From e61a41256edf9f425039129757af4a80b5ed8162 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 9 Aug 2019 08:01:17 +0530
Subject: [PATCH 1/4] cpufreq: dev_pm_qos_update_request() can return 1 on
success
dev_pm_qos_update_request() can return 1 on success, so don't treat
it as an error.
Fixes: 18c49926c4bf ("cpufreq: Add QoS requests for userspace constraints")
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/cpufreq/cpufreq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 8dda62367816..c28ebf2810f1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2528,7 +2528,7 @@ static int cpufreq_boost_set_sw(int state)
}
ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max);
- if (ret)
+ if (ret < 0)
break;
}
From 600f5badb78c316146d062cfd7af4a2cfb655baa Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 7 Aug 2019 12:36:01 +0530
Subject: [PATCH 2/4] cpufreq: schedutil: Don't skip freq update when limits
change
To avoid reducing the frequency of a CPU prematurely, we skip reducing
the frequency if the CPU had been busy recently.
This should not be done when the limits of the policy are changed, for
example due to thermal throttling. We should always get the frequency
within the new limits as soon as possible.
Trying to fix this by using only one flag, i.e. need_freq_update, can
lead to a race condition where the flag gets cleared without forcing us
to change the frequency at least once. And so this patch introduces
another flag to avoid that race condition.
Fixes: ecd288429126 ("cpufreq: schedutil: Don't set next_freq to UINT_MAX")
Cc: v4.18+ <stable@vger.kernel.org> # v4.18+
Reported-by: Doug Smythies <dsmythies@telus.net>
Tested-by: Doug Smythies <dsmythies@telus.net>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
kernel/sched/cpufreq_schedutil.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 636ca6f88c8e..867b4bb6d4be 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -40,6 +40,7 @@ struct sugov_policy {
struct task_struct *thread;
bool work_in_progress;
+ bool limits_changed;
bool need_freq_update;
};
@@ -89,8 +90,11 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (unlikely(sg_policy->need_freq_update))
+ if (unlikely(sg_policy->limits_changed)) {
+ sg_policy->limits_changed = false;
+ sg_policy->need_freq_update = true;
return true;
+ }
delta_ns = time - sg_policy->last_freq_update_time;
@@ -437,7 +441,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -457,7 +461,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
- busy = sugov_cpu_is_busy(sg_cpu);
+ /* Limits may have changed, don't skip frequency update */
+ busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
@@ -831,6 +836,7 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->last_freq_update_time = 0;
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
+ sg_policy->limits_changed = false;
sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
@@ -879,7 +885,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
mutex_unlock(&sg_policy->work_lock);
}
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
struct cpufreq_governor schedutil_gov = {
From accd2dd72c8f087441d725dd916688171519e4e6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 9 Aug 2019 10:23:57 +0200
Subject: [PATCH 3/4] PCI/ASPM: Add pcie_aspm_enabled()
Add a function checking whether or not PCIe ASPM has been enabled for
a given device.
It will be used by the NVMe driver to decide how to handle the
device during system suspend.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
drivers/pci/pcie/aspm.c | 20 ++++++++++++++++++++
include/linux/pci.h | 2 ++
2 files changed, 22 insertions(+)
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index e44af7f4d37f..464f8f92653f 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1170,6 +1170,26 @@ static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp)
module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy,
NULL, 0644);
+/**
+ * pcie_aspm_enabled - Check if PCIe ASPM has been enabled for a device.
+ * @pdev: Target device.
+ */
+bool pcie_aspm_enabled(struct pci_dev *pdev)
+{
+ struct pci_dev *bridge = pci_upstream_bridge(pdev);
+ bool ret;
+
+ if (!bridge)
+ return false;
+
+ mutex_lock(&aspm_lock);
+ ret = bridge->link_state ? !!bridge->link_state->aspm_enabled : false;
+ mutex_unlock(&aspm_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pcie_aspm_enabled);
+
#ifdef CONFIG_PCIEASPM_DEBUG
static ssize_t link_state_show(struct device *dev,
struct device_attribute *attr,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9e700d9f9f28..82e4cd1b7ac3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1567,8 +1567,10 @@ extern bool pcie_ports_native;
#ifdef CONFIG_PCIEASPM
bool pcie_aspm_support_enabled(void);
+bool pcie_aspm_enabled(struct pci_dev *pdev);
#else
static inline bool pcie_aspm_support_enabled(void) { return false; }
+static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
#endif
#ifdef CONFIG_PCIEAER
From 4eaefe8c621c6195c91044396ed8060c179f7aae Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 8 Aug 2019 23:58:38 +0200
Subject: [PATCH 4/4] nvme-pci: Allow PCI bus-level PM to be used if ASPM is
disabled
One of the modifications made by commit d916b1be94b6 ("nvme-pci: use
host managed power state for suspend") was adding a pci_save_state()
call to nvme_suspend() so as to instruct the PCI bus type to leave
devices handled by the nvme driver in D0 during suspend-to-idle.
That was done with the assumption that ASPM would transition the
device's PCIe link into a low-power state when the device became
inactive. However, if ASPM is disabled for the device, its PCIe
link will stay in L0 and in that case commit d916b1be94b6 is likely
to cause the energy used by the system while suspended to increase.
Namely, if the device in question works in accordance with the PCIe
specification, putting it into D3hot causes its PCIe link to go to
L1 or L2/L3 Ready, which is lower-power than L0. Since the energy
used by the system while suspended depends on the state of its PCIe
link (as a general rule, the lower-power the state of the link, the
less energy the system will use), putting the device into D3hot
during suspend-to-idle should be more energy-efficient that leaving
it in D0 with disabled ASPM.
For this reason, avoid leaving NVMe devices with disabled ASPM in D0
during suspend-to-idle. Instead, shut them down entirely and let
the PCI bus type put them into D3.
Fixes: d916b1be94b6 ("nvme-pci: use host managed power state for suspend")
Link: https://lore.kernel.org/linux-pm/2763495.NmdaWeg79L@kreacher/T/#t
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
---
drivers/nvme/host/pci.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index db160cee42ad..108e109e99f1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2846,7 +2846,7 @@ static int nvme_resume(struct device *dev)
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
struct nvme_ctrl *ctrl = &ndev->ctrl;
- if (pm_resume_via_firmware() || !ctrl->npss ||
+ if (ndev->last_ps == U32_MAX ||
nvme_set_power_state(ctrl, ndev->last_ps) != 0)
nvme_reset_ctrl(ctrl);
return 0;
@@ -2859,6 +2859,8 @@ static int nvme_suspend(struct device *dev)
struct nvme_ctrl *ctrl = &ndev->ctrl;
int ret = -EBUSY;
+ ndev->last_ps = U32_MAX;
+
/*
* The platform does not remove power for a kernel managed suspend so
* use host managed nvme power settings for lowest idle power if
@@ -2866,8 +2868,14 @@ static int nvme_suspend(struct device *dev)
* shutdown. But if the firmware is involved after the suspend or the
* device does not support any non-default power states, shut down the
* device fully.
+ *
+ * If ASPM is not enabled for the device, shut down the device and allow
+ * the PCI bus layer to put it into D3 in order to take the PCIe link
+ * down, so as to allow the platform to achieve its minimum low-power
+ * state (which may not be possible if the link is up).
*/
- if (pm_suspend_via_firmware() || !ctrl->npss) {
+ if (pm_suspend_via_firmware() || !ctrl->npss ||
+ !pcie_aspm_enabled(pdev)) {
nvme_dev_disable(ndev, true);
return 0;
}
@@ -2880,7 +2888,6 @@ static int nvme_suspend(struct device *dev)
ctrl->state != NVME_CTRL_ADMIN_ONLY)
goto unfreeze;
- ndev->last_ps = 0;
ret = nvme_get_power_state(ctrl, &ndev->last_ps);
if (ret < 0)
goto unfreeze;