diff mbox series

[v4,01/13] clk: microchip: mpfs: fix clk_cfg array bounds violation

Message ID 20220830125249.2373416-1-conor.dooley@microchip.com
State New
Headers show
Series PolarFire SoC reset controller & clock cleanups | expand

Commit Message

Conor Dooley Aug. 30, 2022, 12:52 p.m. UTC
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 <nathan@kernel.org>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/clk/microchip/clk-mpfs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

Comments

Claudiu Beznea Sept. 8, 2022, 6:44 a.m. UTC | #1
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 <nathan@kernel.org>
> Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
> ---
>  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),
Conor Dooley Sept. 8, 2022, 6:48 a.m. UTC | #2
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 <nathan@kernel.org>
>> Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
>> ---
>>   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),
>
diff mbox series

Patch

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),