X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Foom_kill.c;h=709aedfaa014946664f2b83857b749d92f79752f;hb=26fd74fc01991a18f0e3bd54f8b1b75945ee3dbb;hp=a7b2460e922b779252ebcc225cecaf6060b0e964;hpb=6d2661ede5f20f968422e790af3334908c3bc857;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a7b2460..709aedf 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -34,6 +35,23 @@ int sysctl_oom_dump_tasks; static DEFINE_SPINLOCK(zone_scan_lock); /* #define DEBUG */ +/* + * Is all threads of the target process nodes overlap ours? + */ +static int has_intersects_mems_allowed(struct task_struct *tsk) +{ + struct task_struct *t; + + t = tsk; + do { + if (cpuset_mems_allowed_intersects(current, t)) + return 1; + t = next_thread(t); + } while (t != tsk); + + return 0; +} + /** * badness - calculate a numeric value for how bad this task has been * @p: task struct of which task we should calculate @@ -58,6 +76,13 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; + int oom_adj = p->signal->oom_adj; + struct task_cputime task_time; + unsigned long utime; + unsigned long stime; + + if (oom_adj == OOM_DISABLE) + return 0; task_lock(p); mm = p->mm; @@ -79,7 +104,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) /* * swapoff can easily use up all memory, so kill those first. */ - if (p->flags & PF_SWAPOFF) + if (p->flags & PF_OOM_ORIGIN) return ULONG_MAX; /* @@ -102,8 +127,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * of seconds. There is no particular reason for this other than * that it turned out to work very well in practice. */ - cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime)) - >> (SHIFT_HZ + 3); + thread_group_cputime(p, &task_time); + utime = cputime_to_jiffies(task_time.utime); + stime = cputime_to_jiffies(task_time.stime); + cpu_time = (utime + stime) >> (SHIFT_HZ + 3); + if (uptime >= p->start_time.tv_sec) run_time = (uptime - p->start_time.tv_sec) >> 10; @@ -144,19 +172,19 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * because p may have allocated or otherwise mapped memory on * this node before. However it will be less likely. */ - if (!cpuset_mems_allowed_intersects(current, p)) + if (!has_intersects_mems_allowed(p)) points /= 8; /* - * Adjust the score by oomkilladj. + * Adjust the score by oom_adj. */ - if (p->oomkilladj) { - if (p->oomkilladj > 0) { + if (oom_adj) { + if (oom_adj > 0) { if (!points) points = 1; - points <<= p->oomkilladj; + points <<= oom_adj; } else - points >>= -(p->oomkilladj); + points >>= -(oom_adj); } #ifdef DEBUG @@ -169,27 +197,46 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) /* * Determine the type of allocation constraint. */ -static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist, - gfp_t gfp_mask) -{ #ifdef CONFIG_NUMA +static enum oom_constraint constrained_alloc(struct zonelist *zonelist, + gfp_t gfp_mask, nodemask_t *nodemask) +{ struct zone *zone; struct zoneref *z; enum zone_type high_zoneidx = gfp_zone(gfp_mask); - nodemask_t nodes = node_states[N_HIGH_MEMORY]; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - if (cpuset_zone_allowed_softwall(zone, gfp_mask)) - node_clear(zone_to_nid(zone), nodes); - else - return CONSTRAINT_CPUSET; + /* + * Reach here only when __GFP_NOFAIL is used. So, we should avoid + * to kill current.We have to random task kill in this case. + * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now. + */ + if (gfp_mask & __GFP_THISNODE) + return CONSTRAINT_NONE; - if (!nodes_empty(nodes)) + /* + * The nodemask here is a nodemask passed to alloc_pages(). Now, + * cpuset doesn't use this nodemask for its hardwall/softwall/hierarchy + * feature. mempolicy is an only user of nodemask here. + * check mempolicy's nodemask contains all N_HIGH_MEMORY + */ + if (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask)) return CONSTRAINT_MEMORY_POLICY; -#endif + + /* Check this allocation failure is caused by cpuset's wall function */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + high_zoneidx, nodemask) + if (!cpuset_zone_allowed_softwall(zone, gfp_mask)) + return CONSTRAINT_CPUSET; return CONSTRAINT_NONE; } +#else +static enum oom_constraint constrained_alloc(struct zonelist *zonelist, + gfp_t gfp_mask, nodemask_t *nodemask) +{ + return CONSTRAINT_NONE; +} +#endif /* * Simple selection loop. We chose the process with the highest @@ -200,13 +247,13 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist, static struct task_struct *select_bad_process(unsigned long *ppoints, struct mem_cgroup *mem) { - struct task_struct *g, *p; + struct task_struct *p; struct task_struct *chosen = NULL; struct timespec uptime; *ppoints = 0; do_posix_clock_monotonic_gettime(&uptime); - do_each_thread(g, p) { + for_each_process(p) { unsigned long points; /* @@ -251,7 +298,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, *ppoints = ULONG_MAX; } - if (p->oomkilladj == OOM_DISABLE) + if (p->signal->oom_adj == OOM_DISABLE) continue; points = badness(p, uptime.tv_sec); @@ -259,7 +306,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, chosen = p; *ppoints = points; } - } while_each_thread(g, p); + } return chosen; } @@ -304,12 +351,30 @@ static void dump_tasks(const struct mem_cgroup *mem) } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, + get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj, p->comm); task_unlock(p); } while_each_thread(g, p); } +static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, + struct mem_cgroup *mem) +{ + pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, " + "oom_adj=%d\n", + current->comm, gfp_mask, order, current->signal->oom_adj); + task_lock(current); + cpuset_print_task_mems_allowed(current); + task_unlock(current); + dump_stack(); + mem_cgroup_print_oom_info(mem, p); + show_mem(); + if (sysctl_oom_dump_tasks) + dump_tasks(mem); +} + +#define K(x) ((x) << (PAGE_SHIFT-10)) + /* * Send SIGKILL to the selected process irrespective of CAP_SYS_RAW_IO * flag though it's unlikely that we select a process with CAP_SYS_RAW_IO @@ -323,15 +388,23 @@ static void __oom_kill_task(struct task_struct *p, int verbose) return; } + task_lock(p); if (!p->mm) { WARN_ON(1); - printk(KERN_WARNING "tried to kill an mm-less task!\n"); + printk(KERN_WARNING "tried to kill an mm-less task %d (%s)!\n", + task_pid_nr(p), p->comm); + task_unlock(p); return; } if (verbose) - printk(KERN_ERR "Killed process %d (%s)\n", - task_pid_nr(p), p->comm); + printk(KERN_ERR "Killed process %d (%s) " + "vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n", + task_pid_nr(p), p->comm, + K(p->mm->total_vm), + K(get_mm_counter(p->mm, MM_ANONPAGES)), + K(get_mm_counter(p->mm, MM_FILEPAGES))); + task_unlock(p); /* * We give our sacrificial lamb high priority and access to @@ -346,11 +419,6 @@ static void __oom_kill_task(struct task_struct *p, int verbose) static int oom_kill_task(struct task_struct *p) { - struct mm_struct *mm; - struct task_struct *g, *q; - - mm = p->mm; - /* WARNING: mm may not be dereferenced since we did not obtain its * value from get_task_mm(p). This is OK since all we need to do is * compare mm to q->mm below. @@ -359,30 +427,11 @@ static int oom_kill_task(struct task_struct *p) * change to NULL at any time since we do not hold task_lock(p). * However, this is of no concern to us. */ - - if (mm == NULL) + if (!p->mm || p->signal->oom_adj == OOM_DISABLE) return 1; - /* - * Don't kill the process if any threads are set to OOM_DISABLE - */ - do_each_thread(g, q) { - if (q->mm == mm && q->oomkilladj == OOM_DISABLE) - return 1; - } while_each_thread(g, q); - __oom_kill_task(p, 1); - /* - * kill all processes that share the ->mm (i.e. all threads), - * but are in a different thread group. Don't let them have access - * to memory reserves though, otherwise we might deplete all memory. - */ - do_each_thread(g, q) { - if (q->mm == mm && !same_thread_group(q, p)) - force_sig(SIGKILL, q); - } while_each_thread(g, q); - return 0; } @@ -392,19 +441,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, { struct task_struct *c; - if (printk_ratelimit()) { - printk(KERN_WARNING "%s invoked oom-killer: " - "gfp_mask=0x%x, order=%d, oomkilladj=%d\n", - current->comm, gfp_mask, order, current->oomkilladj); - task_lock(current); - cpuset_print_task_mems_allowed(current); - task_unlock(current); - dump_stack(); - mem_cgroup_print_oom_info(mem, current); - show_mem(); - if (sysctl_oom_dump_tasks) - dump_tasks(mem); - } + if (printk_ratelimit()) + dump_header(p, gfp_mask, order, mem); /* * If the task is already exiting, don't alarm the sysadmin or kill @@ -422,6 +460,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, list_for_each_entry(c, &p->children, sibling) { if (c->mm == p->mm) continue; + if (mem && !task_in_mem_cgroup(c, mem)) + continue; if (!oom_kill_task(c)) return 0; } @@ -434,15 +474,14 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) unsigned long points = 0; struct task_struct *p; + if (sysctl_panic_on_oom == 2) + panic("out of memory(memcg). panic_on_oom is selected.\n"); read_lock(&tasklist_lock); retry: p = select_bad_process(&points, mem); - if (PTR_ERR(p) == -1UL) + if (!p || PTR_ERR(p) == -1UL) goto out; - if (!p) - p = current; - if (oom_kill_process(p, gfp_mask, 0, points, mem, "Memory cgroup out of memory")) goto retry; @@ -540,6 +579,7 @@ retry: /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { read_unlock(&tasklist_lock); + dump_header(NULL, gfp_mask, order, NULL); panic("Out of memory and no killable processes...\n"); } @@ -561,13 +601,6 @@ void pagefault_out_of_memory(void) /* Got some memory back in the last second. */ return; - /* - * If this is from memcg, oom-killer is already invoked. - * and not worth to go system-wide-oom. - */ - if (mem_cgroup_oom_called(current)) - goto rest_and_return; - if (sysctl_panic_on_oom) panic("out of memory from page fault. panic_on_oom is selected.\n"); @@ -579,7 +612,6 @@ void pagefault_out_of_memory(void) * Give "p" a good chance of killing itself before we * retry to allocate memory. */ -rest_and_return: if (!test_thread_flag(TIF_MEMDIE)) schedule_timeout_uninterruptible(1); } @@ -595,7 +627,8 @@ rest_and_return: * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) +void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, + int order, nodemask_t *nodemask) { unsigned long freed = 0; enum oom_constraint constraint; @@ -605,14 +638,16 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) /* Got some memory back in the last second. */ return; - if (sysctl_panic_on_oom == 2) + if (sysctl_panic_on_oom == 2) { + dump_header(NULL, gfp_mask, order, NULL); panic("out of memory. Compulsory panic_on_oom is selected.\n"); + } /* * Check if there were limitations on the allocation (only relevant for * NUMA) that may require different handling. */ - constraint = constrained_alloc(zonelist, gfp_mask); + constraint = constrained_alloc(zonelist, gfp_mask, nodemask); read_lock(&tasklist_lock); switch (constraint) { @@ -622,8 +657,10 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) break; case CONSTRAINT_NONE: - if (sysctl_panic_on_oom) + if (sysctl_panic_on_oom) { + dump_header(NULL, gfp_mask, order, NULL); panic("out of memory. panic_on_oom is selected\n"); + } /* Fall-through */ case CONSTRAINT_CPUSET: __out_of_memory(gfp_mask, order);