in sorted(sortlist): for sortkey in sorted(sortlist):
cg = sortlist[sortkey] cg = sortlist[sortkey]
name = cg.list[0].name name = cg.name
if sysvals.isCallgraphFunc(name): if sysvals.isCallgraphFunc(name):
vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name)) vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
cg.newActionFromFunction(data) cg.newActionFromFunction(data)
...@@ -3100,149 +3128,154 @@ def parseKernelLog(data): ...@@ -3100,149 +3128,154 @@ def parseKernelLog(data):
data.fixupInitcallsThatDidntReturn() data.fixupInitcallsThatDidntReturn()
return True return True
def callgraphHTML(sv, hf, num, cg, title, color, devid):
html_func_top = '<article id="{0}" class="atop" style="background:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
html_func_end = '</article>\n'
html_func_leaf = '<article>{0} {1}</article>\n'
cgid = devid
if cg.id:
cgid += cg.id
cglen = (cg.end - cg.start) * 1000
if cglen < sv.mincglen:
return num
fmt = '<r>(%.3f ms @ '+sv.timeformat+' to '+sv.timeformat+')</r>'
flen = fmt % (cglen, cg.start, cg.end)
hf.write(html_func_top.format(cgid, color, num, title, flen))
num += 1
for line in cg.list:
if(line.length < 0.000000001):
flen = ''
else:
fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>'
flen = fmt % (line.length*1000, line.time)
if(line.freturn and line.fcall):
hf.write(html_func_leaf.format(line.name, flen))
elif(line.freturn):
hf.write(html_func_end)
else:
hf.write(html_func_start.format(num, line.name, flen))
num += 1
hf.write(html_func_end)
return num
def addCallgraphs(sv, hf, data):
hf.write('<section id="callgraphs" class="callgraph">\n')
# write out the ftrace data converted to html
num = 0
for p in data.phases:
if sv.cgphase and p != sv.cgphase:
continue
list = data.dmesg[p]['list']
for devname in data.sortedDevices(p):
dev = list[devname]
color = 'white'
if 'color' in data.dmesg[p]:
color = data.dmesg[p]['color']
if 'color' in dev:
color = dev['color']
name = devname
if(devname in sv.devprops):
name = sv.devprops[devname].altName(devname)
if sv.suspendmode in suspendmodename:
name += ' '+p
if('ftrace' in dev):
cg = dev['ftrace']
num = callgraphHTML(sv, hf, num, cg,
name, color, dev['id'])
if('ftraces' in dev):
for cg in dev['ftraces']:
num = callgraphHTML(sv, hf, num, cg,
name+' &rarr; '+cg.name, color, dev['id'])
hf.write('\n\n </section>\n')
# Function: createHTMLSummarySimple # Function: createHTMLSummarySimple
# Description: # Description:
# Create summary html file for a series of tests # Create summary html file for a series of tests
# Arguments: # Arguments:
# testruns: array of Data objects from parseTraceLog # testruns: array of Data objects from parseTraceLog
def createHTMLSummarySimple(testruns, htmlfile): def createHTMLSummarySimple(testruns, htmlfile, folder):
# print out the basic summary of all the tests
hf = open(htmlfile, 'w')
# write the html header first (html head, css code, up to body start) # write the html header first (html head, css code, up to body start)
html = '<!DOCTYPE html>\n<html>\n<head>\n\ html = '<!DOCTYPE html>\n<html>\n<head>\n\
<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\ <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
<title>AnalyzeSuspend Summary</title>\n\ <title>SleepGraph Summary</title>\n\
<style type=\'text/css\'>\n\ <style type=\'text/css\'>\n\
body {overflow-y: scroll;}\n\ .stamp {width: 100%;text-align:center;background:#888;line-height:30px;color:white;font: 25px Arial;}\n\
.stamp {width: 100%;text-align:center;background-color:#495E09;line-height:30px;color:white;font: 25px Arial;}\n\
table {width:100%;border-collapse: collapse;}\n\ table {width:100%;border-collapse: collapse;}\n\
.summary {font: 22px Arial;border:1px solid;}\n\ .summary {border:1px solid;}\n\
th {border: 1px solid black;background-color:#A7C942;color:white;}\n\ th {border: 1px solid black;background:#222;color:white;}\n\
td {text-align: center;}\n\ td {font: 16px "Times New Roman";text-align: center;}\n\
tr.alt td {background-color:#EAF2D3;}\n\ tr.alt td {background:#ddd;}\n\
tr.avg td {background-color:#BDE34C;}\n\ tr.avg td {background:#aaa;}\n\
a:link {color: #90B521;}\n\
a:visited {color: #495E09;}\n\
a:hover {color: #B1DF28;}\n\
a:active {color: #FFFFFF;}\n\
</style>\n</head>\n<body>\n' </style>\n</head>\n<body>\n'
# group test header # group test header
count = len(testruns) html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns))
headline_stamp = '<div class="stamp">{0} {1} {2} {3} ({4} tests)</div>\n'
html += headline_stamp.format(sysvals.stamp['host'],
sysvals.stamp['kernel'], sysvals.stamp['mode'],
sysvals.stamp['time'], count)
# check to see if all the tests have the same value
stampcolumns = False
for data in testruns:
if diffStamp(sysvals.stamp, data.stamp):
stampcolumns = True
break
th = '\t<th>{0}</th>\n' th = '\t<th>{0}</th>\n'
td = '\t<td>{0}</td>\n' td = '\t<td>{0}</td>\n'
tdlink = '\t<td><a href="{0}">Click Here</a></td>\n' tdlink = '\t<td><a href="{0}">html</a></td>\n'
# table header # table header
html += '<table class="summary">\n<tr>\n' html += '<table class="summary">\n<tr>\n' + th.format('#') +\
html += th.format("Test #") th.format('Mode') + th.format('Host') + th.format('Kernel') +\
if stampcolumns: th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\
html += th.format("Hostname") th.format('Detail') + '</tr>\n'
html += th.format("Kernel Version")
html += th.format("Suspend Mode")
html += th.format("Test Time")
html += th.format("Suspend Time")
html += th.format("Resume Time")
html += th.format("Detail")
html += '</tr>\n'
# test data, 1 row per test # test data, 1 row per test
sTimeAvg = 0.0 avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\
rTimeAvg = 0.0 '<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n'
sTimeAvg = rTimeAvg = 0.0
mode = ''
num = 0
for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'])):
if mode != data['mode']:
# test average line
if(num > 0):
sTimeAvg /= (num - 1)
rTimeAvg /= (num - 1)
html += avg.format('%d' % (num - 1), mode,
'%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
sTimeAvg = rTimeAvg = 0.0
mode = data['mode']
num = 1 num = 1
for data in testruns: # alternate row color
# data.end is the end of post_resume
resumeEnd = data.dmesg['resume_complete']['end']
if num % 2 == 1: if num % 2 == 1:
html += '<tr class="alt">\n' html += '<tr class="alt">\n'
else: else:
html += '<tr>\n' html += '<tr>\n'
html += td.format("%d" % num)
# test num
html += td.format("test %d" % num)
num += 1 num += 1
if stampcolumns: # basic info
# host name for item in ['mode', 'host', 'kernel', 'time']:
val = "unknown"
if('host' in data.stamp):
val = data.stamp['host']
html += td.format(val)
# host kernel
val = "unknown"
if('kernel' in data.stamp):
val = data.stamp['kernel']
html += td.format(val)
# suspend mode
val = "unknown" val = "unknown"
if('mode' in data.stamp): if(item in data):
val = data.stamp['mode'] val = data[item]
html += td.format(val)
# test time
val = "unknown"
if('time' in data.stamp):
val = data.stamp['time']
html += td.format(val) html += td.format(val)
# suspend time # suspend time
sTime = (data.tSuspended - data.start)*1000 sTime = float(data['suspend'])
sTimeAvg += sTime sTimeAvg += sTime
html += td.format("%3.3f ms" % sTime) html += td.format('%.3f ms' % sTime)
# resume time # resume time
rTime = (resumeEnd - data.tResumed)*1000 rTime = float(data['resume'])
rTimeAvg += rTime rTimeAvg += rTime
html += td.format("%3.3f ms" % rTime) html += td.format('%.3f ms' % rTime)
# link to the output html # link to the output html
html += tdlink.format(data.outfile) html += tdlink.format(data['url']) + '</tr>\n'
# last test average line
html += '</tr>\n' if(num > 0):
sTimeAvg /= (num - 1)
# last line: test average rTimeAvg /= (num - 1)
if(count > 0): html += avg.format('%d' % (num - 1), mode,
sTimeAvg /= count '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
rTimeAvg /= count
html += '<tr class="avg">\n'
html += td.format('Average') # name
if stampcolumns:
html += td.format('') # host
html += td.format('') # kernel
html += td.format('') # mode
html += td.format('') # time
html += td.format("%3.3f ms" % sTimeAvg) # suspend time
html += td.format("%3.3f ms" % rTimeAvg) # resume time
html += td.format('') # output link
html += '</tr>\n'
# flush the data to file # flush the data to file
hf.write(html+'</table>\n') hf = open(htmlfile, 'w')
hf.write('</body>\n</html>\n') hf.write(html+'</table>\n</body>\n</html>\n')
hf.close() hf.close()
def htmlTitle():
modename = {
'freeze': 'Freeze (S0)',
'standby': 'Standby (S1)',
'mem': 'Suspend (S3)',
'disk': 'Hibernate (S4)'
}
kernel = sysvals.stamp['kernel']
host = sysvals.hostname[0].upper()+sysvals.hostname[1:]
mode = sysvals.suspendmode
if sysvals.suspendmode in modename:
mode = modename[sysvals.suspendmode]
return host+' '+mode+' '+kernel
def ordinal(value): def ordinal(value):
suffix = 'th' suffix = 'th'
if value < 10 or value > 19: if value < 10 or value > 19:
...@@ -3272,24 +3305,11 @@ def createHTML(testruns): ...@@ -3272,24 +3305,11 @@ def createHTML(testruns):
kerror = True kerror = True
data.normalizeTime(testruns[-1].tSuspended) data.normalizeTime(testruns[-1].tSuspended)
x2changes = ['', 'absolute']
if len(testruns) > 1:
x2changes = ['1', 'relative']
# html function templates # html function templates
headline_version = '<div class="version"><a href="https://01.org/suspendresume">AnalyzeSuspend v%s</a></div>' % sysvals.version
headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail%s</button>' % x2changes[0]
html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR&rarr;</div>\n' html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR&rarr;</div>\n'
html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n' html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n'
html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n' html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n'
html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background-color:{4}">{5}</div>\n' html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}">&nbsp;{2}</div>\n'
html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
html_legend = '<div id="p{3}" class="square" style="left:{0}%;background-color:{1}">&nbsp;{2}</div>\n'
html_timetotal = '<table class="time1">\n<tr>'\ html_timetotal = '<table class="time1">\n<tr>'\
'<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\ '<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\
'<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\ '<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\
...@@ -3311,20 +3331,18 @@ def createHTML(testruns): ...@@ -3311,20 +3331,18 @@ def createHTML(testruns):
'</tr>\n</table>\n' '</tr>\n</table>\n'
# html format variables # html format variables
hoverZ = 'z-index:8;'
if sysvals.usedevsrc:
hoverZ = ''
scaleH = 20 scaleH = 20
scaleTH = 20
if kerror: if kerror:
scaleH = 40 scaleH = 40
scaleTH = 60
# device timeline # device timeline
vprint('Creating Device Timeline...') vprint('Creating Device Timeline...')
devtl = Timeline(30, scaleH) devtl = Timeline(30, scaleH)
# write the test title and general info header
devtl.createHeader(sysvals)
# Generate the header for this timeline # Generate the header for this timeline
for data in testruns: for data in testruns:
tTotal = data.end - data.start tTotal = data.end - data.start
...@@ -3346,7 +3364,7 @@ def createHTML(testruns): ...@@ -3346,7 +3364,7 @@ def createHTML(testruns):
if(len(testruns) > 1): if(len(testruns) > 1):
testdesc = ordinal(data.testnumber+1)+' '+testdesc testdesc = ordinal(data.testnumber+1)+' '+testdesc
thtml = html_timetotal3.format(run_time, testdesc) thtml = html_timetotal3.format(run_time, testdesc)
devtl.html['header'] += thtml devtl.html += thtml
elif data.fwValid: elif data.fwValid:
suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0)) suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0))
resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0)) resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0))
...@@ -3363,10 +3381,10 @@ def createHTML(testruns): ...@@ -3363,10 +3381,10 @@ def createHTML(testruns):
else: else:
thtml = html_timetotal2.format(suspend_time, low_time, \ thtml = html_timetotal2.format(suspend_time, low_time, \
resume_time, testdesc1, stitle, rtitle) resume_time, testdesc1, stitle, rtitle)
devtl.html['header'] += thtml devtl.html += thtml
sftime = '%.3f'%(data.fwSuspend / 1000000.0) sftime = '%.3f'%(data.fwSuspend / 1000000.0)
rftime = '%.3f'%(data.fwResume / 1000000.0) rftime = '%.3f'%(data.fwResume / 1000000.0)
devtl.html['header'] += html_timegroups.format('%.3f'%sktime, \ devtl.html += html_timegroups.format('%.3f'%sktime, \
sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode) sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode)
else: else:
suspend_time = '%.3f' % sktime suspend_time = '%.3f' % sktime
...@@ -3382,7 +3400,7 @@ def createHTML(testruns): ...@@ -3382,7 +3400,7 @@ def createHTML(testruns):
else: else:
thtml = html_timetotal2.format(suspend_time, low_time, \ thtml = html_timetotal2.format(suspend_time, low_time, \
resume_time, testdesc, stitle, rtitle) resume_time, testdesc, stitle, rtitle)
devtl.html['header'] += thtml devtl.html += thtml
# time scale for potentially multiple datasets # time scale for potentially multiple datasets
t0 = testruns[0].start t0 = testruns[0].start
...@@ -3429,15 +3447,8 @@ def createHTML(testruns): ...@@ -3429,15 +3447,8 @@ def createHTML(testruns):
devtl.getPhaseRows(threadlist, devtl.rows) devtl.getPhaseRows(threadlist, devtl.rows)
devtl.calcTotalRows() devtl.calcTotalRows()
# create bounding box, add buttons
if sysvals.suspendmode != 'command':
devtl.html['timeline'] += html_devlist1
if len(testruns) > 1:
devtl.html['timeline'] += html_devlist2
devtl.html['timeline'] += html_zoombox
devtl.html['timeline'] += html_timeline.format('dmesg', devtl.height)
# draw the full timeline # draw the full timeline
devtl.createZoomBox(sysvals.suspendmode, len(testruns))
phases = {'suspend':[],'resume':[]} phases = {'suspend':[],'resume':[]}
for phase in data.dmesg: for phase in data.dmesg:
if 'resume' in phase: if 'resume' in phase:
...@@ -3452,37 +3463,36 @@ def createHTML(testruns): ...@@ -3452,37 +3463,36 @@ def createHTML(testruns):
# draw suspend and resume blocks separately # draw suspend and resume blocks separately
bname = '%s%d' % (dir[0], data.testnumber) bname = '%s%d' % (dir[0], data.testnumber)
if dir == 'suspend': if dir == 'suspend':
m0 = testruns[data.testnumber].start m0 = data.start
mMax = testruns[data.testnumber].tSuspended mMax = data.tSuspended
mTotal = mMax - m0
left = '%f' % (((m0-t0)*100.0)/tTotal) left = '%f' % (((m0-t0)*100.0)/tTotal)
else: else:
m0 = testruns[data.testnumber].tSuspended m0 = data.tSuspended
mMax = testruns[data.testnumber].end mMax = data.end
# in an x2 run, remove any gap between blocks # in an x2 run, remove any gap between blocks
if len(testruns) > 1 and data.testnumber == 0: if len(testruns) > 1 and data.testnumber == 0:
mMax = testruns[1].start mMax = testruns[1].start
mTotal = mMax - m0
left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal) left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal)
mTotal = mMax - m0
# if a timeline block is 0 length, skip altogether # if a timeline block is 0 length, skip altogether
if mTotal == 0: if mTotal == 0:
continue continue
width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal) width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
devtl.html['timeline'] += html_tblock.format(bname, left, width, devtl.scaleH) devtl.html += devtl.html_tblock.format(bname, left, width, devtl.scaleH)
for b in sorted(phases[dir]): for b in sorted(phases[dir]):
# draw the phase color background # draw the phase color background
phase = data.dmesg[b] phase = data.dmesg[b]
length = phase['end']-phase['start'] length = phase['end']-phase['start']
left = '%f' % (((phase['start']-m0)*100.0)/mTotal) left = '%f' % (((phase['start']-m0)*100.0)/mTotal)
width = '%f' % ((length*100.0)/mTotal) width = '%f' % ((length*100.0)/mTotal)
devtl.html['timeline'] += html_phase.format(left, width, \ devtl.html += devtl.html_phase.format(left, width, \
'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \ '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
data.dmesg[b]['color'], '') data.dmesg[b]['color'], '')
for e in data.errorinfo[dir]: for e in data.errorinfo[dir]:
# draw red lines for any kernel errors found # draw red lines for any kernel errors found
t, err = e t, err = e
right = '%f' % (((mMax-t)*100.0)/mTotal) right = '%f' % (((mMax-t)*100.0)/mTotal)
devtl.html['timeline'] += html_error.format(right, err) devtl.html += html_error.format(right, err)
for b in sorted(phases[dir]): for b in sorted(phases[dir]):
# draw the devices for this phase # draw the devices for this phase
phaselist = data.dmesg[b]['list'] phaselist = data.dmesg[b]['list']
...@@ -3496,7 +3506,7 @@ def createHTML(testruns): ...@@ -3496,7 +3506,7 @@ def createHTML(testruns):
if 'htmlclass' in dev: if 'htmlclass' in dev:
xtraclass = dev['htmlclass'] xtraclass = dev['htmlclass']
if 'color' in dev: if 'color' in dev:
xtrastyle = 'background-color:%s;' % dev['color'] xtrastyle = 'background:%s;' % dev['color']
if(d in sysvals.devprops): if(d in sysvals.devprops):
name = sysvals.devprops[d].altName(d) name = sysvals.devprops[d].altName(d)
xtraclass = sysvals.devprops[d].xtraClass() xtraclass = sysvals.devprops[d].xtraClass()
...@@ -3521,7 +3531,7 @@ def createHTML(testruns): ...@@ -3521,7 +3531,7 @@ def createHTML(testruns):
title += 'post_resume_process' title += 'post_resume_process'
else: else:
title += b title += b
devtl.html['timeline'] += html_device.format(dev['id'], \ devtl.html += devtl.html_device.format(dev['id'], \
title, left, top, '%.3f'%rowheight, width, \ title, left, top, '%.3f'%rowheight, width, \
d+drv, xtraclass, xtrastyle) d+drv, xtraclass, xtrastyle)
if('cpuexec' in dev): if('cpuexec' in dev):
...@@ -3535,7 +3545,7 @@ def createHTML(testruns): ...@@ -3535,7 +3545,7 @@ def createHTML(testruns):
left = '%f' % (((start-m0)*100)/mTotal) left = '%f' % (((start-m0)*100)/mTotal)
width = '%f' % ((end-start)*100/mTotal) width = '%f' % ((end-start)*100/mTotal)
color = 'rgba(255, 0, 0, %f)' % j color = 'rgba(255, 0, 0, %f)' % j
devtl.html['timeline'] += \ devtl.html += \
html_cpuexec.format(left, top, height, width, color) html_cpuexec.format(left, top, height, width, color)
if('src' not in dev): if('src' not in dev):
continue continue
...@@ -3548,20 +3558,20 @@ def createHTML(testruns): ...@@ -3548,20 +3558,20 @@ def createHTML(testruns):
xtrastyle = '' xtrastyle = ''
if e.color: if e.color:
xtrastyle = 'background:%s;' % e.color xtrastyle = 'background:%s;' % e.color
devtl.html['timeline'] += \ devtl.html += \
html_traceevent.format(e.title(), \ html_traceevent.format(e.title(), \
left, top, height, width, e.text(), '', xtrastyle) left, top, height, width, e.text(), '', xtrastyle)
# draw the time scale, try to make the number of labels readable # draw the time scale, try to make the number of labels readable
devtl.html['timeline'] += devtl.createTimeScale(m0, mMax, tTotal, dir) devtl.createTimeScale(m0, mMax, tTotal, dir)
devtl.html['timeline'] += '</div>\n' devtl.html += '</div>\n'
# timeline is finished # timeline is finished
devtl.html['timeline'] += '</div>\n</div>\n' devtl.html += '</div>\n</div>\n'
# draw a legend which describes the phases by color # draw a legend which describes the phases by color
if sysvals.suspendmode != 'command': if sysvals.suspendmode != 'command':
data = testruns[-1] data = testruns[-1]
devtl.html['legend'] = '<div class="legend">\n' devtl.html += '<div class="legend">\n'
pdelta = 100.0/len(data.phases) pdelta = 100.0/len(data.phases)
pmargin = pdelta / 4.0 pmargin = pdelta / 4.0
for phase in data.phases: for phase in data.phases:
...@@ -3571,127 +3581,41 @@ def createHTML(testruns): ...@@ -3571,127 +3581,41 @@ def createHTML(testruns):
id += tmp[1][0] id += tmp[1][0]
order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin) order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
name = string.replace(phase, '_', ' &nbsp;') name = string.replace(phase, '_', ' &nbsp;')
devtl.html['legend'] += html_legend.format(order, \ devtl.html += html_legend.format(order, \
data.dmesg[phase]['color'], name, id) data.dmesg[phase]['color'], name, id)
devtl.html['legend'] += '</div>\n' devtl.html += '</div>\n'
hf = open(sysvals.htmlfile, 'w') hf = open(sysvals.htmlfile, 'w')
if not sysvals.cgexp:
cgchk = 'checked'
cgnchk = 'not(:checked)'
else:
cgchk = 'not(:checked)'
cgnchk = 'checked'
# write the html header first (html head, css code, up to body start)
html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
<title>'+htmlTitle()+'</title>\n\
<style type=\'text/css\'>\n\
body {overflow-y:scroll;}\n\
.stamp {width:100%;text-align:center;background-color:gray;line-height:30px;color:white;font:25px Arial;}\n\
.callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
.callgraph article * {padding-left:28px;}\n\
h1 {color:black;font:bold 30px Times;}\n\
t0 {color:black;font:bold 30px Times;}\n\
t1 {color:black;font:30px Times;}\n\
t2 {color:black;font:25px Times;}\n\
t3 {color:black;font:20px Times;white-space:nowrap;}\n\
t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
cS {font:bold 13px Times;}\n\
table {width:100%;}\n\
.gray {background-color:rgba(80,80,80,0.1);}\n\
.green {background-color:rgba(204,255,204,0.4);}\n\
.purple {background-color:rgba(128,0,128,0.2);}\n\
.yellow {background-color:rgba(255,255,204,0.4);}\n\
.time1 {font:22px Arial;border:1px solid;}\n\
.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
td {text-align:center;}\n\
r {color:#500000;font:15px Tahoma;}\n\
n {color:#505050;font:15px Tahoma;}\n\
.tdhl {color:red;}\n\
.hide {display:none;}\n\
.pf {display:none;}\n\
.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
.zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
.thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
.thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
.thread:hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
.thread.sec,.thread.sec:hover {background-color:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
.hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
.hover.sync {background-color:white;}\n\
.hover.bg,.hover.kth,.hover.sync,.hover.ps {background-color:white;}\n\
.jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
.traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
.traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
.phaselet {position:absolute;overflow:hidden;border:0px;text-align:center;height:100px;font-size:24px;}\n\
.t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
.err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
.logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
.devlist {position:'+x2changes[1]+';width:190px;}\n\
a:link {color:white;text-decoration:none;}\n\
a:visited {color:white;}\n\
a:hover {color:white;}\n\
a:active {color:white;}\n\
.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
#devicedetail {height:100px;box-shadow:5px 5px 20px black;}\n\
.tblock {position:absolute;height:100%;background-color:#ddd;}\n\
.tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
.bg {z-index:1;}\n\
</style>\n</head>\n<body>\n'
# no header or css if its embedded # no header or css if its embedded
if(sysvals.embedded): if(sysvals.embedded):
hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' % hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' %
(data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \ (data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \
data.fwSuspend/1000000, data.fwResume/1000000)) data.fwSuspend/1000000, data.fwResume/1000000))
else: else:
hf.write(html_header) addCSS(hf, sysvals, len(testruns), kerror)
# write the test title and general info header
if(sysvals.stamp['time'] != ""):
hf.write(headline_version)
if sysvals.logmsg:
hf.write('<button id="showtest" class="logbtn">log</button>')
if sysvals.addlogs and sysvals.dmesgfile:
hf.write('<button id="showdmesg" class="logbtn">dmesg</button>')
if sysvals.addlogs and sysvals.ftracefile:
hf.write('<button id="showftrace" class="logbtn">ftrace</button>')
hf.write(headline_stamp.format(sysvals.stamp['host'],
sysvals.stamp['kernel'], sysvals.stamp['mode'], \
sysvals.stamp['time']))
# write the device timeline # write the device timeline
hf.write(devtl.html['header']) hf.write(devtl.html)
hf.write(devtl.html['timeline'])
hf.write(devtl.html['legend'])
hf.write('<div id="devicedetailtitle"></div>\n') hf.write('<div id="devicedetailtitle"></div>\n')
hf.write('<div id="devicedetail" style="display:none;">\n') hf.write('<div id="devicedetail" style="display:none;">\n')
# draw the colored boxes for the device detail section # draw the colored boxes for the device detail section
for data in testruns: for data in testruns:
hf.write('<div id="devicedetail%d">\n' % data.testnumber) hf.write('<div id="devicedetail%d">\n' % data.testnumber)
pscolor = 'linear-gradient(to top left, #ccc, #eee)' pscolor = 'linear-gradient(to top left, #ccc, #eee)'
hf.write(html_phaselet.format('pre_suspend_process', \ hf.write(devtl.html_phaselet.format('pre_suspend_process', \
'0', '0', pscolor)) '0', '0', pscolor))
for b in data.phases: for b in data.phases:
phase = data.dmesg[b] phase = data.dmesg[b]
length = phase['end']-phase['start'] length = phase['end']-phase['start']
left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal) left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
width = '%.3f' % ((length*100.0)/tTotal) width = '%.3f' % ((length*100.0)/tTotal)
hf.write(html_phaselet.format(b, left, width, \ hf.write(devtl.html_phaselet.format(b, left, width, \
data.dmesg[b]['color'])) data.dmesg[b]['color']))
hf.write(html_phaselet.format('post_resume_process', \ hf.write(devtl.html_phaselet.format('post_resume_process', \
'0', '0', pscolor)) '0', '0', pscolor))
if sysvals.suspendmode == 'command': if sysvals.suspendmode == 'command':
hf.write(html_phaselet.format('cmdexec', '0', '0', pscolor)) hf.write(devtl.html_phaselet.format('cmdexec', '0', '0', pscolor))
hf.write('</div>\n') hf.write('</div>\n')
hf.write('</div>\n') hf.write('</div>\n')
...@@ -3701,52 +3625,7 @@ def createHTML(testruns): ...@@ -3701,52 +3625,7 @@ def createHTML(testruns):
else: else:
data = testruns[-1] data = testruns[-1]
if(sysvals.usecallgraph and not sysvals.embedded): if(sysvals.usecallgraph and not sysvals.embedded):
hf.write('<section id="callgraphs" class="callgraph">\n') addCallgraphs(sysvals, hf, data)
# write out the ftrace data converted to html
html_func_top = '<article id="{0}" class="atop" style="background-color:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
html_func_end = '</article>\n'
html_func_leaf = '<article>{0} {1}</article>\n'
num = 0
for p in data.phases:
if sysvals.cgphase and p != sysvals.cgphase:
continue
list = data.dmesg[p]['list']
for devname in data.sortedDevices(p):
if('ftrace' not in list[devname]):
continue
devid = list[devname]['id']
cg = list[devname]['ftrace']
clen = (cg.end - cg.start) * 1000
if clen < sysvals.mincglen:
continue
fmt = '<r>(%.3f ms @ '+sysvals.timeformat+' to '+sysvals.timeformat+')</r>'
flen = fmt % (clen, cg.start, cg.end)
name = devname
if(devname in sysvals.devprops):
name = sysvals.devprops[devname].altName(devname)
if sysvals.suspendmode == 'command':
ftitle = name
else:
ftitle = name+' '+p
hf.write(html_func_top.format(devid, data.dmesg[p]['color'], \
num, ftitle, flen))
num += 1
for line in cg.list:
if(line.length < 0.000000001):
flen = ''
else:
fmt = '<n>(%.3f ms @ '+sysvals.timeformat+')</n>'
flen = fmt % (line.length*1000, line.time)
if(line.freturn and line.fcall):
hf.write(html_func_leaf.format(line.name, flen))
elif(line.freturn):
hf.write(html_func_end)
else:
hf.write(html_func_start.format(num, line.name, flen))
num += 1
hf.write(html_func_end)
hf.write('\n\n </section>\n')
# add the test log as a hidden div # add the test log as a hidden div
if sysvals.logmsg: if sysvals.logmsg:
...@@ -3788,6 +3667,100 @@ def createHTML(testruns): ...@@ -3788,6 +3667,100 @@ def createHTML(testruns):
hf.close() hf.close()
return True return True
def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
kernel = sv.stamp['kernel']
host = sv.hostname[0].upper()+sv.hostname[1:]
mode = sv.suspendmode
if sv.suspendmode in suspendmodename:
mode = suspendmodename[sv.suspendmode]
title = host+' '+mode+' '+kernel
# various format changes by flags
cgchk = 'checked'
cgnchk = 'not(:checked)'
if sv.cgexp:
cgchk = 'not(:checked)'
cgnchk = 'checked'
hoverZ = 'z-index:8;'
if sv.usedevsrc:
hoverZ = ''
devlistpos = 'absolute'
if testcount > 1:
devlistpos = 'relative'
scaleTH = 20
if kerror:
scaleTH = 60
# write the html header first (html head, css code, up to body start)
html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
<title>'+title+'</title>\n\
<style type=\'text/css\'>\n\
body {overflow-y:scroll;}\n\
.stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\
.callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
.callgraph article * {padding-left:28px;}\n\
h1 {color:black;font:bold 30px Times;}\n\
t0 {color:black;font:bold 30px Times;}\n\
t1 {color:black;font:30px Times;}\n\
t2 {color:black;font:25px Times;}\n\
t3 {color:black;font:20px Times;white-space:nowrap;}\n\
t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
cS {font:bold 13px Times;}\n\
table {width:100%;}\n\
.gray {background:rgba(80,80,80,0.1);}\n\
.green {background:rgba(204,255,204,0.4);}\n\
.purple {background:rgba(128,0,128,0.2);}\n\
.yellow {background:rgba(255,255,204,0.4);}\n\
.blue {background:rgba(169,208,245,0.4);}\n\
.time1 {font:22px Arial;border:1px solid;}\n\
.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
td {text-align:center;}\n\
r {color:#500000;font:15px Tahoma;}\n\
n {color:#505050;font:15px Tahoma;}\n\
.tdhl {color:red;}\n\
.hide {display:none;}\n\
.pf {display:none;}\n\
.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
.zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
.thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
.thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
.thread:hover {background:white;border:1px solid red;'+hoverZ+'}\n\
.thread.sec,.thread.sec:hover {background:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
.hover {background:white;border:1px solid red;'+hoverZ+'}\n\
.hover.sync {background:white;}\n\
.hover.bg,.hover.kth,.hover.sync,.hover.ps {background:white;}\n\
.jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
.traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
.traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
.phaselet {float:left;overflow:hidden;border:0px;text-align:center;min-height:100px;font-size:24px;}\n\
.t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
.err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
.logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
.devlist {position:'+devlistpos+';width:190px;}\n\
a:link {color:white;text-decoration:none;}\n\
a:visited {color:white;}\n\
a:hover {color:white;}\n\
a:active {color:white;}\n\
.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
#devicedetail {min-height:100px;box-shadow:5px 5px 20px black;}\n\
.tblock {position:absolute;height:100%;background:#ddd;}\n\
.tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
.bg {z-index:1;}\n\
'+extra+'\
</style>\n</head>\n<body>\n'
hf.write(html_header)
# Function: addScriptCode # Function: addScriptCode
# Description: # Description:
# Adds the javascript code to the output html # Adds the javascript code to the output html
...@@ -3809,7 +3782,7 @@ def addScriptCode(hf, testruns): ...@@ -3809,7 +3782,7 @@ def addScriptCode(hf, testruns):
' var resolution = -1;\n'\ ' var resolution = -1;\n'\
' var dragval = [0, 0];\n'\ ' var dragval = [0, 0];\n'\
' function redrawTimescale(t0, tMax, tS) {\n'\ ' function redrawTimescale(t0, tMax, tS) {\n'\
' var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cS>&larr;R</cS></div>\';\n'\ ' var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;">\';\n'\
' var tTotal = tMax - t0;\n'\ ' var tTotal = tMax - t0;\n'\
' var list = document.getElementsByClassName("tblock");\n'\ ' var list = document.getElementsByClassName("tblock");\n'\
' for (var i = 0; i < list.length; i++) {\n'\ ' for (var i = 0; i < list.length; i++) {\n'\
...@@ -3824,19 +3797,23 @@ def addScriptCode(hf, testruns): ...@@ -3824,19 +3797,23 @@ def addScriptCode(hf, testruns):
' var pos = 0.0, val = 0.0;\n'\ ' var pos = 0.0, val = 0.0;\n'\
' for (var j = 0; j < divTotal; j++) {\n'\ ' for (var j = 0; j < divTotal; j++) {\n'\
' var htmlline = "";\n'\ ' var htmlline = "";\n'\
' if(list[i].id[5] == "r") {\n'\ ' var mode = list[i].id[5];\n'\
' pos = 100 - (((j)*tS*100)/mTotal);\n'\ ' if(mode == "s") {\n'\
' val = (j)*tS;\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
' if(j == 0)\n'\
' htmlline = rline;\n'\
' } else {\n'\
' pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\ ' pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\
' val = (j-divTotal+1)*tS;\n'\ ' val = (j-divTotal+1)*tS;\n'\
' if(j == divTotal - 1)\n'\ ' if(j == divTotal - 1)\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S&rarr;</cS></div>\';\n'\ ' htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S&rarr;</cS></div>\';\n'\
' else\n'\ ' else\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\ ' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
' } else {\n'\
' pos = 100 - (((j)*tS*100)/mTotal);\n'\
' val = (j)*tS;\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
' if(j == 0)\n'\
' if(mode == "r")\n'\
' htmlline = rline+"<cS>&larr;R</cS></div>";\n'\
' else\n'\
' htmlline = rline+"<cS>0ms</div>";\n'\
' }\n'\ ' }\n'\
' html += htmlline;\n'\ ' html += htmlline;\n'\
' }\n'\ ' }\n'\
...@@ -4002,12 +3979,80 @@ def addScriptCode(hf, testruns): ...@@ -4002,12 +3979,80 @@ def addScriptCode(hf, testruns):
' }\n'\ ' }\n'\
' }\n'\ ' }\n'\
' }\n'\ ' }\n'\
' if(typeof devstats !== \'undefined\')\n'\
' callDetail(this.id, this.title);\n'\
' var cglist = document.getElementById("callgraphs");\n'\ ' var cglist = document.getElementById("callgraphs");\n'\
' if(!cglist) return;\n'\ ' if(!cglist) return;\n'\
' var cg = cglist.getElementsByClassName("atop");\n'\ ' var cg = cglist.getElementsByClassName("atop");\n'\
' if(cg.length < 10) return;\n'\ ' if(cg.length < 10) return;\n'\
' for (var i = 0; i < cg.length; i++) {\n'\ ' for (var i = 0; i < cg.length; i++) {\n'\
' if(idlist.indexOf(cg[i].id) >= 0) {\n'\ ' cgid = cg[i].id.split("x")[0]\n'\
' if(idlist.indexOf(cgid) >= 0) {\n'\
' cg[i].style.display = "block";\n'\
' } else {\n'\
' cg[i].style.display = "none";\n'\
' }\n'\
' }\n'\
' }\n'\
' function callDetail(devid, devtitle) {\n'\
' if(!(devid in devstats) || devstats[devid].length < 1)\n'\
' return;\n'\
' var list = devstats[devid];\n'\
' var tmp = devtitle.split(" ");\n'\
' var name = tmp[0], phase = tmp[tmp.length-1];\n'\
' var dd = document.getElementById(phase);\n'\
' var total = parseFloat(tmp[1].slice(1));\n'\
' var mlist = [];\n'\
' var maxlen = 0;\n'\
' var info = []\n'\
' for(var i in list) {\n'\
' if(list[i][0] == "@") {\n'\
' info = list[i].split("|");\n'\
' continue;\n'\
' }\n'\
' var tmp = list[i].split("|");\n'\
' var t = parseFloat(tmp[0]), f = tmp[1], c = parseInt(tmp[2]);\n'\
' var p = (t*100.0/total).toFixed(2);\n'\
' mlist[mlist.length] = [f, c, t.toFixed(2), p+"%"];\n'\
' if(f.length > maxlen)\n'\
' maxlen = f.length;\n'\
' }\n'\
' var pad = 5;\n'\
' if(mlist.length == 0) pad = 30;\n'\
' var html = \'<div style="padding-top:\'+pad+\'px"><t3> <b>\'+name+\':</b>\';\n'\
' if(info.length > 2)\n'\
' html += " start=<b>"+info[1]+"</b>, end=<b>"+info[2]+"</b>";\n'\
' if(info.length > 3)\n'\
' html += ", length<i>(w/o overhead)</i>=<b>"+info[3]+" ms</b>";\n'\
' if(info.length > 4)\n'\
' html += ", return=<b>"+info[4]+"</b>";\n'\
' html += "</t3></div>";\n'\
' if(mlist.length > 0) {\n'\
' html += \'<table class=fstat style="padding-top:\'+(maxlen*5)+\'px;"><tr><th>Function</th>\';\n'\
' for(var i in mlist)\n'\
' html += "<td class=vt>"+mlist[i][0]+"</td>";\n'\
' html += "</tr><tr><th>Calls</th>";\n'\
' for(var i in mlist)\n'\
' html += "<td>"+mlist[i][1]+"</td>";\n'\
' html += "</tr><tr><th>Time(ms)</th>";\n'\
' for(var i in mlist)\n'\
' html += "<td>"+mlist[i][2]+"</td>";\n'\
' html += "</tr><tr><th>Percent</th>";\n'\
' for(var i in mlist)\n'\
' html += "<td>"+mlist[i][3]+"</td>";\n'\
' html += "</tr></table>";\n'\
' }\n'\
' dd.innerHTML = html;\n'\
' var height = (maxlen*5)+100;\n'\
' dd.style.height = height+"px";\n'\
' document.getElementById("devicedetail").style.height = height+"px";\n'\
' }\n'\
' function callSelect() {\n'\
' var cglist = document.getElementById("callgraphs");\n'\
' if(!cglist) return;\n'\
' var cg = cglist.getElementsByClassName("atop");\n'\
' for (var i = 0; i < cg.length; i++) {\n'\
' if(this.id == cg[i].id) {\n'\
' cg[i].style.display = "block";\n'\ ' cg[i].style.display = "block";\n'\
' } else {\n'\ ' } else {\n'\
' cg[i].style.display = "none";\n'\ ' cg[i].style.display = "none";\n'\
...@@ -4093,6 +4138,9 @@ def addScriptCode(hf, testruns): ...@@ -4093,6 +4138,9 @@ def addScriptCode(hf, testruns):
' dev[i].onmouseover = deviceHover;\n'\ ' dev[i].onmouseover = deviceHover;\n'\
' dev[i].onmouseout = deviceUnhover;\n'\ ' dev[i].onmouseout = deviceUnhover;\n'\
' }\n'\ ' }\n'\
' var dev = dmesg.getElementsByClassName("srccall");\n'\
' for (var i = 0; i < dev.length; i++)\n'\
' dev[i].onclick = callSelect;\n'\
' zoomTimeline();\n'\ ' zoomTimeline();\n'\
' });\n'\ ' });\n'\
'</script>\n' '</script>\n'
...@@ -4675,7 +4723,7 @@ def rootCheck(fatal): ...@@ -4675,7 +4723,7 @@ def rootCheck(fatal):
if(os.access(sysvals.powerfile, os.W_OK)): if(os.access(sysvals.powerfile, os.W_OK)):
return True return True
if fatal: if fatal:
doError('This command must be run as root') doError('This command requires sysfs mount and root access')
return False return False
# Function: getArgInt # Function: getArgInt
...@@ -4767,51 +4815,62 @@ def runTest(subdir, testpath=''): ...@@ -4767,51 +4815,62 @@ def runTest(subdir, testpath=''):
cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True) call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True)
def find_in_html(html, strs, div=False):
for str in strs:
l = len(str)
i = html.find(str)
if i >= 0:
break
if i < 0:
return ''
if not div:
return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group()
n = html[i+l:].find('</div>')
if n < 0:
return ''
return html[i+l:i+l+n]
# Function: runSummary # Function: runSummary
# Description: # Description:
# create a summary of tests in a sub-directory # create a summary of tests in a sub-directory
def runSummary(subdir, output): def runSummary(subdir, local=True):
# get a list of ftrace output files inpath = os.path.abspath(subdir)
files = [] outpath = inpath
if local:
outpath = os.path.abspath('.')
print('Generating a summary of folder "%s"' % inpath)
testruns = []
for dirname, dirnames, filenames in os.walk(subdir): for dirname, dirnames, filenames in os.walk(subdir):
for filename in filenames: for filename in filenames:
if(re.match('.*_ftrace.txt', filename)): if(not re.match('.*.html', filename)):
files.append("%s/%s" % (dirname, filename))
# process the files in order and get an array of data objects
testruns = []
for file in sorted(files):
if output:
print("Test found in %s" % os.path.dirname(file))
sysvals.ftracefile = file
sysvals.dmesgfile = file.replace('_ftrace.txt', '_dmesg.txt')
doesTraceLogHaveTraceEvents()
sysvals.usecallgraph = False
if not sysvals.usetraceeventsonly:
if(not os.path.exists(sysvals.dmesgfile)):
print("Skipping %s: not a valid test input" % file)
continue continue
else: file = os.path.join(dirname, filename)
if output: html = open(file, 'r').read(10000)
f = os.path.basename(sysvals.ftracefile) suspend = find_in_html(html,
d = os.path.basename(sysvals.dmesgfile) ['Kernel Suspend: ', 'Kernel Suspend Time: '])
print("\tInput files: %s and %s" % (f, d)) resume = find_in_html(html,
testdata = loadKernelLog() ['Kernel Resume: ', 'Kernel Resume Time: '])
data = testdata[0] line = find_in_html(html, ['<div class="stamp">'], True)
parseKernelLog(data) stmp = line.split()
testdata = [data] if not suspend or not resume or len(stmp) < 4:
appendIncompleteTraceLog(testdata) continue
else: data = {
if output: 'host': stmp[0],
print("\tInput file: %s" % os.path.basename(sysvals.ftracefile)) 'kernel': stmp[1],
testdata = parseTraceLog() 'mode': stmp[2],
data = testdata[0] 'time': string.join(stmp[3:], ' '),
data.normalizeTime(data.tSuspended) 'suspend': suspend,
link = file.replace(subdir+'/', '').replace('_ftrace.txt', '.html') 'resume': resume,
data.outfile = link 'url': os.path.relpath(file, outpath),
}
if len(stmp) == 7:
data['kernel'] = 'unknown'
data['mode'] = stmp[1]
data['time'] = string.join(stmp[2:], ' ')
testruns.append(data) testruns.append(data)
outfile = os.path.join(outpath, 'summary.html')
createHTMLSummarySimple(testruns, subdir+'/summary.html') print('Summary file: %s' % outfile)
createHTMLSummarySimple(testruns, outfile, inpath)
# Function: checkArgBool # Function: checkArgBool
# Description: # Description:
...@@ -4869,7 +4928,12 @@ def configFromFile(file): ...@@ -4869,7 +4928,12 @@ def configFromFile(file):
sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False) sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False)
elif(opt.lower() == 'postdelay'): elif(opt.lower() == 'postdelay'):
sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False) sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False)
elif(opt.lower() == 'maxdepth'):
sysvals.max_graph_depth = getArgInt('-maxdepth', value, 0, 1000, False)
elif(opt.lower() == 'rtcwake'): elif(opt.lower() == 'rtcwake'):
if value.lower() == 'off':
sysvals.rtcwake = False
else:
sysvals.rtcwake = True sysvals.rtcwake = True
sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False) sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
elif(opt.lower() == 'timeprec'): elif(opt.lower() == 'timeprec'):
...@@ -4969,8 +5033,8 @@ def printHelp(): ...@@ -4969,8 +5033,8 @@ def printHelp():
modes = getModes() modes = getModes()
print('') print('')
print('AnalyzeSuspend v%s' % sysvals.version) print('%s v%s' % (sysvals.title, sysvals.version))
print('Usage: sudo analyze_suspend.py <options>') print('Usage: sudo sleepgraph <options> <commands>')
print('') print('')
print('Description:') print('Description:')
print(' This tool is designed to assist kernel and OS developers in optimizing') print(' This tool is designed to assist kernel and OS developers in optimizing')
...@@ -4981,22 +5045,22 @@ def printHelp(): ...@@ -4981,22 +5045,22 @@ def printHelp():
print(' a detailed view of which devices/subsystems are taking the most') print(' a detailed view of which devices/subsystems are taking the most')
print(' time in suspend/resume.') print(' time in suspend/resume.')
print('') print('')
print(' If no specific command is given, the default behavior is to initiate')
print(' a suspend/resume and capture the dmesg/ftrace output as an html timeline.')
print('')
print(' Generates output files in subdirectory: suspend-mmddyy-HHMMSS') print(' Generates output files in subdirectory: suspend-mmddyy-HHMMSS')
print(' HTML output: <hostname>_<mode>.html') print(' HTML output: <hostname>_<mode>.html')
print(' raw dmesg output: <hostname>_<mode>_dmesg.txt') print(' raw dmesg output: <hostname>_<mode>_dmesg.txt')
print(' raw ftrace output: <hostname>_<mode>_ftrace.txt') print(' raw ftrace output: <hostname>_<mode>_ftrace.txt')
print('') print('')
print('Options:') print('Options:')
print(' [general]')
print(' -h Print this help text') print(' -h Print this help text')
print(' -v Print the current tool version') print(' -v Print the current tool version')
print(' -config fn Pull arguments and config options from file fn') print(' -config fn Pull arguments and config options from file fn')
print(' -verbose Print extra information during execution and analysis') print(' -verbose Print extra information during execution and analysis')
print(' -status Test to see if the system is enabled to run this tool')
print(' -modes List available suspend modes')
print(' -m mode Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode) print(' -m mode Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
print(' -o subdir Override the output subdirectory') print(' -o subdir Override the output subdirectory')
print(' -rtcwake t Use rtcwake to autoresume after <t> seconds (default: disabled)') print(' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)')
print(' -addlogs Add the dmesg and ftrace logs to the html output') print(' -addlogs Add the dmesg and ftrace logs to the html output')
print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)') print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)')
print(' [advanced]') print(' [advanced]')
...@@ -5012,23 +5076,25 @@ def printHelp(): ...@@ -5012,23 +5076,25 @@ def printHelp():
print(' be created in a new subdirectory with a summary page.') print(' be created in a new subdirectory with a summary page.')
print(' [debug]') print(' [debug]')
print(' -f Use ftrace to create device callgraphs (default: disabled)') print(' -f Use ftrace to create device callgraphs (default: disabled)')
print(' -maxdepth N limit the callgraph data to N call levels (default: 0=all)')
print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)') print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)')
print(' -flist Print the list of functions currently being captured in ftrace')
print(' -flistall Print all functions capable of being captured in ftrace')
print(' -fadd file Add functions to be graphed in the timeline from a list in a text file') print(' -fadd file Add functions to be graphed in the timeline from a list in a text file')
print(' -filter "d1,d2,..." Filter out all but this comma-delimited list of device names') print(' -filter "d1,d2,..." Filter out all but this comma-delimited list of device names')
print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)') print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)') print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)')
print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)') print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)') print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
print(' [utilities]') print(' [commands]')
print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)')
print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)')
print(' -summary directory Create a summary of all test in this dir')
print(' -modes List available suspend modes')
print(' -status Test to see if the system is enabled to run this tool')
print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table') print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table')
print(' -usbtopo Print out the current USB topology with power info') print(' -usbtopo Print out the current USB topology with power info')
print(' -usbauto Enable autosuspend for all connected USB devices') print(' -usbauto Enable autosuspend for all connected USB devices')
print(' [re-analyze data from previous runs]') print(' -flist Print the list of functions currently being captured in ftrace')
print(' -ftrace ftracefile Create HTML output using ftrace input') print(' -flistall Print all functions capable of being captured in ftrace')
print(' -dmesg dmesgfile Create HTML output using dmesg (not needed for kernel >= 3.15)')
print(' -summary directory Create a summary of all test in this dir')
print('') print('')
return True return True
...@@ -5076,9 +5142,18 @@ if __name__ == '__main__': ...@@ -5076,9 +5142,18 @@ if __name__ == '__main__':
sysvals.useprocmon = True sysvals.useprocmon = True
elif(arg == '-dev'): elif(arg == '-dev'):
sysvals.usedevsrc = True sysvals.usedevsrc = True
elif(arg == '-maxdepth'):
sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000)
elif(arg == '-rtcwake'): elif(arg == '-rtcwake'):
try:
val = args.next()
except:
doError('No rtcwake time supplied', True)
if val.lower() == 'off':
sysvals.rtcwake = False
else:
sysvals.rtcwake = True sysvals.rtcwake = True
sysvals.rtcwaketime = getArgInt('-rtcwake', args, 0, 3600) sysvals.rtcwaketime = getArgInt('-rtcwake', val, 0, 3600, False)
elif(arg == '-timeprec'): elif(arg == '-timeprec'):
sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6)) sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6))
elif(arg == '-mindev'): elif(arg == '-mindev'):
...@@ -5201,7 +5276,6 @@ if __name__ == '__main__': ...@@ -5201,7 +5276,6 @@ if __name__ == '__main__':
elif(cmd == 'usbauto'): elif(cmd == 'usbauto'):
setUSBDevicesAuto() setUSBDevicesAuto()
elif(cmd == 'summary'): elif(cmd == 'summary'):
print("Generating a summary of folder \"%s\"" % cmdarg)
runSummary(cmdarg, True) runSummary(cmdarg, True)
sys.exit() sys.exit()
......
.TH BOOTGRAPH 8
.SH NAME
bootgraph \- Kernel boot timing analysis
.SH SYNOPSIS
.ft B
.B bootgraph
.RB [ OPTIONS ]
.RB [ COMMAND ]
.SH DESCRIPTION
\fBbootgraph \fP reads the dmesg log from kernel boot and
creates an html representation of the initcall timeline up to the start
of the init process.
.PP
If no specific command is given, the tool reads the current dmesg log and
outputs bootgraph.html.
.PP
The tool can also augment the timeline with ftrace data on custom target
functions as well as full trace callgraphs.
.SH OPTIONS
.TP
\fB-h\fR
Print this help text
.TP
\fB-v\fR
Print the current tool version
.TP
\fB-addlogs\fR
Add the dmesg log to the html output. It will be viewable by
clicking a button in the timeline.
.TP
\fB-o \fIfile\fR
Override the HTML output filename (default: bootgraph.html)
.SS "Ftrace Debug"
.TP
\fB-f\fR
Use ftrace to add function detail (default: disabled)
.TP
\fB-callgraph\fR
Use ftrace to create initcall callgraphs (default: disabled). If -filter
is not used there will be one callgraph per initcall. This can produce
very large outputs, i.e. 10MB - 100MB.
.TP
\fB-maxdepth \fIlevel\fR
limit the callgraph trace depth to \fIlevel\fR (default: 2). This is
the best way to limit the output size when using -callgraph.
.TP
\fB-mincg \fIt\fR
Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0=all).
This reduces the html file size as there can be many tiny callgraphs
which are barely visible in the timeline.
The value is a float: e.g. 0.001 represents 1 us.
.TP
\fB-timeprec \fIn\fR
Number of significant digits in timestamps (0:S, 3:ms, [6:us])
.TP
\fB-expandcg\fR
pre-expand the callgraph data in the html output (default: disabled)
.TP
\fB-filter \fI"func1,func2,..."\fR
Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall)
.SH COMMANDS
.TP
\fB-reboot\fR
Reboot the machine and generate a new timeline automatically. Works in 4 steps.
1. updates grub with the required kernel parameters
2. installs a cron job which re-runs the tool after reboot
3. reboots the system
4. after startup, extracts the data and generates the timeline
.TP
\fB-manual\fR
Show the requirements to generate a new timeline manually. Requires 3 steps.
1. append the string to the kernel command line via your native boot manager.
2. reboot the system
3. after startup, re-run the tool with the same arguments and no command
.TP
\fB-dmesg \fIfile\fR
Create HTML output from an existing dmesg file.
.TP
\fB-ftrace \fIfile\fR
Create HTML output from an existing ftrace file (used with -dmesg).
.TP
\fB-flistall\fR
Print all ftrace functions capable of being captured. These are all the
possible values you can add to trace via the -filter argument.
.SH EXAMPLES
Create a timeline using the current dmesg log.
.IP
\f(CW$ bootgraph\fR
.PP
Create a timeline using the current dmesg and ftrace log.
.IP
\f(CW$ bootgraph -callgraph\fR
.PP
Create a timeline using the current dmesg, add the log to the html and change the name.
.IP
\f(CW$ bootgraph -addlogs -o myboot.html\fR
.PP
Capture a new boot timeline by automatically rebooting the machine.
.IP
\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR
.PP
Capture a new boot timeline with function trace data.
.IP
\f(CW$ sudo bootgraph -reboot -f\fR
.PP
Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller than 5ms.
.IP
\f(CW$ sudo bootgraph -reboot -callgraph -mincg 5\fR
.PP
Capture a new boot timeline with callgraph data over custom functions.
.IP
\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR
.PP
Capture a brand new boot timeline with manual reboot.
.IP
\f(CW$ sudo bootgraph -callgraph -manual\fR
.IP
\f(CW$ vi /etc/default/grub # add the CMDLINE string to your kernel params\fR
.IP
\f(CW$ sudo reboot # reboot the machine\fR
.IP
\f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR
.PP
.SH "SEE ALSO"
dmesg(1), update-grub(8), crontab(1), reboot(8)
.PP
.SH AUTHOR
.nf
Written by Todd Brandt <todd.e.brandt@linux.intel.com>
.TH SLEEPGRAPH 8
.SH NAME
sleepgraph \- Suspend/Resume timing analysis
.SH SYNOPSIS
.ft B
.B sleepgraph
.RB [ OPTIONS ]
.RB [ COMMAND ]
.SH DESCRIPTION
\fBsleepgraph \fP is designed to assist kernel and OS developers
in optimizing their linux stack's suspend/resume time. Using a kernel
image built with a few extra options enabled, the tool will execute a
suspend and capture dmesg and ftrace data until resume is complete.
This data is transformed into a device timeline and an optional
callgraph to give a detailed view of which devices/subsystems are
taking the most time in suspend/resume.
.PP
If no specific command is given, the default behavior is to initiate
a suspend/resume.
.PP
Generates output files in subdirectory: suspend-yymmdd-HHMMSS
html timeline : <hostname>_<mode>.html
raw dmesg file : <hostname>_<mode>_dmesg.txt
raw ftrace file : <hostname>_<mode>_ftrace.txt
.SH OPTIONS
.TP
\fB-h\fR
Print the help text.
.TP
\fB-v\fR
Print the current tool version.
.TP
\fB-verbose\fR
Print extra information during execution and analysis.
.TP
\fB-config \fIfile\fR
Pull arguments and config options from a file.
.TP
\fB-m \fImode\fR
Mode to initiate for suspend e.g. standby, freeze, mem (default: mem).
.TP
\fB-o \fIsubdir\fR
Override the output subdirectory. Use {date}, {time}, {hostname} for current values.
.sp
e.g. suspend-{hostname}-{date}-{time}
.TP
\fB-rtcwake \fIt\fR | off
Use rtcwake to autoresume after \fIt\fR seconds (default: 15). Set t to "off" to
disable rtcwake and require a user keypress to resume.
.TP
\fB-addlogs\fR
Add the dmesg and ftrace logs to the html output. They will be viewable by
clicking buttons in the timeline.
.SS "Advanced"
.TP
\fB-cmd \fIstr\fR
Run the timeline over a custom suspend command, e.g. pm-suspend. By default
the tool forces suspend via /sys/power/state so this allows testing over
an OS's official suspend method. The output file will change to
hostname_command.html and will autodetect which suspend mode was triggered.
.TP
\fB-filter \fI"d1,d2,..."\fR
Filter out all but these device callbacks. These strings can be device names
or module names. e.g. 0000:00:02.0, ata5, i915, usb, etc.
.TP
\fB-mindev \fIt\fR
Discard all device callbacks shorter than \fIt\fR milliseconds (default: 0.0).
This reduces the html file size as there can be many tiny callbacks which are barely
visible. The value is a float: e.g. 0.001 represents 1 us.
.TP
\fB-proc\fR
Add usermode process info into the timeline (default: disabled).
.TP
\fB-dev\fR
Add kernel source calls and threads to the timeline (default: disabled).
.TP
\fB-x2\fR
Run two suspend/resumes back to back (default: disabled).
.TP
\fB-x2delay \fIt\fR
Include \fIt\fR ms delay between multiple test runs (default: 0 ms).
.TP
\fB-predelay \fIt\fR
Include \fIt\fR ms delay before 1st suspend (default: 0 ms).
.TP
\fB-postdelay \fIt\fR
Include \fIt\fR ms delay after last resume (default: 0 ms).
.TP
\fB-multi \fIn d\fR
Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will
be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}.
.SS "Ftrace Debug"
.TP
\fB-f\fR
Use ftrace to create device callgraphs (default: disabled). This can produce
very large outputs, i.e. 10MB - 100MB.
.TP
\fB-maxdepth \fIlevel\fR
limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is
the best way to limit the output size when using callgraphs via -f.
.TP
\fB-expandcg\fR
pre-expand the callgraph data in the html output (default: disabled)
.TP
\fB-fadd \fIfile\fR
Add functions to be graphed in the timeline from a list in a text file
.TP
\fB-mincg \fIt\fR
Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0.0).
This reduces the html file size as there can be many tiny callgraphs
which are barely visible in the timeline.
The value is a float: e.g. 0.001 represents 1 us.
.TP
\fB-cgphase \fIp\fR
Only show callgraph data for phase \fIp\fR (e.g. suspend_late).
.TP
\fB-cgtest \fIn\fR
In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1).
.TP
\fB-timeprec \fIn\fR
Number of significant digits in timestamps (0:S, [3:ms], 6:us).
.SH COMMANDS
.TP
\fB-ftrace \fIfile\fR
Create HTML output from an existing ftrace file.
.TP
\fB-dmesg \fIfile\fR
Create HTML output from an existing dmesg file.
.TP
\fB-summary \fIindir\fR
Create a summary page of all tests in \fIindir\fR. Creates summary.html
in the current folder. The output page is a table of tests with
suspend and resume values sorted by suspend mode, host, and kernel.
Includes test averages by mode and links to the test html files.
.TP
\fB-modes\fR
List available suspend modes.
.TP
\fB-status\fR
Test to see if the system is able to run this tool. Use this along
with any options you intend to use to see if they will work.
.TP
\fB-fpdt\fR
Print out the contents of the ACPI Firmware Performance Data Table.
.TP
\fB-usbtopo\fR
Print out the current USB topology with power info.
.TP
\fB-usbauto\fR
Enable autosuspend for all connected USB devices.
.TP
\fB-flist\fR
Print the list of ftrace functions currently being captured. Functions
that are not available as symbols in the current kernel are shown in red.
By default, the tool traces a list of important suspend/resume functions
in order to better fill out the timeline. If the user has added their own
with -fadd they will also be checked.
.TP
\fB-flistall\fR
Print all ftrace functions capable of being captured. These are all the
possible values you can add to trace via the -fadd argument.
.SH EXAMPLES
.SS "Simple Commands"
Check which suspend modes are currently supported.
.IP
\f(CW$ sleepgraph -modes\fR
.PP
Read the Firmware Performance Data Table (FPDT)
.IP
\f(CW$ sudo sleepgraph -fpdt\fR
.PP
Print out the current USB power topology
.IP
\f(CW$ sleepgraph -usbtopo
.PP
Verify that you can run a command with a set of arguments
.IP
\f(CW$ sudo sleepgraph -f -rtcwake 30 -status
.PP
Generate a summary of all timelines in a particular folder.
.IP
\f(CW$ sleepgraph -summary ~/workspace/myresults/\fR
.PP
Re-generate the html output from a previous run's dmesg and ftrace log.
.IP
\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR
.PP
.SS "Capturing Simple Timelines"
Execute a mem suspend with a 15 second wakeup. Include the logs in the html.
.IP
\f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR
.PP
Execute a standby with a 15 second wakeup. Change the output folder name.
.IP
\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{hostname}-{date}-{time}"\fR
.PP
Execute a freeze with no wakeup (require keypress). Change output folder name.
.IP
\f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR
.PP
.SS "Capturing Advanced Timelines"
Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger.
.IP
\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR
.PP
Run two suspends back to back, include a 500ms delay before, after, and in between runs.
.IP
\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR
.PP
Do a batch run of 10 freezes with 30 seconds delay between runs.
.IP
\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR
.PP
Execute a suspend using a custom command.
.IP
\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
.PP
.SS "Capturing Timelines with Callgraph Data"
Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
.IP
\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR
.PP
Capture a full callgraph across all suspend, then filter the html by a single phase.
.IP
\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f\fR
.IP
\f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume
.PP
.SH "SEE ALSO"
dmesg(1)
.PP
.SH AUTHOR
.nf
Written by Todd Brandt <todd.e.brandt@linux.intel.com>
...@@ -353,6 +353,14 @@ def split_csv(): ...@@ -353,6 +353,14 @@ def split_csv():
os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index)) os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index))
os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index)) os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index))
def fix_ownership(path):
"""Change the owner of the file to SUDO_UID, if required"""
uid = os.environ.get('SUDO_UID')
gid = os.environ.get('SUDO_GID')
if uid is not None:
os.chown(path, int(uid), int(gid))
def cleanup_data_files(): def cleanup_data_files():
""" clean up existing data files """ """ clean up existing data files """
...@@ -518,12 +526,16 @@ else: ...@@ -518,12 +526,16 @@ else:
if not os.path.exists('results'): if not os.path.exists('results'):
os.mkdir('results') os.mkdir('results')
# The regular user needs to own the directory, not root.
fix_ownership('results')
os.chdir('results') os.chdir('results')
if os.path.exists(testname): if os.path.exists(testname):
print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
sys.exit() sys.exit()
os.mkdir(testname) os.mkdir(testname)
# The regular user needs to own the directory, not root.
fix_ownership(testname)
os.chdir(testname) os.chdir(testname)
# Temporary (or perhaps not) # Temporary (or perhaps not)
...@@ -566,4 +578,9 @@ plot_scaled_cpu() ...@@ -566,4 +578,9 @@ plot_scaled_cpu()
plot_boost_cpu() plot_boost_cpu()
plot_ghz_cpu() plot_ghz_cpu()
# It is preferrable, but not necessary, that the regular user owns the files, not root.
for root, dirs, files in os.walk('.'):
for f in files:
fix_ownership(f)
os.chdir('../../') os.chdir('../../')
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment