mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 17:50:54 +07:00
87b0959285
If we're using the default implementation of kgdb_roundup_cpus() that uses smp_call_function_single_async() we can end up hanging kgdb_roundup_cpus() if we try to round up a CPU that failed to round up before. Specifically smp_call_function_single_async() will try to wait on the csd lock for the CPU that we're trying to round up. If the previous round up never finished then that lock could still be held and we'll just sit there hanging. There's not a lot of use trying to round up a CPU that failed to round up before. Let's keep a flag that indicates whether the CPU started but didn't finish to round up before. If we see that flag set then we'll skip the next round up. In general we have a few goals here: - We never want to end up calling smp_call_function_single_async() when the csd is still locked. This is accomplished because flush_smp_call_function_queue() unlocks the csd _before_ invoking the callback. That means that when kgdb_nmicallback() runs we know for sure the the csd is no longer locked. Thus when we set "rounding_up = false" we know for sure that the csd is unlocked. - If there are no timeouts rounding up we should never skip a round up. NOTE #1: In general trying to continue running after failing to round up CPUs doesn't appear to be supported in the debugger. When I simulate this I find that kdb reports "Catastrophic error detected" when I try to continue. I can overrule and continue anyway, but it should be noted that we may be entering the land of dragons here. Possibly the "Catastrophic error detected" was added _because_ of the future failure to round up, but even so this is an area of the code that hasn't been strongly tested. NOTE #2: I did a bit of testing before and after this change. I introduced a 10 second hang in the kernel while holding a spinlock that I could invoke on a certain CPU with 'taskset -c 3 cat /sys/...". Before this change if I did: - Invoke hang - Enter debugger - g (which warns about Catastrophic error, g again to go anyway) - g - Enter debugger ...I'd hang the rest of the 10 seconds without getting a debugger prompt. After this change I end up in the debugger the 2nd time after only 1 second with the standard warning about 'Timed out waiting for secondary CPUs.' I'll also note that once the CPU finished waiting I could actually debug it (aka "btc" worked) I won't promise that everything works perfectly if the errant CPU comes back at just the wrong time (like as we're entering or exiting the debugger) but it certainly seems like an improvement. NOTE #3: setting 'kgdb_info[cpu].rounding_up = false' is in kgdb_nmicallback() instead of kgdb_call_nmi_hook() because some implementations override kgdb_call_nmi_hook(). It shouldn't hurt to have it in kgdb_nmicallback() in any case. NOTE #4: this logic is really only needed because there is no API call like "smp_try_call_function_single_async()" or "smp_csd_is_locked()". If such an API existed then we'd use it instead, but it seemed a bit much to add an API like this just for kgdb. Signed-off-by: Douglas Anderson <dianders@chromium.org> Acked-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
87 lines
2.5 KiB
C
87 lines
2.5 KiB
C
/*
|
|
* Created by: Jason Wessel <jason.wessel@windriver.com>
|
|
*
|
|
* Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved.
|
|
*
|
|
* This file is licensed under the terms of the GNU General Public
|
|
* License version 2. This program is licensed "as is" without any
|
|
* warranty of any kind, whether express or implied.
|
|
*/
|
|
|
|
#ifndef _DEBUG_CORE_H_
|
|
#define _DEBUG_CORE_H_
|
|
/*
|
|
* These are the private implementation headers between the kernel
|
|
* debugger core and the debugger front end code.
|
|
*/
|
|
|
|
/* kernel debug core data structures */
|
|
struct kgdb_state {
|
|
int ex_vector;
|
|
int signo;
|
|
int err_code;
|
|
int cpu;
|
|
int pass_exception;
|
|
unsigned long thr_query;
|
|
unsigned long threadid;
|
|
long kgdb_usethreadid;
|
|
struct pt_regs *linux_regs;
|
|
atomic_t *send_ready;
|
|
};
|
|
|
|
/* Exception state values */
|
|
#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
|
|
#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
|
|
#define DCPU_IS_SLAVE 0x4 /* Slave cpu enter exception */
|
|
#define DCPU_SSTEP 0x8 /* CPU is single stepping */
|
|
|
|
struct debuggerinfo_struct {
|
|
void *debuggerinfo;
|
|
struct task_struct *task;
|
|
int exception_state;
|
|
int ret_state;
|
|
int irq_depth;
|
|
int enter_kgdb;
|
|
bool rounding_up;
|
|
};
|
|
|
|
extern struct debuggerinfo_struct kgdb_info[];
|
|
|
|
/* kernel debug core break point routines */
|
|
extern int dbg_remove_all_break(void);
|
|
extern int dbg_set_sw_break(unsigned long addr);
|
|
extern int dbg_remove_sw_break(unsigned long addr);
|
|
extern int dbg_activate_sw_breakpoints(void);
|
|
extern int dbg_deactivate_sw_breakpoints(void);
|
|
|
|
/* polled character access to i/o module */
|
|
extern int dbg_io_get_char(void);
|
|
|
|
/* stub return value for switching between the gdbstub and kdb */
|
|
#define DBG_PASS_EVENT -12345
|
|
/* Switch from one cpu to another */
|
|
#define DBG_SWITCH_CPU_EVENT -123456
|
|
extern int dbg_switch_cpu;
|
|
|
|
/* gdbstub interface functions */
|
|
extern int gdb_serial_stub(struct kgdb_state *ks);
|
|
extern void gdbstub_msg_write(const char *s, int len);
|
|
|
|
/* gdbstub functions used for kdb <-> gdbstub transition */
|
|
extern int gdbstub_state(struct kgdb_state *ks, char *cmd);
|
|
extern int dbg_kdb_mode;
|
|
|
|
#ifdef CONFIG_KGDB_KDB
|
|
extern int kdb_stub(struct kgdb_state *ks);
|
|
extern int kdb_parse(const char *cmdstr);
|
|
extern int kdb_common_init_state(struct kgdb_state *ks);
|
|
extern int kdb_common_deinit_state(void);
|
|
#else /* ! CONFIG_KGDB_KDB */
|
|
static inline int kdb_stub(struct kgdb_state *ks)
|
|
{
|
|
return DBG_PASS_EVENT;
|
|
}
|
|
#endif /* CONFIG_KGDB_KDB */
|
|
|
|
#endif /* _DEBUG_CORE_H_ */
|