Skip to contentSkip to conversation

mmc: sdhci-pci-gli: Enlarge ASPM L1 entry delay of GL9763E

PATCH In review Renius Chen 2 participants 5 messages Jan 6, 2021 – Jan 15, 2021

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 mmc: sdhci-pci-gli: Enlarge ASPM L1 entry delay of GL9763E

The R/W performance of GL9763E is low with some platforms, which support ASPM mechanism, due to entering L1 state very frequently in R/W process. Enlarge its ASPM L1 entry delay to improve the R/W performance of GL9763E.

---
 drivers/mmc/host/sdhci-pci-gli.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/mmc/host/sdhci-pci-gli.c +9 -0
index c6a107d7c742..2d13bfcbcacf 100644
@@ -88,6 +88,10 @@
 #define PCIE_GLI_9763E_SCR	 0x8E0
 #define   GLI_9763E_SCR_AXI_REQ	   BIT(9)
 
+#define PCIE_GLI_9763E_CFG2      0x8A4
+#define   GLI_9763E_CFG2_L1DLY	   GENMASK(28, 19)
+#define   GLI_9763E_CFG2_L1DLY_MAX 0x3FF
+
 #define PCIE_GLI_9763E_MMC_CTRL  0x960
 #define   GLI_9763E_HS400_SLOW     BIT(3)
 
@@ -792,6 +796,11 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
 	value &= ~GLI_9763E_HS400_SLOW;
 	pci_write_config_dword(pdev, PCIE_GLI_9763E_MMC_CTRL, value);
 
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG2, &value);
+	value &= ~GLI_9763E_CFG2_L1DLY;
+	value |= FIELD_PREP(GLI_9763E_CFG2_L1DLY, GLI_9763E_CFG2_L1DLY_MAX);
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG2, value);
+
 	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
 	value &= ~GLI_9763E_VHS_REV;
 	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
Signature · 1 line
2.27.0
#1 lore raw
Quoted 5 lines · Renius Chen

The R/W performance of GL9763E is low with some platforms, which support ASPM mechanism, due to entering L1 state very frequently in R/W process. Enlarge its ASPM L1 entry delay to improve the R/W performance of GL9763E.

What do you mean by frequently? In between a burst of request or during a burst of request?

I am thinking that this could have an effect on energy instead, but I guess it's not always straightforward to decide what's most important.

Anyway, what does it mean when you change to use 0x3FF? Are you increasing the idle period? Then for how long?

Kind regards
Uffe

Quoted 36 lines
---
 drivers/mmc/host/sdhci-pci-gli.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/mmc/host/sdhci-pci-gli.c +9 -1
index c6a107d7c742..2d13bfcbcacf 100644
@@ -88,6 +88,10 @@
 #define PCIE_GLI_9763E_SCR      0x8E0
 #define   GLI_9763E_SCR_AXI_REQ           BIT(9)
 
+#define PCIE_GLI_9763E_CFG2      0x8A4
+#define   GLI_9763E_CFG2_L1DLY    GENMASK(28, 19)
+#define   GLI_9763E_CFG2_L1DLY_MAX 0x3FF
+
 #define PCIE_GLI_9763E_MMC_CTRL  0x960
 #define   GLI_9763E_HS400_SLOW     BIT(3)
 
@@ -792,6 +796,11 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
        value &= ~GLI_9763E_HS400_SLOW;
        pci_write_config_dword(pdev, PCIE_GLI_9763E_MMC_CTRL, value);
 
+       pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG2, &value);
+       value &= ~GLI_9763E_CFG2_L1DLY;
+       value |= FIELD_PREP(GLI_9763E_CFG2_L1DLY, GLI_9763E_CFG2_L1DLY_MAX);
+       pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG2, value);
+
        pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
        value &= ~GLI_9763E_VHS_REV;
        value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
--

2.27.0

author
#2 lore raw
Quoted 11 lines

Ulf Hansson <[email protected]> 於 2021年1月13日 週三 下午6:53寫道:

Quoted 5 lines · Renius Chen

The R/W performance of GL9763E is low with some platforms, which support ASPM mechanism, due to entering L1 state very frequently in R/W process. Enlarge its ASPM L1 entry delay to improve the R/W performance of GL9763E.

What do you mean by frequently? In between a burst of request or during a burst of request?

GL9763E enters ASPM L1 state after a very short idle in default, even during a burst of request.

Quoted 5 lines

I am thinking that this could have an effect on energy instead, but I guess it's not always straightforward to decide what's most important.

Anyway, what does it mean when you change to use 0x3FF? Are you increasing the idle period? Then for how long?

Yes, we considered that having high performance is more important than saving power during a burst of request.
So we increased the idle period for 260us, by setting 0x3FF to the ASPM L1 entry delay bits of our vendor-specific register. Anyway, GL9763E can still enter ASPM L1 state by a longer idle.

Thanks for reviewing.

Best regards,
Renius

Quoted 39 lines

Kind regards
Uffe

Quoted 36 lines
---
 drivers/mmc/host/sdhci-pci-gli.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/mmc/host/sdhci-pci-gli.c +9 -1
index c6a107d7c742..2d13bfcbcacf 100644
@@ -88,6 +88,10 @@
 #define PCIE_GLI_9763E_SCR      0x8E0
 #define   GLI_9763E_SCR_AXI_REQ           BIT(9)
 
+#define PCIE_GLI_9763E_CFG2      0x8A4
+#define   GLI_9763E_CFG2_L1DLY    GENMASK(28, 19)
+#define   GLI_9763E_CFG2_L1DLY_MAX 0x3FF
+
 #define PCIE_GLI_9763E_MMC_CTRL  0x960
 #define   GLI_9763E_HS400_SLOW     BIT(3)
 
@@ -792,6 +796,11 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
        value &= ~GLI_9763E_HS400_SLOW;
        pci_write_config_dword(pdev, PCIE_GLI_9763E_MMC_CTRL, value);
 
+       pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG2, &value);
+       value &= ~GLI_9763E_CFG2_L1DLY;
+       value |= FIELD_PREP(GLI_9763E_CFG2_L1DLY, GLI_9763E_CFG2_L1DLY_MAX);
+       pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG2, value);
+
        pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
        value &= ~GLI_9763E_VHS_REV;
        value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
--

2.27.0

#3 lore raw
Quoted 10 lines · 陳建宏
Quoted 10 lines

Ulf Hansson <[email protected]> 於 2021年1月13日 週三 下午6:53寫道:

Quoted 5 lines · Renius Chen

The R/W performance of GL9763E is low with some platforms, which support ASPM mechanism, due to entering L1 state very frequently in R/W process. Enlarge its ASPM L1 entry delay to improve the R/W performance of GL9763E.

Quoted 5 lines
Quoted 2 lines

What do you mean by frequently? In between a burst of request or during a burst of request?

GL9763E enters ASPM L1 state after a very short idle in default, even during a burst of request.

Okay, then it certainly makes sense to extend the idle period.

Would you mind extending the commit message with some of this information, as I think it's useful.

Quoted 4 lines
Quoted 4 lines

I am thinking that this could have an effect on energy instead, but I guess it's not always straightforward to decide what's most important.

Quoted 8 lines
Quoted 2 lines

Anyway, what does it mean when you change to use 0x3FF? Are you increasing the idle period? Then for how long?

Yes, we considered that having high performance is more important than saving power during a burst of request.
So we increased the idle period for 260us, by setting 0x3FF to the ASPM L1 entry delay bits of our vendor-specific register. Anyway, GL9763E can still enter ASPM L1 state by a longer idle.

Most mmc controllers that uses runtime PM autosuspend for the same reasons, uses and idle period time of ~50us. 260us is in the same ballpark, so I am fine with that, if that works for you.

However, can you please add a comment in the code (and preferably also to the commit message) that 0x3FF means using a 260us idle period?

[...]

Kind regards
Uffe

#4 lore raw
Quoted 37 lines

Ulf Hansson <[email protected]> 於 2021年1月14日 週四 下午8:04寫道:

Quoted 10 lines · 陳建宏
Quoted 10 lines

Ulf Hansson <[email protected]> 於 2021年1月13日 週三 下午6:53寫道:

Quoted 5 lines · Renius Chen

The R/W performance of GL9763E is low with some platforms, which support ASPM mechanism, due to entering L1 state very frequently in R/W process. Enlarge its ASPM L1 entry delay to improve the R/W performance of GL9763E.

Quoted 5 lines
Quoted 2 lines

What do you mean by frequently? In between a burst of request or during a burst of request?

GL9763E enters ASPM L1 state after a very short idle in default, even during a burst of request.

Okay, then it certainly makes sense to extend the idle period.

Would you mind extending the commit message with some of this information, as I think it's useful.

Quoted 4 lines
Quoted 4 lines

I am thinking that this could have an effect on energy instead, but I guess it's not always straightforward to decide what's most important.

Quoted 8 lines
Quoted 2 lines

Anyway, what does it mean when you change to use 0x3FF? Are you increasing the idle period? Then for how long?

Yes, we considered that having high performance is more important than saving power during a burst of request.
So we increased the idle period for 260us, by setting 0x3FF to the ASPM L1 entry delay bits of our vendor-specific register. Anyway, GL9763E can still enter ASPM L1 state by a longer idle.

Quoted 6 lines

Most mmc controllers that uses runtime PM autosuspend for the same reasons, uses and idle period time of ~50us. 260us is in the same ballpark, so I am fine with that, if that works for you.

However, can you please add a comment in the code (and preferably also to the commit message) that 0x3FF means using a 260us idle period?

OK, I'll extend the commit message with some of these information and add a comment in the code to describe that the idle period is set to 260us.

Then I'll submit a newer version: mmc: sdhci-pci-gli: Enlarge ASPM L1 entry delay of GL9763E (v2).

Thank you.

Quoted 5 lines

[...]

Kind regards
Uffe