lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 12 Aug 2020 16:59:48 -0700
From:   Doug Anderson <dianders@...omium.org>
To:     Sumit Garg <sumit.garg@...aro.org>
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Daniel Thompson <daniel.thompson@...aro.org>,
        linux-serial@...r.kernel.org, kgdb-bugreport@...ts.sourceforge.net,
        Jiri Slaby <jslaby@...e.com>,
        Russell King - ARM Linux <linux@...linux.org.uk>,
        Jason Wessel <jason.wessel@...driver.com>,
        LKML <linux-kernel@...r.kernel.org>,
        Linux ARM <linux-arm-kernel@...ts.infradead.org>
Subject: Re: [RFC 1/5] tty/sysrq: Make sysrq handler NMI aware

Hi,

On Tue, Jul 21, 2020 at 5:10 AM Sumit Garg <sumit.garg@...aro.org> wrote:
>
> In a future patch we will add support to the serial core to make it
> possible to trigger a magic sysrq from an NMI context. Prepare for this
> by marking some sysrq actions as NMI safe. Safe actions will be allowed
> to run from NMI context whilst that cannot run from an NMI will be queued
> as irq_work for later processing.
>
> A particular sysrq handler is only marked as NMI safe in case the handler
> isn't contending for any synchronization primitives as in NMI context
> they are expected to cause deadlocks. Note that the debug sysrq do not
> contend for any synchronization primitives. It does call kgdb_breakpoint()
> to provoke a trap but that trap handler should be NMI safe on
> architectures that implement an NMI.
>
> Signed-off-by: Sumit Garg <sumit.garg@...aro.org>
> ---
>  drivers/tty/sysrq.c       | 33 ++++++++++++++++++++++++++++++++-
>  include/linux/sysrq.h     |  1 +
>  kernel/debug/debug_core.c |  1 +
>  3 files changed, 34 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
> index 7c95afa9..8017e33 100644
> --- a/drivers/tty/sysrq.c
> +++ b/drivers/tty/sysrq.c
> @@ -50,6 +50,8 @@
>  #include <linux/syscalls.h>
>  #include <linux/of.h>
>  #include <linux/rcupdate.h>
> +#include <linux/irq_work.h>
> +#include <linux/kfifo.h>
>
>  #include <asm/ptrace.h>
>  #include <asm/irq_regs.h>
> @@ -111,6 +113,7 @@ static const struct sysrq_key_op sysrq_loglevel_op = {
>         .help_msg       = "loglevel(0-9)",
>         .action_msg     = "Changing Loglevel",
>         .enable_mask    = SYSRQ_ENABLE_LOG,
> +       .nmi_safe       = true,
>  };
>
>  #ifdef CONFIG_VT
> @@ -157,6 +160,7 @@ static const struct sysrq_key_op sysrq_crash_op = {
>         .help_msg       = "crash(c)",
>         .action_msg     = "Trigger a crash",
>         .enable_mask    = SYSRQ_ENABLE_DUMP,
> +       .nmi_safe       = true,
>  };
>
>  static void sysrq_handle_reboot(int key)
> @@ -170,6 +174,7 @@ static const struct sysrq_key_op sysrq_reboot_op = {
>         .help_msg       = "reboot(b)",
>         .action_msg     = "Resetting",
>         .enable_mask    = SYSRQ_ENABLE_BOOT,
> +       .nmi_safe       = true,
>  };
>
>  const struct sysrq_key_op *__sysrq_reboot_op = &sysrq_reboot_op;
> @@ -217,6 +222,7 @@ static const struct sysrq_key_op sysrq_showlocks_op = {
>         .handler        = sysrq_handle_showlocks,
>         .help_msg       = "show-all-locks(d)",
>         .action_msg     = "Show Locks Held",
> +       .nmi_safe       = true,
>  };
>  #else
>  #define sysrq_showlocks_op (*(const struct sysrq_key_op *)NULL)
> @@ -289,6 +295,7 @@ static const struct sysrq_key_op sysrq_showregs_op = {
>         .help_msg       = "show-registers(p)",
>         .action_msg     = "Show Regs",
>         .enable_mask    = SYSRQ_ENABLE_DUMP,
> +       .nmi_safe       = true,
>  };
>
>  static void sysrq_handle_showstate(int key)
> @@ -326,6 +333,7 @@ static const struct sysrq_key_op sysrq_ftrace_dump_op = {
>         .help_msg       = "dump-ftrace-buffer(z)",
>         .action_msg     = "Dump ftrace buffer",
>         .enable_mask    = SYSRQ_ENABLE_DUMP,
> +       .nmi_safe       = true,
>  };
>  #else
>  #define sysrq_ftrace_dump_op (*(const struct sysrq_key_op *)NULL)
> @@ -538,6 +546,23 @@ static void __sysrq_put_key_op(int key, const struct sysrq_key_op *op_p)
>                  sysrq_key_table[i] = op_p;
>  }
>
> +#define SYSRQ_NMI_FIFO_SIZE    64
> +static DEFINE_KFIFO(sysrq_nmi_fifo, int, SYSRQ_NMI_FIFO_SIZE);

A 64-entry FIFO seems excessive. Quite honestly even a FIFO seems a
bit excessive and it feels like if two sysrqs were received in super
quick succession that it would be OK to just process the first one.  I
guess if it simplifies the processing to have a FIFO then it shouldn't
hurt, but no need for 64 entries.


> +static void sysrq_do_nmi_work(struct irq_work *work)
> +{
> +       const struct sysrq_key_op *op_p;
> +       int key;
> +
> +       while (kfifo_out(&sysrq_nmi_fifo, &key, 1)) {
> +               op_p = __sysrq_get_key_op(key);
> +               if (op_p)
> +                       op_p->handler(key);
> +       }

Do you need to manage "suppress_printk" in this function?  Do you need
to call rcu_sysrq_start() and rcu_read_lock()?

If so, how do you prevent racing between the mucking we're doing with
these things and the mucking that the NMI does with them?


> +}
> +
> +static DEFINE_IRQ_WORK(sysrq_nmi_work, sysrq_do_nmi_work);
> +
>  void __handle_sysrq(int key, bool check_mask)
>  {
>         const struct sysrq_key_op *op_p;
> @@ -568,7 +593,13 @@ void __handle_sysrq(int key, bool check_mask)
>                 if (!check_mask || sysrq_on_mask(op_p->enable_mask)) {
>                         pr_info("%s\n", op_p->action_msg);
>                         console_loglevel = orig_log_level;
> -                       op_p->handler(key);
> +
> +                       if (in_nmi() && !op_p->nmi_safe) {
> +                               kfifo_in(&sysrq_nmi_fifo, &key, 1);

Rather than kfifo_in() and kfifo_out(), I think you can use
kfifo_put() and kfifo_get().  As I understand it those just get/put
one element which is what you want.


> +                               irq_work_queue(&sysrq_nmi_work);

Wishful thinking, but (as far as I can tell) irq_work_queue() only
queues work on the CPU running the NMI.  I don't have lots of NMI
experience, but any chance there is a variant that will queue work on
any CPU?  Then sysrq handlers that aren't NMI aware will be more
likely to work.




> +                       } else {
> +                               op_p->handler(key);
> +                       }
>                 } else {
>                         pr_info("This sysrq operation is disabled.\n");
>                         console_loglevel = orig_log_level;
> diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
> index 3a582ec..630b5b9 100644
> --- a/include/linux/sysrq.h
> +++ b/include/linux/sysrq.h
> @@ -34,6 +34,7 @@ struct sysrq_key_op {
>         const char * const help_msg;
>         const char * const action_msg;
>         const int enable_mask;
> +       const bool nmi_safe;
>  };
>
>  #ifdef CONFIG_MAGIC_SYSRQ
> diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
> index 9e59347..2b51173 100644
> --- a/kernel/debug/debug_core.c
> +++ b/kernel/debug/debug_core.c
> @@ -943,6 +943,7 @@ static const struct sysrq_key_op sysrq_dbg_op = {
>         .handler        = sysrq_handle_dbg,
>         .help_msg       = "debug(g)",
>         .action_msg     = "DEBUG",
> +       .nmi_safe       = true,
>  };
>  #endif
>
> --
> 2.7.4
>

Powered by blists - more mailing lists