summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorDouglas Anderson <dianders@chromium.org>2018-12-04 19:38:26 -0800
committerDaniel Thompson <daniel.thompson@linaro.org>2018-12-30 08:28:02 +0000
commit3cd99ac3559855f69afbc1d5080e17eaa12394ff (patch)
tree39731c43ed540124099d310bfd2bb2a4490b3ded /kernel
parent9ef7fa507d6b53a96de4da3298c5f01bde603c0a (diff)
downloadlinux-3cd99ac3559855f69afbc1d5080e17eaa12394ff.tar.bz2
kgdb: Fix kgdb_roundup_cpus() for arches who used smp_call_function()
When I had lockdep turned on and dropped into kgdb I got a nice splat on my system. Specifically it hit: DEBUG_LOCKS_WARN_ON(current->hardirq_context) Specifically it looked like this: sysrq: SysRq : DEBUG ------------[ cut here ]------------ DEBUG_LOCKS_WARN_ON(current->hardirq_context) WARNING: CPU: 0 PID: 0 at .../kernel/locking/lockdep.c:2875 lockdep_hardirqs_on+0xf0/0x160 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.0 #27 pstate: 604003c9 (nZCv DAIF +PAN -UAO) pc : lockdep_hardirqs_on+0xf0/0x160 ... Call trace: lockdep_hardirqs_on+0xf0/0x160 trace_hardirqs_on+0x188/0x1ac kgdb_roundup_cpus+0x14/0x3c kgdb_cpu_enter+0x53c/0x5cc kgdb_handle_exception+0x180/0x1d4 kgdb_compiled_brk_fn+0x30/0x3c brk_handler+0x134/0x178 do_debug_exception+0xfc/0x178 el1_dbg+0x18/0x78 kgdb_breakpoint+0x34/0x58 sysrq_handle_dbg+0x54/0x5c __handle_sysrq+0x114/0x21c handle_sysrq+0x30/0x3c qcom_geni_serial_isr+0x2dc/0x30c ... ... irq event stamp: ...45 hardirqs last enabled at (...44): [...] __do_softirq+0xd8/0x4e4 hardirqs last disabled at (...45): [...] el1_irq+0x74/0x130 softirqs last enabled at (...42): [...] _local_bh_enable+0x2c/0x34 softirqs last disabled at (...43): [...] irq_exit+0xa8/0x100 ---[ end trace adf21f830c46e638 ]--- Looking closely at it, it seems like a really bad idea to be calling local_irq_enable() in kgdb_roundup_cpus(). If nothing else that seems like it could violate spinlock semantics and cause a deadlock. Instead, let's use a private csd alongside smp_call_function_single_async() to round up the other CPUs. Using smp_call_function_single_async() doesn't require interrupts to be enabled so we can remove the offending bit of code. In order to avoid duplicating this across all the architectures that use the default kgdb_roundup_cpus(), we'll add a "weak" implementation to debug_core.c. Looking at all the people who previously had copies of this code, there were a few variants. I've attempted to keep the variants working like they used to. Specifically: * For arch/arc we passed NULL to kgdb_nmicallback() instead of get_irq_regs(). * For arch/mips there was a bit of extra code around kgdb_nmicallback() NOTE: In this patch we will still get into trouble if we try to round up a CPU that failed to round up before. We'll try to round it up again and potentially hang when we try to grab the csd lock. That's not new behavior but we'll still try to do better in a future patch. Suggested-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Douglas Anderson <dianders@chromium.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Burton <paul.burton@mips.com> Cc: James Hogan <jhogan@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Rich Felker <dalias@libc.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/debug/debug_core.c41
1 files changed, 41 insertions, 0 deletions
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index f3cadda45f07..10db2833a423 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -55,6 +55,7 @@
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/rcupdate.h>
+#include <linux/irq.h>
#include <asm/cacheflush.h>
#include <asm/byteorder.h>
@@ -220,6 +221,46 @@ int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
return 0;
}
+#ifdef CONFIG_SMP
+
+/*
+ * Default (weak) implementation for kgdb_roundup_cpus
+ */
+
+static DEFINE_PER_CPU(call_single_data_t, kgdb_roundup_csd);
+
+void __weak kgdb_call_nmi_hook(void *ignored)
+{
+ /*
+ * NOTE: get_irq_regs() is supposed to get the registers from
+ * before the IPI interrupt happened and so is supposed to
+ * show where the processor was. In some situations it's
+ * possible we might be called without an IPI, so it might be
+ * safer to figure out how to make kgdb_breakpoint() work
+ * properly here.
+ */
+ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void __weak kgdb_roundup_cpus(void)
+{
+ call_single_data_t *csd;
+ int this_cpu = raw_smp_processor_id();
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ /* No need to roundup ourselves */
+ if (cpu == this_cpu)
+ continue;
+
+ csd = &per_cpu(kgdb_roundup_csd, cpu);
+ csd->func = kgdb_call_nmi_hook;
+ smp_call_function_single_async(cpu, csd);
+ }
+}
+
+#endif
+
/*
* Some architectures need cache flushes when we set/clear a
* breakpoint: