From: Rajat Jain <rajatja@google.com>
To: Bjorn Helgaas <bhelgaas@google.com>,
Keith Busch <keith.busch@intel.com>,
Andreas Ziegler <andreas.ziegler@fau.de>,
Jonathan Yong <jonathan.yong@intel.com>,
Shawn Lin <shawn.lin@rock-chips.com>,
David Daney <david.daney@cavium.com>,
Julia Lawall <Julia.Lawall@lip6.fr>,
Ram Amrani <Ram.Amrani@cavium.com>,
Doug Ledford <dledford@redhat.com>,
Wang Sheng-Hui <shhuiw@foxmail.com>,
linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Rajat Jain <rajatja@google.com>,
Rajat Jain <rajatxjain@gmail.com>,
Brian Norris <briannorris@google.com>
Subject: [PATCH 2/6] PCI/ASPM: Introduce L1 substates and a Kconfig for it
Date: Mon, 2 Jan 2017 22:34:11 -0800 [thread overview]
Message-ID: <1483425255-101923-3-git-send-email-rajatja@google.com> (raw)
In-Reply-To: <1483425255-101923-1-git-send-email-rajatja@google.com>
Introduce the L1 sub states. (For details about L1 substates,
please refer to:
https://pcisig.com/sites/default/files/specification_documents/ECN_L1_PM_Substates_with_CLKREQ_31_May_2013_Rev10a.pdf)
This patch adds macros for the 4 new L1 substates, and adds
a new ASPM "POWER_SUPERSAVE" policy that can be used to enable
L1 substates on a system if desired. The new policy is in a sense,
a super set of the existing POWERSAVE policy. The 4 policies are now:
DEFAULT: Reads and uses whatever ASPM states BIOS enabled
PERFORMANCE: Everything except L0 disabled.
POWERSAVE: L0s and L1 enabled (but not L1 substates)
POWER_SUPERSAVE: L0s + L1 + L1 substates also enabled.
Signed-off-by: Rajat Jain <rajatja@google.com>
---
drivers/pci/pcie/Kconfig | 8 ++++++++
drivers/pci/pcie/aspm.c | 39 +++++++++++++++++++++++++++++----------
2 files changed, 37 insertions(+), 10 deletions(-)
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 7ce7763..ac53edb 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -71,6 +71,14 @@ config PCIEASPM_POWERSAVE
Enable PCI Express ASPM L0s and L1 where possible, even if the
BIOS did not.
+config PCIEASPM_POWER_SUPERSAVE
+ bool "Power Supersave"
+ depends on PCIEASPM
+ help
+ Same as PCIEASPM_POWERSAVE, except it also enables L1 substates where
+ possible. This would result in higher power savings while staying in L1
+ where the components support it.
+
config PCIEASPM_PERFORMANCE
bool "Performance"
depends on PCIEASPM
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 17ac1dc..402c229 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -30,8 +30,17 @@
#define ASPM_STATE_L0S_UP (1) /* Upstream direction L0s state */
#define ASPM_STATE_L0S_DW (2) /* Downstream direction L0s state */
#define ASPM_STATE_L1 (4) /* L1 state */
+#define ASPM_STATE_L1_1 (8) /* ASPM L1.1 state */
+#define ASPM_STATE_L1_2 (0x10) /* ASPM L1.2 state */
+#define ASPM_STATE_L1_1_PCIPM (0x20) /* PCI PM L1.1 state */
+#define ASPM_STATE_L1_2_PCIPM (0x40) /* PCI PM L1.2 state */
+#define ASPM_STATE_L1_SS_PCIPM (ASPM_STATE_L1_1_PCIPM | ASPM_STATE_L1_2_PCIPM)
+#define ASPM_STATE_L1_2_MASK (ASPM_STATE_L1_2 | ASPM_STATE_L1_2_PCIPM)
+#define ASPM_STATE_L1SS (ASPM_STATE_L1_1 | ASPM_STATE_L1_1_PCIPM |\
+ ASPM_STATE_L1_2_MASK)
#define ASPM_STATE_L0S (ASPM_STATE_L0S_UP | ASPM_STATE_L0S_DW)
-#define ASPM_STATE_ALL (ASPM_STATE_L0S | ASPM_STATE_L1)
+#define ASPM_STATE_ALL (ASPM_STATE_L0S | ASPM_STATE_L1 | \
+ ASPM_STATE_L1SS)
struct aspm_latency {
u32 l0s; /* L0s latency (nsec) */
@@ -47,11 +56,11 @@ struct pcie_link_state {
struct list_head link; /* node in parent's children list */
/* ASPM state */
- u32 aspm_support:3; /* Supported ASPM state */
- u32 aspm_enabled:3; /* Enabled ASPM state */
- u32 aspm_capable:3; /* Capable ASPM state with latency */
- u32 aspm_default:3; /* Default ASPM state by BIOS */
- u32 aspm_disable:3; /* Disabled ASPM state */
+ u32 aspm_support:7; /* Supported ASPM state */
+ u32 aspm_enabled:7; /* Enabled ASPM state */
+ u32 aspm_capable:7; /* Capable ASPM state with latency */
+ u32 aspm_default:7; /* Default ASPM state by BIOS */
+ u32 aspm_disable:7; /* Disabled ASPM state */
/* Clock PM state */
u32 clkpm_capable:1; /* Clock PM capable? */
@@ -76,11 +85,14 @@ 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 */
+#define POLICY_POWER_SUPERSAVE 3 /* Possibly Even higher power saving */
#ifdef CONFIG_PCIEASPM_PERFORMANCE
static int aspm_policy = POLICY_PERFORMANCE;
#elif defined CONFIG_PCIEASPM_POWERSAVE
static int aspm_policy = POLICY_POWERSAVE;
+#elif defined CONFIG_PCIEASPM_POWER_SUPERSAVE
+static int aspm_policy = POLICY_POWER_SUPERSAVE;
#else
static int aspm_policy;
#endif
@@ -88,7 +100,8 @@ static int aspm_policy;
static const char *policy_str[] = {
[POLICY_DEFAULT] = "default",
[POLICY_PERFORMANCE] = "performance",
- [POLICY_POWERSAVE] = "powersave"
+ [POLICY_POWERSAVE] = "powersave",
+ [POLICY_POWER_SUPERSAVE] = "powersupersave"
};
#define LINK_RETRAIN_TIMEOUT HZ
@@ -101,6 +114,9 @@ static int policy_to_aspm_state(struct pcie_link_state *link)
return 0;
case POLICY_POWERSAVE:
/* Enable ASPM L0s/L1 */
+ return (ASPM_STATE_L0S | ASPM_STATE_L1);
+ case POLICY_POWER_SUPERSAVE:
+ /* Enable Everything */
return ASPM_STATE_ALL;
case POLICY_DEFAULT:
return link->aspm_default;
@@ -115,7 +131,8 @@ static int policy_to_clkpm_state(struct pcie_link_state *link)
/* Disable ASPM and Clock PM */
return 0;
case POLICY_POWERSAVE:
- /* Disable Clock PM */
+ case POLICY_POWER_SUPERSAVE:
+ /* Enable Clock PM */
return 1;
case POLICY_DEFAULT:
return link->clkpm_default;
@@ -612,7 +629,8 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
* the BIOS's expectation, we'll do so once pci_enable_device() is
* called.
*/
- if (aspm_policy != POLICY_POWERSAVE) {
+ if (aspm_policy != POLICY_POWERSAVE &&
+ aspm_policy != POLICY_POWER_SUPERSAVE) {
pcie_config_aspm_path(link);
pcie_set_clkpm(link, policy_to_clkpm_state(link));
}
@@ -712,7 +730,8 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
if (aspm_disabled || !link)
return;
- if (aspm_policy != POLICY_POWERSAVE)
+ if (aspm_policy != POLICY_POWERSAVE &&
+ aspm_policy != POLICY_POWER_SUPERSAVE)
return;
down_read(&pci_bus_sem);
--
2.8.0.rc3.226.g39d4020
next prev parent reply other threads:[~2017-01-03 6:34 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-03 6:34 [PATCH 0/6] PCI/ASPM: Add PCIe L1 PM substate support Rajat Jain
2017-01-03 6:34 ` [PATCH 1/6] PCI: Add L1 substate capability structure register definitions Rajat Jain
2017-01-03 6:34 ` Rajat Jain [this message]
2017-01-03 6:34 ` [PATCH 3/6] PCI/ASPM: Read and setup L1 substate capabilities Rajat Jain
2017-01-03 6:34 ` [PATCH 4/6] PCI/ASPM: Calculate and save the L1.2 timing parameters Rajat Jain
2017-01-03 6:34 ` [PATCH 5/6] PCI/ASPM: Actually configure the L1 substate settings to the device Rajat Jain
2017-03-08 18:44 ` James Morse
2017-03-08 22:39 ` Bjorn Helgaas
2017-03-08 23:08 ` Rajat Jain
2017-03-09 11:00 ` James Morse
2017-01-03 6:34 ` [PATCH 6/6] PCI/ASPM: Add comment about L1 substate latency Rajat Jain
2017-02-14 23:45 ` [PATCH 0/6] PCI/ASPM: Add PCIe L1 PM substate support Bjorn Helgaas
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1483425255-101923-3-git-send-email-rajatja@google.com \
--to=rajatja@google.com \
--cc=Julia.Lawall@lip6.fr \
--cc=Ram.Amrani@cavium.com \
--cc=andreas.ziegler@fau.de \
--cc=bhelgaas@google.com \
--cc=briannorris@google.com \
--cc=david.daney@cavium.com \
--cc=dledford@redhat.com \
--cc=jonathan.yong@intel.com \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=rajatxjain@gmail.com \
--cc=shawn.lin@rock-chips.com \
--cc=shhuiw@foxmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).