2/6] eal: oops handling API implementation

Message ID 20210730084938.2426128-3-jerinj@marvell.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series 2/6] eal: oops handling API implementation |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation warning apply issues

Commit Message

Jerin Jacob Kollanukkaran July 30, 2021, 8:49 a.m. UTC
  From: Jerin Jacob <jerinj@marvell.com>

Implement the base oops handling APIs.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
---
 lib/eal/unix/eal_oops.c | 175 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 168 insertions(+), 7 deletions(-)
  

Comments

David Christensen Aug. 2, 2021, 10:46 p.m. UTC | #1
On 7/30/21 1:49 AM, jerinj@marvell.com wrote:
> From: Jerin Jacob <jerinj@marvell.com>
> 
> Implement the base oops handling APIs.
> 
> Signed-off-by: Jerin Jacob <jerinj@marvell.com>

Building on POWER generates the following error:

ninja: Entering directory `build'
[1/244] Compiling C object 'lib/76b5a35@@rte_eal@sta/eal_unix_eal_oops.c.o'.
../lib/eal/unix/eal_oops.c: In function ‘back_trace_dump’:
../lib/eal/unix/eal_oops.c:33:2: warning: implicit declaration of 
function ‘rte_dump_stack’; did you mean ‘rte_bus_scan’? 
[-Wimplicit-function-declaration]
   rte_dump_stack();
   ^~~~~~~~~~~~~~
   rte_bus_scan
../lib/eal/unix/eal_oops.c:33:2: warning: nested extern declaration of 
‘rte_dump_stack’ [-Wnested-externs]
[19/19] Linking target app/test/dpdk-test.

You can fix the issue by adding <rte_debug.h> to eal_oops.c.  Must be a 
hidden include dependency in the x86/ARM code.

Dave
  

Patch

diff --git a/lib/eal/unix/eal_oops.c b/lib/eal/unix/eal_oops.c
index 53b580f733..1120c8ad8c 100644
--- a/lib/eal/unix/eal_oops.c
+++ b/lib/eal/unix/eal_oops.c
@@ -2,35 +2,196 @@ 
  * Copyright(C) 2021 Marvell.
  */
 
+#include <inttypes.h>
+#include <signal.h>
+#include <ucontext.h>
+#include <unistd.h>
 
+#include <rte_byteorder.h>
+#include <rte_log.h>
 #include <rte_oops.h>
 
 #include "eal_private.h"
 
-void
-rte_oops_decode(int sig, siginfo_t *info, ucontext_t *uc)
+#define oops_print(...) rte_log(RTE_LOG_ERR, RTE_LOGTYPE_EAL, __VA_ARGS__)
+
+static int oops_signals[] = {SIGSEGV, SIGBUS, SIGILL, SIGABRT, SIGFPE, SIGSYS};
+
+struct oops_signal {
+	int sig;
+	bool enabled;
+	struct sigaction sa;
+};
+
+static struct oops_signal signals_db[RTE_DIM(oops_signals)];
+
+static void
+back_trace_dump(ucontext_t *context)
+{
+	RTE_SET_USED(context);
+
+	rte_dump_stack();
+}
+static void
+siginfo_dump(int sig, siginfo_t *info)
+{
+	oops_print("PID:           %" PRIdMAX "\n", (intmax_t)getpid());
+
+	if (info == NULL)
+		return;
+	if (sig != info->si_signo)
+		oops_print("Invalid signal info\n");
+
+	oops_print("Signal number: %d\n", info->si_signo);
+	oops_print("Fault address: %p\n", info->si_addr);
+}
+
+static void
+mem32_dump(void *ptr)
+{
+	uint32_t *p = ptr;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		oops_print("%p: 0x%x\n", p + i, rte_be_to_cpu_32(p[i]));
+}
+
+static void
+stack_dump_header(void)
+{
+	oops_print("Stack dump:\n");
+	oops_print("----------\n");
+}
+
+static void
+code_dump_header(void)
+{
+	oops_print("Code dump:\n");
+	oops_print("----------\n");
+}
+
+static void
+stack_code_dump(void *stack, void *code)
+{
+	if (stack == NULL || code == NULL)
+		return;
+
+	oops_print("\n");
+	stack_dump_header();
+	mem32_dump(stack);
+	oops_print("\n");
+
+	code_dump_header();
+	mem32_dump(code);
+	oops_print("\n");
+}
+static void
+archinfo_dump(ucontext_t *uc)
 {
-	RTE_SET_USED(sig);
-	RTE_SET_USED(info);
 	RTE_SET_USED(uc);
 
+	stack_code_dump(NULL, NULL);
+}
+
+static void
+default_signal_handler_invoke(int sig)
+{
+	unsigned int idx;
+
+	for (idx = 0; idx < RTE_DIM(oops_signals); idx++) {
+		/* Skip disabled signals */
+		if (signals_db[idx].sig != sig)
+			continue;
+		if (!signals_db[idx].enabled)
+			continue;
+		/* Replace with stored handler */
+		sigaction(sig, &signals_db[idx].sa, NULL);
+		kill(getpid(), sig);
+	}
+}
+
+void
+rte_oops_decode(int sig, siginfo_t *info, ucontext_t *uc)
+{
+	oops_print("Signal info:\n");
+	oops_print("------------\n");
+	siginfo_dump(sig, info);
+	oops_print("\n");
+
+	oops_print("Backtrace:\n");
+	oops_print("----------\n");
+	back_trace_dump(uc);
+	oops_print("\n");
+
+	oops_print("Arch info:\n");
+	oops_print("----------\n");
+	if (uc)
+		archinfo_dump(uc);
+}
+
+static void
+eal_oops_handler(int sig, siginfo_t *info, void *ctx)
+{
+	ucontext_t *uc = ctx;
+
+	rte_oops_decode(sig, info, uc);
+	default_signal_handler_invoke(sig);
 }
 
 int
 rte_oops_signals_enabled(int *signals)
 {
-	RTE_SET_USED(signals);
+	int count = 0, sig[RTE_OOPS_SIGNALS_MAX];
+	unsigned int idx = 0;
 
-	return 0;
+	for (idx = 0; idx < RTE_DIM(oops_signals); idx++) {
+		if (signals_db[idx].enabled) {
+			sig[count] = signals_db[idx].sig;
+			count++;
+		}
+	}
+	if (signals)
+		memcpy(signals, sig, sizeof(*signals) * count);
+
+	return count;
 }
 
 int
 eal_oops_init(void)
 {
-	return 0;
+	unsigned int idx, rc = 0;
+	struct sigaction sa;
+
+	RTE_BUILD_BUG_ON(RTE_DIM(oops_signals) > RTE_OOPS_SIGNALS_MAX);
+
+	sigemptyset(&sa.sa_mask);
+	sa.sa_sigaction = &eal_oops_handler;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO | SA_ONSTACK;
+
+	for (idx = 0; idx < RTE_DIM(oops_signals); idx++) {
+		signals_db[idx].sig = oops_signals[idx];
+		/* Get exiting sigaction */
+		rc = sigaction(signals_db[idx].sig, NULL, &signals_db[idx].sa);
+		if (rc)
+			continue;
+		/* Replace with oops handler */
+		rc = sigaction(signals_db[idx].sig, &sa, NULL);
+		if (rc)
+			continue;
+		signals_db[idx].enabled = true;
+	}
+	return rc;
 }
 
 void
 eal_oops_fini(void)
 {
+	unsigned int idx;
+
+	for (idx = 0; idx < RTE_DIM(oops_signals); idx++) {
+		if (!signals_db[idx].enabled)
+			continue;
+		/* Replace with stored handler */
+		sigaction(signals_db[idx].sig, &signals_db[idx].sa, NULL);
+	}
 }