aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/misc/ibmasm/command.c
blob: 276d3fb68094a53d6815979688b89cd412e8b489 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185

/*
 * IBM ASM Service Processor Device Driver
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) IBM Corporation, 2004
 *
 * Author: Max Asböck <amax@us.ibm.com>
 *
 */

#include "ibmasm.h"
#include "lowlevel.h"

static void exec_next_command(struct service_processor *sp);

static atomic_t command_count = ATOMIC_INIT(0);

struct command *ibmasm_new_command(struct service_processor *sp, size_t buffer_size)
{
	struct command *cmd;

	if (buffer_size > IBMASM_CMD_MAX_BUFFER_SIZE)
		return NULL;

	cmd = kzalloc(sizeof(struct command), GFP_KERNEL);
	if (cmd == NULL)
		return NULL;


	cmd->buffer = kzalloc(buffer_size, GFP_KERNEL);
	if (cmd->buffer == NULL) {
		kfree(cmd);
		return NULL;
	}
	cmd->buffer_size = buffer_size;

	kref_init(&cmd->kref);
	cmd->lock = &sp->lock;

	cmd->status = IBMASM_CMD_PENDING;
	init_waitqueue_head(&cmd->wait);
	INIT_LIST_HEAD(&cmd->queue_node);

	atomic_inc(&command_count);
	dbg("command count: %d\n", atomic_read(&command_count));

	return cmd;
}

void ibmasm_free_command(struct kref *kref)
{
	struct command *cmd = to_command(kref);

	list_del(&cmd->queue_node);
	atomic_dec(&command_count);
	dbg("command count: %d\n", atomic_read(&command_count));
	kfree(cmd->buffer);
	kfree(cmd);
}

static void enqueue_command(struct service_processor *sp, struct command *cmd)
{
	list_add_tail(&cmd->queue_node, &sp->command_queue);
}

static struct command *dequeue_command(struct service_processor *sp)
{
	struct command *cmd;
	struct list_head *next;

	if (list_empty(&sp->command_queue))
		return NULL;

	next = sp->command_queue.next;
	list_del_init(next);
	cmd = list_entry(next, struct command, queue_node);

	return cmd;
}

static inline void do_exec_command(struct service_processor *sp)
{
	char tsbuf[32];

	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));

	if (ibmasm_send_i2o_message(sp)) {
		sp->current_command->status = IBMASM_CMD_FAILED;
		wake_up(&sp->current_command->wait);
		command_put(sp->current_command);
		exec_next_command(sp);
	}
}

/**
 * exec_command
 * send a command to a service processor
 * Commands are executed sequentially. One command (sp->current_command)
 * is sent to the service processor. Once the interrupt handler gets a
 * message of type command_response, the message is copied into
 * the current commands buffer,
 */
void ibmasm_exec_command(struct service_processor *sp, struct command *cmd)
{
	unsigned long flags;
	char tsbuf[32];

	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));

	spin_lock_irqsave(&sp->lock, flags);

	if (!sp->current_command) {
		sp->current_command = cmd;
		command_get(sp->current_command);
		spin_unlock_irqrestore(&sp->lock, flags);
		do_exec_command(sp);
	} else {
		enqueue_command(sp, cmd);
		spin_unlock_irqrestore(&sp->lock, flags);
	}
}

static void exec_next_command(struct service_processor *sp)
{
	unsigned long flags;
	char tsbuf[32];

	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));

	spin_lock_irqsave(&sp->lock, flags);
	sp->current_command = dequeue_command(sp);
	if (sp->current_command) {
		command_get(sp->current_command);
		spin_unlock_irqrestore(&sp->lock, flags);
		do_exec_command(sp);
	} else {
		spin_unlock_irqrestore(&sp->lock, flags);
	}
}

/**
 * Sleep until a command has failed or a response has been received
 * and the command status been updated by the interrupt handler.
 * (see receive_response).
 */
void ibmasm_wait_for_response(struct command *cmd, int timeout)
{
	wait_event_interruptible_timeout(cmd->wait,
				cmd->status == IBMASM_CMD_COMPLETE ||
				cmd->status == IBMASM_CMD_FAILED,
				timeout * HZ);
}

/**
 * receive_command_response
 * called by the interrupt handler when a dot command of type command_response
 * was received.
 */
void ibmasm_receive_command_response(struct service_processor *sp, void *response, size_t size)
{
	struct command *cmd = sp->current_command;

	if (!sp->current_command)
		return;

	memcpy_fromio(cmd->buffer, response, min(size, cmd->buffer_size));
	cmd->status = IBMASM_CMD_COMPLETE;
	wake_up(&sp->current_command->wait);
	command_put(sp->current_command);
	exec_next_command(sp);
}
>mm, with * task_lock() held. */ static struct task_struct *find_lock_task_mm(struct task_struct *p) { struct task_struct *t = p; do { task_lock(t); if (likely(t->mm)) return t; task_unlock(t); } while_each_thread(p, t); return NULL; } /** * badness - calculate a numeric value for how bad this task has been * @p: task struct of which task we should calculate * @uptime: current uptime in seconds * * The formula used is relatively simple and documented inline in the * function. The main rationale is that we want to select a good task * to kill when we run out of memory. * * Good in this context means that: * 1) we lose the minimum amount of work done * 2) we recover a large amount of memory * 3) we don't kill anything innocent of eating tons of memory * 4) we want to kill the minimum amount of processes (one) * 5) we try to kill the process the user expects us to kill, this * algorithm has been meticulously tuned to meet the principle * of least surprise ... (be careful when you change it) */ unsigned long badness(struct task_struct *p, unsigned long uptime) { unsigned long points, cpu_time, run_time; struct task_struct *child; struct task_struct *c, *t; 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; p = find_lock_task_mm(p); if (!p) return 0; /* * The memory size of the process is the basis for the badness. */ points = p->mm->total_vm; task_unlock(p); /* * swapoff can easily use up all memory, so kill those first. */ if (p->flags & PF_OOM_ORIGIN) return ULONG_MAX; /* * Processes which fork a lot of child processes are likely * a good choice. We add half the vmsize of the children if they * have an own mm. This prevents forking servers to flood the * machine with an endless amount of children. In case a single * child is eating the vast majority of memory, adding only half * to the parents will make the child our kill candidate of choice. */ t = p; do { list_for_each_entry(c, &t->children, sibling) { child = find_lock_task_mm(c); if (child) { if (child->mm != p->mm) points += child->mm->total_vm/2 + 1; task_unlock(child); } } } while_each_thread(p, t); /* * CPU time is in tens of seconds and run time is in thousands * of seconds. There is no particular reason for this other than * that it turned out to work very well in practice. */ 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; else run_time = 0; if (cpu_time) points /= int_sqrt(cpu_time); if (run_time) points /= int_sqrt(int_sqrt(run_time)); /* * Niced processes are most likely less important, so double * their badness points. */ if (task_nice(p) > 0) points *= 2; /* * Superuser processes are usually more important, so we make it * less likely that we kill those. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN) || has_capability_noaudit(p, CAP_SYS_RESOURCE)) points /= 4; /* * We don't want to kill a process with direct hardware access. * Not only could that mess up the hardware, but usually users * tend to only have this flag set on applications they think * of as important. */ if (has_capability_noaudit(p, CAP_SYS_RAWIO)) points /= 4; /* * Adjust the score by oom_adj. */ if (oom_adj) { if (oom_adj > 0) { if (!points) points = 1; points <<= oom_adj; } else points >>= -(oom_adj); } #ifdef DEBUG printk(KERN_DEBUG "OOMkill: task %d (%s) got %lu points\n", p->pid, p->comm, points); #endif return points; } /* * Determine the type of allocation constraint. */ #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); /* * 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; /* * 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; /* 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 * number of 'points'. We expect the caller will lock the tasklist. * * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned long *ppoints, struct mem_cgroup *mem, enum oom_constraint constraint, const nodemask_t *mask) { struct task_struct *p; struct task_struct *chosen = NULL; struct timespec uptime; *ppoints = 0; do_posix_clock_monotonic_gettime(&uptime); for_each_process(p) { unsigned long points; /* skip the init task and kthreads */ if (is_global_init(p) || (p->flags & PF_KTHREAD)) continue; if (mem && !task_in_mem_cgroup(p, mem)) continue; if (!has_intersects_mems_allowed(p, constraint == CONSTRAINT_MEMORY_POLICY ? mask : NULL)) continue; /* * This task already has access to memory reserves and is * being killed. Don't allow any other task access to the * memory reserve. * * Note: this may have a chance of deadlock if it gets * blocked waiting for another task which itself is waiting * for memory. Is there a better alternative? */ if (test_tsk_thread_flag(p, TIF_MEMDIE)) return ERR_PTR(-1UL); /* * This is in the process of releasing memory so wait for it * to finish before killing some other task by mistake. * * However, if p is the current task, we allow the 'kill' to * go ahead if it is exiting: this will simply set TIF_MEMDIE, * which will allow it to gain access to memory reserves in * the process of exiting and releasing its resources. * Otherwise we could get an easy OOM deadlock. */ if ((p->flags & PF_EXITING) && p->mm) { if (p != current) return ERR_PTR(-1UL); chosen = p; *ppoints = ULONG_MAX; } if (p->signal->oom_adj == OOM_DISABLE) continue; points = badness(p, uptime.tv_sec); if (points > *ppoints || !chosen) { chosen = p; *ppoints = points; } } return chosen; } /** * dump_tasks - dump current memory state of all system tasks * @mem: current's memory controller, if constrained * * Dumps the current memory state of all system tasks, excluding kernel threads. * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj * score, and name. * * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are * shown. * * Call with tasklist_lock read-locked. */ static void dump_tasks(const struct mem_cgroup *mem) { struct task_struct *p; struct task_struct *task; printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj " "name\n"); for_each_process(p) { if (p->flags & PF_KTHREAD) continue; if (mem && !task_in_mem_cgroup(p, mem)) continue; task = find_lock_task_mm(p); if (!task) { /* * This is a kthread or all of p's threads have already * detached their mm's. There's no need to report * them; they can't be oom killed anyway. */ continue; } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3u %3d %s\n", task->pid, __task_cred(task)->uid, task->tgid, task->mm->total_vm, get_mm_rss(task->mm), task_cpu(task), task->signal->oom_adj, task->comm); task_unlock(task); } } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, struct mem_cgroup *mem) { task_lock(current); 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); 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 * set. */ static void __oom_kill_task(struct task_struct *p, int verbose) { if (is_global_init(p)) { WARN_ON(1); printk(KERN_WARNING "tried to kill init!\n"); return; } p = find_lock_task_mm(p); if (!p) return; if (verbose) 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 * all the memory it needs. That way it should be able to * exit() and clear out its resources quickly... */ p->rt.time_slice = HZ; set_tsk_thread_flag(p, TIF_MEMDIE); force_sig(SIGKILL, p); } static int oom_kill_task(struct task_struct *p) { /* 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. * * Furthermore, even if mm contains a non-NULL value, p->mm may * change to NULL at any time since we do not hold task_lock(p). * However, this is of no concern to us. */ if (!p->mm || p->signal->oom_adj == OOM_DISABLE) return 1; __oom_kill_task(p, 1); return 0; } static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned long points, struct mem_cgroup *mem, const char *message) { struct task_struct *victim = p; struct task_struct *child; struct task_struct *t = p; unsigned long victim_points = 0; struct timespec uptime; if (printk_ratelimit()) dump_header(p, gfp_mask, order, mem); /* * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); return 0; } task_lock(p); pr_err("%s: Kill process %d (%s) score %lu or sacrifice child\n", message, task_pid_nr(p), p->comm, points); task_unlock(p); /* * If any of p's children has a different mm and is eligible for kill, * the one with the highest badness() score is sacrificed for its * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ do_posix_clock_monotonic_gettime(&uptime); do { list_for_each_entry(child, &t->children, sibling) { unsigned long child_points; if (child->mm == p->mm) continue; if (mem && !task_in_mem_cgroup(child, mem)) continue; /* badness() returns 0 if the thread is unkillable */ child_points = badness(child, uptime.tv_sec); if (child_points > victim_points) { victim = child; victim_points = child_points; } } } while_each_thread(p, t); return oom_kill_task(victim); } #ifdef CONFIG_CGROUP_MEM_RES_CTLR 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, CONSTRAINT_NONE, NULL); if (!p || PTR_ERR(p) == -1UL) goto out; if (oom_kill_process(p, gfp_mask, 0, points, mem, "Memory cgroup out of memory")) goto retry; out: read_unlock(&tasklist_lock); } #endif static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&oom_notify_list, nb); } EXPORT_SYMBOL_GPL(register_oom_notifier); int unregister_oom_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&oom_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_oom_notifier); /* * Try to acquire the OOM killer lock for the zones in zonelist. Returns zero * if a parallel OOM killing is already taking place that includes a zone in * the zonelist. Otherwise, locks all zones in the zonelist and returns 1. */ int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask) { struct zoneref *z; struct zone *zone; int ret = 1; spin_lock(&zone_scan_lock); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { if (zone_is_oom_locked(zone)) { ret = 0; goto out; } } for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { /* * Lock each zone in the zonelist under zone_scan_lock so a * parallel invocation of try_set_zone_oom() doesn't succeed * when it shouldn't. */ zone_set_flag(zone, ZONE_OOM_LOCKED); } out: spin_unlock(&zone_scan_lock); return ret; } /* * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed * allocation attempts with zonelists containing them may now recall the OOM * killer, if necessary. */ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask) { struct zoneref *z; struct zone *zone; spin_lock(&zone_scan_lock); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) { zone_clear_flag(zone, ZONE_OOM_LOCKED); } spin_unlock(&zone_scan_lock); } /* * Must be called with tasklist_lock held for read. */ static void __out_of_memory(gfp_t gfp_mask, int order, enum oom_constraint constraint, const nodemask_t *mask) { struct task_struct *p; unsigned long points; if (sysctl_oom_kill_allocating_task) if (!oom_kill_process(current, gfp_mask, order, 0, NULL, "Out of memory (oom_kill_allocating_task)")) return; retry: /* * Rambo mode: Shoot down a process and hope it solves whatever * issues we may have. */ p = select_bad_process(&points, NULL, constraint, mask); if (PTR_ERR(p) == -1UL) return; /* 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"); } if (oom_kill_process(p, gfp_mask, order, points, NULL, "Out of memory")) goto retry; } /* * pagefault handler calls into here because it is out of memory but * doesn't know exactly how or why. */ void pagefault_out_of_memory(void) { unsigned long freed = 0; blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0) /* Got some memory back in the last second. */ return; if (sysctl_panic_on_oom) panic("out of memory from page fault. panic_on_oom is selected.\n"); read_lock(&tasklist_lock); /* unknown gfp_mask and order */ __out_of_memory(0, 0, CONSTRAINT_NONE, NULL); read_unlock(&tasklist_lock); /* * Give "p" a good chance of killing itself before we * retry to allocate memory. */ if (!test_thread_flag(TIF_MEMDIE)) schedule_timeout_uninterruptible(1); } /** * out_of_memory - kill the "best" process when we run out of memory * @zonelist: zonelist pointer * @gfp_mask: memory allocation flags * @order: amount of memory being requested as a power of 2 * @nodemask: nodemask passed to page allocator * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) * 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, nodemask_t *nodemask) { unsigned long freed = 0; enum oom_constraint constraint; blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0) /* Got some memory back in the last second. */ return; /* * If current has a pending SIGKILL, then automatically select it. The * goal is to allow it to allocate so that it may quickly exit and free * its memory. */ if (fatal_signal_pending(current)) { set_thread_flag(TIF_MEMDIE); return; } 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, nodemask); read_lock(&tasklist_lock); if (unlikely(sysctl_panic_on_oom)) { /* * panic_on_oom only affects CONSTRAINT_NONE, the kernel * should not panic for cpuset or mempolicy induced memory * failures. */ if (constraint == CONSTRAINT_NONE) { dump_header(NULL, gfp_mask, order, NULL); read_unlock(&tasklist_lock); panic("Out of memory: panic_on_oom is enabled\n"); } } __out_of_memory(gfp_mask, order, constraint, nodemask); read_unlock(&tasklist_lock); /* * Give "p" a good chance of killing itself before we * retry to allocate memory unless "p" is current */ if (!test_thread_flag(TIF_MEMDIE)) schedule_timeout_uninterruptible(1); }