diff options
Diffstat (limited to 'arch/s390/mm/fault.c')
| -rw-r--r-- | arch/s390/mm/fault.c | 80 |
1 files changed, 51 insertions, 29 deletions
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index cce577feab1e..661d9fe63c43 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -24,7 +24,7 @@ #include <linux/kdebug.h> #include <linux/init.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/uaccess.h> @@ -250,6 +250,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code) report_user_fault(regs, SIGSEGV, 1); si.si_signo = SIGSEGV; + si.si_errno = 0; si.si_code = si_code; si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK); force_sig_info(SIGSEGV, &si, current); @@ -417,6 +418,8 @@ static inline int do_exception(struct pt_regs *regs, int access) (struct gmap *) S390_lowcore.gmap : NULL; if (gmap) { current->thread.gmap_addr = address; + current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE); + current->thread.gmap_int_code = regs->int_code & 0xffff; address = __gmap_translate(gmap, address); if (address == -EFAULT) { fault = VM_FAULT_BADMAP; @@ -455,7 +458,7 @@ retry: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); /* No reason to continue if interrupted by SIGKILL. */ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { fault = VM_FAULT_SIGNAL; @@ -623,7 +626,7 @@ void pfault_fini(void) diag_stat_inc(DIAG_STAT_X258); asm volatile( " diag %0,0,0x258\n" - "0:\n" + "0: nopr %%r7\n" EX_TABLE(0b,0b) : : "a" (&refbk), "m" (refbk) : "cc"); } @@ -631,6 +634,29 @@ void pfault_fini(void) static DEFINE_SPINLOCK(pfault_lock); static LIST_HEAD(pfault_list); +#define PF_COMPLETE 0x0080 + +/* + * The mechanism of our pfault code: if Linux is running as guest, runs a user + * space process and the user space process accesses a page that the host has + * paged out we get a pfault interrupt. + * + * This allows us, within the guest, to schedule a different process. Without + * this mechanism the host would have to suspend the whole virtual cpu until + * the page has been paged in. + * + * So when we get such an interrupt then we set the state of the current task + * to uninterruptible and also set the need_resched flag. Both happens within + * interrupt context(!). If we later on want to return to user space we + * recognize the need_resched flag and then call schedule(). It's not very + * obvious how this works... + * + * Of course we have a lot of additional fun with the completion interrupt (-> + * host signals that a page of a process has been paged in and the process can + * continue to run). This interrupt can arrive on any cpu and, since we have + * virtual cpus, actually appear before the interrupt that signals that a page + * is missing. + */ static void pfault_interrupt(struct ext_code ext_code, unsigned int param32, unsigned long param64) { @@ -639,10 +665,9 @@ static void pfault_interrupt(struct ext_code ext_code, pid_t pid; /* - * Get the external interruption subcode & pfault - * initial/completion signal bit. VM stores this - * in the 'cpu address' field associated with the - * external interrupt. + * Get the external interruption subcode & pfault initial/completion + * signal bit. VM stores this in the 'cpu address' field associated + * with the external interrupt. */ subcode = ext_code.subcode; if ((subcode & 0xff00) != __SUBCODE_MASK) @@ -658,7 +683,7 @@ static void pfault_interrupt(struct ext_code ext_code, if (!tsk) return; spin_lock(&pfault_lock); - if (subcode & 0x0080) { + if (subcode & PF_COMPLETE) { /* signal bit is set -> a page has been swapped in by VM */ if (tsk->thread.pfault_wait == 1) { /* Initial interrupt was faster than the completion @@ -687,8 +712,7 @@ static void pfault_interrupt(struct ext_code ext_code, goto out; if (tsk->thread.pfault_wait == 1) { /* Already on the list with a reference: put to sleep */ - __set_task_state(tsk, TASK_UNINTERRUPTIBLE); - set_tsk_need_resched(tsk); + goto block; } else if (tsk->thread.pfault_wait == -1) { /* Completion interrupt was faster than the initial * interrupt (pfault_wait == -1). Set pfault_wait @@ -703,7 +727,11 @@ static void pfault_interrupt(struct ext_code ext_code, get_task_struct(tsk); tsk->thread.pfault_wait = 1; list_add(&tsk->thread.list, &pfault_list); - __set_task_state(tsk, TASK_UNINTERRUPTIBLE); +block: + /* Since this must be a userspace fault, there + * is no kernel task state to trample. Rely on the + * return to userspace schedule() to block. */ + __set_current_state(TASK_UNINTERRUPTIBLE); set_tsk_need_resched(tsk); } } @@ -712,28 +740,21 @@ out: put_task_struct(tsk); } -static int pfault_cpu_notify(struct notifier_block *self, unsigned long action, - void *hcpu) +static int pfault_cpu_dead(unsigned int cpu) { struct thread_struct *thread, *next; struct task_struct *tsk; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DEAD: - spin_lock_irq(&pfault_lock); - list_for_each_entry_safe(thread, next, &pfault_list, list) { - thread->pfault_wait = 0; - list_del(&thread->list); - tsk = container_of(thread, struct task_struct, thread); - wake_up_process(tsk); - put_task_struct(tsk); - } - spin_unlock_irq(&pfault_lock); - break; - default: - break; + spin_lock_irq(&pfault_lock); + list_for_each_entry_safe(thread, next, &pfault_list, list) { + thread->pfault_wait = 0; + list_del(&thread->list); + tsk = container_of(thread, struct task_struct, thread); + wake_up_process(tsk); + put_task_struct(tsk); } - return NOTIFY_OK; + spin_unlock_irq(&pfault_lock); + return 0; } static int __init pfault_irq_init(void) @@ -747,7 +768,8 @@ static int __init pfault_irq_init(void) if (rc) goto out_pfault; irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); - hotcpu_notifier(pfault_cpu_notify, 0); + cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead", + NULL, pfault_cpu_dead); return 0; out_pfault: |