* [RESEND PATCH v1] PCI: replace msleep to save waiting time
@ 2026-02-23 6:19 Hongyu Xie
2026-02-23 12:05 ` Ilpo Järvinen
2026-02-25 18:10 ` Bjorn Helgaas
0 siblings, 2 replies; 3+ messages in thread
From: Hongyu Xie @ 2026-02-23 6:19 UTC (permalink / raw)
To: bhelgaas; +Cc: linux-pci, linux-kernel, Hongyu Xie
In pcie_wait_for_link_status, using msleep(1) to wait for link status
change.
But msleep(1) can sleep for nearly 5ms.
ftrace shows:
0) | pcie_wait_for_link_status() {
0) 0.500 us | pcie_capability_read_word();
0) 0.580 us | pcie_capability_read_word();
0) * 10292.26 us | }
after changing to usleep_range.
ftrace shows:
0) | pcie_wait_for_link_status() {
0) 0.320 us | pcie_capability_read_word();
0) 0.480 us | pcie_capability_read_word();
0) # 2483.980 us | }
So fix this by using usleep_range.
Signed-off-by: Hongyu Xie <xiehongyu1@kylinos.cn>
---
drivers/pci/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index f3244630bfd0..68532e248e51 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4519,7 +4519,7 @@ static int pcie_wait_for_link_status(struct pci_dev *pdev,
pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
if ((lnksta & lnksta_mask) == lnksta_match)
return 0;
- msleep(1);
+ usleep_range(1000, 1100);
} while (time_before(jiffies, end_jiffies));
return -ETIMEDOUT;
--
2.25.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [RESEND PATCH v1] PCI: replace msleep to save waiting time
2026-02-23 6:19 [RESEND PATCH v1] PCI: replace msleep to save waiting time Hongyu Xie
@ 2026-02-23 12:05 ` Ilpo Järvinen
2026-02-25 18:10 ` Bjorn Helgaas
1 sibling, 0 replies; 3+ messages in thread
From: Ilpo Järvinen @ 2026-02-23 12:05 UTC (permalink / raw)
To: Hongyu Xie; +Cc: bhelgaas, linux-pci, LKML
On Mon, 23 Feb 2026, Hongyu Xie wrote:
> In pcie_wait_for_link_status, using msleep(1) to wait for link status
Add () after any function name in the commit message.
> change.
> But msleep(1) can sleep for nearly 5ms.
Why does the extra delay matter/is a problem? It would be good to include
such a justification into this change description.
> ftrace shows:
> 0) | pcie_wait_for_link_status() {
> 0) 0.500 us | pcie_capability_read_word();
> 0) 0.580 us | pcie_capability_read_word();
> 0) * 10292.26 us | }
>
> after changing to usleep_range.
+ ()
> ftrace shows:
>
> 0) | pcie_wait_for_link_status() {
> 0) 0.320 us | pcie_capability_read_word();
> 0) 0.480 us | pcie_capability_read_word();
> 0) # 2483.980 us | }
>
> So fix this by using usleep_range.
Ditto.
> Signed-off-by: Hongyu Xie <xiehongyu1@kylinos.cn>
> ---
> drivers/pci/pci.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index f3244630bfd0..68532e248e51 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -4519,7 +4519,7 @@ static int pcie_wait_for_link_status(struct pci_dev *pdev,
> pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
> if ((lnksta & lnksta_mask) == lnksta_match)
> return 0;
> - msleep(1);
> + usleep_range(1000, 1100);
> } while (time_before(jiffies, end_jiffies));
>
> return -ETIMEDOUT;
>
--
i.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [RESEND PATCH v1] PCI: replace msleep to save waiting time
2026-02-23 6:19 [RESEND PATCH v1] PCI: replace msleep to save waiting time Hongyu Xie
2026-02-23 12:05 ` Ilpo Järvinen
@ 2026-02-25 18:10 ` Bjorn Helgaas
1 sibling, 0 replies; 3+ messages in thread
From: Bjorn Helgaas @ 2026-02-25 18:10 UTC (permalink / raw)
To: Hongyu Xie; +Cc: bhelgaas, linux-pci, linux-kernel
On Mon, Feb 23, 2026 at 02:19:19PM +0800, Hongyu Xie wrote:
> In pcie_wait_for_link_status, using msleep(1) to wait for link status
> change.
> But msleep(1) can sleep for nearly 5ms.
>
> ftrace shows:
> 0) | pcie_wait_for_link_status() {
> 0) 0.500 us | pcie_capability_read_word();
> 0) 0.580 us | pcie_capability_read_word();
> 0) * 10292.26 us | }
>
> after changing to usleep_range.
> ftrace shows:
>
> 0) | pcie_wait_for_link_status() {
> 0) 0.320 us | pcie_capability_read_word();
> 0) 0.480 us | pcie_capability_read_word();
> 0) # 2483.980 us | }
>
> So fix this by using usleep_range.
>
> Signed-off-by: Hongyu Xie <xiehongyu1@kylinos.cn>
> ---
> drivers/pci/pci.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index f3244630bfd0..68532e248e51 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -4519,7 +4519,7 @@ static int pcie_wait_for_link_status(struct pci_dev *pdev,
> pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
> if ((lnksta & lnksta_mask) == lnksta_match)
> return 0;
> - msleep(1);
> + usleep_range(1000, 1100);
Perhaps consider fsleep(), since it's a little more generic and I
don't think there's anything magic about the 100 us range value.
> } while (time_before(jiffies, end_jiffies));
>
> return -ETIMEDOUT;
> --
> 2.25.1
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-02-25 18:10 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-02-23 6:19 [RESEND PATCH v1] PCI: replace msleep to save waiting time Hongyu Xie
2026-02-23 12:05 ` Ilpo Järvinen
2026-02-25 18:10 ` Bjorn Helgaas
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox