qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PULL 15/24] linux-user/arm: Deliver SIGTRAP for UDF patterns used as breakpoints
Date: Mon, 23 Nov 2020 11:43:06 +0000	[thread overview]
Message-ID: <20201123114315.13372-16-peter.maydell@linaro.org> (raw)
In-Reply-To: <20201123114315.13372-1-peter.maydell@linaro.org>

The Linux kernel doesn't use the official bkpt insn for breakpoints;
instead it uses three instructions in the guaranteed-to-UNDEF space,
and generates SIGTRAP for these rather than the SIGILL that most
UNDEF insns generate:

https://elixir.bootlin.com/linux/v5.9.8/source/arch/arm/kernel/ptrace.c#L197

Make QEMU treat these insns specially too.  The main benefit of this
is that if you're running a debugger on a guest program that runs
into a GCC __builtin_trap() or LLVM "trap because execution should
never reach here" then you'll get the expected signal rather than a
SIGILL.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20201117155634.6924-1-peter.maydell@linaro.org
---
 linux-user/arm/cpu_loop.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c
index 13629ee1f6a..3d272b56ef0 100644
--- a/linux-user/arm/cpu_loop.c
+++ b/linux-user/arm/cpu_loop.c
@@ -205,6 +205,24 @@ do_kernel_trap(CPUARMState *env)
     return 0;
 }
 
+static bool insn_is_linux_bkpt(uint32_t opcode, bool is_thumb)
+{
+    /*
+     * Return true if this insn is one of the three magic UDF insns
+     * which the kernel treats as breakpoint insns.
+     */
+    if (!is_thumb) {
+        return (opcode & 0x0fffffff) == 0x07f001f0;
+    } else {
+        /*
+         * Note that we get the two halves of the 32-bit T32 insn
+         * in the opposite order to the value the kernel uses in
+         * its undef_hook struct.
+         */
+        return ((opcode & 0xffff) == 0xde01) || (opcode == 0xa000f7f0);
+    }
+}
+
 void cpu_loop(CPUARMState *env)
 {
     CPUState *cs = env_cpu(env);
@@ -234,6 +252,16 @@ void cpu_loop(CPUARMState *env)
                 /* FIXME - what to do if get_user() fails? */
                 get_user_code_u32(opcode, env->regs[15], env);
 
+                /*
+                 * The Linux kernel treats some UDF patterns specially
+                 * to use as breakpoints (instead of the architectural
+                 * bkpt insn). These should trigger a SIGTRAP rather
+                 * than SIGILL.
+                 */
+                if (insn_is_linux_bkpt(opcode, env->thumb)) {
+                    goto excp_debug;
+                }
+
                 rc = EmulateAll(opcode, &ts->fpa, env);
                 if (rc == 0) { /* illegal instruction */
                     info.si_signo = TARGET_SIGILL;
-- 
2.20.1



  parent reply	other threads:[~2020-11-23 11:51 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-23 11:42 [PULL 00/24] target-arm queue Peter Maydell
2020-11-23 11:42 ` [PULL 01/24] target/arm: fix stage 2 page-walks in 32-bit emulation Peter Maydell
2020-11-23 11:42 ` [PULL 02/24] hw/arm: Fix bad print format specifiers Peter Maydell
2020-11-23 11:42 ` [PULL 03/24] hw/intc: fix heap-buffer-overflow in rxicu_realize() Peter Maydell
2020-11-23 11:42 ` [PULL 04/24] MAINTAINERS: Cover system/arm/cpu-features.rst with ARM TCG CPUs Peter Maydell
2020-11-23 11:42 ` [PULL 05/24] MAINTAINERS: Cover system/arm/aspeed.rst with ASPEED BMC machines Peter Maydell
2020-11-23 11:42 ` [PULL 06/24] MAINTAINERS: Cover system/arm/nuvoton.rst with Nuvoton NPCM7xx Peter Maydell
2020-11-23 11:42 ` [PULL 07/24] MAINTAINERS: Fix system/arm/orangepi.rst path Peter Maydell
2020-11-23 11:42 ` [PULL 08/24] MAINTAINERS: Cover system/arm/sbsa.rst with SBSA-REF machine Peter Maydell
2020-11-23 11:43 ` [PULL 09/24] MAINTAINERS: Cover system/arm/sx1.rst with OMAP machines Peter Maydell
2020-11-23 11:43 ` [PULL 10/24] docs/system: Deprecate raspi2/raspi3 machine aliases Peter Maydell
2020-11-23 11:43 ` [PULL 11/24] docs/system/arm: Document the various raspi boards Peter Maydell
2020-11-23 11:43 ` [PULL 12/24] docs/system/arm: Document OpenPOWER Witherspoon BMC model Front LEDs Peter Maydell
2020-11-23 11:43 ` [PULL 13/24] docs/system/arm: Document the Sharp Zaurus SL-6000 Peter Maydell
2020-11-23 11:43 ` [PULL 14/24] target/arm: Make SYS_HEAPINFO work with RAM that doesn't start at 0 Peter Maydell
2020-11-23 11:43 ` Peter Maydell [this message]
2020-11-23 11:43 ` [PULL 16/24] docs: Move virtio-net-failover.rst into the system manual Peter Maydell
2020-11-23 11:43 ` [PULL 17/24] docs: Move cpu-hotplug.rst " Peter Maydell
2020-11-23 11:43 ` [PULL 18/24] docs: Move virtio-pmem.rst " Peter Maydell
2020-11-23 11:43 ` [PULL 19/24] docs/system/virtio-pmem.rst: Fix minor style issues Peter Maydell
2020-11-23 11:43 ` [PULL 20/24] docs: Split out 'pc' machine model docs into their own file Peter Maydell
2020-11-23 11:43 ` [PULL 21/24] docs: Move microvm.rst into the system manual Peter Maydell
2020-11-23 11:43 ` [PULL 22/24] docs: Move pr-manager.rst " Peter Maydell
2020-11-23 11:43 ` [PULL 23/24] docs: Split qemu-pr-helper documentation into tools manual Peter Maydell
2020-11-23 11:43 ` [PULL 24/24] docs/system/pr-manager.rst: Fix minor docs nits Peter Maydell
2020-11-23 17:03 ` [PULL 00/24] target-arm queue Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201123114315.13372-16-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).