Skip to contentSkip to conversation

PCI: rcar: Check if device is runtime suspended instead of __clk_is_enabled()

PATCH Superseded [email protected] 4 participants 7 messages Nov 7, 2021 – Nov 8, 2021

Subsystems (4)

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

PATCH v3 1/1 PCI: rcar: Check if device is runtime suspended instead of __clk_is_enabled()

From: Marek Vasut <[email protected]>

Replace __clk_is_enabled() with pm_runtime_suspended(),
otherwise the following build error occurs:
arm-linux-gnueabi-ld: drivers/pci/controller/pcie-rcar-host.o: in function `rcar_pcie_aarch32_abort_handler':
pcie-rcar-host.c:(.text+0xdd0): undefined reference to `__clk_is_enabled'

Fixes a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")
Cc Arnd Bergmann <[email protected]>
Cc Bjorn Helgaas <[email protected]>
Cc Geert Uytterhoeven <[email protected]>
Cc Lorenzo Pieralisi <[email protected]>
Cc Stephen Boyd <[email protected]>
Cc Wolfram Sang <[email protected]>
Cc Yoshihiro Shimoda <[email protected]>

---
V2: Drop the __clk_is_enabled(), like it was done already in V1 of
a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")
V3: Use pm_runtime_suspended() instead of __clk_is_enabled()

---
 drivers/pci/controller/pcie-rcar-host.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/pci/controller/pcie-rcar-host.c +5 -5
index e12c2d8be05a..138592e22600 100644
@@ -50,10 +50,10 @@ struct rcar_msi {
  */
 static void __iomem *pcie_base;
 /*
- * Static copy of bus clock pointer, so we can check whether the clock
- * is enabled or not.
+ * Static copy of pcie device pointer, so we can check whether the
+ * device is runtime suspended or not.
  */
-static struct clk *pcie_bus_clk;
+static struct device *pcie_dev;
 #endif
 
 /* Structure representing the PCIe interface */
@@ -792,7 +792,7 @@ static int rcar_pcie_get_resources(struct rcar_pcie_host *host)
 #ifdef CONFIG_ARM
 	/* Cache static copy for L1 link state fixup hook on aarch32 */
 	pcie_base = pcie->base;
-	pcie_bus_clk = host->bus_clk;
+	pcie_dev = pcie->dev;
 #endif
 
 	return 0;
@@ -1062,7 +1062,7 @@ static int rcar_pcie_aarch32_abort_handler(unsigned long addr,
 
 	spin_lock_irqsave(&pmsr_lock, flags);
 
-	if (!pcie_base || !__clk_is_enabled(pcie_bus_clk)) {
+	if (!pcie_base || pm_runtime_suspended(pcie_dev)) {
 		ret = 1;
 		goto unlock_exit;
 	}
Signature · 1 line
2.33.0
#1 lore raw

[+CC Randy as he sent a patch to fix the same thing]

Hi Marek,

Quoted 6 lines

Replace __clk_is_enabled() with pm_runtime_suspended(),
otherwise the following build error occurs:
arm-linux-gnueabi-ld: drivers/pci/controller/pcie-rcar-host.o: in function `rcar_pcie_aarch32_abort_handler':
pcie-rcar-host.c:(.text+0xdd0): undefined reference to `__clk_is_enabled'

Fixes a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")

Randy sent a patch which aims to fix the same issue, albeit in a slightly different way. I wonder if it would make sense for the two of you to look at which approach should we pick, or even whether we should combine the two into one patch?

https://lore.kernel.org/linux-pci/[email protected]/

Krzysztof

#2 lore raw
Quoted 9 lines · Krzysztof Wilczyński

[+CC Randy as he sent a patch to fix the same thing]

Hi Marek,

Quoted 5 lines

Replace __clk_is_enabled() with pm_runtime_suspended(),
otherwise the following build error occurs:
arm-linux-gnueabi-ld: drivers/pci/controller/pcie-rcar-host.o: in function `rcar_pcie_aarch32_abort_handler':

   pcie-rcar-host.c:(.text+0xdd0): undefined reference to `__clk_is_enabled'
Quoted 8 lines
Quoted 1 line
Fixes a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")

Randy sent a patch which aims to fix the same issue, albeit in a slightly different way. I wonder if it would make sense for the two of you to look at which approach should we pick, or even whether we should combine the two into one patch?

   https://lore.kernel.org/linux-pci/[email protected]/

Hi,
I saw Marek's patch a couple of hours ago.

As long as pm_runtime_suspended() is always available, either live or as a stub (and it looks like it is), I don't see any reason for my patch at all.

thanks.

Signature · 1 line
~Randy
#3 lore raw

Hi Randy,

[...]

Quoted 5 lines
Quoted 5 lines

Randy sent a patch which aims to fix the same issue, albeit in a slightly different way. I wonder if it would make sense for the two of you to look at which approach should we pick, or even whether we should combine the two into one patch?

Quoted 8 lines
Quoted 1 line
   https://lore.kernel.org/linux-pci/[email protected]/

Hi,
I saw Marek's patch a couple of hours ago.

As long as pm_runtime_suspended() is always available, either live or as a stub (and it looks like it is), I don't see any reason for my patch at all.

Understood! I marked it accordingly in Patchwok. Thank you both!

By the way, can I count on your Acked-by or Reviewed-by here for Marek? If you agree with the premise of the changes here, etc., of course.

Krzysztof

Acked-by
#4 lore raw
Quoted 13 lines · Krzysztof Wilczyński

Hi Randy,

[...]

Quoted 10 lines
Quoted 6 lines

Randy sent a patch which aims to fix the same issue, albeit in a slightly different way. I wonder if it would make sense for the two of you to look at which approach should we pick, or even whether we should combine the two into one patch?

    https://lore.kernel.org/linux-pci/[email protected]/

Hi,
I saw Marek's patch a couple of hours ago.

Quoted 8 lines
Quoted 3 lines

As long as pm_runtime_suspended() is always available, either live or as a stub (and it looks like it is), I don't see any reason for my patch at all.

Understood! I marked it accordingly in Patchwok. Thank you both!

By the way, can I count on your Acked-by or Reviewed-by here for Marek? If you agree with the premise of the changes here, etc., of course.

Sure.

thanks.

Signature · 1 line
~Randy
Reviewed-by on v3 1/1
#5 lore raw
In reply to [email protected]

Hi Marek,

Thanks for your patch!

Quoted 6 lines · On Sun, Nov 7, 2021 at 8:11 PM <[email protected]> wrote:

From: Marek Vasut <[email protected]>

Replace __clk_is_enabled() with pm_runtime_suspended(),
otherwise the following build error occurs:
arm-linux-gnueabi-ld: drivers/pci/controller/pcie-rcar-host.o: in function `rcar_pcie_aarch32_abort_handler':
pcie-rcar-host.c:(.text+0xdd0): undefined reference to `__clk_is_enabled'

While this describes what is done and why, it misses one important semantic change: the old __clk_is_enabled() actually checked the wrong clock (bus clock instead of module clock), while pm_runtime_suspended() reflects (a.o.) the state of the module clock.

Quoted 3 lines
Fixes a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")

Gr{oetje,eeting}s,

Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]

In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds

#6 lore raw

[+CC Adding Sasha for visibiity]

Hi Geert,

[...]

Quoted 9 lines
Quoted 4 lines

Replace __clk_is_enabled() with pm_runtime_suspended(),
otherwise the following build error occurs:
arm-linux-gnueabi-ld: drivers/pci/controller/pcie-rcar-host.o: in function `rcar_pcie_aarch32_abort_handler':
pcie-rcar-host.c:(.text+0xdd0): undefined reference to `__clk_is_enabled'

While this describes what is done and why, it misses one important semantic change: the old __clk_is_enabled() actually checked the wrong clock (bus clock instead of module clock), while pm_runtime_suspended() reflects (a.o.) the state of the module clock.

This looks like it was a latent bug then, something that we might need to port back to the stable and long-term kernels, I believe.

Thank you, Geert!

Krzysztof