PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/*
|
|
|
|
* File: drivers/pci/pcie/aspm.c
|
|
|
|
* Enabling PCIE link L0s/L1 state and Clock Power Management
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Intel
|
|
|
|
* Copyright (C) Zhang Yanmin (yanmin.zhang@intel.com)
|
|
|
|
* Copyright (C) Shaohua Li (shaohua.li@intel.com)
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/moduleparam.h>
|
|
|
|
#include <linux/pci.h>
|
|
|
|
#include <linux/pci_regs.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/pm.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/slab.h>
|
2008-12-09 20:05:09 +08:00
|
|
|
#include <linux/jiffies.h>
|
2009-01-06 07:21:04 +08:00
|
|
|
#include <linux/delay.h>
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
#include <linux/pci-aspm.h>
|
|
|
|
#include "../pci.h"
|
|
|
|
|
|
|
|
#ifdef MODULE_PARAM_PREFIX
|
|
|
|
#undef MODULE_PARAM_PREFIX
|
|
|
|
#endif
|
|
|
|
#define MODULE_PARAM_PREFIX "pcie_aspm."
|
|
|
|
|
2009-05-13 11:14:58 +08:00
|
|
|
struct aspm_latency {
|
|
|
|
u32 l0s; /* L0s latency (nsec) */
|
|
|
|
u32 l1; /* L1 latency (nsec) */
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct pcie_link_state {
|
2009-05-13 11:11:33 +08:00
|
|
|
struct list_head sibling;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
struct pci_dev *pdev;
|
2008-12-19 09:27:42 +08:00
|
|
|
bool downstream_has_switch;
|
|
|
|
|
|
|
|
struct pcie_link_state *parent;
|
|
|
|
struct list_head children;
|
|
|
|
struct list_head link;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
/* ASPM state */
|
2009-05-13 11:12:43 +08:00
|
|
|
u32 aspm_support:2; /* Supported ASPM state */
|
|
|
|
u32 aspm_enabled:2; /* Enabled ASPM state */
|
|
|
|
u32 aspm_default:2; /* Default ASPM state by BIOS */
|
|
|
|
|
2009-05-13 11:15:38 +08:00
|
|
|
/* Clock PM state */
|
|
|
|
u32 clkpm_capable:1; /* Clock PM capable? */
|
|
|
|
u32 clkpm_enabled:1; /* Current Clock PM state */
|
|
|
|
u32 clkpm_default:1; /* Default Clock PM state by BIOS */
|
|
|
|
|
2009-05-13 11:14:58 +08:00
|
|
|
/* Latencies */
|
|
|
|
struct aspm_latency latency; /* Exit latency */
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/*
|
2009-05-13 11:14:58 +08:00
|
|
|
* Endpoint acceptable latencies. A pcie downstream port only
|
|
|
|
* has one slot under it, so at most there are 8 functions.
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
*/
|
2009-05-13 11:14:58 +08:00
|
|
|
struct aspm_latency acceptable[8];
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
};
|
|
|
|
|
2008-07-23 10:32:42 +08:00
|
|
|
static int aspm_disabled, aspm_force;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
static DEFINE_MUTEX(aspm_lock);
|
|
|
|
static LIST_HEAD(link_list);
|
|
|
|
|
|
|
|
#define POLICY_DEFAULT 0 /* BIOS default setting */
|
|
|
|
#define POLICY_PERFORMANCE 1 /* high performance */
|
|
|
|
#define POLICY_POWERSAVE 2 /* high power saving */
|
|
|
|
static int aspm_policy;
|
|
|
|
static const char *policy_str[] = {
|
|
|
|
[POLICY_DEFAULT] = "default",
|
|
|
|
[POLICY_PERFORMANCE] = "performance",
|
|
|
|
[POLICY_POWERSAVE] = "powersave"
|
|
|
|
};
|
|
|
|
|
2009-01-06 07:21:04 +08:00
|
|
|
#define LINK_RETRAIN_TIMEOUT HZ
|
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
static int policy_to_aspm_state(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
switch (aspm_policy) {
|
|
|
|
case POLICY_PERFORMANCE:
|
|
|
|
/* Disable ASPM and Clock PM */
|
|
|
|
return 0;
|
|
|
|
case POLICY_POWERSAVE:
|
|
|
|
/* Enable ASPM L0s/L1 */
|
2009-05-13 11:12:43 +08:00
|
|
|
return PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
case POLICY_DEFAULT:
|
2009-05-13 11:12:43 +08:00
|
|
|
return link_state->aspm_default;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int policy_to_clkpm_state(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
switch (aspm_policy) {
|
|
|
|
case POLICY_PERFORMANCE:
|
|
|
|
/* Disable ASPM and Clock PM */
|
|
|
|
return 0;
|
|
|
|
case POLICY_POWERSAVE:
|
|
|
|
/* Disable Clock PM */
|
|
|
|
return 1;
|
|
|
|
case POLICY_DEFAULT:
|
2009-05-13 11:15:38 +08:00
|
|
|
return link_state->clkpm_default;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pcie_set_clock_pm(struct pci_dev *pdev, int enable)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
int pos;
|
|
|
|
u16 reg16;
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
if (!pos)
|
|
|
|
return;
|
|
|
|
pci_read_config_word(child_dev, pos + PCI_EXP_LNKCTL, ®16);
|
|
|
|
if (enable)
|
|
|
|
reg16 |= PCI_EXP_LNKCTL_CLKREQ_EN;
|
|
|
|
else
|
|
|
|
reg16 &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
|
|
|
|
pci_write_config_word(child_dev, pos + PCI_EXP_LNKCTL, reg16);
|
|
|
|
}
|
2009-05-13 11:15:38 +08:00
|
|
|
link_state->clkpm_enabled = !!enable;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
static void pcie_check_clock_pm(struct pci_dev *pdev, int blacklist)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
{
|
|
|
|
int pos;
|
|
|
|
u32 reg32;
|
|
|
|
u16 reg16;
|
|
|
|
int capable = 1, enabled = 1;
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
/* All functions should have the same cap and state, take the worst */
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
if (!pos)
|
|
|
|
return;
|
|
|
|
pci_read_config_dword(child_dev, pos + PCI_EXP_LNKCAP, ®32);
|
|
|
|
if (!(reg32 & PCI_EXP_LNKCAP_CLKPM)) {
|
|
|
|
capable = 0;
|
|
|
|
enabled = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
pci_read_config_word(child_dev, pos + PCI_EXP_LNKCTL, ®16);
|
|
|
|
if (!(reg16 & PCI_EXP_LNKCTL_CLKREQ_EN))
|
|
|
|
enabled = 0;
|
|
|
|
}
|
2009-05-13 11:15:38 +08:00
|
|
|
link_state->clkpm_enabled = enabled;
|
|
|
|
link_state->clkpm_default = enabled;
|
2008-12-19 09:27:42 +08:00
|
|
|
if (!blacklist) {
|
2009-05-13 11:15:38 +08:00
|
|
|
link_state->clkpm_capable = capable;
|
2008-12-19 09:27:42 +08:00
|
|
|
pcie_set_clock_pm(pdev, policy_to_clkpm_state(pdev));
|
|
|
|
} else {
|
2009-05-13 11:15:38 +08:00
|
|
|
link_state->clkpm_capable = 0;
|
2008-12-19 09:27:42 +08:00
|
|
|
pcie_set_clock_pm(pdev, 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool pcie_aspm_downstream_has_switch(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
if (child_dev->pcie_type == PCI_EXP_TYPE_UPSTREAM)
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pcie_aspm_configure_common_clock: check if the 2 ends of a link
|
|
|
|
* could use common clock. If they are, configure them to use the
|
|
|
|
* common clock. That will reduce the ASPM state exit latency.
|
|
|
|
*/
|
|
|
|
static void pcie_aspm_configure_common_clock(struct pci_dev *pdev)
|
|
|
|
{
|
2008-12-09 20:05:09 +08:00
|
|
|
int pos, child_pos, i = 0;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
u16 reg16 = 0;
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
int same_clock = 1;
|
2008-12-09 20:05:09 +08:00
|
|
|
unsigned long start_jiffies;
|
|
|
|
u16 child_regs[8], parent_reg;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/*
|
|
|
|
* all functions of a slot should have the same Slot Clock
|
|
|
|
* Configuration, so just check one function
|
|
|
|
* */
|
|
|
|
child_dev = list_entry(pdev->subordinate->devices.next, struct pci_dev,
|
|
|
|
bus_list);
|
|
|
|
BUG_ON(!child_dev->is_pcie);
|
|
|
|
|
|
|
|
/* Check downstream component if bit Slot Clock Configuration is 1 */
|
|
|
|
child_pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
pci_read_config_word(child_dev, child_pos + PCI_EXP_LNKSTA, ®16);
|
|
|
|
if (!(reg16 & PCI_EXP_LNKSTA_SLC))
|
|
|
|
same_clock = 0;
|
|
|
|
|
|
|
|
/* Check upstream component if bit Slot Clock Configuration is 1 */
|
|
|
|
pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
|
|
|
|
pci_read_config_word(pdev, pos + PCI_EXP_LNKSTA, ®16);
|
|
|
|
if (!(reg16 & PCI_EXP_LNKSTA_SLC))
|
|
|
|
same_clock = 0;
|
|
|
|
|
|
|
|
/* Configure downstream component, all functions */
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
child_pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
pci_read_config_word(child_dev, child_pos + PCI_EXP_LNKCTL,
|
|
|
|
®16);
|
2008-12-09 20:05:09 +08:00
|
|
|
child_regs[i] = reg16;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (same_clock)
|
|
|
|
reg16 |= PCI_EXP_LNKCTL_CCC;
|
|
|
|
else
|
|
|
|
reg16 &= ~PCI_EXP_LNKCTL_CCC;
|
|
|
|
pci_write_config_word(child_dev, child_pos + PCI_EXP_LNKCTL,
|
|
|
|
reg16);
|
2008-12-09 20:05:09 +08:00
|
|
|
i++;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Configure upstream component */
|
|
|
|
pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16);
|
2008-12-09 20:05:09 +08:00
|
|
|
parent_reg = reg16;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (same_clock)
|
|
|
|
reg16 |= PCI_EXP_LNKCTL_CCC;
|
|
|
|
else
|
|
|
|
reg16 &= ~PCI_EXP_LNKCTL_CCC;
|
|
|
|
pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);
|
|
|
|
|
|
|
|
/* retrain link */
|
|
|
|
reg16 |= PCI_EXP_LNKCTL_RL;
|
|
|
|
pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);
|
|
|
|
|
|
|
|
/* Wait for link training end */
|
2009-01-06 07:21:04 +08:00
|
|
|
/* break out after waiting for timeout */
|
2008-12-09 20:05:09 +08:00
|
|
|
start_jiffies = jiffies;
|
2009-01-06 07:21:04 +08:00
|
|
|
for (;;) {
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
pci_read_config_word(pdev, pos + PCI_EXP_LNKSTA, ®16);
|
|
|
|
if (!(reg16 & PCI_EXP_LNKSTA_LT))
|
|
|
|
break;
|
2009-01-06 07:21:04 +08:00
|
|
|
if (time_after(jiffies, start_jiffies + LINK_RETRAIN_TIMEOUT))
|
|
|
|
break;
|
|
|
|
msleep(1);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
2008-12-09 20:05:09 +08:00
|
|
|
/* training failed -> recover */
|
2009-01-06 07:21:04 +08:00
|
|
|
if (reg16 & PCI_EXP_LNKSTA_LT) {
|
2008-12-09 20:05:09 +08:00
|
|
|
dev_printk (KERN_ERR, &pdev->dev, "ASPM: Could not configure"
|
|
|
|
" common clock\n");
|
|
|
|
i = 0;
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices,
|
|
|
|
bus_list) {
|
|
|
|
child_pos = pci_find_capability(child_dev,
|
|
|
|
PCI_CAP_ID_EXP);
|
|
|
|
pci_write_config_word(child_dev,
|
|
|
|
child_pos + PCI_EXP_LNKCTL,
|
|
|
|
child_regs[i]);
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, parent_reg);
|
|
|
|
}
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* calc_L0S_latency: Convert L0s latency encoding to ns
|
|
|
|
*/
|
|
|
|
static unsigned int calc_L0S_latency(unsigned int latency_encoding, int ac)
|
|
|
|
{
|
|
|
|
unsigned int ns = 64;
|
|
|
|
|
|
|
|
if (latency_encoding == 0x7) {
|
|
|
|
if (ac)
|
|
|
|
ns = -1U;
|
|
|
|
else
|
|
|
|
ns = 5*1000; /* > 4us */
|
|
|
|
} else
|
|
|
|
ns *= (1 << latency_encoding);
|
|
|
|
return ns;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* calc_L1_latency: Convert L1 latency encoding to ns
|
|
|
|
*/
|
|
|
|
static unsigned int calc_L1_latency(unsigned int latency_encoding, int ac)
|
|
|
|
{
|
|
|
|
unsigned int ns = 1000;
|
|
|
|
|
|
|
|
if (latency_encoding == 0x7) {
|
|
|
|
if (ac)
|
|
|
|
ns = -1U;
|
|
|
|
else
|
|
|
|
ns = 65*1000; /* > 64us */
|
|
|
|
} else
|
|
|
|
ns *= (1 << latency_encoding);
|
|
|
|
return ns;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pcie_aspm_get_cap_device(struct pci_dev *pdev, u32 *state,
|
|
|
|
unsigned int *l0s, unsigned int *l1, unsigned int *enabled)
|
|
|
|
{
|
|
|
|
int pos;
|
|
|
|
u16 reg16;
|
|
|
|
u32 reg32;
|
|
|
|
unsigned int latency;
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
*l0s = *l1 = *enabled = 0;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
|
|
|
|
pci_read_config_dword(pdev, pos + PCI_EXP_LNKCAP, ®32);
|
|
|
|
*state = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10;
|
|
|
|
if (*state != PCIE_LINK_STATE_L0S &&
|
|
|
|
*state != (PCIE_LINK_STATE_L1|PCIE_LINK_STATE_L0S))
|
|
|
|
*state = 0;
|
|
|
|
if (*state == 0)
|
|
|
|
return;
|
|
|
|
|
|
|
|
latency = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12;
|
|
|
|
*l0s = calc_L0S_latency(latency, 0);
|
|
|
|
if (*state & PCIE_LINK_STATE_L1) {
|
|
|
|
latency = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15;
|
|
|
|
*l1 = calc_L1_latency(latency, 0);
|
|
|
|
}
|
|
|
|
pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16);
|
|
|
|
*enabled = reg16 & (PCIE_LINK_STATE_L0S|PCIE_LINK_STATE_L1);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pcie_aspm_cap_init(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
2009-05-13 11:12:43 +08:00
|
|
|
u32 support, l0s, l1, enabled;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
/* upstream component states */
|
2009-05-13 11:12:43 +08:00
|
|
|
pcie_aspm_get_cap_device(pdev, &support, &l0s, &l1, &enabled);
|
|
|
|
link_state->aspm_support = support;
|
2009-05-13 11:14:58 +08:00
|
|
|
link_state->latency.l0s = l0s;
|
|
|
|
link_state->latency.l1 = l1;
|
2009-05-13 11:12:43 +08:00
|
|
|
link_state->aspm_enabled = enabled;
|
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/* downstream component states, all functions have the same setting */
|
|
|
|
child_dev = list_entry(pdev->subordinate->devices.next, struct pci_dev,
|
|
|
|
bus_list);
|
2009-05-13 11:12:43 +08:00
|
|
|
pcie_aspm_get_cap_device(child_dev, &support, &l0s, &l1, &enabled);
|
|
|
|
link_state->aspm_support &= support;
|
2009-05-13 11:14:58 +08:00
|
|
|
link_state->latency.l0s = max_t(u32, link_state->latency.l0s, l0s);
|
|
|
|
link_state->latency.l1 = max_t(u32, link_state->latency.l1, l1);
|
2009-05-13 11:12:43 +08:00
|
|
|
|
|
|
|
if (!link_state->aspm_support)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
return;
|
2009-05-13 11:12:43 +08:00
|
|
|
|
|
|
|
link_state->aspm_enabled &= link_state->aspm_support;
|
|
|
|
link_state->aspm_default = link_state->aspm_enabled;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
/* ENDPOINT states*/
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
int pos;
|
|
|
|
u32 reg32;
|
|
|
|
unsigned int latency;
|
2009-05-13 11:14:58 +08:00
|
|
|
struct aspm_latency *acceptable =
|
|
|
|
&link_state->acceptable[PCI_FUNC(child_dev->devfn)];
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
if (child_dev->pcie_type != PCI_EXP_TYPE_ENDPOINT &&
|
|
|
|
child_dev->pcie_type != PCI_EXP_TYPE_LEG_END)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
pci_read_config_dword(child_dev, pos + PCI_EXP_DEVCAP, ®32);
|
|
|
|
latency = (reg32 & PCI_EXP_DEVCAP_L0S) >> 6;
|
|
|
|
latency = calc_L0S_latency(latency, 1);
|
2009-05-13 11:14:58 +08:00
|
|
|
acceptable->l0s = latency;
|
2009-05-13 11:12:43 +08:00
|
|
|
if (link_state->aspm_support & PCIE_LINK_STATE_L1) {
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
latency = (reg32 & PCI_EXP_DEVCAP_L1) >> 9;
|
|
|
|
latency = calc_L1_latency(latency, 1);
|
2009-05-13 11:14:58 +08:00
|
|
|
acceptable->l1 = latency;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int __pcie_aspm_check_state_one(struct pci_dev *pdev,
|
|
|
|
unsigned int state)
|
|
|
|
{
|
|
|
|
struct pci_dev *parent_dev, *tmp_dev;
|
2009-05-13 11:14:58 +08:00
|
|
|
unsigned int l1_latency = 0;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
struct pcie_link_state *link_state;
|
2009-05-13 11:14:58 +08:00
|
|
|
struct aspm_latency *acceptable;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
parent_dev = pdev->bus->self;
|
|
|
|
link_state = parent_dev->link_state;
|
2009-05-13 11:12:43 +08:00
|
|
|
state &= link_state->aspm_support;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (state == 0)
|
|
|
|
return 0;
|
2009-05-13 11:14:58 +08:00
|
|
|
acceptable = &link_state->acceptable[PCI_FUNC(pdev->devfn)];
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Check latency for endpoint device.
|
|
|
|
* TBD: The latency from the endpoint to root complex vary per
|
|
|
|
* switch's upstream link state above the device. Here we just do a
|
|
|
|
* simple check which assumes all links above the device can be in L1
|
|
|
|
* state, that is we just consider the worst case. If switch's upstream
|
|
|
|
* link can't be put into L0S/L1, then our check is too strictly.
|
|
|
|
*/
|
|
|
|
tmp_dev = pdev;
|
|
|
|
while (state & (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1)) {
|
|
|
|
parent_dev = tmp_dev->bus->self;
|
|
|
|
link_state = parent_dev->link_state;
|
2009-05-13 11:14:58 +08:00
|
|
|
if ((state & PCIE_LINK_STATE_L0S) &&
|
|
|
|
(link_state->latency.l0s > acceptable->l0s))
|
|
|
|
state &= ~PCIE_LINK_STATE_L0S;
|
|
|
|
|
|
|
|
if ((state & PCIE_LINK_STATE_L1) &&
|
|
|
|
(link_state->latency.l1 + l1_latency > acceptable->l1))
|
|
|
|
state &= ~PCIE_LINK_STATE_L1;
|
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (!parent_dev->bus->self) /* parent_dev is a root port */
|
|
|
|
break;
|
|
|
|
else {
|
|
|
|
/*
|
|
|
|
* parent_dev is the downstream port of a switch, make
|
|
|
|
* tmp_dev the upstream port of the switch
|
|
|
|
*/
|
|
|
|
tmp_dev = parent_dev->bus->self;
|
|
|
|
/*
|
|
|
|
* every switch on the path to root complex need 1 more
|
|
|
|
* microsecond for L1. Spec doesn't mention L0S.
|
|
|
|
*/
|
|
|
|
if (state & PCIE_LINK_STATE_L1)
|
|
|
|
l1_latency += 1000;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return state;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int pcie_aspm_check_state(struct pci_dev *pdev,
|
|
|
|
unsigned int state)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
/* If no child, ignore the link */
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (list_empty(&pdev->subordinate->devices))
|
2008-12-19 09:27:42 +08:00
|
|
|
return state;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
if (child_dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) {
|
|
|
|
/*
|
|
|
|
* If downstream component of a link is pci bridge, we
|
|
|
|
* disable ASPM for now for the link
|
|
|
|
* */
|
|
|
|
state = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if ((child_dev->pcie_type != PCI_EXP_TYPE_ENDPOINT &&
|
|
|
|
child_dev->pcie_type != PCI_EXP_TYPE_LEG_END))
|
|
|
|
continue;
|
|
|
|
/* Device not in D0 doesn't need check latency */
|
|
|
|
if (child_dev->current_state == PCI_D1 ||
|
|
|
|
child_dev->current_state == PCI_D2 ||
|
|
|
|
child_dev->current_state == PCI_D3hot ||
|
|
|
|
child_dev->current_state == PCI_D3cold)
|
|
|
|
continue;
|
|
|
|
state = __pcie_aspm_check_state_one(child_dev, state);
|
|
|
|
}
|
|
|
|
return state;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __pcie_aspm_config_one_dev(struct pci_dev *pdev, unsigned int state)
|
|
|
|
{
|
|
|
|
u16 reg16;
|
|
|
|
int pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
|
|
|
|
|
|
|
|
pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16);
|
|
|
|
reg16 &= ~0x3;
|
|
|
|
reg16 |= state;
|
|
|
|
pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __pcie_aspm_config_link(struct pci_dev *pdev, unsigned int state)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
int valid = 1;
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
/* If no child, disable the link */
|
|
|
|
if (list_empty(&pdev->subordinate->devices))
|
|
|
|
state = 0;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/*
|
|
|
|
* if the downstream component has pci bridge function, don't do ASPM
|
|
|
|
* now
|
|
|
|
*/
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
if (child_dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) {
|
|
|
|
valid = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!valid)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* spec 2.0 suggests all functions should be configured the same
|
|
|
|
* setting for ASPM. Enabling ASPM L1 should be done in upstream
|
|
|
|
* component first and then downstream, and vice versa for disabling
|
|
|
|
* ASPM L1. Spec doesn't mention L0S.
|
|
|
|
*/
|
|
|
|
if (state & PCIE_LINK_STATE_L1)
|
|
|
|
__pcie_aspm_config_one_dev(pdev, state);
|
|
|
|
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list)
|
|
|
|
__pcie_aspm_config_one_dev(child_dev, state);
|
|
|
|
|
|
|
|
if (!(state & PCIE_LINK_STATE_L1))
|
|
|
|
__pcie_aspm_config_one_dev(pdev, state);
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
link_state->aspm_enabled = state;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
static struct pcie_link_state *get_root_port_link(struct pcie_link_state *link)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *root_port_link = link;
|
|
|
|
while (root_port_link->parent)
|
|
|
|
root_port_link = root_port_link->parent;
|
|
|
|
return root_port_link;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* check the whole hierarchy, and configure each link in the hierarchy */
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
static void __pcie_aspm_configure_link_state(struct pci_dev *pdev,
|
|
|
|
unsigned int state)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
2008-12-19 09:27:42 +08:00
|
|
|
struct pcie_link_state *root_port_link = get_root_port_link(link_state);
|
|
|
|
struct pcie_link_state *leaf;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
state &= PCIE_LINK_STATE_L0S|PCIE_LINK_STATE_L1;
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
/* check all links who have specific root port link */
|
2009-05-13 11:11:33 +08:00
|
|
|
list_for_each_entry(leaf, &link_list, sibling) {
|
2008-12-19 09:27:42 +08:00
|
|
|
if (!list_empty(&leaf->children) ||
|
|
|
|
get_root_port_link(leaf) != root_port_link)
|
|
|
|
continue;
|
|
|
|
state = pcie_aspm_check_state(leaf->pdev, state);
|
|
|
|
}
|
|
|
|
/* check root port link too in case it hasn't children */
|
|
|
|
state = pcie_aspm_check_state(root_port_link->pdev, state);
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
if (link_state->aspm_enabled == state)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
return;
|
2008-12-19 09:27:42 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* we must change the hierarchy. See comments in
|
|
|
|
* __pcie_aspm_config_link for the order
|
|
|
|
**/
|
|
|
|
if (state & PCIE_LINK_STATE_L1) {
|
2009-05-13 11:11:33 +08:00
|
|
|
list_for_each_entry(leaf, &link_list, sibling) {
|
2008-12-19 09:27:42 +08:00
|
|
|
if (get_root_port_link(leaf) == root_port_link)
|
|
|
|
__pcie_aspm_config_link(leaf->pdev, state);
|
|
|
|
}
|
|
|
|
} else {
|
2009-05-13 11:11:33 +08:00
|
|
|
list_for_each_entry_reverse(leaf, &link_list, sibling) {
|
2008-12-19 09:27:42 +08:00
|
|
|
if (get_root_port_link(leaf) == root_port_link)
|
|
|
|
__pcie_aspm_config_link(leaf->pdev, state);
|
|
|
|
}
|
|
|
|
}
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pcie_aspm_configure_link_state: enable/disable PCI express link state
|
|
|
|
* @pdev: the root port or switch downstream port
|
|
|
|
*/
|
|
|
|
static void pcie_aspm_configure_link_state(struct pci_dev *pdev,
|
|
|
|
unsigned int state)
|
|
|
|
{
|
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
__pcie_aspm_configure_link_state(pdev, state);
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_link_state(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
kfree(pdev->link_state);
|
|
|
|
pdev->link_state = NULL;
|
|
|
|
}
|
|
|
|
|
2008-05-21 16:58:40 +08:00
|
|
|
static int pcie_aspm_sanity_check(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pci_dev *child_dev;
|
|
|
|
int child_pos;
|
2008-07-23 10:32:31 +08:00
|
|
|
u32 reg32;
|
2008-05-21 16:58:40 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Some functions in a slot might not all be PCIE functions, very
|
|
|
|
* strange. Disable ASPM for the whole slot
|
|
|
|
*/
|
|
|
|
list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
|
|
|
|
child_pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
|
|
|
|
if (!child_pos)
|
|
|
|
return -EINVAL;
|
2008-07-23 10:32:31 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Disable ASPM for pre-1.1 PCIe device, we follow MS to use
|
|
|
|
* RBER bit to determine if a function is 1.1 version device
|
|
|
|
*/
|
|
|
|
pci_read_config_dword(child_dev, child_pos + PCI_EXP_DEVCAP,
|
|
|
|
®32);
|
2008-09-16 21:27:13 +08:00
|
|
|
if (!(reg32 & PCI_EXP_DEVCAP_RBER) && !aspm_force) {
|
2008-10-12 18:26:12 +08:00
|
|
|
dev_printk(KERN_INFO, &child_dev->dev, "disabling ASPM"
|
|
|
|
" on pre-1.1 PCIe device. You can enable it"
|
|
|
|
" with 'pcie_aspm=force'\n");
|
2008-07-23 10:32:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
2008-05-21 16:58:40 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/*
|
|
|
|
* pcie_aspm_init_link_state: Initiate PCI express link state.
|
|
|
|
* It is called after the pcie and its children devices are scaned.
|
|
|
|
* @pdev: the root port or switch downstream port
|
|
|
|
*/
|
|
|
|
void pcie_aspm_init_link_state(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
unsigned int state;
|
|
|
|
struct pcie_link_state *link_state;
|
|
|
|
int error = 0;
|
2008-12-19 09:27:42 +08:00
|
|
|
int blacklist;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
if (aspm_disabled || !pdev->is_pcie || pdev->link_state)
|
|
|
|
return;
|
|
|
|
if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
|
|
|
|
return;
|
2009-06-08 09:27:25 +08:00
|
|
|
/* VIA has a strange chipset, root port is under a bridge */
|
|
|
|
if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
pdev->bus->self)
|
|
|
|
return;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
if (list_empty(&pdev->subordinate->devices))
|
|
|
|
goto out;
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
blacklist = !!pcie_aspm_sanity_check(pdev);
|
2008-05-21 16:58:40 +08:00
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
|
|
|
|
link_state = kzalloc(sizeof(*link_state), GFP_KERNEL);
|
|
|
|
if (!link_state)
|
|
|
|
goto unlock_out;
|
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
link_state->downstream_has_switch = pcie_aspm_downstream_has_switch(pdev);
|
|
|
|
INIT_LIST_HEAD(&link_state->children);
|
|
|
|
INIT_LIST_HEAD(&link_state->link);
|
|
|
|
if (pdev->bus->self) {/* this is a switch */
|
|
|
|
struct pcie_link_state *parent_link_state;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
parent_link_state = pdev->bus->parent->self->link_state;
|
|
|
|
if (!parent_link_state) {
|
|
|
|
kfree(link_state);
|
|
|
|
goto unlock_out;
|
|
|
|
}
|
|
|
|
list_add(&link_state->link, &parent_link_state->children);
|
|
|
|
link_state->parent = parent_link_state;
|
|
|
|
}
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
pdev->link_state = link_state;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
if (!blacklist) {
|
|
|
|
pcie_aspm_configure_common_clock(pdev);
|
|
|
|
pcie_aspm_cap_init(pdev);
|
|
|
|
} else {
|
2009-05-13 11:12:43 +08:00
|
|
|
link_state->aspm_enabled =
|
|
|
|
(PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
|
|
|
|
link_state->aspm_default = 0;
|
2008-12-19 09:27:42 +08:00
|
|
|
/* Set support state to 0, so we will disable ASPM later */
|
2009-05-13 11:12:43 +08:00
|
|
|
link_state->aspm_support = 0;
|
2008-12-19 09:27:42 +08:00
|
|
|
}
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
|
|
|
link_state->pdev = pdev;
|
2009-05-13 11:11:33 +08:00
|
|
|
list_add(&link_state->sibling, &link_list);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2008-12-19 09:27:42 +08:00
|
|
|
if (link_state->downstream_has_switch) {
|
|
|
|
/*
|
|
|
|
* If link has switch, delay the link config. The leaf link
|
|
|
|
* initialization will config the whole hierarchy. but we must
|
|
|
|
* make sure BIOS doesn't set unsupported link state
|
|
|
|
**/
|
2009-05-13 11:12:43 +08:00
|
|
|
state = pcie_aspm_check_state(pdev, link_state->aspm_default);
|
2008-12-19 09:27:42 +08:00
|
|
|
__pcie_aspm_config_link(pdev, state);
|
|
|
|
} else
|
|
|
|
__pcie_aspm_configure_link_state(pdev,
|
|
|
|
policy_to_aspm_state(pdev));
|
|
|
|
|
|
|
|
pcie_check_clock_pm(pdev, blacklist);
|
|
|
|
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
unlock_out:
|
|
|
|
if (error)
|
|
|
|
free_link_state(pdev);
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
out:
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* @pdev: the endpoint device */
|
|
|
|
void pcie_aspm_exit_link_state(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pci_dev *parent = pdev->bus->self;
|
|
|
|
struct pcie_link_state *link_state = parent->link_state;
|
|
|
|
|
|
|
|
if (aspm_disabled || !pdev->is_pcie || !parent || !link_state)
|
|
|
|
return;
|
|
|
|
if (parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
|
|
|
|
return;
|
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* All PCIe functions are in one slot, remove one function will remove
|
2009-01-29 05:59:18 +08:00
|
|
|
* the whole slot, so just wait until we are the last function left.
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
*/
|
2009-01-29 05:59:18 +08:00
|
|
|
if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices))
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* All functions are removed, so just disable ASPM for the link */
|
|
|
|
__pcie_aspm_config_one_dev(parent, 0);
|
2009-05-13 11:11:33 +08:00
|
|
|
list_del(&link_state->sibling);
|
2008-12-19 09:27:42 +08:00
|
|
|
list_del(&link_state->link);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
/* Clock PM is for endpoint device */
|
|
|
|
|
|
|
|
free_link_state(parent);
|
|
|
|
out:
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* @pdev: the root port or switch downstream port */
|
|
|
|
void pcie_aspm_pm_state_change(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
if (aspm_disabled || !pdev->is_pcie || !pdev->link_state)
|
|
|
|
return;
|
|
|
|
if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
|
|
|
|
return;
|
|
|
|
/*
|
|
|
|
* devices changed PM state, we should recheck if latency meets all
|
|
|
|
* functions' requirement
|
|
|
|
*/
|
2009-05-13 11:12:43 +08:00
|
|
|
pcie_aspm_configure_link_state(pdev, link_state->aspm_enabled);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pci_disable_link_state - disable pci device's link state, so the link will
|
|
|
|
* never enter specific states
|
|
|
|
*/
|
|
|
|
void pci_disable_link_state(struct pci_dev *pdev, int state)
|
|
|
|
{
|
|
|
|
struct pci_dev *parent = pdev->bus->self;
|
|
|
|
struct pcie_link_state *link_state;
|
|
|
|
|
|
|
|
if (aspm_disabled || !pdev->is_pcie)
|
|
|
|
return;
|
|
|
|
if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
|
|
|
|
pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)
|
|
|
|
parent = pdev;
|
|
|
|
if (!parent || !parent->link_state)
|
|
|
|
return;
|
|
|
|
|
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
link_state = parent->link_state;
|
2009-05-13 11:12:43 +08:00
|
|
|
link_state->aspm_support &= ~state;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
if (state & PCIE_LINK_STATE_CLKPM)
|
2009-05-13 11:15:38 +08:00
|
|
|
link_state->clkpm_capable = 0;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
__pcie_aspm_configure_link_state(parent, link_state->aspm_enabled);
|
2009-05-13 11:15:38 +08:00
|
|
|
if (!link_state->clkpm_capable && link_state->clkpm_enabled)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
pcie_set_clock_pm(parent, 0);
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(pci_disable_link_state);
|
|
|
|
|
|
|
|
static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
struct pci_dev *pdev;
|
|
|
|
struct pcie_link_state *link_state;
|
|
|
|
|
|
|
|
for (i = 0; i < ARRAY_SIZE(policy_str); i++)
|
|
|
|
if (!strncmp(val, policy_str[i], strlen(policy_str[i])))
|
|
|
|
break;
|
|
|
|
if (i >= ARRAY_SIZE(policy_str))
|
|
|
|
return -EINVAL;
|
|
|
|
if (i == aspm_policy)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
aspm_policy = i;
|
2009-05-13 11:11:33 +08:00
|
|
|
list_for_each_entry(link_state, &link_list, sibling) {
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
pdev = link_state->pdev;
|
|
|
|
__pcie_aspm_configure_link_state(pdev,
|
|
|
|
policy_to_aspm_state(pdev));
|
2009-05-13 11:15:38 +08:00
|
|
|
if (link_state->clkpm_capable &&
|
|
|
|
link_state->clkpm_enabled != policy_to_clkpm_state(pdev))
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
pcie_set_clock_pm(pdev, policy_to_clkpm_state(pdev));
|
|
|
|
|
|
|
|
}
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp)
|
|
|
|
{
|
|
|
|
int i, cnt = 0;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(policy_str); i++)
|
|
|
|
if (i == aspm_policy)
|
|
|
|
cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]);
|
|
|
|
else
|
|
|
|
cnt += sprintf(buffer + cnt, "%s ", policy_str[i]);
|
|
|
|
return cnt;
|
|
|
|
}
|
|
|
|
|
|
|
|
module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy,
|
|
|
|
NULL, 0644);
|
|
|
|
|
|
|
|
#ifdef CONFIG_PCIEASPM_DEBUG
|
|
|
|
static ssize_t link_state_show(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
char *buf)
|
|
|
|
{
|
|
|
|
struct pci_dev *pci_device = to_pci_dev(dev);
|
|
|
|
struct pcie_link_state *link_state = pci_device->link_state;
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
return sprintf(buf, "%d\n", link_state->aspm_enabled);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t link_state_store(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
const char *buf,
|
|
|
|
size_t n)
|
|
|
|
{
|
|
|
|
struct pci_dev *pci_device = to_pci_dev(dev);
|
|
|
|
int state;
|
|
|
|
|
|
|
|
if (n < 1)
|
|
|
|
return -EINVAL;
|
|
|
|
state = buf[0]-'0';
|
|
|
|
if (state >= 0 && state <= 3) {
|
|
|
|
/* setup link aspm state */
|
|
|
|
pcie_aspm_configure_link_state(pci_device, state);
|
|
|
|
return n;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t clk_ctl_show(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
char *buf)
|
|
|
|
{
|
|
|
|
struct pci_dev *pci_device = to_pci_dev(dev);
|
|
|
|
struct pcie_link_state *link_state = pci_device->link_state;
|
|
|
|
|
2009-05-13 11:15:38 +08:00
|
|
|
return sprintf(buf, "%d\n", link_state->clkpm_enabled);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t clk_ctl_store(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
|
|
|
const char *buf,
|
|
|
|
size_t n)
|
|
|
|
{
|
|
|
|
struct pci_dev *pci_device = to_pci_dev(dev);
|
|
|
|
int state;
|
|
|
|
|
|
|
|
if (n < 1)
|
|
|
|
return -EINVAL;
|
|
|
|
state = buf[0]-'0';
|
|
|
|
|
|
|
|
down_read(&pci_bus_sem);
|
|
|
|
mutex_lock(&aspm_lock);
|
|
|
|
pcie_set_clock_pm(pci_device, !!state);
|
|
|
|
mutex_unlock(&aspm_lock);
|
|
|
|
up_read(&pci_bus_sem);
|
|
|
|
|
|
|
|
return n;
|
|
|
|
}
|
|
|
|
|
|
|
|
static DEVICE_ATTR(link_state, 0644, link_state_show, link_state_store);
|
|
|
|
static DEVICE_ATTR(clk_ctl, 0644, clk_ctl_show, clk_ctl_store);
|
|
|
|
|
|
|
|
static char power_group[] = "power";
|
|
|
|
void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
if (!pdev->is_pcie || (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
|
|
|
|
return;
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
if (link_state->aspm_support)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
sysfs_add_file_to_group(&pdev->dev.kobj,
|
|
|
|
&dev_attr_link_state.attr, power_group);
|
2009-05-13 11:15:38 +08:00
|
|
|
if (link_state->clkpm_capable)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
sysfs_add_file_to_group(&pdev->dev.kobj,
|
|
|
|
&dev_attr_clk_ctl.attr, power_group);
|
|
|
|
}
|
|
|
|
|
|
|
|
void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
|
|
|
|
{
|
|
|
|
struct pcie_link_state *link_state = pdev->link_state;
|
|
|
|
|
|
|
|
if (!pdev->is_pcie || (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
|
|
|
|
pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
|
|
|
|
return;
|
|
|
|
|
2009-05-13 11:12:43 +08:00
|
|
|
if (link_state->aspm_support)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
sysfs_remove_file_from_group(&pdev->dev.kobj,
|
|
|
|
&dev_attr_link_state.attr, power_group);
|
2009-05-13 11:15:38 +08:00
|
|
|
if (link_state->clkpm_capable)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
sysfs_remove_file_from_group(&pdev->dev.kobj,
|
|
|
|
&dev_attr_clk_ctl.attr, power_group);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static int __init pcie_aspm_disable(char *str)
|
|
|
|
{
|
2008-07-23 10:32:42 +08:00
|
|
|
if (!strcmp(str, "off")) {
|
|
|
|
aspm_disabled = 1;
|
|
|
|
printk(KERN_INFO "PCIe ASPM is disabled\n");
|
|
|
|
} else if (!strcmp(str, "force")) {
|
|
|
|
aspm_force = 1;
|
|
|
|
printk(KERN_INFO "PCIe ASPM is forcedly enabled\n");
|
|
|
|
}
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2008-07-23 10:32:42 +08:00
|
|
|
__setup("pcie_aspm=", pcie_aspm_disable);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|
2008-07-23 10:32:24 +08:00
|
|
|
void pcie_no_aspm(void)
|
|
|
|
{
|
2008-07-23 10:32:42 +08:00
|
|
|
if (!aspm_force)
|
|
|
|
aspm_disabled = 1;
|
2008-07-23 10:32:24 +08:00
|
|
|
}
|
|
|
|
|
2008-11-11 06:30:55 +08:00
|
|
|
/**
|
|
|
|
* pcie_aspm_enabled - is PCIe ASPM enabled?
|
|
|
|
*
|
|
|
|
* Returns true if ASPM has not been disabled by the command-line option
|
|
|
|
* pcie_aspm=off.
|
|
|
|
**/
|
|
|
|
int pcie_aspm_enabled(void)
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
{
|
2008-11-11 06:30:55 +08:00
|
|
|
return !aspm_disabled;
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
}
|
2008-11-11 06:30:55 +08:00
|
|
|
EXPORT_SYMBOL(pcie_aspm_enabled);
|
PCI: add PCI Express ASPM support
PCI Express ASPM defines a protocol for PCI Express components in the D0
state to reduce Link power by placing their Links into a low power state
and instructing the other end of the Link to do likewise. This
capability allows hardware-autonomous, dynamic Link power reduction
beyond what is achievable by software-only controlled power management.
However, The device should be configured by software appropriately.
Enabling ASPM will save power, but will introduce device latency.
This patch adds ASPM support in Linux. It introduces a global policy for
ASPM, a sysfs file /sys/module/pcie_aspm/parameters/policy can control
it. The interface can be used as a boot option too. Currently we have
below setting:
-default, BIOS default setting
-powersave, highest power saving mode, enable all available ASPM
state and clock power management
-performance, highest performance, disable ASPM and clock power
management
By default, the 'default' policy is used currently.
In my test, power difference between powersave mode and performance mode
is about 1.3w in a system with 3 PCIE links.
Note: some devices might not work well with aspm, either because chipset
issue or device issue. The patch provide API (pci_disable_link_state),
driver can disable ASPM for specific device.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-02-25 09:46:41 +08:00
|
|
|
|