Hi Marek,
Thanks for your patch!
On Mon, Oct 11, 2021 at 12:07 AM <marek.vasut@xxxxxxxxx> wrote:
> From: Marek Vasut <marek.vasut+renesas@xxxxxxxxx>
>
> Remove __clk_is_enabled() call, 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'
> This should be OK, since the bus clock are always enabled in probe() of the driver.
As I said in [1], the bus clock is the wrong clock to check. The
correct clock to check is the module clock (like in the ATF version
of your patch). Unfortunately I missed this in the review of the
original patch, sorry for that.
As I said in [2], while the bus clock is always enabled, the module
clock is under control of Runtime PM. I'm not sure it's never
disabled (e.g. during system suspend). So you may have to check
pm_runtime_suspended().
If you ever get an imprecise external abort for some other reason,
while the PCIe module clock is disabled, accessing the PCIe module
registers will lead to another imprecise external abort, causing
infinite recursion.
> Fixes: a115b1bd3af0 ("PCI: rcar: Add L1 link state fix into data abort hook")
> Signed-off-by: Marek Vasut <marek.vasut+renesas@xxxxxxxxx>
> 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")
I couldn't find v1, not in my mailbox, and not in lore?
[1] https://lore.kernel.org/linux-pci/CAMuHMdV8Xu-Pgda9ZrgaXFqXdzBrSRWwiSQFLjzxqRGNWkO3wQ@xxxxxxxxxxxxxx
[2] https://lore.kernel.org/linux-pci/CAMuHMdVQ7r6-H8kBiNYXdqHQRGJxc4eE4hYthFw+XJZx86g6eA@xxxxxxxxxxxxxx
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@xxxxxxxxxxxxxx
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
