PCI: PCIE 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.
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

drivers/pci/pci-sysfs.c

@@ -21,6 +21,7 @@
 #include <linux/topology.h>
 #include <linux/mm.h>
 #include <linux/capability.h>
+#include <linux/aspm.h>
 #include "pci.h"
 
 static int sysfs_initialized;	/* = 0 */
@@ -650,6 +651,8 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
 	if (pcibios_add_platform_entries(pdev))
 		goto err_rom_file;
 
+	pcie_aspm_create_sysfs_dev_files(pdev);
+
 	return 0;
 
 err_rom_file:
@@ -679,6 +682,8 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 	if (!sysfs_initialized)
 		return;
 
+	pcie_aspm_remove_sysfs_dev_files(pdev);
+
 	if (pdev->cfg_size < 4096)
 		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
 	else

drivers/pci/pci.c

@@ -18,6 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/log2.h>
+#include <linux/aspm.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -519,6 +520,9 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 	if (need_restore)
 		pci_restore_bars(dev);
 
+	if (dev->bus->self)
+		pcie_aspm_pm_state_change(dev->bus->self);
+
 	return 0;
 }
 

drivers/pci/pcie/Kconfig

@@ -26,3 +26,23 @@ config HOTPLUG_PCI_PCIE
 	  When in doubt, say N.
 
 source "drivers/pci/pcie/aer/Kconfig"
+
+#
+# PCI Express ASPM
+#
+config PCIEASPM
+	bool "PCI Express ASPM support(Experimental)"
+	depends on PCI && EXPERIMENTAL
+	default y
+	help
+	  This enables PCI Express ASPM (Active State Power Management) and
+	  Clock Power Management. ASPM supports state L0/L0s/L1.
+
+	  When in doubt, say N.
+config PCIEASPM_DEBUG
+	bool "Debug PCI Express ASPM"
+	depends on PCIEASPM
+	default n
+	help
+	  This enables PCI Express ASPM debug support. It will add per-device
+	  interface to control ASPM.

drivers/pci/pcie/Makefile

@@ -2,6 +2,9 @@
 # Makefile for PCI-Express PORT Driver
 #
 
+# Build PCI Express ASPM if needed
+obj-$(CONFIG_PCIEASPM)		+= aspm.o
+
 pcieportdrv-y			:= portdrv_core.o portdrv_pci.o portdrv_bus.o
 
 obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o

drivers/pci/probe.c

@@ -9,6 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
+#include <linux/aspm.h>
 #include "pci.h"
 
 #define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
@@ -1010,6 +1011,10 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 				break;
 		}
 	}
+
+	if (bus->self)
+		pcie_aspm_init_link_state(bus->self);
+
 	return nr;
 }
 

drivers/pci/remove.c

 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/aspm.h>
 #include "pci.h"
 
 static void pci_free_resources(struct pci_dev *dev)
@@ -30,6 +31,9 @@ static void pci_stop_dev(struct pci_dev *dev)
 		dev->global_list.next = dev->global_list.prev = NULL;
 		up_write(&pci_bus_sem);
 	}
+
+	if (dev->bus->self)
+		pcie_aspm_exit_link_state(dev);
 }
 
 static void pci_destroy_dev(struct pci_dev *dev)

include/linux/aspm.h

+/*
+ *	aspm.h
+ *
+ *	PCI Express ASPM defines and function prototypes
+ *
+ *	Copyright (C) 2007 Intel Corp.
+ *		Zhang Yanmin (yanmin.zhang@intel.com)
+ *		Shaohua Li (shaohua.li@intel.com)
+ *
+ *	For more information, please consult the following manuals (look at
+ *	http://www.pcisig.com/ for how to get them):
+ *
+ *	PCI Express Specification
+ */
+
+#ifndef LINUX_ASPM_H
+#define LINUX_ASPM_H
+
+#include <linux/pci.h>
+
+#define PCIE_LINK_STATE_L0S	1
+#define PCIE_LINK_STATE_L1	2
+#define PCIE_LINK_STATE_CLKPM	4
+
+#ifdef CONFIG_PCIEASPM
+extern void pcie_aspm_init_link_state(struct pci_dev *pdev);
+extern void pcie_aspm_exit_link_state(struct pci_dev *pdev);
+extern void pcie_aspm_pm_state_change(struct pci_dev *pdev);
+extern void pci_disable_link_state(struct pci_dev *pdev, int state);
+#else
+#define pcie_aspm_init_link_state(pdev)		do {} while (0)
+#define pcie_aspm_exit_link_state(pdev)		do {} while (0)
+#define pcie_aspm_pm_state_change(pdev)		do {} while (0)
+#define pci_disable_link_state(pdev, state)	do {} while (0)
+#endif
+
+#ifdef CONFIG_PCIEASPM_DEBUG /* this depends on CONFIG_PCIEASPM */
+extern void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev);
+extern void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev);
+#else
+#define pcie_aspm_create_sysfs_dev_files(pdev)	do {} while (0)
+#define pcie_aspm_remove_sysfs_dev_files(pdev)	do {} while (0)
+#endif
+#endif /* LINUX_ASPM_H */

include/linux/pci.h

@@ -128,6 +128,7 @@ struct pci_cap_saved_state {
 	u32 data[0];
 };
 
+struct pcie_link_state;
 /*
  * The pci_dev structure is used to describe PCI devices.
  */
@@ -163,6 +164,10 @@ struct pci_dev {
 					   this is D0-D3, D0 being fully functional,
 					   and D3 being off. */
 
+#ifdef CONFIG_PCIEASPM
+	struct pcie_link_state	*link_state;	/* ASPM link state. */
+#endif
+
 	pci_channel_state_t error_state;	/* current connectivity state */
 	struct	device	dev;		/* Generic device interface */
 

include/linux/pci_regs.h

@@ -395,9 +395,17 @@
 #define  PCI_EXP_DEVSTA_AUXPD	0x10	/* AUX Power Detected */
 #define  PCI_EXP_DEVSTA_TRPND	0x20	/* Transactions Pending */
 #define PCI_EXP_LNKCAP		12	/* Link Capabilities */
+#define  PCI_EXP_LNKCAP_ASPMS	0xc00	/* ASPM Support */
+#define  PCI_EXP_LNKCAP_L0SEL	0x7000	/* L0s Exit Latency */
+#define  PCI_EXP_LNKCAP_L1EL	0x38000	/* L1 Exit Latency */
+#define  PCI_EXP_LNKCAP_CLKPM	0x40000	/* L1 Clock Power Management */
 #define PCI_EXP_LNKCTL		16	/* Link Control */
+#define  PCI_EXP_LNKCTL_RL	0x20	/* Retrain Link */
+#define  PCI_EXP_LNKCTL_CCC	0x40	/* Common Clock COnfiguration */
 #define  PCI_EXP_LNKCTL_CLKREQ_EN 0x100	/* Enable clkreq */
 #define PCI_EXP_LNKSTA		18	/* Link Status */
+#define  PCI_EXP_LNKSTA_LT	0x800	/* Link Training */
+#define  PCI_EXP_LNKSTA_SLC	0x1000	/* Slot Clock Configuration */
 #define PCI_EXP_SLTCAP		20	/* Slot Capabilities */
 #define PCI_EXP_SLTCTL		24	/* Slot Control */
 #define PCI_EXP_SLTSTA		26	/* Slot Status */