linux_dsm_epyc7002/include/linux/kgdb.h

351 lines
12 KiB
C
Raw Normal View History

/*
* This provides the callbacks and functions that KGDB needs to share between
* the core, I/O and arch-specific portions.
*
* Author: Amit Kale <amitkale@linsyssoft.com> and
* Tom Rini <trini@kernel.crashing.org>
*
* 2001-2004 (c) Amit S. Kale and 2003-2005 (c) MontaVista Software, Inc.
* 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 _KGDB_H_
#define _KGDB_H_
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/atomic.h>
#ifdef CONFIG_HAVE_ARCH_KGDB
#include <asm/kgdb.h>
#endif
#ifdef CONFIG_KGDB
struct pt_regs;
/**
* kgdb_skipexception - (optional) exit kgdb_handle_exception early
* @exception: Exception vector number
* @regs: Current &struct pt_regs.
*
* On some architectures it is required to skip a breakpoint
* exception when it occurs after a breakpoint has been removed.
* This can be implemented in the architecture specific portion of kgdb.
*/
extern int kgdb_skipexception(int exception, struct pt_regs *regs);
struct tasklet_struct;
struct task_struct;
struct uart_port;
/**
* kgdb_breakpoint - compiled in breakpoint
*
* This will be implemented as a static inline per architecture. This
* function is called by the kgdb core to execute an architecture
* specific trap to cause kgdb to enter the exception processing.
*
*/
void kgdb_breakpoint(void);
extern int kgdb_connected;
extern int kgdb_io_module_registered;
extern atomic_t kgdb_setting_breakpoint;
extern atomic_t kgdb_cpu_doing_single_step;
extern struct task_struct *kgdb_usethread;
extern struct task_struct *kgdb_contthread;
enum kgdb_bptype {
BP_BREAKPOINT = 0,
BP_HARDWARE_BREAKPOINT,
BP_WRITE_WATCHPOINT,
BP_READ_WATCHPOINT,
BP_ACCESS_WATCHPOINT,
BP_POKE_BREAKPOINT,
};
enum kgdb_bpstate {
BP_UNDEFINED = 0,
BP_REMOVED,
BP_SET,
BP_ACTIVE
};
struct kgdb_bkpt {
unsigned long bpt_addr;
unsigned char saved_instr[BREAK_INSTR_SIZE];
enum kgdb_bptype type;
enum kgdb_bpstate state;
};
struct dbg_reg_def_t {
char *name;
int size;
int offset;
};
#ifndef DBG_MAX_REG_NUM
#define DBG_MAX_REG_NUM 0
#else
extern struct dbg_reg_def_t dbg_reg_def[];
extern char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs);
extern int dbg_set_reg(int regno, void *mem, struct pt_regs *regs);
#endif
#ifndef KGDB_MAX_BREAKPOINTS
# define KGDB_MAX_BREAKPOINTS 1000
#endif
#define KGDB_HW_BREAKPOINT 1
/*
* Functions each KGDB-supporting architecture must provide:
*/
/**
* kgdb_arch_init - Perform any architecture specific initalization.
*
* This function will handle the initalization of any architecture
* specific callbacks.
*/
extern int kgdb_arch_init(void);
/**
* kgdb_arch_exit - Perform any architecture specific uninitalization.
*
* This function will handle the uninitalization of any architecture
* specific callbacks, for dynamic registration and unregistration.
*/
extern void kgdb_arch_exit(void);
/**
* pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs
* @gdb_regs: A pointer to hold the registers in the order GDB wants.
* @regs: The &struct pt_regs of the current process.
*
* Convert the pt_regs in @regs into the format for registers that
* GDB expects, stored in @gdb_regs.
*/
extern void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs);
/**
* sleeping_thread_to_gdb_regs - Convert ptrace regs to GDB regs
* @gdb_regs: A pointer to hold the registers in the order GDB wants.
* @p: The &struct task_struct of the desired process.
*
* Convert the register values of the sleeping process in @p to
* the format that GDB expects.
* This function is called when kgdb does not have access to the
* &struct pt_regs and therefore it should fill the gdb registers
* @gdb_regs with what has been saved in &struct thread_struct
* thread field during switch_to.
*/
extern void
sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p);
/**
* gdb_regs_to_pt_regs - Convert GDB regs to ptrace regs.
* @gdb_regs: A pointer to hold the registers we've received from GDB.
* @regs: A pointer to a &struct pt_regs to hold these values in.
*
* Convert the GDB regs in @gdb_regs into the pt_regs, and store them
* in @regs.
*/
extern void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs);
/**
* kgdb_arch_handle_exception - Handle architecture specific GDB packets.
* @vector: The error vector of the exception that happened.
* @signo: The signal number of the exception that happened.
* @err_code: The error code of the exception that happened.
* @remcom_in_buffer: The buffer of the packet we have read.
* @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into.
* @regs: The &struct pt_regs of the current process.
*
* This function MUST handle the 'c' and 's' command packets,
* as well packets to set / remove a hardware breakpoint, if used.
* If there are additional packets which the hardware needs to handle,
* they are handled here. The code should return -1 if it wants to
* process more packets, and a %0 or %1 if it wants to exit from the
* kgdb callback.
*/
extern int
kgdb_arch_handle_exception(int vector, int signo, int err_code,
char *remcom_in_buffer,
char *remcom_out_buffer,
struct pt_regs *regs);
/**
* kgdb_arch_handle_qxfer_pkt - Handle architecture specific GDB XML
* packets.
* @remcom_in_buffer: The buffer of the packet we have read.
* @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into.
*/
extern void
kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
char *remcom_out_buffer);
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>
2018-12-05 10:38:26 +07:00
/**
* kgdb_call_nmi_hook - Call kgdb_nmicallback() on the current CPU
* @ignored: This parameter is only here to match the prototype.
*
* If you're using the default implementation of kgdb_roundup_cpus()
* this function will be called per CPU. If you don't implement
* kgdb_call_nmi_hook() a default will be used.
*/
extern void kgdb_call_nmi_hook(void *ignored);
/**
* kgdb_roundup_cpus - Get other CPUs into a holding pattern
*
* On SMP systems, we need to get the attention of the other CPUs
* and get them into a known state. This should do what is needed
* to get the other CPUs to call kgdb_wait(). Note that on some arches,
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>
2018-12-05 10:38:26 +07:00
* the NMI approach is not used for rounding up all the CPUs. Normally
* those architectures can just not implement this and get the default.
*
* On non-SMP systems, this is not called.
*/
extern void kgdb_roundup_cpus(void);
/**
* kgdb_arch_set_pc - Generic call back to the program counter
* @regs: Current &struct pt_regs.
* @pc: The new value for the program counter
*
* This function handles updating the program counter and requires an
* architecture specific implementation.
*/
extern void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc);
/* Optional functions. */
extern int kgdb_validate_break_address(unsigned long addr);
extern int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt);
extern int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt);
/**
* kgdb_arch_late - Perform any architecture specific initalization.
*
* This function will handle the late initalization of any
* architecture specific callbacks. This is an optional function for
* handling things like late initialization of hw breakpoints. The
* default implementation does nothing.
*/
extern void kgdb_arch_late(void);
/**
* struct kgdb_arch - Describe architecture specific values.
* @gdb_bpt_instr: The instruction to trigger a breakpoint.
* @flags: Flags for the breakpoint, currently just %KGDB_HW_BREAKPOINT.
* @set_breakpoint: Allow an architecture to specify how to set a software
* breakpoint.
* @remove_breakpoint: Allow an architecture to specify how to remove a
* software breakpoint.
* @set_hw_breakpoint: Allow an architecture to specify how to set a hardware
* breakpoint.
* @remove_hw_breakpoint: Allow an architecture to specify how to remove a
* hardware breakpoint.
* @disable_hw_break: Allow an architecture to specify how to disable
* hardware breakpoints for a single cpu.
* @remove_all_hw_break: Allow an architecture to specify how to remove all
* hardware breakpoints.
* @correct_hw_break: Allow an architecture to specify how to correct the
* hardware debug registers.
* @enable_nmi: Manage NMI-triggered entry to KGDB
*/
struct kgdb_arch {
unsigned char gdb_bpt_instr[BREAK_INSTR_SIZE];
unsigned long flags;
int (*set_breakpoint)(unsigned long, char *);
int (*remove_breakpoint)(unsigned long, char *);
int (*set_hw_breakpoint)(unsigned long, int, enum kgdb_bptype);
int (*remove_hw_breakpoint)(unsigned long, int, enum kgdb_bptype);
void (*disable_hw_break)(struct pt_regs *regs);
void (*remove_all_hw_break)(void);
void (*correct_hw_break)(void);
void (*enable_nmi)(bool on);
};
/**
* struct kgdb_io - Describe the interface for an I/O driver to talk with KGDB.
* @name: Name of the I/O driver.
* @read_char: Pointer to a function that will return one char.
* @write_char: Pointer to a function that will write one char.
* @flush: Pointer to a function that will flush any pending writes.
* @init: Pointer to a function that will initialize the device.
kgdboc: Add kgdboc_earlycon to support early kgdb using boot consoles We want to enable kgdb to debug the early parts of the kernel. Unfortunately kgdb normally is a client of the tty API in the kernel and serial drivers don't register to the tty layer until fairly late in the boot process. Serial drivers do, however, commonly register a boot console. Let's enable the kgdboc driver to work with boot consoles to provide early debugging. This change co-opts the existing read() function pointer that's part of "struct console". It's assumed that if a boot console (with the flag CON_BOOT) has implemented read() that both the read() and write() function are polling functions. That means they work without interrupts and read() will return immediately (with 0 bytes read) if there's nothing to read. This should be a safe assumption since it appears that no current boot consoles implement read() right now and there seems no reason to do so unless they wanted to support "kgdboc_earlycon". The normal/expected way to make all this work is to use "kgdboc_earlycon" and "kgdboc" together. You should point them both to the same physical serial connection. At boot time, as the system transitions from the boot console to the normal console (and registers a tty), kgdb will switch over. One awkward part of all this, though, is that there can be a window where the boot console goes away and we can't quite transtion over to the main kgdboc that uses the tty layer. There are two main problems: 1. The act of registering the tty doesn't cause any call into kgdboc so there is a window of time when the tty is there but kgdboc's init code hasn't been called so we can't transition to it. 2. On some serial drivers the normal console inits (and replaces the boot console) quite early in the system. Presumably these drivers were coded up before earlycon worked as well as it does today and probably they don't need to do this anymore, but it causes us problems nontheless. Problem #1 is not too big of a deal somewhat due to the luck of probe ordering. kgdboc is last in the tty/serial/Makefile so its probe gets right after all other tty devices. It's not fun to rely on this, but it does work for the most part. Problem #2 is a big deal, but only for some serial drivers. Other serial drivers end up registering the console (which gets rid of the boot console) and tty at nearly the same time. The way we'll deal with the window when the system has stopped using the boot console and the time when we're setup using the tty is to keep using the boot console. This may sound surprising, but it has been found to work well in practice. If it doesn't work, it shouldn't be too hard for a given serial driver to make it keep working. Specifically, it's expected that the read()/write() function provided in the boot console should be the same (or nearly the same) as the normal kgdb polling functions. That means continuing to use them should work just fine. To make things even more likely to work work we'll also trap the recently added exit() function in the boot console we're using and delay any calls to it until we're all done with the boot console. NOTE: there could be ways to use all this in weird / unexpected ways. If you do something like this, it's a bit of a buyer beware situation. Specifically: - If you specify only "kgdboc_earlycon" but not "kgdboc" then (depending on your serial driver) things will probably work OK, but you'll get a warning printed the first time you use kgdb after the boot console is gone. You'd only be able to do this, of course, if the serial driver you're running atop provided an early boot console. - If your "kgdboc_earlycon" and "kgdboc" devices are not the same device things should work OK, but it'll be your job to switch over which device you're monitoring (including figuring out how to switch over gdb in-flight if you're using it). When trying to enable "kgdboc_earlycon" it should be noted that the names that are registered through the boot console layer and the tty layer are not the same for the same port. For example when debugging on one board I'd need to pass "kgdboc_earlycon=qcom_geni kgdboc=ttyMSM0" to enable things properly. Since digging up the boot console name is a pain and there will rarely be more than one boot console enabled, you can provide the "kgdboc_earlycon" parameter without specifying the name of the boot console. In this case we'll just pick the first boot that implements read() that we find. This new "kgdboc_earlycon" parameter should be contrasted to the existing "ekgdboc" parameter. While both provide a way to debug very early, the usage and mechanisms are quite different. Specifically "kgdboc_earlycon" is meant to be used in tandem with "kgdboc" and there is a transition from one to the other. The "ekgdboc" parameter, on the other hand, replaces the "kgdboc" parameter. It runs the same logic as the "kgdboc" parameter but just relies on your TTY driver being present super early. The only known usage of the old "ekgdboc" parameter is documented as "ekgdboc=kbd earlyprintk=vga". It should be noted that "kbd" has special treatment allowing it to init early as a tty device. Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Tested-by: Sumit Garg <sumit.garg@linaro.org> Link: https://lore.kernel.org/r/20200507130644.v4.8.I8fba5961bf452ab92350654aa61957f23ecf0100@changeid Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
2020-05-08 03:08:46 +07:00
* @deinit: Pointer to a function that will deinit the device. Implies that
* this I/O driver is temporary and expects to be replaced. Called when
* an I/O driver is replaced or explicitly unregistered.
* @pre_exception: Pointer to a function that will do any prep work for
* the I/O driver.
* @post_exception: Pointer to a function that will do any cleanup work
* for the I/O driver.
kdb: Switch to use safer dbg_io_ops over console APIs In kgdb context, calling console handlers aren't safe due to locks used in those handlers which could in turn lead to a deadlock. Although, using oops_in_progress increases the chance to bypass locks in most console handlers but it might not be sufficient enough in case a console uses more locks (VT/TTY is good example). Currently when a driver provides both polling I/O and a console then kdb will output using the console. We can increase robustness by using the currently active polling I/O driver (which should be lockless) instead of the corresponding console. For several common cases (e.g. an embedded system with a single serial port that is used both for console output and debugger I/O) this will result in no console handler being used. In order to achieve this we need to reverse the order of preference to use dbg_io_ops (uses polling I/O mode) over console APIs. So we just store "struct console" that represents debugger I/O in dbg_io_ops and while emitting kdb messages, skip console that matches dbg_io_ops console in order to avoid duplicate messages. After this change, "is_console" param becomes redundant and hence removed. Suggested-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Sumit Garg <sumit.garg@linaro.org> Link: https://lore.kernel.org/r/1591264879-25920-5-git-send-email-sumit.garg@linaro.org Reviewed-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
2020-06-04 17:01:19 +07:00
* @cons: valid if the I/O device is a console; else NULL.
*/
struct kgdb_io {
const char *name;
int (*read_char) (void);
void (*write_char) (u8);
void (*flush) (void);
int (*init) (void);
kgdboc: Add kgdboc_earlycon to support early kgdb using boot consoles We want to enable kgdb to debug the early parts of the kernel. Unfortunately kgdb normally is a client of the tty API in the kernel and serial drivers don't register to the tty layer until fairly late in the boot process. Serial drivers do, however, commonly register a boot console. Let's enable the kgdboc driver to work with boot consoles to provide early debugging. This change co-opts the existing read() function pointer that's part of "struct console". It's assumed that if a boot console (with the flag CON_BOOT) has implemented read() that both the read() and write() function are polling functions. That means they work without interrupts and read() will return immediately (with 0 bytes read) if there's nothing to read. This should be a safe assumption since it appears that no current boot consoles implement read() right now and there seems no reason to do so unless they wanted to support "kgdboc_earlycon". The normal/expected way to make all this work is to use "kgdboc_earlycon" and "kgdboc" together. You should point them both to the same physical serial connection. At boot time, as the system transitions from the boot console to the normal console (and registers a tty), kgdb will switch over. One awkward part of all this, though, is that there can be a window where the boot console goes away and we can't quite transtion over to the main kgdboc that uses the tty layer. There are two main problems: 1. The act of registering the tty doesn't cause any call into kgdboc so there is a window of time when the tty is there but kgdboc's init code hasn't been called so we can't transition to it. 2. On some serial drivers the normal console inits (and replaces the boot console) quite early in the system. Presumably these drivers were coded up before earlycon worked as well as it does today and probably they don't need to do this anymore, but it causes us problems nontheless. Problem #1 is not too big of a deal somewhat due to the luck of probe ordering. kgdboc is last in the tty/serial/Makefile so its probe gets right after all other tty devices. It's not fun to rely on this, but it does work for the most part. Problem #2 is a big deal, but only for some serial drivers. Other serial drivers end up registering the console (which gets rid of the boot console) and tty at nearly the same time. The way we'll deal with the window when the system has stopped using the boot console and the time when we're setup using the tty is to keep using the boot console. This may sound surprising, but it has been found to work well in practice. If it doesn't work, it shouldn't be too hard for a given serial driver to make it keep working. Specifically, it's expected that the read()/write() function provided in the boot console should be the same (or nearly the same) as the normal kgdb polling functions. That means continuing to use them should work just fine. To make things even more likely to work work we'll also trap the recently added exit() function in the boot console we're using and delay any calls to it until we're all done with the boot console. NOTE: there could be ways to use all this in weird / unexpected ways. If you do something like this, it's a bit of a buyer beware situation. Specifically: - If you specify only "kgdboc_earlycon" but not "kgdboc" then (depending on your serial driver) things will probably work OK, but you'll get a warning printed the first time you use kgdb after the boot console is gone. You'd only be able to do this, of course, if the serial driver you're running atop provided an early boot console. - If your "kgdboc_earlycon" and "kgdboc" devices are not the same device things should work OK, but it'll be your job to switch over which device you're monitoring (including figuring out how to switch over gdb in-flight if you're using it). When trying to enable "kgdboc_earlycon" it should be noted that the names that are registered through the boot console layer and the tty layer are not the same for the same port. For example when debugging on one board I'd need to pass "kgdboc_earlycon=qcom_geni kgdboc=ttyMSM0" to enable things properly. Since digging up the boot console name is a pain and there will rarely be more than one boot console enabled, you can provide the "kgdboc_earlycon" parameter without specifying the name of the boot console. In this case we'll just pick the first boot that implements read() that we find. This new "kgdboc_earlycon" parameter should be contrasted to the existing "ekgdboc" parameter. While both provide a way to debug very early, the usage and mechanisms are quite different. Specifically "kgdboc_earlycon" is meant to be used in tandem with "kgdboc" and there is a transition from one to the other. The "ekgdboc" parameter, on the other hand, replaces the "kgdboc" parameter. It runs the same logic as the "kgdboc" parameter but just relies on your TTY driver being present super early. The only known usage of the old "ekgdboc" parameter is documented as "ekgdboc=kbd earlyprintk=vga". It should be noted that "kbd" has special treatment allowing it to init early as a tty device. Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Tested-by: Sumit Garg <sumit.garg@linaro.org> Link: https://lore.kernel.org/r/20200507130644.v4.8.I8fba5961bf452ab92350654aa61957f23ecf0100@changeid Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
2020-05-08 03:08:46 +07:00
void (*deinit) (void);
void (*pre_exception) (void);
void (*post_exception) (void);
kdb: Switch to use safer dbg_io_ops over console APIs In kgdb context, calling console handlers aren't safe due to locks used in those handlers which could in turn lead to a deadlock. Although, using oops_in_progress increases the chance to bypass locks in most console handlers but it might not be sufficient enough in case a console uses more locks (VT/TTY is good example). Currently when a driver provides both polling I/O and a console then kdb will output using the console. We can increase robustness by using the currently active polling I/O driver (which should be lockless) instead of the corresponding console. For several common cases (e.g. an embedded system with a single serial port that is used both for console output and debugger I/O) this will result in no console handler being used. In order to achieve this we need to reverse the order of preference to use dbg_io_ops (uses polling I/O mode) over console APIs. So we just store "struct console" that represents debugger I/O in dbg_io_ops and while emitting kdb messages, skip console that matches dbg_io_ops console in order to avoid duplicate messages. After this change, "is_console" param becomes redundant and hence removed. Suggested-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Sumit Garg <sumit.garg@linaro.org> Link: https://lore.kernel.org/r/1591264879-25920-5-git-send-email-sumit.garg@linaro.org Reviewed-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
2020-06-04 17:01:19 +07:00
struct console *cons;
};
extern const struct kgdb_arch arch_kgdb_ops;
extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
kgdb: fix signedness mixmatches, add statics, add declaration to header Noticed by sparse: arch/x86/kernel/kgdb.c:556:15: warning: symbol 'kgdb_arch_pc' was not declared. Should it be static? kernel/kgdb.c:149:8: warning: symbol 'kgdb_do_roundup' was not declared. Should it be static? kernel/kgdb.c:193:22: warning: symbol 'kgdb_arch_pc' was not declared. Should it be static? kernel/kgdb.c:712:5: warning: symbol 'remove_all_break' was not declared. Should it be static? Related to kgdb_hex2long: arch/x86/kernel/kgdb.c:371:28: warning: incorrect type in argument 2 (different signedness) arch/x86/kernel/kgdb.c:371:28: expected long *long_val arch/x86/kernel/kgdb.c:371:28: got unsigned long *<noident> kernel/kgdb.c:469:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:469:27: expected long *long_val kernel/kgdb.c:469:27: got unsigned long *<noident> kernel/kgdb.c:470:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:470:27: expected long *long_val kernel/kgdb.c:470:27: got unsigned long *<noident> kernel/kgdb.c:894:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:894:27: expected long *long_val kernel/kgdb.c:894:27: got unsigned long *<noident> kernel/kgdb.c:895:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:895:27: expected long *long_val kernel/kgdb.c:895:27: got unsigned long *<noident> kernel/kgdb.c:1127:28: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:1127:28: expected long *long_val kernel/kgdb.c:1127:28: got unsigned long *<noident> kernel/kgdb.c:1132:25: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:1132:25: expected long *long_val kernel/kgdb.c:1132:25: got unsigned long *<noident> Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
2008-04-25 04:57:23 +07:00
tty/serial: Add kgdb_nmi driver This special driver makes it possible to temporary use NMI debugger port as a normal console by issuing 'nmi_console' command (assuming that the port is attached to KGDB). Unlike KDB's disable_nmi command, with this driver you are always able to go back to the debugger using KGDB escape sequence ($3#33). This is because this console driver processes the input in NMI context, and thus is able to intercept the magic sequence. Note that since the console interprets input and uses polling communication methods, for things like PPP it is still better to fully detach debugger port from the KGDB NMI (i.e. disable_nmi), and use raw console. Usually, to enter the debugger one have to type the magic sequence, so initially the kernel will print the following prompt on the NMI debugger console: Type $3#33 to enter the debugger> For convenience, there is a kgdb_fiq.knock kernel command line option, when set to 0, this turns the special command to just a return key press, so the kernel will be printing this: Hit <return> to enter the debugger> This is more convenient for long debugging sessions, although it makes nmi_console feature somewhat useless. And for the cases when NMI connected to a dedicated button, the knocking can be disabled altogether by setting kgdb_fiq.knock to -1. Suggested-by: Colin Cross <ccross@android.com> Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org> Acked-by: Alan Cox <alan@linux.intel.com> Acked-by: Jason Wessel <jason.wessel@windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-09-25 04:27:56 +07:00
#ifdef CONFIG_SERIAL_KGDB_NMI
extern int kgdb_register_nmi_console(void);
extern int kgdb_unregister_nmi_console(void);
extern bool kgdb_nmi_poll_knock(void);
#else
static inline int kgdb_register_nmi_console(void) { return 0; }
static inline int kgdb_unregister_nmi_console(void) { return 0; }
static inline bool kgdb_nmi_poll_knock(void) { return true; }
tty/serial: Add kgdb_nmi driver This special driver makes it possible to temporary use NMI debugger port as a normal console by issuing 'nmi_console' command (assuming that the port is attached to KGDB). Unlike KDB's disable_nmi command, with this driver you are always able to go back to the debugger using KGDB escape sequence ($3#33). This is because this console driver processes the input in NMI context, and thus is able to intercept the magic sequence. Note that since the console interprets input and uses polling communication methods, for things like PPP it is still better to fully detach debugger port from the KGDB NMI (i.e. disable_nmi), and use raw console. Usually, to enter the debugger one have to type the magic sequence, so initially the kernel will print the following prompt on the NMI debugger console: Type $3#33 to enter the debugger> For convenience, there is a kgdb_fiq.knock kernel command line option, when set to 0, this turns the special command to just a return key press, so the kernel will be printing this: Hit <return> to enter the debugger> This is more convenient for long debugging sessions, although it makes nmi_console feature somewhat useless. And for the cases when NMI connected to a dedicated button, the knocking can be disabled altogether by setting kgdb_fiq.knock to -1. Suggested-by: Colin Cross <ccross@android.com> Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org> Acked-by: Alan Cox <alan@linux.intel.com> Acked-by: Jason Wessel <jason.wessel@windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-09-25 04:27:56 +07:00
#endif
extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops);
extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops);
extern struct kgdb_io *dbg_io_ops;
kgdb: fix signedness mixmatches, add statics, add declaration to header Noticed by sparse: arch/x86/kernel/kgdb.c:556:15: warning: symbol 'kgdb_arch_pc' was not declared. Should it be static? kernel/kgdb.c:149:8: warning: symbol 'kgdb_do_roundup' was not declared. Should it be static? kernel/kgdb.c:193:22: warning: symbol 'kgdb_arch_pc' was not declared. Should it be static? kernel/kgdb.c:712:5: warning: symbol 'remove_all_break' was not declared. Should it be static? Related to kgdb_hex2long: arch/x86/kernel/kgdb.c:371:28: warning: incorrect type in argument 2 (different signedness) arch/x86/kernel/kgdb.c:371:28: expected long *long_val arch/x86/kernel/kgdb.c:371:28: got unsigned long *<noident> kernel/kgdb.c:469:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:469:27: expected long *long_val kernel/kgdb.c:469:27: got unsigned long *<noident> kernel/kgdb.c:470:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:470:27: expected long *long_val kernel/kgdb.c:470:27: got unsigned long *<noident> kernel/kgdb.c:894:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:894:27: expected long *long_val kernel/kgdb.c:894:27: got unsigned long *<noident> kernel/kgdb.c:895:27: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:895:27: expected long *long_val kernel/kgdb.c:895:27: got unsigned long *<noident> kernel/kgdb.c:1127:28: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:1127:28: expected long *long_val kernel/kgdb.c:1127:28: got unsigned long *<noident> kernel/kgdb.c:1132:25: warning: incorrect type in argument 2 (different signedness) kernel/kgdb.c:1132:25: expected long *long_val kernel/kgdb.c:1132:25: got unsigned long *<noident> Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
2008-04-25 04:57:23 +07:00
extern int kgdb_hex2long(char **ptr, unsigned long *long_val);
extern char *kgdb_mem2hex(char *mem, char *buf, int count);
extern int kgdb_hex2mem(char *buf, char *mem, int count);
extern int kgdb_isremovedbreak(unsigned long addr);
extern void kgdb_schedule_breakpoint(void);
extern int kgdb_has_hit_break(unsigned long addr);
extern int
kgdb_handle_exception(int ex_vector, int signo, int err_code,
struct pt_regs *regs);
extern int kgdb_nmicallback(int cpu, void *regs);
extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code,
atomic_t *snd_rdy);
extern void gdbstub_exit(int status);
extern int kgdb_single_step;
extern atomic_t kgdb_active;
#define in_dbg_master() \
(irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active)))
extern bool dbg_is_early;
extern void __init dbg_late_init(void);
kgdb: don't use a notifier to enter kgdb at panic; call directly Right now kgdb/kdb hooks up to debug panics by registering for the panic notifier. This works OK except that it means that kgdb/kdb gets called _after_ the CPUs in the system are taken offline. That means that if anything important was happening on those CPUs (like something that might have contributed to the panic) you can't debug them. Specifically I ran into a case where I got a panic because a task was "blocked for more than 120 seconds" which was detected on CPU 2. I nicely got shown stack traces in the kernel log for all CPUs including CPU 0, which was running 'PID: 111 Comm: kworker/0:1H' and was in the middle of __mmc_switch(). I then ended up at the kdb prompt where switched over to kgdb to try to look at local variables of the process on CPU 0. I found that I couldn't. Digging more, I found that I had no info on any tasks running on CPUs other than CPU 2 and that asking kdb for help showed me "Error: no saved data for this cpu". This was because all the CPUs were offline. Let's move the entry of kdb/kgdb to a direct call from panic() and stop using the generic notifier. Putting a direct call in allows us to order things more properly and it also doesn't seem like we're breaking any abstractions by calling into the debugger from the panic function. Daniel said: : This patch changes the way kdump and kgdb interact with each other. : However it would seem rather odd to have both tools simultaneously armed : and, even if they were, the user still has the option to use panic_timeout : to force a kdump to happen. Thus I think the change of order is : acceptable. Link: http://lkml.kernel.org/r/20190703170354.217312-1-dianders@chromium.org Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org> Cc: Jason Wessel <jason.wessel@windriver.com> Cc: Kees Cook <keescook@chromium.org> Cc: Borislav Petkov <bp@suse.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Feng Tang <feng.tang@intel.com> Cc: YueHaibing <yuehaibing@huawei.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: "Steven Rostedt (VMware)" <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-26 06:47:45 +07:00
extern void kgdb_panic(const char *msg);
#else /* ! CONFIG_KGDB */
#define in_dbg_master() (0)
#define dbg_late_init()
kgdb: don't use a notifier to enter kgdb at panic; call directly Right now kgdb/kdb hooks up to debug panics by registering for the panic notifier. This works OK except that it means that kgdb/kdb gets called _after_ the CPUs in the system are taken offline. That means that if anything important was happening on those CPUs (like something that might have contributed to the panic) you can't debug them. Specifically I ran into a case where I got a panic because a task was "blocked for more than 120 seconds" which was detected on CPU 2. I nicely got shown stack traces in the kernel log for all CPUs including CPU 0, which was running 'PID: 111 Comm: kworker/0:1H' and was in the middle of __mmc_switch(). I then ended up at the kdb prompt where switched over to kgdb to try to look at local variables of the process on CPU 0. I found that I couldn't. Digging more, I found that I had no info on any tasks running on CPUs other than CPU 2 and that asking kdb for help showed me "Error: no saved data for this cpu". This was because all the CPUs were offline. Let's move the entry of kdb/kgdb to a direct call from panic() and stop using the generic notifier. Putting a direct call in allows us to order things more properly and it also doesn't seem like we're breaking any abstractions by calling into the debugger from the panic function. Daniel said: : This patch changes the way kdump and kgdb interact with each other. : However it would seem rather odd to have both tools simultaneously armed : and, even if they were, the user still has the option to use panic_timeout : to force a kdump to happen. Thus I think the change of order is : acceptable. Link: http://lkml.kernel.org/r/20190703170354.217312-1-dianders@chromium.org Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org> Cc: Jason Wessel <jason.wessel@windriver.com> Cc: Kees Cook <keescook@chromium.org> Cc: Borislav Petkov <bp@suse.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Feng Tang <feng.tang@intel.com> Cc: YueHaibing <yuehaibing@huawei.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: "Steven Rostedt (VMware)" <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-26 06:47:45 +07:00
static inline void kgdb_panic(const char *msg) {}
#endif /* ! CONFIG_KGDB */
#endif /* _KGDB_H_ */