PCI: rcar: Check if device is runtime suspended instead of __clk_is_enabled()
Subsystems (4)
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'
---
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
@@ -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
[+CC Randy as he sent a patch to fix the same thing]
Hi Marek,
Quoted 6 lines
Replace
__clk_is_enabled()withpm_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
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()withpm_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
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
Randy Dunlap
Acked-byQuoted 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
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()withpm_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")Signed-off-by Marek Vasut <[email protected]>
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
[+CC Adding Sasha for visibiity]
Hi Geert,
[...]
Quoted 9 lines
Quoted 4 lines
Replace
__clk_is_enabled()withpm_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), whilepm_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