diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-17 05:49:30 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-17 05:49:30 +0200 |
commit | 35ce8ae9ae2e471f92759f9d6880eab42cc1c3b6 (patch) | |
tree | d6299a6010d1d88c1ab93f406c0a392e3aaa919e | |
parent | 6661224e66f03706daea8e27714436851cf01731 (diff) | |
parent | a403df29789ba38796edb97dad9bfb47836b68c0 (diff) |
Merge branch 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull signal/exit/ptrace updates from Eric Biederman:
"This set of changes deletes some dead code, makes a lot of cleanups
which hopefully make the code easier to follow, and fixes bugs found
along the way.
The end-game which I have not yet reached yet is for fatal signals
that generate coredumps to be short-circuit deliverable from
complete_signal, for force_siginfo_to_task not to require changing
userspace configured signal delivery state, and for the ptrace stops
to always happen in locations where we can guarantee on all
architectures that the all of the registers are saved and available on
the stack.
Removal of profile_task_ext, profile_munmap, and profile_handoff_task
are the big successes for dead code removal this round.
A bunch of small bug fixes are included, as most of the issues
reported were small enough that they would not affect bisection so I
simply added the fixes and did not fold the fixes into the changes
they were fixing.
There was a bug that broke coredumps piped to systemd-coredump. I
dropped the change that caused that bug and replaced it entirely with
something much more restrained. Unfortunately that required some
rebasing.
Some successes after this set of changes: There are few enough calls
to do_exit to audit in a reasonable amount of time. The lifetime of
struct kthread now matches the lifetime of struct task, and the
pointer to struct kthread is no longer stored in set_child_tid. The
flag SIGNAL_GROUP_COREDUMP is removed. The field group_exit_task is
removed. Issues where task->exit_code was examined with
signal->group_exit_code should been examined were fixed.
There are several loosely related changes included because I am
cleaning up and if I don't include them they will probably get lost.
The original postings of these changes can be found at:
https://lkml.kernel.org/r/87a6ha4zsd.fsf@email.froward.int.ebiederm.org
https://lkml.kernel.org/r/87bl1kunjj.fsf@email.froward.int.ebiederm.org
https://lkml.kernel.org/r/87r19opkx1.fsf_-_@email.froward.int.ebiederm.org
I trimmed back the last set of changes to only the obviously correct
once. Simply because there was less time for review than I had hoped"
* 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (44 commits)
ptrace/m68k: Stop open coding ptrace_report_syscall
ptrace: Remove unused regs argument from ptrace_report_syscall
ptrace: Remove second setting of PT_SEIZED in ptrace_attach
taskstats: Cleanup the use of task->exit_code
exit: Use the correct exit_code in /proc/<pid>/stat
exit: Fix the exit_code for wait_task_zombie
exit: Coredumps reach do_group_exit
exit: Remove profile_handoff_task
exit: Remove profile_task_exit & profile_munmap
signal: clean up kernel-doc comments
signal: Remove the helper signal_group_exit
signal: Rename group_exit_task group_exec_task
coredump: Stop setting signal->group_exit_task
signal: Remove SIGNAL_GROUP_COREDUMP
signal: During coredumps set SIGNAL_GROUP_EXIT in zap_process
signal: Make coredump handling explicit in complete_signal
signal: Have prepare_signal detect coredumps using signal->core_state
signal: Have the oom killer detect coredumps using signal->core_state
exit: Move force_uaccess back into do_exit
exit: Guarantee make_task_dead leaks the tsk when calling do_task_exit
...
86 files changed, 308 insertions, 400 deletions
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 2ae34702456c..8a66fe544c69 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -190,7 +190,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } #ifndef CONFIG_MATHEMU @@ -575,7 +575,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); got_exception: /* Ok, we caught the exception, but we don't want it. Is there @@ -630,7 +630,7 @@ got_exception: local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 6c0a277388dd..ec20c1004abf 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -202,7 +202,7 @@ retry: printk(KERN_ALERT "Unable to handle kernel paging request at " "virtual address %016lx\n", address); die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16); - do_exit(SIGKILL); + make_task_dead(SIGKILL); /* We ran out of memory, or some other thing happened to us that made us unable to handle the page fault gracefully. */ diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index c5e25cf7219b..da04ed85855a 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -335,7 +335,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) if (panic_on_oops) panic("Fatal exception"); if (signr) - do_exit(signr); + make_task_dead(signr); } /* diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 13949510772a..a062e07516dd 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -117,7 +117,7 @@ static void die_kernel_fault(const char *msg, struct mm_struct *mm, show_pte(KERN_ALERT, mm, addr); die("Oops", regs, fsr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index e8986e6067a9..70fc42470f13 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -235,7 +235,7 @@ void die(const char *str, struct pt_regs *regs, int err) raw_spin_unlock_irqrestore(&die_lock, flags); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } static void arm64_show_signal(int signo, const char *str) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 11e04cca0f4f..77341b160aca 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -304,7 +304,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index cb2a0d94a144..2df115d0e210 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -294,7 +294,7 @@ bad_area: __func__, opcode, rz, rx, imm, addr); show_regs(regs); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr); diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c index 2020af88b636..6e426fba0119 100644 --- a/arch/csky/kernel/traps.c +++ b/arch/csky/kernel/traps.c @@ -109,7 +109,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 466ad949818a..7215a46b6b8e 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -67,7 +67,7 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) pr_alert("Unable to handle kernel paging request at virtual " "addr 0x%08lx, pc: 0x%08lx\n", addr, regs->pc); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index bdbe988d8dbc..a92c39e03802 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task.h> #include <linux/mm_types.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -106,7 +107,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index d4bc9c16f2df..b465441f490d 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -51,7 +51,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - do_exit(SIGKILL); + make_task_dead(SIGKILL); return 1; } diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index edfc35dafeb1..1240f038cce0 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -214,7 +214,7 @@ int die(const char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(err); + make_task_dead(err); return 0; } diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 5bfc79be4cef..23c203639a96 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -176,7 +176,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) spin_unlock(&mca_bh_lock); /* This process is about to be killed itself */ - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /** diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index e13cb905930f..753642366e12 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -85,7 +85,7 @@ die (const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); return 0; } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 32417f49ad2f..07379d1a227f 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -257,7 +257,7 @@ retry: regs = NULL; bust_spinlocks(0); if (regs) - do_exit(SIGKILL); + make_task_dead(SIGKILL); return; out_of_memory: diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c index 94b3b274186d..aa3a0b8d07e9 100644 --- a/arch/m68k/kernel/ptrace.c +++ b/arch/m68k/kernel/ptrace.c @@ -273,17 +273,7 @@ out_eio: asmlinkage void syscall_trace(void) { - ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) - ? 0x80 : 0)); - /* - * this isn't the same as continuing with a signal, but it will do - * for normal use. strace only continues with a signal if the - * stopping signal is not SIGTRAP. -brl - */ - if (current->exit_code) { - send_sig(current->exit_code, current, 1); - current->exit_code = 0; - } + ptrace_report_syscall(0); } #if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU) diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 34d6458340b0..59fc63feb0dc 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1131,7 +1131,7 @@ void die_if_kernel (char *str, struct pt_regs *fp, int nr) pr_crit("%s: %08x\n", str, nr); show_registers(fp); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } asmlinkage void set_esp0(unsigned long ssp) diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 53cfb9bc1066..1493cf5eac1e 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -48,7 +48,7 @@ int send_fault_sig(struct pt_regs *regs) pr_alert("Unable to handle kernel access"); pr_cont(" at virtual address %p\n", addr); die_if_kernel("Oops", regs, 0 /*error_code*/); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } return 1; diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c index 908788497b28..fd153d5fab98 100644 --- a/arch/microblaze/kernel/exceptions.c +++ b/arch/microblaze/kernel/exceptions.c @@ -44,10 +44,10 @@ void die(const char *str, struct pt_regs *fp, long err) pr_warn("Oops: %s, sig: %ld\n", str, err); show_regs(fp); spin_unlock_irq(&die_lock); - /* do_exit() should take care of panic'ing from an interrupt + /* make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } /* for user application debugging */ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index d26b0fb8ea06..a486486b2355 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -422,7 +422,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) if (regs && kexec_should_crash(current)) crash_kexec(regs); - do_exit(sig); + make_task_dead(sig); } extern struct exception_table_entry __start___dbe_table[]; diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c index 9edd7ed7d7bf..701c09a668de 100644 --- a/arch/nds32/kernel/fpu.c +++ b/arch/nds32/kernel/fpu.c @@ -223,7 +223,7 @@ inline void handle_fpu_exception(struct pt_regs *regs) } } else if (fpcsr & FPCSR_mskRIT) { if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); si_signo = SIGILL; } diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index ca75d475eda4..c0a8f3344fb9 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -141,7 +141,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, int err) bust_spinlocks(0); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } EXPORT_SYMBOL(die); @@ -240,7 +240,7 @@ void unhandled_interruption(struct pt_regs *regs) pr_emerg("unhandled_interruption\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -251,7 +251,7 @@ void unhandled_exceptions(unsigned long entry, unsigned long addr, addr, type); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -278,7 +278,7 @@ void do_revinsn(struct pt_regs *regs) pr_emerg("Reserved Instruction\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); force_sig(SIGILL); } diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c index 596986a74a26..85ac49d64cf7 100644 --- a/arch/nios2/kernel/traps.c +++ b/arch/nios2/kernel/traps.c @@ -37,10 +37,10 @@ void die(const char *str, struct pt_regs *regs, long err) show_regs(regs); spin_unlock_irq(&die_lock); /* - * do_exit() should take care of panic'ing from an interrupt + * make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } void _exception(int signo, struct pt_regs *regs, int code, unsigned long addr) diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 0898cb159fac..0446a3c34372 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -212,7 +212,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, long err) __asm__ __volatile__("l.nop 1"); do {} while (1); #endif - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* This is normally the 'Oops' routine */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index eb41fece1910..b6fdebddc8e9 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -269,7 +269,7 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* gdb uses break 4,8 */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 11741703d26e..a08bb7cefdc5 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -245,7 +245,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + make_task_dead(signr); } NOKPROBE_SYMBOL(oops_end); @@ -792,9 +792,9 @@ int machine_check_generic(struct pt_regs *regs) void die_mce(const char *str, struct pt_regs *regs, long err) { /* - * The machine check wants to kill the interrupted context, but - * do_exit() checks for in_interrupt() and panics in that case, so - * exit the irq/nmi before calling die. + * The machine check wants to kill the interrupted context, + * but make_task_dead() checks for in_interrupt() and panics + * in that case, so exit the irq/nmi before calling die. */ if (in_nmi()) nmi_exit(); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 0daaa3e4630d..fe92e119e6a3 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -54,7 +54,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index cae4b6363607..02a0ee2d3c10 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -31,7 +31,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, bust_spinlocks(0); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static inline void no_context(struct pt_regs *regs, unsigned long addr) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 0681c55e831d..1e3233eb510a 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -224,5 +224,5 @@ void __noreturn die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception: panic_on_oops"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 1cf1e37553e8..0c9e894913dc 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -166,7 +166,7 @@ void __s390_handle_mcck(void) "malfunction (code 0x%016lx).\n", mcck.mcck_code); printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", current->comm, current->pid); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } } diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index cbe3201d4f21..01884054aeb2 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -57,7 +57,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void die_if_kernel(const char *str, struct pt_regs *regs, long err) diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index 5630e5a395e0..179aabfa712e 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -86,9 +86,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } printk("Instruction DUMP:"); instruction_dump ((unsigned long *) regs->pc); - if(regs->psr & PSR_PS) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->psr & PSR_PS) ? SIGKILL : SIGSEGV); } void do_hw_interrupt(struct pt_regs *regs, unsigned long type) diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 6863025ed56d..21077821f427 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2559,9 +2559,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } if (panic_on_oops) panic("Fatal exception"); - if (regs->tstate & TSTATE_PRIV) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->tstate & TSTATE_PRIV)? SIGKILL : SIGSEGV); } EXPORT_SYMBOL(die_if_kernel); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index a7ec22b1d06c..887420844066 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1241,14 +1241,14 @@ SYM_CODE_START(asm_exc_nmi) SYM_CODE_END(asm_exc_nmi) .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp movl PER_CPU_VAR(cpu_current_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp - call do_exit + call make_task_dead 1: jmp 1b -SYM_CODE_END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 1ffdbfaad2e2..466df3e50276 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1427,7 +1427,7 @@ SYM_CODE_END(ignore_sysret) #endif .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1436,6 +1436,6 @@ SYM_CODE_START(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS - call do_exit -SYM_CODE_END(rewind_stack_do_exit) + call make_task_dead +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ea4fe192189d..53de044e5654 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -351,7 +351,7 @@ unsigned long oops_begin(void) } NOKPROBE_SYMBOL(oops_begin); -void __noreturn rewind_stack_do_exit(int signr); +void __noreturn rewind_stack_and_make_dead(int signr); void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { @@ -386,7 +386,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * reuse the task stack and that existing poisons are invalid. */ kasan_unpoison_task_stack(current); - rewind_stack_do_exit(signr); + rewind_stack_and_make_dead(signr); } NOKPROBE_SYMBOL(oops_end); diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 99ab3c1a3387..a1029a5b6a1d 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1433,7 +1433,7 @@ ENTRY(fast_syscall_spill_registers) rsync movi abi_arg0, SIGSEGV - abi_call do_exit + abi_call make_task_dead /* shouldn't return, so panic */ diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 4b4dbeb2d612..9345007d474d 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -552,5 +552,5 @@ void __noreturn die(const char * str, struct pt_regs * regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(err); + make_task_dead(err); } diff --git a/crypto/algboss.c b/crypto/algboss.c index 1814d2c5188a..eb5fe84efb83 100644 --- a/crypto/algboss.c +++ b/crypto/algboss.c @@ -67,7 +67,7 @@ out: complete_all(¶m->larval->completion); crypto_alg_put(¶m->larval->alg); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_probe(struct crypto_larval *larval) @@ -190,7 +190,7 @@ skiptest: crypto_alg_tested(param->driver, err); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_test(struct crypto_alg *alg) diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c index a0c5d02ae88c..8a3d86897ea8 100644 --- a/drivers/net/wireless/rsi/rsi_91x_coex.c +++ b/drivers/net/wireless/rsi/rsi_91x_coex.c @@ -63,7 +63,7 @@ static void rsi_coex_scheduler_thread(struct rsi_common *common) rsi_coex_sched_tx_pkts(coex_cb); } while (atomic_read(&coex_cb->coex_tx_thread.thread_done) == 0); - complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); + kthread_complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); } int rsi_coex_recv_pkt(struct rsi_common *common, u8 *msg) diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index 5d1490fc32db..f9f004446b07 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -264,7 +264,7 @@ static void rsi_tx_scheduler_thread(struct rsi_common *common) if (common->init_done) rsi_core_qos_processor(common); } while (atomic_read(&common->tx_thread.thread_done) == 0); - complete_and_exit(&common->tx_thread.completion, 0); + kthread_complete_and_exit(&common->tx_thread.completion, 0); } #ifdef CONFIG_RSI_COEX diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c index 8ace1874e5cb..b2b47a0abcbf 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c @@ -75,7 +75,7 @@ void rsi_sdio_rx_thread(struct rsi_common *common) rsi_dbg(INFO_ZONE, "%s: Terminated SDIO RX thread\n", __func__); atomic_inc(&sdev->rx_thread.thread_done); - complete_and_exit(&sdev->rx_thread.completion, 0); + kthread_complete_and_exit(&sdev->rx_thread.completion, 0); } /** diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c index 4ffcdde1acb1..5130b0e72adc 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c @@ -56,6 +56,6 @@ void rsi_usb_rx_thread(struct rsi_common *common) out: rsi_dbg(INFO_ZONE, "%s: Terminated thread\n", __func__); skb_queue_purge(&dev->rx_q); - complete_and_exit(&dev->rx_thread.completion, 0); + kthread_complete_and_exit(&dev->rx_thread.completion, 0); } diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index 669ef4700c1a..f7e86ae9f72f 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -160,7 +160,7 @@ static int pnp_dock_thread(void *unused) * No dock to manage */ case PNP_FUNCTION_NOT_SUPPORTED: - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); case PNP_SYSTEM_NOT_DOCKED: d = 0; break; @@ -170,7 +170,7 @@ static int pnp_dock_thread(void *unused) default: pnpbios_print_status("pnp_dock_thread", status); printk(KERN_WARNING "PnPBIOS: disabling dock monitoring.\n"); - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } if (d != docked) { if (pnp_dock_event(d, &now) == 0) { @@ -183,7 +183,7 @@ static int pnp_dock_thread(void *unused) } } } - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } static int pnpbios_get_resources(struct pnp_dev *dev) diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c index 91fcf85e150a..5a58dac76c88 100644 --- a/drivers/staging/rts5208/rtsx.c +++ b/drivers/staging/rts5208/rtsx.c @@ -450,13 +450,13 @@ skip_for_abort: * after the down() -- that's necessary for the thread-shutdown * case. * - * complete_and_exit() goes even further than this -- it is safe in - * the case that the thread of the caller is going away (not just - * the structure) -- this is necessary for the module-remove case. - * This is important in preemption kernels, which transfer the flow - * of execution immediately upon a complete(). + * kthread_complete_and_exit() goes even further than this -- + * it is safe in the case that the thread of the caller is going away + * (not just the structure) -- this is necessary for the module-remove + * case. This is important in preemption kernels, which transfer the + * flow of execution immediately upon a complete(). */ - complete_and_exit(&dev->control_exit, 0); + kthread_complete_and_exit(&dev->control_exit, 0); } static int rtsx_polling_thread(void *__dev) @@ -501,7 +501,7 @@ static int rtsx_polling_thread(void *__dev) mutex_unlock(&dev->dev_mutex); } - complete_and_exit(&dev->polling_exit, 0); + kthread_complete_and_exit(&dev->polling_exit, 0); } /* @@ -682,7 +682,7 @@ static int rtsx_scan_thread(void *__dev) /* Should we unbind if no devices were detected? */ } - complete_and_exit(&dev->scanning_done, 0); + kthread_complete_and_exit(&dev->scanning_done, 0); } static void rtsx_init_options(struct rtsx_chip *chip) diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index da17be1ef64e..e3a49d837609 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -969,7 +969,7 @@ static int usbatm_do_heavy_init(void *arg) instance->thread = NULL; mutex_unlock(&instance->serialize); - complete_and_exit(&instance->thread_exited, ret); + kthread_complete_and_exit(&instance->thread_exited, ret); } static int usbatm_heavy_init(struct usbatm_data *instance) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 752439690fda..46dd11dcb3a8 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2547,7 +2547,7 @@ static int fsg_main_thread(void *common_) up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ - complete_and_exit(&common->thread_notifier, 0); + kthread_complete_and_exit(&common->thread_notifier, 0); } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1060164b984a..68ed29cff7e8 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1139,7 +1139,7 @@ next_pdu: } memalloc_noreclaim_restore(noreclaim_flag); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } /* diff --git a/fs/coredump.c b/fs/coredump.c index a6b3c196cdef..7dece20b162b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -347,13 +347,13 @@ out: return ispipe; } -static int zap_process(struct task_struct *start, int exit_code, int flags) +static int zap_process(struct task_struct *start, int exit_code) { struct task_struct *t; int nr = 0; /* ignore all signals except SIGKILL, see prepare_signal() */ - start->signal->flags = SIGNAL_GROUP_COREDUMP | flags; + start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -372,13 +372,13 @@ static int zap_process(struct task_struct *start, int exit_code, int flags) static int zap_threads(struct task_struct *tsk, struct core_state *core_state, int exit_code) { + struct signal_struct *signal = tsk->signal; int nr = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); - if (!signal_group_exit(tsk->signal)) { - tsk->signal->core_state = core_state; - tsk->signal->group_exit_task = tsk; - nr = zap_process(tsk, exit_code, 0); + if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) { + signal->core_state = core_state; + nr = zap_process(tsk, exit_code); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); tsk->flags |= PF_DUMPCORE; atomic_set(&core_state->nr_threads, nr); @@ -426,8 +426,6 @@ static void coredump_finish(bool core_dumped) spin_lock_irq(¤t->sighand->siglock); if (core_dumped && !__fatal_signal_pending(current)) current->signal->group_exit_code |= 0x80; - current->signal->group_exit_task = NULL; - current->signal->flags = SIGNAL_GROUP_EXIT; next = current->signal->core_state->dumper.next; current->signal->core_state = NULL; spin_unlock_irq(¤t->sighand->siglock); diff --git a/fs/exec.c b/fs/exec.c index 537d92c41105..82db656ca709 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1045,7 +1045,7 @@ static int de_thread(struct task_struct *tsk) * Kill all other threads in the thread group. */ spin_lock_irq(lock); - if (signal_group_exit(sig)) { + if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. @@ -1054,7 +1054,7 @@ static int de_thread(struct task_struct *tsk) return -EAGAIN; } - sig->group_exit_task = tsk; + sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; @@ -1082,7 +1082,7 @@ static int de_thread(struct task_struct *tsk) write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that - * exit_notify() can't miss ->group_exit_task + * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) @@ -1149,7 +1149,7 @@ static int de_thread(struct task_struct *tsk) release_task(leader); } - sig->group_exit_task = NULL; + sig->group_exec_task = NULL; sig->notify_count = 0; no_thread_group: @@ -1162,7 +1162,7 @@ no_thread_group: killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); - sig->group_exit_task = NULL; + sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; @@ -1307,6 +1307,8 @@ int begin_new_exec(struct linux_binprm * bprm) */ force_uaccess_begin(); + if (me->flags & PF_KTHREAD) + free_kthread_struct(me); me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); diff --git a/fs/io-wq.c b/fs/io-wq.c index 5c4f582d6549..a7763127f884 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -670,7 +670,7 @@ loop: */ void io_wq_worker_running(struct task_struct *tsk) { - struct io_worker *worker = tsk->pf_io_worker; + struct io_worker *worker = tsk->worker_private; if (!worker) return; @@ -688,7 +688,7 @@ void io_wq_worker_running(struct task_struct *tsk) */ void io_wq_worker_sleeping(struct task_struct *tsk) { - struct io_worker *worker = tsk->pf_io_worker; + struct io_worker *worker = tsk->worker_private; if (!worker) return; @@ -707,7 +707,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk) static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, struct task_struct *tsk) { - tsk->pf_io_worker = worker; + tsk->worker_private = worker; worker->task = tsk; set_cpus_allowed_ptr(tsk, wqe->cpu_mask); tsk->flags |= PF_NO_SETAFFINITY; diff --git a/fs/io-wq.h b/fs/io-wq.h index 3709b7c5ec98..dbecd27656c7 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -222,6 +222,6 @@ static inline void io_wq_worker_running(struct task_struct *tsk) static inline bool io_wq_current_is_worker(void) { return in_task() && (current->flags & PF_IO_WORKER) && - current->pf_io_worker; + current->worker_private; } #endif diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 2b4d5013dc5d..6da92ecaf66d 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -161,5 +161,5 @@ static int jffs2_garbage_collect_thread(void *_c) spin_lock(&c->erase_completion_lock); c->gc_task = NULL; spin_unlock(&c->erase_completion_lock); - complete_and_exit(&c->gc_thread_exit, 0); + kthread_complete_and_exit(&c->gc_thread_exit, 0); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 4defefd89cbf..0475c5a5d061 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -185,7 +185,7 @@ lockd(void *vrqstp) svc_exit_thread(rqstp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int create_lockd_listener(struct svc_serv *serv, const char *name, diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index c4994c1d4e36..054cc1255fac 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -93,7 +93,7 @@ nfs4_callback_svc(void *vrqstp) svc_process(rqstp); } svc_exit_thread(rqstp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } @@ -137,7 +137,7 @@ nfs41_callback_svc(void *vrqstp) } } svc_exit_thread(rqstp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f63dfa01001c..d88b779f9dd0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2693,6 +2693,6 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); nfs4_state_manager(clp); nfs_put_client(clp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 07193595b8e0..b8c682b62d29 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1020,7 +1020,7 @@ out: } /* Release module */ - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index ff869a66b34e..43a7abde9e42 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -468,6 +468,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cgtime, gtime; unsigned long rsslim = 0; unsigned long flags; + int exit_code = task->exit_code; state = *get_task_state(task); vsize = eip = esp = 0; @@ -531,6 +532,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, maj_flt += sig->maj_flt; thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; + + if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) + exit_code = sig->group_exit_code; } sid = task_session_nr_ns(task, ns); @@ -630,7 +634,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_puts(m, " 0 0 0 0 0 0 0"); if (permitted) - seq_put_decimal_ll(m, " ", task->exit_code); + seq_put_decimal_ll(m, " ", exit_code); else seq_puts(m, " 0"); diff --git a/fs/signalfd.c b/fs/signalfd.c index 65ce0e72e7b9..e20d1484c663 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -155,11 +155,12 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info, int nonblock) { + enum pid_type type; ssize_t ret; DECLARE_WAITQUEUE(wait, current); spin_lock_irq(¤t->sighand->siglock); - ret = dequeue_signal(current, &ctx->sigmask, info); + ret = dequeue_signal(current, &ctx->sigmask, info, &type); switch (ret) { case 0: if (!nonblock) @@ -174,7 +175,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - ret = dequeue_signal(current, &ctx->sigmask, info); + ret = dequeue_signal(current, &ctx->sigmask, info, &type); if (ret != 0) break; if (signal_pending(current)) { diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..055eb203c00e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -187,7 +187,6 @@ static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; -void complete_and_exit(struct completion *, long) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index db47aae7c481..b6c8aafa8db5 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,7 +33,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); -void set_kthread_struct(struct task_struct *p); +bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); @@ -95,6 +95,8 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_exit(long result) __noreturn; +void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/module.h b/include/linux/module.h index c9f1200b2312..f03be97e9ec1 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -595,9 +595,9 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -extern void __noreturn __module_put_and_exit(struct module *mod, +extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); -#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) +#define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); @@ -790,7 +790,7 @@ static inline int unregister_module_notifier(struct notifier_block *nb) return 0; } -#define module_put_and_exit(code) do_exit(code) +#define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { diff --git a/include/linux/profile.h b/include/linux/profile.h index fd18ca96f557..11db1ec516e2 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -31,11 +31,6 @@ static inline int create_proc_profile(void) } #endif -enum profile_type { - PROFILE_TASK_EXIT, - PROFILE_MUNMAP -}; - #ifdef CONFIG_PROFILING extern int prof_on __read_mostly; @@ -66,23 +61,6 @@ static inline void profile_hit(int type, void *ip) struct task_struct; struct mm_struct; -/* task is in do_exit() */ -void profile_task_exit(struct task_struct * task); - -/* task is dead, free task struct ? Returns 1 if - * the task was taken, 0 if the task should be freed. - */ -int profile_handoff_task(struct task_struct * task); - -/* sys_munmap */ -void profile_munmap(unsigned long addr); - -int task_handoff_register(struct notifier_block * n); -int task_handoff_unregister(struct notifier_block * n); - -int profile_event_register(enum profile_type, struct notifier_block * n); -int profile_event_unregister(enum profile_type, struct notifier_block * n); - #else #define prof_on 0 @@ -107,29 +85,6 @@ static inline void profile_hit(int type, void *ip) return; } -static inline int task_handoff_register(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int task_handoff_unregister(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_register(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_unregister(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -#define profile_task_exit(a) do { } while (0) -#define profile_handoff_task(a) (0) -#define profile_munmap(a) do { } while (0) #endif /* CONFIG_PROFILING */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a1f16df66e3..a6a2db5f85ac 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -991,8 +991,8 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; + /* PF_KTHREAD | PF_IO_WORKER */ + void *worker_private; u64 utime; u64 stime; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 33a50642cf41..b6ecb9fc4cd2 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -109,13 +109,9 @@ struct signal_struct { /* thread group exit support */ int group_exit_code; - /* overloaded: - * - notify group_exit_task when ->count is equal to notify_count - * - everyone except group_exit_task is stopped during signal delivery - * of fatal signals, group_exit_task processes the signal. - */ + /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; - struct task_struct *group_exit_task; + struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; @@ -256,7 +252,6 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ -#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -272,31 +267,25 @@ struct signal_struct { static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { - WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } -/* If true, all threads except ->group_exit_task have pending SIGKILL */ -static inline int signal_group_exit(const struct signal_struct *sig) -{ - return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exit_task != NULL); -} - extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, - sigset_t *mask, kernel_siginfo_t *info); +extern int dequeue_signal(struct task_struct *task, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; + enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info); + ret = dequeue_signal(task, &task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 058d7f371e25..b9198a1b3a84 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -59,6 +59,7 @@ extern void sched_post_fork(struct task_struct *p, extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr); extern void proc_caches_init(void); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index cf175d47c6b7..f35c22b3355f 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -65,7 +65,7 @@ struct svc_serv_ops { void (*svo_enqueue_xprt)(struct svc_xprt *); /* optional module to count when adding threads. - * Thread function must call module_put_and_exit() to exit. + * Thread function must call module_put_and_kthread_exit() to exit. */ struct module *svo_module; }; diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 2564b7434b4d..88c007ab5ebc 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -54,8 +54,7 @@ struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ -static inline int ptrace_report_syscall(struct pt_regs *regs, - unsigned long message) +static inline int ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; @@ -102,7 +101,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs, static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { - return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); + return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** @@ -127,7 +126,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) if (step) user_single_step_report(regs); else - ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); + ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); } /** diff --git a/kernel/exit.c b/kernel/exit.c index f702a6a63686..b00a25bb4ab9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -116,7 +116,7 @@ static void __exit_signal(struct task_struct *tsk) * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) - wake_up_process(sig->group_exit_task); + wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); @@ -697,7 +697,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) - wake_up_process(tsk->signal->group_exit_task); + wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { @@ -735,37 +735,22 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; - /* - * We can get here from a kernel oops, sometimes with preemption off. - * Start by checking for critical errors. - * Then fix up important state like USER_DS and preemption. - * Then do everything else. - */ - WARN_ON(blk_needs_flush_plug(tsk)); - if (unlikely(in_interrupt())) - panic("Aiee, killing interrupt handler!"); - if (unlikely(!tsk->pid)) - panic("Attempted to kill the idle task!"); - /* - * If do_exit is called because this processes oopsed, it's possible + * If do_dead is called because this processes oopsed, it's possible * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before * continuing. Amongst other possible reasons, this is to prevent * mm_release()->clear_child_tid() from writing to a user-controlled * kernel address. + * + * On uptodate architectures force_uaccess_begin is a noop. On + * architectures that still have set_fs/get_fs in addition to handling + * oopses handles kernel threads that run as set_fs(KERNEL_DS) by + * default. */ force_uaccess_begin(); - if (unlikely(in_atomic())) { - pr_info("note: %s[%d] exited with preempt_count %d\n", - current->comm, task_pid_nr(current), - preempt_count()); - preempt_count_set(PREEMPT_ENABLED); - } - - profile_task_exit(tsk); kcov_task_exit(tsk); coredump_task_exit(tsk); @@ -773,17 +758,6 @@ void __noreturn do_exit(long code) validate_creds_for_do_exit(tsk); - /* - * We're taking recursive faults here in do_exit. Safest is to just - * leave this task alone and wait for reboot. - */ - if (unlikely(tsk->flags & PF_EXITING)) { - pr_alert("Fixing recursive fault but reboot is needed!\n"); - futex_exit_recursive(tsk); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule(); - } - io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ @@ -882,16 +856,46 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } -EXPORT_SYMBOL_GPL(do_exit); -void complete_and_exit(struct completion *comp, long code) +void __noreturn make_task_dead(int signr) { - if (comp) - complete(comp); + /* + * Take the task off the cpu after something catastrophic has + * happened. + * + * We can get here from a kernel oops, sometimes with preemption off. + * Start by checking for critical errors. + * Then fix up important state like USER_DS and preemption. + * Then do everything else. + */ + struct task_struct *tsk = current; - do_exit(code); + if (unlikely(in_interrupt())) + panic("Aiee, killing interrupt handler!"); + if (unlikely(!tsk->pid)) + panic("Attempted to kill the idle task!"); + + if (unlikely(in_atomic())) { + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } + + /* + * We're taking recursive faults here in make_task_dead. Safest is to just + * leave this task alone and wait for reboot. + */ + if (unlikely(tsk->flags & PF_EXITING)) { + pr_alert("Fixing recursive fault but reboot is needed!\n"); + futex_exit_recursive(tsk); + tsk->exit_state = EXIT_DEAD; + refcount_inc(&tsk->rcu_users); + do_task_dead(); + } + + do_exit(signr); } -EXPORT_SYMBOL(complete_and_exit); SYSCALL_DEFINE1(exit, int, error_code) { @@ -907,17 +911,19 @@ do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; - BUG_ON(exit_code & 0x80); /* core dumps don't get here */ - - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else if (!thread_group_empty(current)) { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; @@ -1012,7 +1018,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { - status = p->exit_code; + status = (p->signal->flags & SIGNAL_GROUP_EXIT) + ? p->signal->group_exit_code : p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); diff --git a/kernel/fork.c b/kernel/fork.c index 1c989cc4208a..d75a528f7b21 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -757,9 +757,7 @@ void __put_task_struct(struct task_struct *tsk) delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); - - if (!profile_handoff_task(tsk)) - free_task(tsk); + free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); @@ -953,7 +951,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - tsk->pf_io_worker = NULL; + tsk->worker_private = NULL; account_kernel_stack(tsk, 1); @@ -2009,12 +2007,6 @@ static __latent_entropy struct task_struct *copy_process( siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } - /* - * This _must_ happen before we call free_task(), i.e. before we jump - * to any of the bad_fork_* labels. This is to avoid freeing - * p->set_child_tid which is (ab)used as a kthread's data pointer for - * kernel threads (PF_KTHREAD). - */ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? @@ -2095,12 +2087,16 @@ static __latent_entropy struct task_struct *copy_process( p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); + if (p->flags & PF_KTHREAD) { + if (!set_kthread_struct(p)) + goto bad_fork_cleanup_delayacct; + } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; - goto bad_fork_cleanup_threadgroup_lock; + goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS @@ -2437,8 +2433,8 @@ bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); -bad_fork_cleanup_threadgroup_lock: #endif +bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 926c2bb752bc..51dd822a8060 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1031,7 +1031,7 @@ static void futex_cleanup(struct task_struct *tsk) * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * - * This is called from the recursive fault handling path in do_exit(). + * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 5a5d192a89ac..68480f731192 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -81,7 +81,7 @@ int kexec_should_crash(struct task_struct *p) if (crash_kexec_post_notifiers) return 0; /* - * There are 4 panic() calls in do_exit() path, each of which + * There are 4 panic() calls in make_task_dead() path, each of which * corresponds to each of these 4 conditions. */ if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) diff --git a/kernel/kthread.c b/kernel/kthread.c index 4ed9e7bce9e8..a2c156ee8275 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -52,6 +52,7 @@ struct kthread_create_info struct kthread { unsigned long flags; unsigned int cpu; + int result; int (*threadfn)(void *); void *data; mm_segment_t oldfs; @@ -71,7 +72,7 @@ enum KTHREAD_BITS { static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); - return (__force void *)k->set_child_tid; + return k->worker_private; } /* @@ -79,7 +80,7 @@ static inline struct kthread *to_kthread(struct task_struct *k) * * Per construction; when: * - * (p->flags & PF_KTHREAD) && p->set_child_tid + * (p->flags & PF_KTHREAD) && p->worker_private * * the task is both a kthread and struct kthread is persistent. However * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and @@ -87,26 +88,29 @@ static inline struct kthread *to_kthread(struct task_struct *k) */ static inline struct kthread *__to_kthread(struct task_struct *p) { - void *kthread = (__force void *)p->set_child_tid; + void *kthread = p->worker_private; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; } -void set_kthread_struct(struct task_struct *p) +bool set_kthread_struct(struct task_struct *p) { struct kthread *kthread; - if (__to_kthread(p)) - return; + if (WARN_ON_ONCE(to_kthread(p))) + return false; kthread = kzalloc(sizeof(*kthread), GFP_KERNEL); - /* - * We abuse ->set_child_tid to avoid the new member and because it - * can't be wrongly copied by copy_process(). We also rely on fact - * that the caller can't exec, so PF_KTHREAD can't be cleared. - */ - p->set_child_tid = (__force void __user *)kthread; + if (!kthread) + return false; + + init_completion(&kthread->exited); + init_completion(&kthread->parked); + p->vfork_done = &kthread->exited; + + p->worker_private = kthread; + return true; } void free_kthread_struct(struct task_struct *k) @@ -114,13 +118,13 @@ void free_kthread_struct(struct task_struct *k) struct kthread *kthread; /* - * Can be NULL if this kthread was created by kernel_thread() - * or if kmalloc() in kthread() failed. + * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread && kthread->blkcg_css); #endif + k->worker_private = NULL; kfree(kthread); } @@ -268,6 +272,44 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +/** + * kthread_exit - Cause the current kthread return @result to kthread_stop(). + * @result: The integer value to return to kthread_stop(). + * + * While kthread_exit can be called directly, it exists so that + * functions which do some additional work in non-modular code such as + * module_put_and_kthread_exit can be implemented. + * + * Does not return. + */ +void __noreturn kthread_exit(long result) +{ + struct kthread *kthread = to_kthread(current); + kthread->result = result; + do_exit(0); +} + +/** + * kthread_complete_and_exit - Exit the current kthread. + * @comp: Completion to complete + * @code: The integer value to return to kthread_stop(). + * + * If present complete @comp and the reuturn code to kthread_stop(). + * + * A kernel thread whose module may be removed after the completion of + * @comp can use this function exit safely. + * + * Does not return. + */ +void __noreturn kthread_complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + kthread_exit(code); +} +EXPORT_SYMBOL(kthread_complete_and_exit); + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; @@ -279,27 +321,17 @@ static int kthread(void *_create) struct kthread *self; int ret; - set_kthread_struct(current); self = to_kthread(current); /* If user was SIGKILLed, I release the structure. */ done = xchg(&create->done, NULL); if (!done) { kfree(create); - do_exit(-EINTR); - } - - if (!self) { - create->result = ERR_PTR(-ENOMEM); - complete(done); - do_exit(-ENOMEM); + kthread_exit(-EINTR); } self->threadfn = threadfn; self->data = data; - init_completion(&self->exited); - init_completion(&self->parked); - current->vfork_done = &self->exited; /* * The new thread inherited kthreadd's priority and CPU mask. Reset @@ -326,7 +358,7 @@ static int kthread(void *_create) __kthread_parkme(self); ret = threadfn(data); } - do_exit(ret); + kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ @@ -628,7 +660,7 @@ EXPORT_SYMBOL_GPL(kthread_park); * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * - * If threadfn() may call do_exit() itself, the caller must ensure + * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() @@ -647,7 +679,7 @@ int kthread_stop(struct task_struct *k) kthread_unpark(k); wake_up_process(k); wait_for_completion(&kthread->exited); - ret = k->exit_code; + ret = kthread->result; put_task_struct(k); trace_sched_kthread_stop_ret(ret); diff --git a/kernel/module.c b/kernel/module.c index 24fc305afe95..1038c013d8b2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -337,12 +337,12 @@ static inline void add_taint_module(struct module *mod, unsigned flag, * A thread that wants to hold a reference to a module only while it * is running can call this to safely exit. nfsd and lockd use this. */ -void __noreturn __module_put_and_exit(struct module *mod, long code) +void __noreturn __module_put_and_kthread_exit(struct module *mod, long code) { module_put(mod); - do_exit(code); + kthread_exit(code); } -EXPORT_SYMBOL(__module_put_and_exit); +EXPORT_SYMBOL(__module_put_and_kthread_exit); /* Find a module section: 0 means not found. */ static unsigned int find_sec(const struct load_info *info, const char *name) diff --git a/kernel/profile.c b/kernel/profile.c index eb9c7f0f5ac5..37640a0bd8a3 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -133,79 +133,6 @@ int __ref profile_init(void) return -ENOMEM; } -/* Profile event notifications */ - -static BLOCKING_NOTIFIER_HEAD(task_exit_notifier); -static ATOMIC_NOTIFIER_HEAD(task_free_notifier); -static BLOCKING_NOTIFIER_HEAD(munmap_notifier); - -void profile_task_exit(struct task_struct *task) -{ - blocking_notifier_call_chain(&task_exit_notifier, 0, task); -} - -int profile_handoff_task(struct task_struct *task) -{ - int ret; - ret = atomic_notifier_call_chain(&task_free_notifier, 0, task); - return (ret == NOTIFY_OK) ? 1 : 0; -} - -void profile_munmap(unsigned long addr) -{ - blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr); -} - -int task_handoff_register(struct notifier_block *n) -{ - return atomic_notifier_chain_register(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_register); - -int task_handoff_unregister(struct notifier_block *n) -{ - return atomic_notifier_chain_unregister(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_unregister); - -int profile_event_register(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_register( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_register( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_register); - -int profile_event_unregister(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_unregister( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_unregister( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_unregister); - #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f8589bf8d7dc..eea265082e97 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -419,8 +419,6 @@ static int ptrace_attach(struct task_struct *task, long request, if (task->ptrace) goto unlock_tasklist; - if (seize) - flags |= PT_SEIZED; task->ptrace = flags; ptrace_link(task, current); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 83872f95a1ea..2e4ae00e52d1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8642,14 +8642,6 @@ void __init init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); - /* - * The idle task doesn't need the kthread struct to function, but it - * is dressed up as a per-CPU kthread and thus needs to play the part - * if we want to avoid special-casing it in code that deals with per-CPU - * kthreads. - */ - set_kthread_struct(idle); - raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_rq_lock(rq); @@ -9469,6 +9461,14 @@ void __init sched_init(void) enter_lazy_tlb(&init_mm, current); /* + * The idle task doesn't need the kthread struct to function, but it + * is dressed up as a per-CPU kthread and thus needs to play the part + * if we want to avoid special-casing it in code that deals with per-CPU + * kthreads. + */ + WARN_ON(!set_kthread_struct(current)); + + /* * Make us the idle thread. Technically, schedule() should not be * called from this thread, however somewhere below it might be, * but because we are the idle thread, we just pick up running again diff --git a/kernel/signal.c b/kernel/signal.c index dfcee3888b00..38602738866e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -626,7 +626,8 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, * * All callers have to hold the siglock. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info) +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type) { bool resched_timer = false; int signr; @@ -634,8 +635,10 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ + *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { + *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS @@ -903,8 +906,8 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) struct task_struct *t; sigset_t flush; - if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { - if (!(signal->flags & SIGNAL_GROUP_EXIT)) + if (signal->flags & SIGNAL_GROUP_EXIT) { + if (signal->core_state) return sig == SIGKILL; /* * The process is in the middle of dying, nothing to do. @@ -1029,7 +1032,7 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type) * then start taking the whole group down immediately. */ if (sig_fatal(p, sig) && - !(signal->flags & SIGNAL_GROUP_EXIT) && + (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || !p->ptrace)) { /* @@ -1820,6 +1823,7 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) * force_sig_seccomp - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland * @reason: filter-supplied reason code to send to userland (via si_errno) + * @force_coredump: true to trigger a coredump * * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. */ @@ -2383,7 +2387,8 @@ static bool do_signal_stop(int signr) WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || - unlikely(signal_group_exit(sig))) + unlikely(sig->flags & SIGNAL_GROUP_EXIT) || + unlikely(sig->group_exec_task)) return false; /* * There is no group stop already in progress. We must @@ -2544,7 +2549,7 @@ static void do_freezer_trap(void) freezable_schedule(); } -static int ptrace_signal(int signr, kernel_siginfo_t *info) +static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type) { /* * We do not check sig_kernel_stop(signr) but set this marker @@ -2584,8 +2589,9 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info) } /* If the (new) signal is now blocked, requeue it. */ - if (sigismember(¤t->blocked, signr)) { - send_signal(signr, info, current, PIDTYPE_PID); + if (sigismember(¤t->blocked, signr) || + fatal_signal_pending(current)) { + send_signal(signr, info, current, type); signr = 0; } @@ -2684,18 +2690,20 @@ relock: goto relock; } - /* Has this task already been marked for death? */ - if (signal_group_exit(signal)) { - ksig->info.si_signo = signr = SIGKILL; - sigdelset(¤t->pending.signal, SIGKILL); - trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, - &sighand->action[SIGKILL - 1]); - recalc_sigpending(); - goto fatal; - } - for (;;) { struct k_sigaction *ka; + enum pid_type type; + + /* Has this task already been marked for death? */ + if ((signal->flags & SIGNAL_GROUP_EXIT) || + signal->group_exec_task) { + ksig->info.si_signo = signr = SIGKILL; + sigdelset(¤t->pending.signal, SIGKILL); + trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, + &sighand->action[SIGKILL - 1]); + recalc_sigpending(); + goto fatal; + } if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && do_signal_stop(0)) @@ -2728,16 +2736,18 @@ relock: * so that the instruction pointer in the signal stack * frame points to the faulting instruction. */ + type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + signr = dequeue_signal(current, ¤t->blocked, + &ksig->info, &type); if (!signr) break; /* will return 0 */ if (unlikely(current->ptrace) && (signr != SIGKILL) && !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { - signr = ptrace_signal(signr, &ksig->info); + signr = ptrace_signal(signr, &ksig->info, type); if (!signr) continue; } @@ -2863,13 +2873,13 @@ out: } /** - * signal_delivered - + * signal_delivered - called after signal delivery to update blocked signals * @ksig: kernel signal struct * @stepping: nonzero if debugger single-step or block-step in use * * This function should be called when a signal has successfully been * delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask - * is always blocked, and the signal itself is blocked unless %SA_NODEFER + * is always blocked), and the signal itself is blocked unless %SA_NODEFER * is set in @ksig->ka.sa.sa_flags. Tracing is notified. */ static void signal_delivered(struct ksignal *ksig, int stepping) @@ -2942,7 +2952,7 @@ void exit_signals(struct task_struct *tsk) */ cgroup_threadgroup_change_begin(tsk); - if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { + if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; @@ -3562,6 +3572,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; sigset_t mask = *which; + enum pid_type type; int sig, ret = 0; if (ts) { @@ -3578,7 +3589,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested @@ -3597,7 +3608,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); diff --git a/kernel/tsacct.c b/kernel/tsacct.c index f00de83d0246..1d261fbe367b 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -38,11 +38,10 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); stats->ac_btime64 = btime; - if (thread_group_leader(tsk)) { + if (tsk->flags & PF_EXITING) stats->ac_exitcode = tsk->exit_code; - if (tsk->flags & PF_FORKNOEXEC) - stats->ac_flag |= AFORK; - } + if (thread_group_leader(tsk) && (tsk->flags & PF_FORKNOEXEC)) + stats->ac_flag |= AFORK; if (tsk->flags & PF_SUPERPRIV) stats->ac_flag |= ASU; if (tsk->flags & PF_DUMPCORE) diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index 0dd434e40487..be38a2c5ecc2 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -17,7 +17,7 @@ void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch) { try_catch->try_result = -EFAULT; - complete_and_exit(try_catch->try_completion, -EFAULT); + kthread_complete_and_exit(try_catch->try_completion, -EFAULT); } EXPORT_SYMBOL_GPL(kunit_try_catch_throw); @@ -27,7 +27,7 @@ static int kunit_generic_run_threadfn_adapter(void *data) try_catch->try(try_catch->context); - complete_and_exit(try_catch->try_completion, 0); + kthread_complete_and_exit(try_catch->try_completion, 0); } static unsigned long kunit_test_timeout(void) diff --git a/mm/mmap.c b/mm/mmap.c index 3f48d0928e6b..1e8fdb0b51ed 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2935,7 +2935,6 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); - profile_munmap(addr); return __vm_munmap(addr, len, true); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3934ff500878..832fb330376e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -793,7 +793,7 @@ static inline bool __task_will_free_mem(struct task_struct *task) * coredump_task_exit(), so the oom killer cannot assume that * the process will promptly exit and release memory. */ - if (sig->flags & SIGNAL_GROUP_COREDUMP) + if (sig->core_state) return false; if (sig->flags & SIGNAL_GROUP_EXIT) diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index c9add7753b9f..40baa6b7321a 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -535,7 +535,7 @@ static int bnep_session(void *arg) up_write(&bnep_session_sem); free_netdev(dev); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 83eb84e8e688..90d130588a3e 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -323,7 +323,7 @@ static int cmtp_session(void *arg) up_write(&cmtp_session_sem); kfree(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 80848dfc01db..5940744a8cd8 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -1305,7 +1305,7 @@ static int hidp_session_thread(void *arg) l2cap_unregister_user(session->conn, &session->user); hidp_session_put(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8c1931eab5f1..c2d2ab9a2861 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -168,14 +168,16 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", - "__module_put_and_exit", - "complete_and_exit", + "kthread_exit", + "make_task_dead", + "__module_put_and_kthread_exit", + "kthread_complete_and_exit", "__reiserfs_panic", "lbug_with_loc", "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_do_exit", + "rewind_stack_and_make_dead", "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", |