From: Michael Bottini <[email protected]>
Devices that appear under the Intel VMD host bridge are not visible to BIOS
and therefore not programmed by BIOS with ASPM settings. For these devices,
it is necessary for the driver to configure ASPM. Since ASPM settings are
adjustable at runtime by module parameter, use the same mechanism to allow
drivers to override the default (in this case never configured) BIOS policy
to ASPM_STATE_ALL. Then, reconfigure ASPM on the link.
Signed-off-by: Michael Bottini <[email protected]>
Signed-off-by: David E. Box <[email protected]>
---
drivers/pci/pci.h | 2 ++
drivers/pci/pcie/aspm.c | 18 ++++++++++++++++++
2 files changed, 20 insertions(+)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 3d60cabde1a1..172ec914e988 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -562,11 +562,13 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev);
void pcie_aspm_exit_link_state(struct pci_dev *pdev);
void pcie_aspm_pm_state_change(struct pci_dev *pdev);
void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
+void pcie_aspm_policy_override(struct pci_dev *dev);
#else
static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
+static inline void pcie_aspm_policy_override(struct pci_dev *dev) {}
#endif
#ifdef CONFIG_PCIE_ECRC
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 52c74682601a..ccb98586bf0d 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1140,6 +1140,24 @@ int pci_disable_link_state(struct pci_dev *pdev, int state)
}
EXPORT_SYMBOL(pci_disable_link_state);
+void pcie_aspm_policy_override(struct pci_dev *pdev)
+{
+ struct pcie_link_state *link = pcie_aspm_get_link(pdev);
+
+ down_read(&pci_bus_sem);
+ mutex_lock(&aspm_lock);
+
+ if (link) {
+ link->aspm_default = ASPM_STATE_ALL;
+ pcie_config_aspm_link(link, policy_to_aspm_state(link));
+ pcie_set_clkpm(link, policy_to_clkpm_state(link));
+ }
+
+ mutex_unlock(&aspm_lock);
+ up_read(&pci_bus_sem);
+}
+EXPORT_SYMBOL(pcie_aspm_policy_override);
+
static int pcie_aspm_set_policy(const char *val,
const struct kernel_param *kp)
{
--
2.25.1
From: Michael Bottini <[email protected]>
On Tiger Lake and Alder Lake platforms, VMD controllers do not have ASPM
enabled nor LTR values set by BIOS. This leads high power consumption on
these platforms when VMD is enabled as reported in bugzilla [1]. Enable
these features in the VMD driver using pcie_aspm_policy_override() to set
the ASPM policy for the root ports.
To do this, add an additional flag in VMD features to specify devices that
must have their respective policies overridden.
[1] https://bugzilla.kernel.org/show_bug.cgi?id=213717
Signed-off-by: Michael Bottini <[email protected]>
Signed-off-by: David E. Box <[email protected]>
---
drivers/pci/controller/vmd.c | 40 +++++++++++++++++++++++++++++++++---
1 file changed, 37 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index a45e8e59d3d4..0d0b8888cd90 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -20,6 +20,8 @@
#include <asm/irqdomain.h>
+#include "../pci.h"
+
#define VMD_CFGBAR 0
#define VMD_MEMBAR1 2
#define VMD_MEMBAR2 4
@@ -67,6 +69,12 @@ enum vmd_features {
* interrupt handling.
*/
VMD_FEAT_CAN_BYPASS_MSI_REMAP = (1 << 4),
+
+ /*
+ * Device must have ASPM policy overridden, as its default policy is
+ * incorrect.
+ */
+ VMD_FEAT_QUIRK_OVERRIDE_ASPM = (1 << 5),
};
static DEFINE_IDA(vmd_instance_ida);
@@ -661,6 +669,27 @@ static int vmd_alloc_irqs(struct vmd_dev *vmd)
return 0;
}
+/*
+ * Override the BIOS ASPM policy and set the LTR value for PCI storage
+ * devices on the VMD bride.
+ */
+int vmd_enable_aspm(struct pci_dev *pdev, void *userdata)
+{
+ int features = *(int *)userdata;
+
+ if (features & VMD_FEAT_QUIRK_OVERRIDE_ASPM &&
+ pdev->class == PCI_CLASS_STORAGE_EXPRESS) {
+ int pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR);
+
+ if (pos) {
+ pci_write_config_word(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, 0x1003);
+ pci_write_config_word(pdev, pos + PCI_LTR_MAX_NOSNOOP_LAT, 0x1003);
+ pcie_aspm_policy_override(pdev);
+ }
+ }
+ return 0;
+}
+
static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
{
struct pci_sysdata *sd = &vmd->sysdata;
@@ -807,6 +836,8 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
pci_scan_child_bus(vmd->bus);
pci_assign_unassigned_bus_resources(vmd->bus);
+ pci_walk_bus(vmd->bus, vmd_enable_aspm, &features);
+
/*
* VMD root buses are virtual and don't return true on pci_is_pcie()
* and will fail pcie_bus_configure_settings() early. It can instead be
@@ -948,15 +979,18 @@ static const struct pci_device_id vmd_ids[] = {
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
VMD_FEAT_HAS_BUS_RESTRICTIONS |
- VMD_FEAT_OFFSET_FIRST_VECTOR,},
+ VMD_FEAT_OFFSET_FIRST_VECTOR |
+ VMD_FEAT_QUIRK_OVERRIDE_ASPM,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
VMD_FEAT_HAS_BUS_RESTRICTIONS |
- VMD_FEAT_OFFSET_FIRST_VECTOR,},
+ VMD_FEAT_OFFSET_FIRST_VECTOR |
+ VMD_FEAT_QUIRK_OVERRIDE_ASPM,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
VMD_FEAT_HAS_BUS_RESTRICTIONS |
- VMD_FEAT_OFFSET_FIRST_VECTOR,},
+ VMD_FEAT_OFFSET_FIRST_VECTOR |
+ VMD_FEAT_QUIRK_OVERRIDE_ASPM,},
{0,}
};
MODULE_DEVICE_TABLE(pci, vmd_ids);
--
2.25.1
Hi David,
[...]
> @@ -562,11 +562,13 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev);
> void pcie_aspm_exit_link_state(struct pci_dev *pdev);
> void pcie_aspm_pm_state_change(struct pci_dev *pdev);
> void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
> +void pcie_aspm_policy_override(struct pci_dev *dev);
> #else
> static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
> static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
> static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
> static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
> +static inline void pcie_aspm_policy_override(struct pci_dev *dev) {}
> #endif
A small nitpick, and a slight OCD on my part, so feel free to ignore this,
of course: a missing space between curly brackets, to keep things aligned
with previous definitions.
> @@ -1140,6 +1140,24 @@ int pci_disable_link_state(struct pci_dev *pdev, int state)
> }
> EXPORT_SYMBOL(pci_disable_link_state);
>
> +void pcie_aspm_policy_override(struct pci_dev *pdev)
> +{
> + struct pcie_link_state *link = pcie_aspm_get_link(pdev);
> +
> + down_read(&pci_bus_sem);
> + mutex_lock(&aspm_lock);
> +
> + if (link) {
> + link->aspm_default = ASPM_STATE_ALL;
> + pcie_config_aspm_link(link, policy_to_aspm_state(link));
> + pcie_set_clkpm(link, policy_to_clkpm_state(link));
> + }
> +
> + mutex_unlock(&aspm_lock);
> + up_read(&pci_bus_sem);
> +}
> +EXPORT_SYMBOL(pcie_aspm_policy_override);
What about the following version where if we have no link (albeit, I am not
sure how often this is going to be the case?) then we don't even attempt to
get a hold on the lock and such:
void pcie_aspm_policy_override(struct pci_dev *pdev)
{
struct pcie_link_state *link = pcie_aspm_get_link(pdev);
if (!link)
return;
down_read(&pci_bus_sem);
mutex_lock(&aspm_lock);
link->aspm_default = ASPM_STATE_ALL;
pcie_config_aspm_link(link, policy_to_aspm_state(link));
pcie_set_clkpm(link, policy_to_clkpm_state(link));
mutex_unlock(&aspm_lock);
up_read(&pci_bus_sem);
}
What do you think? Would this make sense?
Krzysztof