aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/tc/tc.c
blob: e5bd4470a570a4d45fcd7ef97d6a93c0a90aa601 (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
186
187
188
189
190
191
192
193
/*
 *	TURBOchannel bus services.
 *
 *	Copyright (c) Harald Koerfgen, 1998
 *	Copyright (c) 2001, 2003, 2005, 2006  Maciej W. Rozycki
 *	Copyright (c) 2005  James Simmons
 *
 *	This file is subject to the terms and conditions of the GNU
 *	General Public License.  See the file "COPYING" in the main
 *	directory of this archive for more details.
 */
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/tc.h>
#include <linux/types.h>

#include <asm/io.h>

static struct tc_bus tc_bus = {
	.name = "TURBOchannel",
};

/*
 * Probing for TURBOchannel modules.
 */
static void __init tc_bus_add_devices(struct tc_bus *tbus)
{
	resource_size_t slotsize = tbus->info.slot_size << 20;
	resource_size_t extslotsize = tbus->ext_slot_size;
	resource_size_t slotaddr;
	resource_size_t extslotaddr;
	resource_size_t devsize;
	void __iomem *module;
	struct tc_dev *tdev;
	int i, slot, err;
	u8 pattern[4];
	long offset;

	for (slot = 0; slot < tbus->num_tcslots; slot++) {
		slotaddr = tbus->slot_base + slot * slotsize;
		extslotaddr = tbus->ext_slot_base + slot * extslotsize;
		module = ioremap_nocache(slotaddr, slotsize);
		BUG_ON(!module);

		offset = TC_OLDCARD;

		err = 0;
		err |= tc_preadb(pattern + 0, module + offset + TC_PATTERN0);
		err |= tc_preadb(pattern + 1, module + offset + TC_PATTERN1);
		err |= tc_preadb(pattern + 2, module + offset + TC_PATTERN2);
		err |= tc_preadb(pattern + 3, module + offset + TC_PATTERN3);
		if (err)
			goto out_err;

		if (pattern[0] != 0x55 || pattern[1] != 0x00 ||
		    pattern[2] != 0xaa || pattern[3] != 0xff) {
			offset = TC_NEWCARD;

			err = 0;
			err |= tc_preadb(pattern + 0,
					 module + offset + TC_PATTERN0);
			err |= tc_preadb(pattern + 1,
					 module + offset + TC_PATTERN1);
			err |= tc_preadb(pattern + 2,
					 module + offset + TC_PATTERN2);
			err |= tc_preadb(pattern + 3,
					 module + offset + TC_PATTERN3);
			if (err)
				goto out_err;
		}

		if (pattern[0] != 0x55 || pattern[1] != 0x00 ||
		    pattern[2] != 0xaa || pattern[3] != 0xff)
			goto out_err;

		/* Found a board, allocate it an entry in the list */
		tdev = kzalloc(sizeof(*tdev), GFP_KERNEL);
		if (!tdev) {
			printk(KERN_ERR "tc%x: unable to allocate tc_dev\n",
			       slot);
			goto out_err;
		}
		dev_set_name(&tdev->dev, "tc%x", slot);
		tdev->bus = tbus;
		tdev->dev.parent = &tbus->dev;
		tdev->dev.bus = &tc_bus_type;
		tdev->slot = slot;

		for (i = 0; i < 8; i++) {
			tdev->firmware[i] =
				readb(module + offset + TC_FIRM_VER + 4 * i);
			tdev->vendor[i] =
				readb(module + offset + TC_VENDOR + 4 * i);
			tdev->name[i] =
				readb(module + offset + TC_MODULE + 4 * i);
		}
		tdev->firmware[8] = 0;
		tdev->vendor[8] = 0;
		tdev->name[8] = 0;

		pr_info("%s: %s %s %s\n", dev_name(&tdev->dev), tdev->vendor,
			tdev->name, tdev->firmware);

		devsize = readb(module + offset + TC_SLOT_SIZE);
		devsize <<= 22;
		if (devsize <= slotsize) {
			tdev->resource.start = slotaddr;
			tdev->resource.end = slotaddr + devsize - 1;
		} else if (devsize <= extslotsize) {
			tdev->resource.start = extslotaddr;
			tdev->resource.end = extslotaddr + devsize - 1;
		} else {
			printk(KERN_ERR "%s: Cannot provide slot space "
			       "(%dMiB required, up to %dMiB supported)\n",
			       dev_name(&tdev->dev), devsize >> 20,
			       max(slotsize, extslotsize) >> 20);
			kfree(tdev);
			goto out_err;
		}
		tdev->resource.name = tdev->name;
		tdev->resource.flags = IORESOURCE_MEM;

		tc_device_get_irq(tdev);

		device_register(&tdev->dev);
		list_add_tail(&tdev->node, &tbus->devices);

out_err:
		iounmap(module);
	}
}

/*
 * The main entry.
 */
static int __init tc_init(void)
{
	/* Initialize the TURBOchannel bus */
	if (tc_bus_get_info(&tc_bus))
		return 0;

	INIT_LIST_HEAD(&tc_bus.devices);
	dev_set_name(&tc_bus.dev, "tc");
	device_register(&tc_bus.dev);

	if (tc_bus.info.slot_size) {
		unsigned int tc_clock = tc_get_speed(&tc_bus) / 100000;

		pr_info("tc: TURBOchannel rev. %d at %d.%d MHz "
			"(with%s parity)\n", tc_bus.info.revision,
			tc_clock / 10, tc_clock % 10,
			tc_bus.info.parity ? "" : "out");

		tc_bus.resource[0].start = tc_bus.slot_base;
		tc_bus.resource[0].end = tc_bus.slot_base +
					 (tc_bus.info.slot_size << 20) *
					 tc_bus.num_tcslots - 1;
		tc_bus.resource[0].name = tc_bus.name;
		tc_bus.resource[0].flags = IORESOURCE_MEM;
		if (request_resource(&iomem_resource,
				     &tc_bus.resource[0]) < 0) {
			printk(KERN_ERR "tc: Cannot reserve resource\n");
			return 0;
		}
		if (tc_bus.ext_slot_size) {
			tc_bus.resource[1].start = tc_bus.ext_slot_base;
			tc_bus.resource[1].end = tc_bus.ext_slot_base +
						 tc_bus.ext_slot_size *
						 tc_bus.num_tcslots - 1;
			tc_bus.resource[1].name = tc_bus.name;
			tc_bus.resource[1].flags = IORESOURCE_MEM;
			if (request_resource(&iomem_resource,
					     &tc_bus.resource[1]) < 0) {
				printk(KERN_ERR
				       "tc: Cannot reserve resource\n");
				release_resource(&tc_bus.resource[0]);
				return 0;
			}
		}

		tc_bus_add_devices(&tc_bus);
	}

	return 0;
}

subsys_initcall(tc_init);
t">; if (adj == OOM_SCORE_ADJ_MIN) { task_unlock(p); return 0; } /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); /* * Root processes get 3% bonus, just like the __vm_enough_memory() * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) points -= (points * 3) / 100; /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; points += adj; /* * Never return 0 for an eligible task regardless of the root bonus and * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). */ return points > 0 ? points : 1; } /* * 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, unsigned long *totalpages) { struct zone *zone; struct zoneref *z; enum zone_type high_zoneidx = gfp_zone(gfp_mask); bool cpuset_limited = false; int nid; /* Default to all available memory */ *totalpages = totalram_pages + total_swap_pages; if (!zonelist) return CONSTRAINT_NONE; /* * 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; /* * This is not a __GFP_THISNODE allocation, so a truncated nodemask in * the page allocator means a mempolicy is in effect. Cpuset policy * is enforced in get_page_from_freelist(). */ if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) { *totalpages = total_swap_pages; for_each_node_mask(nid, *nodemask) *totalpages += node_spanned_pages(nid); 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)) cpuset_limited = true; if (cpuset_limited) { *totalpages = total_swap_pages; for_each_node_mask(nid, cpuset_current_mems_allowed) *totalpages += node_spanned_pages(nid); return CONSTRAINT_CPUSET; } return CONSTRAINT_NONE; } #else static enum oom_constraint constrained_alloc(struct zonelist *zonelist, gfp_t gfp_mask, nodemask_t *nodemask, unsigned long *totalpages) { *totalpages = totalram_pages + total_swap_pages; return CONSTRAINT_NONE; } #endif enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill) { if (oom_unkillable_task(task, NULL, nodemask)) return OOM_SCAN_CONTINUE; /* * This task already has access to memory reserves and is being killed. * Don't allow any other task to have access to the reserves. */ if (test_tsk_thread_flag(task, TIF_MEMDIE)) { if (unlikely(frozen(task))) __thaw_task(task); if (!force_kill) return OOM_SCAN_ABORT; } if (!task->mm) return OOM_SCAN_CONTINUE; /* * If task is allocating a lot of memory and has been marked to be * killed first if it triggers an oom, then select it. */ if (oom_task_origin(task)) return OOM_SCAN_SELECT; if (task->flags & PF_EXITING && !force_kill) { /* * If this task is not being ptraced on exit, then wait for it * to finish before killing some other task unnecessarily. */ if (!(task->group_leader->ptrace & PT_TRACE_EXIT)) return OOM_SCAN_ABORT; } return OOM_SCAN_OK; } /* * Simple selection loop. We chose the process with the highest * number of 'points'. Returns -1 on scan abort. * * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned int *ppoints, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill) { struct task_struct *g, *p; struct task_struct *chosen = NULL; unsigned long chosen_points = 0; rcu_read_lock(); for_each_process_thread(g, p) { unsigned int points; switch (oom_scan_process_thread(p, totalpages, nodemask, force_kill)) { case OOM_SCAN_SELECT: chosen = p; chosen_points = ULONG_MAX; /* fall through */ case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: rcu_read_unlock(); return (struct task_struct *)(-1UL); case OOM_SCAN_OK: break; }; points = oom_badness(p, NULL, nodemask, totalpages); if (!points || points < chosen_points) continue; /* Prefer thread group leaders for display purposes */ if (points == chosen_points && thread_group_leader(chosen)) continue; chosen = p; chosen_points = points; } if (chosen) get_task_struct(chosen); rcu_read_unlock(); *ppoints = chosen_points * 1000 / totalpages; return chosen; } /** * dump_tasks - dump current memory state of all system tasks * @memcg: current's memory controller, if constrained * @nodemask: nodemask passed to page allocator for mempolicy ooms * * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes * are not shown. * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes, * swapents, oom_score_adj value, and name. */ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask) { struct task_struct *p; struct task_struct *task; pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) 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; } pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), atomic_long_read(&task->mm->nr_ptes), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); } rcu_read_unlock(); } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, struct mem_cgroup *memcg, const nodemask_t *nodemask) { task_lock(current); pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, " "oom_score_adj=%hd\n", current->comm, gfp_mask, order, current->signal->oom_score_adj); cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); if (memcg) mem_cgroup_print_oom_info(memcg, p); else show_mem(SHOW_MEM_FILTER_NODES); if (sysctl_oom_dump_tasks) dump_tasks(memcg, nodemask); } #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon * returning. */ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, const char *message) { struct task_struct *victim = p; struct task_struct *child; struct task_struct *t; struct mm_struct *mm; unsigned int victim_points = 0; static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); /* * 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); put_task_struct(p); return; } if (__ratelimit(&oom_rs)) dump_header(p, gfp_mask, order, memcg, nodemask); task_lock(p); pr_err("%s: Kill process %d (%s) score %d 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 oom_badness() score is sacrificed for its * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ read_lock(&tasklist_lock); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; if (child->mm == p->mm) continue; /* * oom_badness() returns 0 if the thread is unkillable */ child_points = oom_badness(child, memcg, nodemask, totalpages); if (child_points > victim_points) { put_task_struct(victim); victim = child; victim_points = child_points; get_task_struct(victim); } } } read_unlock(&tasklist_lock); p = find_lock_task_mm(victim); if (!p) { put_task_struct(victim); return; } else if (victim != p) { get_task_struct(p); put_task_struct(victim); victim = p; } /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), K(get_mm_counter(victim->mm, MM_FILEPAGES))); task_unlock(victim); /* * Kill all user processes sharing victim->mm in other thread groups, if * any. They don't get access to memory reserves, though, to avoid * depletion of all memory. This prevents mm->mmap_sem livelock when an * oom killed thread cannot exit because it requires the semaphore and * its contended by another thread trying to allocate memory itself. * That thread will now get access to memory reserves since it has a * pending fatal signal. */ rcu_read_lock(); for_each_process(p) if (p->mm == mm && !same_thread_group(p, victim) && !(p->flags & PF_KTHREAD)) { if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) continue; task_lock(p); /* Protect ->comm from prctl() */ pr_err("Kill process %d (%s) sharing same memory\n", task_pid_nr(p), p->comm); task_unlock(p); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); } rcu_read_unlock(); set_tsk_thread_flag(victim, TIF_MEMDIE); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); put_task_struct(victim); } #undef K /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, int order, const nodemask_t *nodemask) { if (likely(!sysctl_panic_on_oom)) return; if (sysctl_panic_on_oom != 2) { /* * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel * does not panic for cpuset, mempolicy, or memcg allocation * failures. */ if (constraint != CONSTRAINT_NONE) return; } dump_header(NULL, gfp_mask, order, NULL, nodemask); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } 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. */ bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask) { struct zoneref *z; struct zone *zone; bool ret = true; spin_lock(&zone_scan_lock); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) if (zone_is_oom_locked(zone)) { ret = false; goto out; } /* * Lock each zone in the zonelist under zone_scan_lock so a parallel * call to oom_zonelist_trylock() doesn't succeed when it shouldn't. */ for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) 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 oom_zonelist_unlock(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); } /** * 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 * @force_kill: true if a task must be killed, even if others are exiting * * 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, bool force_kill) { const nodemask_t *mpol_mask; struct task_struct *p; unsigned long totalpages; unsigned long freed = 0; unsigned int uninitialized_var(points); enum oom_constraint constraint = CONSTRAINT_NONE; int killed = 0; 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 or is exiting, 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) || current->flags & PF_EXITING) { set_thread_flag(TIF_MEMDIE); return; } /* * Check if there were limitations on the allocation (only relevant for * NUMA) that may require different handling. */ constraint = constrained_alloc(zonelist, gfp_mask, nodemask, &totalpages); mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, nodemask) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, nodemask, "Out of memory (oom_kill_allocating_task)"); goto out; } p = select_bad_process(&points, totalpages, mpol_mask, force_kill); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); panic("Out of memory and no killable processes...\n"); } if (p != (void *)-1UL) { oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, nodemask, "Out of memory"); killed = 1; } out: /* * Give the killed threads a good chance of exiting before trying to * allocate memory again. */ if (killed) schedule_timeout_killable(1); } /* * The pagefault handler calls here because it is out of memory, so kill a * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a * parallel oom killing is already in progress so do nothing. */ void pagefault_out_of_memory(void) { struct zonelist *zonelist; if (mem_cgroup_oom_synchronize(true)) return; zonelist = node_zonelist(first_memory_node, GFP_KERNEL); if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) { out_of_memory(NULL, 0, 0, NULL, false); oom_zonelist_unlock(zonelist, GFP_KERNEL); } }