diff mbox series

[v4,1/2] riscv: move sbi_init() earlier before jump_label_init()

Message ID 20220521143456.2759-2-jszhang@kernel.org (mailing list archive)
State New, archived
Headers show
Series use static key to optimize pgtable_l4_enabled | expand

Commit Message

Jisheng Zhang May 21, 2022, 2:34 p.m. UTC 
We call jump_label_init() in setup_arch() is to use static key
mechanism earlier, but riscv jump label relies on the sbi functions,
If we enable static key before sbi_init(), the code path looks like:
  static_branch_enable()
    ..
      arch_jump_label_transform()
        patch_text_nosync()
          flush_icache_range()
            flush_icache_all()
              sbi_remote_fence_i() for CONFIG_RISCV_SBI case
                __sbi_rfence()

Since sbi isn't initialized, so NULL deference! Here is a typical
panic log:

[    0.000000] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[    0.000000] Oops [#1]
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.18.0-rc7+ #79
[    0.000000] Hardware name: riscv-virtio,qemu (DT)
[    0.000000] epc : 0x0
[    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
[    0.000000] epc : 0000000000000000 ra : ffffffff80005826 sp : ffffffff80c03d50
[    0.000000]  gp : ffffffff80ca6178 tp : ffffffff80c0ad80 t0 : 6200000000000000
[    0.000000]  t1 : 0000000000000000 t2 : 62203a6b746e6972 s0 : ffffffff80c03d60
[    0.000000]  s1 : ffffffff80001af6 a0 : 0000000000000000 a1 : 0000000000000000
[    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
[    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000080200
[    0.000000]  s2 : ffffffff808b3e48 s3 : ffffffff808bf698 s4 : ffffffff80cb2818
[    0.000000]  s5 : 0000000000000001 s6 : ffffffff80c9c345 s7 : ffffffff80895aa0
[    0.000000]  s8 : 0000000000000001 s9 : 000000000000007f s10: 0000000000000000
[    0.000000]  s11: 0000000000000000 t3 : ffffffff80824d08 t4 : 0000000000000022
[    0.000000]  t5 : 000000000000003d t6 : 0000000000000000
[    0.000000] status: 0000000000000100 badaddr: 0000000000000000 cause: 000000000000000c
[    0.000000] ---[ end trace 0000000000000000 ]---
[    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
[    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---

Fix this issue by moving sbi_init() earlier before jump_label_init()

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---
 arch/riscv/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Atish Patra May 22, 2022, 8:01 a.m. UTC | #1 
On Sat, May 21, 2022 at 7:44 AM Jisheng Zhang <jszhang@kernel.org> wrote:
>
> We call jump_label_init() in setup_arch() is to use static key
> mechanism earlier, but riscv jump label relies on the sbi functions,
> If we enable static key before sbi_init(), the code path looks like:
>   static_branch_enable()
>     ..
>       arch_jump_label_transform()
>         patch_text_nosync()
>           flush_icache_range()
>             flush_icache_all()
>               sbi_remote_fence_i() for CONFIG_RISCV_SBI case
>                 __sbi_rfence()
>

@Alexandre Ghiti : Is this the root cause of the panic you were seeing ?

IIRC, you mentioned in your last email that you don't see the issue
anymore. May be you avoided the issue because alternatives usage
was moved but root case remains as it is ?

> Since sbi isn't initialized, so NULL deference! Here is a typical
> panic log:
>
> [    0.000000] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
> [    0.000000] Oops [#1]
> [    0.000000] Modules linked in:
> [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.18.0-rc7+ #79
> [    0.000000] Hardware name: riscv-virtio,qemu (DT)
> [    0.000000] epc : 0x0
> [    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
> [    0.000000] epc : 0000000000000000 ra : ffffffff80005826 sp : ffffffff80c03d50
> [    0.000000]  gp : ffffffff80ca6178 tp : ffffffff80c0ad80 t0 : 6200000000000000
> [    0.000000]  t1 : 0000000000000000 t2 : 62203a6b746e6972 s0 : ffffffff80c03d60
> [    0.000000]  s1 : ffffffff80001af6 a0 : 0000000000000000 a1 : 0000000000000000
> [    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
> [    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000080200
> [    0.000000]  s2 : ffffffff808b3e48 s3 : ffffffff808bf698 s4 : ffffffff80cb2818
> [    0.000000]  s5 : 0000000000000001 s6 : ffffffff80c9c345 s7 : ffffffff80895aa0
> [    0.000000]  s8 : 0000000000000001 s9 : 000000000000007f s10: 0000000000000000
> [    0.000000]  s11: 0000000000000000 t3 : ffffffff80824d08 t4 : 0000000000000022
> [    0.000000]  t5 : 000000000000003d t6 : 0000000000000000
> [    0.000000] status: 0000000000000100 badaddr: 0000000000000000 cause: 000000000000000c
> [    0.000000] ---[ end trace 0000000000000000 ]---
> [    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
> [    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---
>
> Fix this issue by moving sbi_init() earlier before jump_label_init()
>
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> ---
>  arch/riscv/kernel/setup.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index 834eb652a7b9..d150cedeb7e0 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -268,6 +268,7 @@ void __init setup_arch(char **cmdline_p)
>         *cmdline_p = boot_command_line;
>
>         early_ioremap_setup();
> +       sbi_init();
>         jump_label_init();
>         parse_early_param();
>
> @@ -284,7 +285,6 @@ void __init setup_arch(char **cmdline_p)
>         misc_mem_init();
>
>         init_resources();
> -       sbi_init();
>
>  #ifdef CONFIG_KASAN
>         kasan_init();
> --
> 2.34.1
>
>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv
Anup Patel June 26, 2022, 4:32 a.m. UTC | #2 
On Sat, May 21, 2022 at 8:13 PM Jisheng Zhang <jszhang@kernel.org> wrote:
>
> We call jump_label_init() in setup_arch() is to use static key
> mechanism earlier, but riscv jump label relies on the sbi functions,
> If we enable static key before sbi_init(), the code path looks like:
>   static_branch_enable()
>     ..
>       arch_jump_label_transform()
>         patch_text_nosync()
>           flush_icache_range()
>             flush_icache_all()
>               sbi_remote_fence_i() for CONFIG_RISCV_SBI case
>                 __sbi_rfence()
>
> Since sbi isn't initialized, so NULL deference! Here is a typical
> panic log:
>
> [    0.000000] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
> [    0.000000] Oops [#1]
> [    0.000000] Modules linked in:
> [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.18.0-rc7+ #79
> [    0.000000] Hardware name: riscv-virtio,qemu (DT)
> [    0.000000] epc : 0x0
> [    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
> [    0.000000] epc : 0000000000000000 ra : ffffffff80005826 sp : ffffffff80c03d50
> [    0.000000]  gp : ffffffff80ca6178 tp : ffffffff80c0ad80 t0 : 6200000000000000
> [    0.000000]  t1 : 0000000000000000 t2 : 62203a6b746e6972 s0 : ffffffff80c03d60
> [    0.000000]  s1 : ffffffff80001af6 a0 : 0000000000000000 a1 : 0000000000000000
> [    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
> [    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000080200
> [    0.000000]  s2 : ffffffff808b3e48 s3 : ffffffff808bf698 s4 : ffffffff80cb2818
> [    0.000000]  s5 : 0000000000000001 s6 : ffffffff80c9c345 s7 : ffffffff80895aa0
> [    0.000000]  s8 : 0000000000000001 s9 : 000000000000007f s10: 0000000000000000
> [    0.000000]  s11: 0000000000000000 t3 : ffffffff80824d08 t4 : 0000000000000022
> [    0.000000]  t5 : 000000000000003d t6 : 0000000000000000
> [    0.000000] status: 0000000000000100 badaddr: 0000000000000000 cause: 000000000000000c
> [    0.000000] ---[ end trace 0000000000000000 ]---
> [    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
> [    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---
>
> Fix this issue by moving sbi_init() earlier before jump_label_init()
>
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>

We are seeing a similar crash when booting kernel via EDK2 with RNG enabled.

Shell> fs0:\Image root=/dev/vda2 rootwait console=ttyS0
earlycon=uart8250,mmio,0x10000000 initrd=\initramfs.cp
EFI stub: Booting Linux Kernel...
EFI stub: Using DTB from configuration table
EFI stub: Exiting boot services...
[    0.000000] Linux version 5.19.0-rc3 (oe-user@oe-host)
(riscv64-unknown-linux-gnu-gcc (Ventana-2022.05.16) 12.1.0, GNU ld
(Ventana-2022.05.16) 2.37.90.20220201) #1 SMP Thu Jun 23 05:33:13 UTC
2022
[    0.000000] OF: fdt: Ignoring memory range 0x80000000 - 0x81200000
[    0.000000] earlycon: uart8250 at MMIO 0x0000000010000000 (options '')
[    0.000000] printk: bootconsole [uart8250] enabled
[    0.000000] efi: EFI v2.70 by EDK II
[    0.000000] efi: RNG=0xff94fd98 MEMRESERVE=0xfe658f18
[    0.000000] efi: seeding entropy pool
[    0.000000] Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000000
[    0.000000] Oops [#1]
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.19.0-rc3 #1
[    0.000000] epc : 0x0
[    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
[    0.000000] epc : 0000000000000000 ra : ffffffff800080f8 sp :
ffffffff81203cd0
[    0.000000]  gp : ffffffff812f1d40 tp : ffffffff8120da80 t0 :
0000000000cb8266
[    0.000000]  t1 : 000000006d5e5146 t2 : 0000000058000000 s0 :
ffffffff81203ce0
[    0.000000]  s1 : ffffffff8047586a a0 : 0000000000000000 a1 :
0000000000000000
[    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 :
0000000000000000
[    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 :
0000000000000000
[    0.000000]  s2 : ffffffff80dea320 s3 : ffffffff80deabb0 s4 :
ffffffff81353d48
[    0.000000]  s5 : 0000000000000001 s6 : 00000000fffde848 s7 :
0000000000000004
[    0.000000]  s8 : 0000000081021714 s9 : 000000008101e6f0 s10:
00000000fffde780
[    0.000000]  s11: 0000000000000004 t3 : 000000001467a415 t4 :
0000000000000000
[    0.000000]  t5 : 00000000007627e0 t6 : ffffffffbc865574
[    0.000000] status: 0000000200000100 badaddr: 0000000000000000
cause: 000000000000000c
[    0.000000] ---[ end trace 0000000000000000 ]---
[    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
[    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill
the idle task! ]---

This patch fixes the above crash as well.

Reviewed-by: Anup Patel <anup@brainfault.org>

Thanks,
Anup

> ---
>  arch/riscv/kernel/setup.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index 834eb652a7b9..d150cedeb7e0 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -268,6 +268,7 @@ void __init setup_arch(char **cmdline_p)
>         *cmdline_p = boot_command_line;
>
>         early_ioremap_setup();
> +       sbi_init();
>         jump_label_init();
>         parse_early_param();
>
> @@ -284,7 +285,6 @@ void __init setup_arch(char **cmdline_p)
>         misc_mem_init();
>
>         init_resources();
> -       sbi_init();
>
>  #ifdef CONFIG_KASAN
>         kasan_init();
> --
> 2.34.1
>
Atish Patra June 27, 2022, 6:47 a.m. UTC | #3 
On Sat, Jun 25, 2022 at 9:33 PM Anup Patel <anup@brainfault.org> wrote:
>
> On Sat, May 21, 2022 at 8:13 PM Jisheng Zhang <jszhang@kernel.org> wrote:
> >
> > We call jump_label_init() in setup_arch() is to use static key
> > mechanism earlier, but riscv jump label relies on the sbi functions,
> > If we enable static key before sbi_init(), the code path looks like:
> >   static_branch_enable()
> >     ..
> >       arch_jump_label_transform()
> >         patch_text_nosync()
> >           flush_icache_range()
> >             flush_icache_all()
> >               sbi_remote_fence_i() for CONFIG_RISCV_SBI case
> >                 __sbi_rfence()
> >
> > Since sbi isn't initialized, so NULL deference! Here is a typical
> > panic log:
> >
> > [    0.000000] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
> > [    0.000000] Oops [#1]
> > [    0.000000] Modules linked in:
> > [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.18.0-rc7+ #79
> > [    0.000000] Hardware name: riscv-virtio,qemu (DT)
> > [    0.000000] epc : 0x0
> > [    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
> > [    0.000000] epc : 0000000000000000 ra : ffffffff80005826 sp : ffffffff80c03d50
> > [    0.000000]  gp : ffffffff80ca6178 tp : ffffffff80c0ad80 t0 : 6200000000000000
> > [    0.000000]  t1 : 0000000000000000 t2 : 62203a6b746e6972 s0 : ffffffff80c03d60
> > [    0.000000]  s1 : ffffffff80001af6 a0 : 0000000000000000 a1 : 0000000000000000
> > [    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
> > [    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000080200
> > [    0.000000]  s2 : ffffffff808b3e48 s3 : ffffffff808bf698 s4 : ffffffff80cb2818
> > [    0.000000]  s5 : 0000000000000001 s6 : ffffffff80c9c345 s7 : ffffffff80895aa0
> > [    0.000000]  s8 : 0000000000000001 s9 : 000000000000007f s10: 0000000000000000
> > [    0.000000]  s11: 0000000000000000 t3 : ffffffff80824d08 t4 : 0000000000000022
> > [    0.000000]  t5 : 000000000000003d t6 : 0000000000000000
> > [    0.000000] status: 0000000000000100 badaddr: 0000000000000000 cause: 000000000000000c
> > [    0.000000] ---[ end trace 0000000000000000 ]---
> > [    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
> > [    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---
> >
> > Fix this issue by moving sbi_init() earlier before jump_label_init()
> >
> > Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
>
> We are seeing a similar crash when booting kernel via EDK2 with RNG enabled.
>
> Shell> fs0:\Image root=/dev/vda2 rootwait console=ttyS0
> earlycon=uart8250,mmio,0x10000000 initrd=\initramfs.cp
> EFI stub: Booting Linux Kernel...
> EFI stub: Using DTB from configuration table
> EFI stub: Exiting boot services...
> [    0.000000] Linux version 5.19.0-rc3 (oe-user@oe-host)
> (riscv64-unknown-linux-gnu-gcc (Ventana-2022.05.16) 12.1.0, GNU ld
> (Ventana-2022.05.16) 2.37.90.20220201) #1 SMP Thu Jun 23 05:33:13 UTC
> 2022
> [    0.000000] OF: fdt: Ignoring memory range 0x80000000 - 0x81200000
> [    0.000000] earlycon: uart8250 at MMIO 0x0000000010000000 (options '')
> [    0.000000] printk: bootconsole [uart8250] enabled
> [    0.000000] efi: EFI v2.70 by EDK II
> [    0.000000] efi: RNG=0xff94fd98 MEMRESERVE=0xfe658f18
> [    0.000000] efi: seeding entropy pool
> [    0.000000] Unable to handle kernel NULL pointer dereference at
> virtual address 0000000000000000
> [    0.000000] Oops [#1]
> [    0.000000] Modules linked in:
> [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.19.0-rc3 #1
> [    0.000000] epc : 0x0
> [    0.000000]  ra : sbi_remote_fence_i+0x1e/0x26
> [    0.000000] epc : 0000000000000000 ra : ffffffff800080f8 sp :
> ffffffff81203cd0
> [    0.000000]  gp : ffffffff812f1d40 tp : ffffffff8120da80 t0 :
> 0000000000cb8266
> [    0.000000]  t1 : 000000006d5e5146 t2 : 0000000058000000 s0 :
> ffffffff81203ce0
> [    0.000000]  s1 : ffffffff8047586a a0 : 0000000000000000 a1 :
> 0000000000000000
> [    0.000000]  a2 : 0000000000000000 a3 : 0000000000000000 a4 :
> 0000000000000000
> [    0.000000]  a5 : 0000000000000000 a6 : 0000000000000000 a7 :
> 0000000000000000
> [    0.000000]  s2 : ffffffff80dea320 s3 : ffffffff80deabb0 s4 :
> ffffffff81353d48
> [    0.000000]  s5 : 0000000000000001 s6 : 00000000fffde848 s7 :
> 0000000000000004
> [    0.000000]  s8 : 0000000081021714 s9 : 000000008101e6f0 s10:
> 00000000fffde780
> [    0.000000]  s11: 0000000000000004 t3 : 000000001467a415 t4 :
> 0000000000000000
> [    0.000000]  t5 : 00000000007627e0 t6 : ffffffffbc865574
> [    0.000000] status: 0000000200000100 badaddr: 0000000000000000
> cause: 000000000000000c
> [    0.000000] ---[ end trace 0000000000000000 ]---
> [    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
> [    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill
> the idle task! ]---
>
> This patch fixes the above crash as well.
>

Thanks for the confirmation.

> Reviewed-by: Anup Patel <anup@brainfault.org>
>
> Thanks,
> Anup
>
> > ---
> >  arch/riscv/kernel/setup.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> > index 834eb652a7b9..d150cedeb7e0 100644
> > --- a/arch/riscv/kernel/setup.c
> > +++ b/arch/riscv/kernel/setup.c
> > @@ -268,6 +268,7 @@ void __init setup_arch(char **cmdline_p)
> >         *cmdline_p = boot_command_line;
> >
> >         early_ioremap_setup();
> > +       sbi_init();
> >         jump_label_init();
> >         parse_early_param();
> >
> > @@ -284,7 +285,6 @@ void __init setup_arch(char **cmdline_p)
> >         misc_mem_init();
> >
> >         init_resources();
> > -       sbi_init();
> >
> >  #ifdef CONFIG_KASAN
> >         kasan_init();
> > --
> > 2.34.1
> >
>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv


Reviewed-by: Atish Patra <atishp@rivosinc.com>
diff mbox series

Patch

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 834eb652a7b9..d150cedeb7e0 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -268,6 +268,7 @@  void __init setup_arch(char **cmdline_p)
 	*cmdline_p = boot_command_line;
 
 	early_ioremap_setup();
+	sbi_init();
 	jump_label_init();
 	parse_early_param();
 
@@ -284,7 +285,6 @@  void __init setup_arch(char **cmdline_p)
 	misc_mem_init();
 
 	init_resources();
-	sbi_init();
 
 #ifdef CONFIG_KASAN
 	kasan_init();