2022-08-30 12:55:53

by Conor Dooley

[permalink] [raw]
Subject: [PATCH v4 01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

Unnoticed in current code, there is an array bounds violation present
during clock registration. This seems to fail gracefully in v6.0-rc1,
and life carrys on. While converting the driver to use standard clock
structs/ops, kernel panics were seen during boot when built with clang:

[ 0.581754] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b1
[ 0.591520] Oops [#1]
[ 0.594045] Modules linked in:
[ 0.597435] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.0.0-rc1-00011-g8e1459cf4eca #1
[ 0.606188] Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
[ 0.613012] epc : __clk_register+0x4a6/0x85c
[ 0.617759] ra : __clk_register+0x49e/0x85c
[ 0.622489] epc : ffffffff803faf7c ra : ffffffff803faf74 sp : ffffffc80400b720
[ 0.630466] gp : ffffffff810e93f8 tp : ffffffe77fe60000 t0 : ffffffe77ffb3800
[ 0.638443] t1 : 000000000000000a t2 : ffffffffffffffff s0 : ffffffc80400b7c0
[ 0.646420] s1 : 0000000000000001 a0 : 0000000000000001 a1 : 0000000000000000
[ 0.654396] a2 : 0000000000000001 a3 : 0000000000000000 a4 : 0000000000000000
[ 0.662373] a5 : ffffffff803a5810 a6 : 0000000200000022 a7 : 0000000000000006
[ 0.670350] s2 : ffffffff81099d48 s3 : ffffffff80d6e28e s4 : 0000000000000028
[ 0.678327] s5 : ffffffff810ed3c8 s6 : ffffffff810ed3d0 s7 : ffffffe77ffbc100
[ 0.686304] s8 : ffffffe77ffb1540 s9 : ffffffe77ffb1540 s10: 0000000000000008
[ 0.694281] s11: 0000000000000000 t3 : 00000000000000c6 t4 : 0000000000000007
[ 0.702258] t5 : ffffffff810c78c0 t6 : ffffffe77ff88cd0
[ 0.708125] status: 0000000200000120 badaddr: 00000000000000b1 cause: 000000000000000d
[ 0.716869] [<ffffffff803fb892>] devm_clk_hw_register+0x62/0xaa
[ 0.723420] [<ffffffff80403412>] mpfs_clk_probe+0x1e0/0x244

It fails on "clk_periph_timer" - which uses a different parent, that it
tries to find using the macro:
\#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].cfg.hw)

If parent is RTCREF, so the macro becomes: &mpfs_cfg_clks[33].cfg.hw
which is well beyond the end of the array. Amazingly, builds with GCC
11.1 see no problem here, booting correctly and hooking the parent up
etc. Builds with clang-15 do not, with the above panic.

Drop the macro for the RTCREF and use the array directly to avoid the
panic, using a newly added define that brings the index into the valid
range.

Fixes: 1c6a7ea32b8c ("clk: microchip: mpfs: add RTCREF clock control")
CC: Nathan Chancellor <[email protected]>
Signed-off-by: Conor Dooley <[email protected]>
---
drivers/clk/microchip/clk-mpfs.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
index 070c3b896559..9e41f07b3fa6 100644
--- a/drivers/clk/microchip/clk-mpfs.c
+++ b/drivers/clk/microchip/clk-mpfs.c
@@ -27,6 +27,8 @@
#define MSSPLL_POSTDIV_WIDTH 0x07u
#define MSSPLL_FIXED_DIV 4u

+#define RTCREF_OFFSET (CLK_RTCREF - CLK_ENVM)
+
struct mpfs_clock_data {
void __iomem *base;
void __iomem *msspll_base;
@@ -381,7 +383,8 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0),
CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0),
CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0),
- CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0),
+ CLK_PERIPH(CLK_TIMER, "clk_periph_timer",
+ &mpfs_cfg_clks[CLK_RTCREF - RTCREF_OFFSET].hw, 4, 0),
CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL),
CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0),
CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0),
--
2.36.1


2022-08-31 17:07:28

by Conor Dooley

[permalink] [raw]
Subject: Re: [PATCH v4 01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

Hey Stephen,

On 30/08/2022 13:52, Conor Dooley wrote:
> Unnoticed in current code, there is an array bounds violation present

Looks like the "Unnoticed in current code" is not accurate. For certain
compiler/kernel version combinations that can be triggered without the
rest of the patchset. Apparently the default yocto gcc used by our BSP &
v6.0-rcN does the trick...

Could you take this one patch onto clk-fixes or would you like me to
resend individually?

Thanks,
Conor.

> during clock registration. This seems to fail gracefully in v6.0-rc1,
> and life carrys on. While converting the driver to use standard clock
> structs/ops, kernel panics were seen during boot when built with clang:
>
> [ 0.581754] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b1
> [ 0.591520] Oops [#1]
> [ 0.594045] Modules linked in:
> [ 0.597435] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.0.0-rc1-00011-g8e1459cf4eca #1
> [ 0.606188] Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
> [ 0.613012] epc : __clk_register+0x4a6/0x85c
> [ 0.617759] ra : __clk_register+0x49e/0x85c
> [ 0.622489] epc : ffffffff803faf7c ra : ffffffff803faf74 sp : ffffffc80400b720
> [ 0.630466] gp : ffffffff810e93f8 tp : ffffffe77fe60000 t0 : ffffffe77ffb3800
> [ 0.638443] t1 : 000000000000000a t2 : ffffffffffffffff s0 : ffffffc80400b7c0
> [ 0.646420] s1 : 0000000000000001 a0 : 0000000000000001 a1 : 0000000000000000
> [ 0.654396] a2 : 0000000000000001 a3 : 0000000000000000 a4 : 0000000000000000
> [ 0.662373] a5 : ffffffff803a5810 a6 : 0000000200000022 a7 : 0000000000000006
> [ 0.670350] s2 : ffffffff81099d48 s3 : ffffffff80d6e28e s4 : 0000000000000028
> [ 0.678327] s5 : ffffffff810ed3c8 s6 : ffffffff810ed3d0 s7 : ffffffe77ffbc100
> [ 0.686304] s8 : ffffffe77ffb1540 s9 : ffffffe77ffb1540 s10: 0000000000000008
> [ 0.694281] s11: 0000000000000000 t3 : 00000000000000c6 t4 : 0000000000000007
> [ 0.702258] t5 : ffffffff810c78c0 t6 : ffffffe77ff88cd0
> [ 0.708125] status: 0000000200000120 badaddr: 00000000000000b1 cause: 000000000000000d
> [ 0.716869] [<ffffffff803fb892>] devm_clk_hw_register+0x62/0xaa
> [ 0.723420] [<ffffffff80403412>] mpfs_clk_probe+0x1e0/0x244
>
> It fails on "clk_periph_timer" - which uses a different parent, that it
> tries to find using the macro:
> \#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].cfg.hw)
>
> If parent is RTCREF, so the macro becomes: &mpfs_cfg_clks[33].cfg.hw
> which is well beyond the end of the array. Amazingly, builds with GCC
> 11.1 see no problem here, booting correctly and hooking the parent up
> etc. Builds with clang-15 do not, with the above panic.
>
> Drop the macro for the RTCREF and use the array directly to avoid the
> panic, using a newly added define that brings the index into the valid
> range.
>
> Fixes: 1c6a7ea32b8c ("clk: microchip: mpfs: add RTCREF clock control")
> CC: Nathan Chancellor <[email protected]>
> Signed-off-by: Conor Dooley <[email protected]>
> ---
> drivers/clk/microchip/clk-mpfs.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
> index 070c3b896559..9e41f07b3fa6 100644
> --- a/drivers/clk/microchip/clk-mpfs.c
> +++ b/drivers/clk/microchip/clk-mpfs.c
> @@ -27,6 +27,8 @@
> #define MSSPLL_POSTDIV_WIDTH 0x07u
> #define MSSPLL_FIXED_DIV 4u
>
> +#define RTCREF_OFFSET (CLK_RTCREF - CLK_ENVM)
> +
> struct mpfs_clock_data {
> void __iomem *base;
> void __iomem *msspll_base;
> @@ -381,7 +383,8 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
> CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0),
> CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0),
> CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0),
> - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0),
> + CLK_PERIPH(CLK_TIMER, "clk_periph_timer",
> + &mpfs_cfg_clks[CLK_RTCREF - RTCREF_OFFSET].hw, 4, 0),
> CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL),
> CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0),
> CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0),

2022-09-08 07:12:12

by Conor Dooley

[permalink] [raw]
Subject: Re: [PATCH v4 01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

On 08/09/2022 07:44, Claudiu Beznea - M18063 wrote:
> On 30.08.2022 15:52, Conor Dooley wrote:
>> Unnoticed in current code, there is an array bounds violation present
>> during clock registration. This seems to fail gracefully in v6.0-rc1,
>> and life carrys on. While converting the driver to use standard clock
>> structs/ops, kernel panics were seen during boot when built with clang:
>>
>> [ 0.581754] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b1
>> [ 0.591520] Oops [#1]
>> [ 0.594045] Modules linked in:
>> [ 0.597435] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.0.0-rc1-00011-g8e1459cf4eca #1
>> [ 0.606188] Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
>> [ 0.613012] epc : __clk_register+0x4a6/0x85c
>> [ 0.617759] ra : __clk_register+0x49e/0x85c
>> [ 0.622489] epc : ffffffff803faf7c ra : ffffffff803faf74 sp : ffffffc80400b720
>> [ 0.630466] gp : ffffffff810e93f8 tp : ffffffe77fe60000 t0 : ffffffe77ffb3800
>> [ 0.638443] t1 : 000000000000000a t2 : ffffffffffffffff s0 : ffffffc80400b7c0
>> [ 0.646420] s1 : 0000000000000001 a0 : 0000000000000001 a1 : 0000000000000000
>> [ 0.654396] a2 : 0000000000000001 a3 : 0000000000000000 a4 : 0000000000000000
>> [ 0.662373] a5 : ffffffff803a5810 a6 : 0000000200000022 a7 : 0000000000000006
>> [ 0.670350] s2 : ffffffff81099d48 s3 : ffffffff80d6e28e s4 : 0000000000000028
>> [ 0.678327] s5 : ffffffff810ed3c8 s6 : ffffffff810ed3d0 s7 : ffffffe77ffbc100
>> [ 0.686304] s8 : ffffffe77ffb1540 s9 : ffffffe77ffb1540 s10: 0000000000000008
>> [ 0.694281] s11: 0000000000000000 t3 : 00000000000000c6 t4 : 0000000000000007
>> [ 0.702258] t5 : ffffffff810c78c0 t6 : ffffffe77ff88cd0
>> [ 0.708125] status: 0000000200000120 badaddr: 00000000000000b1 cause: 000000000000000d
>> [ 0.716869] [<ffffffff803fb892>] devm_clk_hw_register+0x62/0xaa
>> [ 0.723420] [<ffffffff80403412>] mpfs_clk_probe+0x1e0/0x244
>>
>> It fails on "clk_periph_timer" - which uses a different parent, that it
>> tries to find using the macro:
>> \#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].cfg.hw)
>>
>> If parent is RTCREF, so the macro becomes: &mpfs_cfg_clks[33].cfg.hw
>> which is well beyond the end of the array. Amazingly, builds with GCC
>> 11.1 see no problem here, booting correctly and hooking the parent up
>> etc. Builds with clang-15 do not, with the above panic.
>>
>> Drop the macro for the RTCREF and use the array directly to avoid the
>> panic, using a newly added define that brings the index into the valid
>> range.
>>
>> Fixes: 1c6a7ea32b8c ("clk: microchip: mpfs: add RTCREF clock control")
>> CC: Nathan Chancellor <[email protected]>
>> Signed-off-by: Conor Dooley <[email protected]>
>> ---
>> drivers/clk/microchip/clk-mpfs.c | 5 ++++-
>> 1 file changed, 4 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
>> index 070c3b896559..9e41f07b3fa6 100644
>> --- a/drivers/clk/microchip/clk-mpfs.c
>> +++ b/drivers/clk/microchip/clk-mpfs.c
>> @@ -27,6 +27,8 @@
>> #define MSSPLL_POSTDIV_WIDTH 0x07u
>> #define MSSPLL_FIXED_DIV 4u
>>
>> +#define RTCREF_OFFSET (CLK_RTCREF - CLK_ENVM)
>> +
>> struct mpfs_clock_data {
>> void __iomem *base;
>> void __iomem *msspll_base;
>> @@ -381,7 +383,8 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
>> CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0),
>> CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0),
>> CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0),
>> - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0),
>> + CLK_PERIPH(CLK_TIMER, "clk_periph_timer",
>> + &mpfs_cfg_clks[CLK_RTCREF - RTCREF_OFFSET].hw, 4, 0),
>
> A personal taste: as clk IDs and clk indexes in mpfs_cfg_clks[] array are
> different thing (ID for clk_periph_timer is already different) and the
> CLK_RTCREF - RTCREF_OFFSET here is in the end CLK_ENVM = 3 maybe easier to
> follow the code would be to add new macros like:
>
> #define CLK_CPU_OFF 0
> #define CLK_AXI_OFF 1
> #define CLK_AHB_OFF 2
> #define CLK_RTCREF_OFF 3
>
> and change the CLK_PARENT() macro something as follows:
>
> #define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT##_OFF].hw)

Sure, but that is out-of-scope for this fix which needs backporting.

>
>> CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL),
>> CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0),
>> CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0),
>

2022-09-08 07:13:15

by Claudiu Beznea

[permalink] [raw]
Subject: Re: [PATCH v4 01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

On 30.08.2022 15:52, Conor Dooley wrote:
> Unnoticed in current code, there is an array bounds violation present
> during clock registration. This seems to fail gracefully in v6.0-rc1,
> and life carrys on. While converting the driver to use standard clock
> structs/ops, kernel panics were seen during boot when built with clang:
>
> [ 0.581754] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b1
> [ 0.591520] Oops [#1]
> [ 0.594045] Modules linked in:
> [ 0.597435] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.0.0-rc1-00011-g8e1459cf4eca #1
> [ 0.606188] Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
> [ 0.613012] epc : __clk_register+0x4a6/0x85c
> [ 0.617759] ra : __clk_register+0x49e/0x85c
> [ 0.622489] epc : ffffffff803faf7c ra : ffffffff803faf74 sp : ffffffc80400b720
> [ 0.630466] gp : ffffffff810e93f8 tp : ffffffe77fe60000 t0 : ffffffe77ffb3800
> [ 0.638443] t1 : 000000000000000a t2 : ffffffffffffffff s0 : ffffffc80400b7c0
> [ 0.646420] s1 : 0000000000000001 a0 : 0000000000000001 a1 : 0000000000000000
> [ 0.654396] a2 : 0000000000000001 a3 : 0000000000000000 a4 : 0000000000000000
> [ 0.662373] a5 : ffffffff803a5810 a6 : 0000000200000022 a7 : 0000000000000006
> [ 0.670350] s2 : ffffffff81099d48 s3 : ffffffff80d6e28e s4 : 0000000000000028
> [ 0.678327] s5 : ffffffff810ed3c8 s6 : ffffffff810ed3d0 s7 : ffffffe77ffbc100
> [ 0.686304] s8 : ffffffe77ffb1540 s9 : ffffffe77ffb1540 s10: 0000000000000008
> [ 0.694281] s11: 0000000000000000 t3 : 00000000000000c6 t4 : 0000000000000007
> [ 0.702258] t5 : ffffffff810c78c0 t6 : ffffffe77ff88cd0
> [ 0.708125] status: 0000000200000120 badaddr: 00000000000000b1 cause: 000000000000000d
> [ 0.716869] [<ffffffff803fb892>] devm_clk_hw_register+0x62/0xaa
> [ 0.723420] [<ffffffff80403412>] mpfs_clk_probe+0x1e0/0x244
>
> It fails on "clk_periph_timer" - which uses a different parent, that it
> tries to find using the macro:
> \#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].cfg.hw)
>
> If parent is RTCREF, so the macro becomes: &mpfs_cfg_clks[33].cfg.hw
> which is well beyond the end of the array. Amazingly, builds with GCC
> 11.1 see no problem here, booting correctly and hooking the parent up
> etc. Builds with clang-15 do not, with the above panic.
>
> Drop the macro for the RTCREF and use the array directly to avoid the
> panic, using a newly added define that brings the index into the valid
> range.
>
> Fixes: 1c6a7ea32b8c ("clk: microchip: mpfs: add RTCREF clock control")
> CC: Nathan Chancellor <[email protected]>
> Signed-off-by: Conor Dooley <[email protected]>
> ---
> drivers/clk/microchip/clk-mpfs.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
> index 070c3b896559..9e41f07b3fa6 100644
> --- a/drivers/clk/microchip/clk-mpfs.c
> +++ b/drivers/clk/microchip/clk-mpfs.c
> @@ -27,6 +27,8 @@
> #define MSSPLL_POSTDIV_WIDTH 0x07u
> #define MSSPLL_FIXED_DIV 4u
>
> +#define RTCREF_OFFSET (CLK_RTCREF - CLK_ENVM)
> +
> struct mpfs_clock_data {
> void __iomem *base;
> void __iomem *msspll_base;
> @@ -381,7 +383,8 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
> CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0),
> CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0),
> CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0),
> - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0),
> + CLK_PERIPH(CLK_TIMER, "clk_periph_timer",
> + &mpfs_cfg_clks[CLK_RTCREF - RTCREF_OFFSET].hw, 4, 0),

A personal taste: as clk IDs and clk indexes in mpfs_cfg_clks[] array are
different thing (ID for clk_periph_timer is already different) and the
CLK_RTCREF - RTCREF_OFFSET here is in the end CLK_ENVM = 3 maybe easier to
follow the code would be to add new macros like:

#define CLK_CPU_OFF 0
#define CLK_AXI_OFF 1
#define CLK_AHB_OFF 2
#define CLK_RTCREF_OFF 3

and change the CLK_PARENT() macro something as follows:

#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT##_OFF].hw)

> CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL),
> CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0),
> CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0),

2022-09-09 11:42:33

by Conor Dooley

[permalink] [raw]
Subject: Re: [PATCH v4 01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

On 08/09/2022 07:48, Conor Dooley wrote:
> On 08/09/2022 07:44, Claudiu Beznea - M18063 wrote:
>> On 30.08.2022 15:52, Conor Dooley wrote:
>>> Unnoticed in current code, there is an array bounds violation present
>>> during clock registration. This seems to fail gracefully in v6.0-rc1,
>>> and life carrys on. While converting the driver to use standard clock
>>> structs/ops, kernel panics were seen during boot when built with clang:
>>>
>>> [    0.581754] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b1
>>> [    0.591520] Oops [#1]
>>> [    0.594045] Modules linked in:
>>> [    0.597435] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.0.0-rc1-00011-g8e1459cf4eca #1
>>> [    0.606188] Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
>>> [    0.613012] epc : __clk_register+0x4a6/0x85c
>>> [    0.617759]  ra : __clk_register+0x49e/0x85c
>>> [    0.622489] epc : ffffffff803faf7c ra : ffffffff803faf74 sp : ffffffc80400b720
>>> [    0.630466]  gp : ffffffff810e93f8 tp : ffffffe77fe60000 t0 : ffffffe77ffb3800
>>> [    0.638443]  t1 : 000000000000000a t2 : ffffffffffffffff s0 : ffffffc80400b7c0
>>> [    0.646420]  s1 : 0000000000000001 a0 : 0000000000000001 a1 : 0000000000000000
>>> [    0.654396]  a2 : 0000000000000001 a3 : 0000000000000000 a4 : 0000000000000000
>>> [    0.662373]  a5 : ffffffff803a5810 a6 : 0000000200000022 a7 : 0000000000000006
>>> [    0.670350]  s2 : ffffffff81099d48 s3 : ffffffff80d6e28e s4 : 0000000000000028
>>> [    0.678327]  s5 : ffffffff810ed3c8 s6 : ffffffff810ed3d0 s7 : ffffffe77ffbc100
>>> [    0.686304]  s8 : ffffffe77ffb1540 s9 : ffffffe77ffb1540 s10: 0000000000000008
>>> [    0.694281]  s11: 0000000000000000 t3 : 00000000000000c6 t4 : 0000000000000007
>>> [    0.702258]  t5 : ffffffff810c78c0 t6 : ffffffe77ff88cd0
>>> [    0.708125] status: 0000000200000120 badaddr: 00000000000000b1 cause: 000000000000000d
>>> [    0.716869] [<ffffffff803fb892>] devm_clk_hw_register+0x62/0xaa
>>> [    0.723420] [<ffffffff80403412>] mpfs_clk_probe+0x1e0/0x244
>>>
>>> It fails on "clk_periph_timer" - which uses a different parent, that it
>>> tries to find using the macro:
>>> \#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].cfg.hw)
>>>
>>> If parent is RTCREF, so the macro becomes: &mpfs_cfg_clks[33].cfg.hw
>>> which is well beyond the end of the array. Amazingly, builds with GCC
>>> 11.1 see no problem here, booting correctly and hooking the parent up
>>> etc. Builds with clang-15 do not, with the above panic.
>>>
>>> Drop the macro for the RTCREF and use the array directly to avoid the
>>> panic, using a newly added define that brings the index into the valid
>>> range.
>>>
>>> Fixes: 1c6a7ea32b8c ("clk: microchip: mpfs: add RTCREF clock control")
>>> CC: Nathan Chancellor <[email protected]>
>>> Signed-off-by: Conor Dooley <[email protected]>
>>> ---
>>>   drivers/clk/microchip/clk-mpfs.c | 5 ++++-
>>>   1 file changed, 4 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
>>> index 070c3b896559..9e41f07b3fa6 100644
>>> --- a/drivers/clk/microchip/clk-mpfs.c
>>> +++ b/drivers/clk/microchip/clk-mpfs.c
>>> @@ -27,6 +27,8 @@
>>>   #define MSSPLL_POSTDIV_WIDTH    0x07u
>>>   #define MSSPLL_FIXED_DIV    4u
>>> +#define RTCREF_OFFSET        (CLK_RTCREF - CLK_ENVM)
>>> +
>>>   struct mpfs_clock_data {
>>>       void __iomem *base;
>>>       void __iomem *msspll_base;
>>> @@ -381,7 +383,8 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
>>>       CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0),
>>>       CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0),
>>>       CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0),
>>> -    CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0),
>>> +    CLK_PERIPH(CLK_TIMER, "clk_periph_timer",
>>> +           &mpfs_cfg_clks[CLK_RTCREF - RTCREF_OFFSET].hw, 4, 0),
>>
>> A personal taste: as clk IDs and clk indexes in mpfs_cfg_clks[] array are
>> different thing (ID for clk_periph_timer is already different) and the
>> CLK_RTCREF - RTCREF_OFFSET here is in the end CLK_ENVM = 3 maybe easier to
>> follow the code would be to add new macros like:
>>
>> #define CLK_CPU_OFF 0
>> #define CLK_AXI_OFF 1
>> #define CLK_AHB_OFF 2
>> #define CLK_RTCREF_OFF 3
>>
>> and change the CLK_PARENT() macro something as follows:
>>
>> #define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT##_OFF].hw)
>
> Sure, but that is out-of-scope for this fix which needs backporting.

I think I mis-interpreted your suggestion. Gonna give it a go & unless
clang screams and yells at me I think I like it more than relying on
the relationships between the binding numbers.

Thanks,
Conor.