aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/timeconst.pl
blob: 41468035473ccbb943495466159173058862d6f0 (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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
#!/usr/bin/perl
# -----------------------------------------------------------------------
#
#   Copyright 2007 rPath, Inc. - All Rights Reserved
#
#   This file is part of the Linux kernel, and is made available under
#   the terms of the GNU General Public License version 2 or (at your
#   option) any later version; incorporated herein by reference.
#
# -----------------------------------------------------------------------
#

#
# Usage: timeconst.pl HZ > timeconst.h
#

# Precomputed values for systems without Math::BigInt
# Generated by:
# timeconst.pl --can 24 32 48 64 100 122 128 200 250 256 300 512 1000 1024 1200
%canned_values = (
	24 => [
		'0xa6aaaaab','0x2aaaaaa',26,
		'0xa6aaaaaaaaaaaaab','0x2aaaaaaaaaaaaaa',58,
		125,3,
		'0xc49ba5e4','0x1fbe76c8b4',37,
		'0xc49ba5e353f7ceda','0x1fbe76c8b439581062',69,
		3,125,
		'0xa2c2aaab','0xaaaa',16,
		'0xa2c2aaaaaaaaaaab','0xaaaaaaaaaaaa',48,
		125000,3,
		'0xc9539b89','0x7fffbce4217d',47,
		'0xc9539b8887229e91','0x7fffbce4217d2849cb25',79,
		3,125000,
	], 32 => [
		'0xfa000000','0x6000000',27,
		'0xfa00000000000000','0x600000000000000',59,
		125,4,
		'0x83126e98','0xfdf3b645a',36,
		'0x83126e978d4fdf3c','0xfdf3b645a1cac0831',68,
		4,125,
		'0xf4240000','0x0',17,
		'0xf424000000000000','0x0',49,
		31250,1,
		'0x8637bd06','0x3fff79c842fa',46,
		'0x8637bd05af6c69b6','0x3fff79c842fa5093964a',78,
		1,31250,
	], 48 => [
		'0xa6aaaaab','0x6aaaaaa',27,
		'0xa6aaaaaaaaaaaaab','0x6aaaaaaaaaaaaaa',59,
		125,6,
		'0xc49ba5e4','0xfdf3b645a',36,
		'0xc49ba5e353f7ceda','0xfdf3b645a1cac0831',68,
		6,125,
		'0xa2c2aaab','0x15555',17,
		'0xa2c2aaaaaaaaaaab','0x1555555555555',49,
		62500,3,
		'0xc9539b89','0x3fffbce4217d',46,
		'0xc9539b8887229e91','0x3fffbce4217d2849cb25',78,
		3,62500,
	], 64 => [
		'0xfa000000','0xe000000',28,
		'0xfa00000000000000','0xe00000000000000',60,
		125,8,
		'0x83126e98','0x7ef9db22d',35,
		'0x83126e978d4fdf3c','0x7ef9db22d0e560418',67,
		8,125,
		'0xf4240000','0x0',18,
		'0xf424000000000000','0x0',50,
		15625,1,
		'0x8637bd06','0x1fff79c842fa',45,
		'0x8637bd05af6c69b6','0x1fff79c842fa5093964a',77,
		1,15625,
	], 100 => [
		'0xa0000000','0x0',28,
		'0xa000000000000000','0x0',60,
		10,1,
		'0xcccccccd','0x733333333',35,
		'0xcccccccccccccccd','0x73333333333333333',67,
		1,10,
		'0x9c400000','0x0',18,
		'0x9c40000000000000','0x0',50,
		10000,1,
		'0xd1b71759','0x1fff2e48e8a7',45,
		'0xd1b71758e219652c','0x1fff2e48e8a71de69ad4',77,
		1,10000,
	], 122 => [
		'0x8325c53f','0xfbcda3a',28,
		'0x8325c53ef368eb05','0xfbcda3ac10c9714',60,
		500,61,
		'0xf9db22d1','0x7fbe76c8b',35,
		'0xf9db22d0e560418a','0x7fbe76c8b43958106',67,
		61,500,
		'0x8012e2a0','0x3ef36',18,
		'0x8012e29f79b47583','0x3ef368eb04325',50,
		500000,61,
		'0xffda4053','0x1ffffbce4217',45,
		'0xffda4052d666a983','0x1ffffbce4217d2849cb2',77,
		61,500000,
	], 128 => [
		'0xfa000000','0x1e000000',29,
		'0xfa00000000000000','0x1e00000000000000',61,
		125,16,
		'0x83126e98','0x3f7ced916',34,
		'0x83126e978d4fdf3c','0x3f7ced916872b020c',66,
		16,125,
		'0xf4240000','0x40000',19,
		'0xf424000000000000','0x4000000000000',51,
		15625,2,
		'0x8637bd06','0xfffbce4217d',44,
		'0x8637bd05af6c69b6','0xfffbce4217d2849cb25',76,
		2,15625,
	], 200 => [
		'0xa0000000','0x0',29,
		'0xa000000000000000','0x0',61,
		5,1,
		'0xcccccccd','0x333333333',34,
		'0xcccccccccccccccd','0x33333333333333333',66,
		1,5,
		'0x9c400000','0x0',19,
		'0x9c40000000000000','0x0',51,
		5000,1,
		'0xd1b71759','0xfff2e48e8a7',44,
		'0xd1b71758e219652c','0xfff2e48e8a71de69ad4',76,
		1,5000,
	], 250 => [
		'0x80000000','0x0',29,
		'0x8000000000000000','0x0',61,
		4,1,
		'0x80000000','0x180000000',33,
		'0x8000000000000000','0x18000000000000000',65,
		1,4,
		'0xfa000000','0x0',20,
		'0xfa00000000000000','0x0',52,
		4000,1,
		'0x83126e98','0x7ff7ced9168',43,
		'0x83126e978d4fdf3c','0x7ff7ced916872b020c4',75,
		1,4000,
	], 256 => [
		'0xfa000000','0x3e000000',30,
		'0xfa00000000000000','0x3e00000000000000',62,
		125,32,
		'0x83126e98','0x1fbe76c8b',33,
		'0x83126e978d4fdf3c','0x1fbe76c8b43958106',65,
		32,125,
		'0xf4240000','0xc0000',20,
		'0xf424000000000000','0xc000000000000',52,
		15625,4,
		'0x8637bd06','0x7ffde7210be',43,
		'0x8637bd05af6c69b6','0x7ffde7210be9424e592',75,
		4,15625,
	], 300 => [
		'0xd5555556','0x2aaaaaaa',30,
		'0xd555555555555556','0x2aaaaaaaaaaaaaaa',62,
		10,3,
		'0x9999999a','0x1cccccccc',33,
		'0x999999999999999a','0x1cccccccccccccccc',65,
		3,10,
		'0xd0555556','0xaaaaa',20,
		'0xd055555555555556','0xaaaaaaaaaaaaa',52,
		10000,3,
		'0x9d495183','0x7ffcb923a29',43,
		'0x9d495182a9930be1','0x7ffcb923a29c779a6b5',75,
		3,10000,
	], 512 => [
		'0xfa000000','0x7e000000',31,
		'0xfa00000000000000','0x7e00000000000000',63,
		125,64,
		'0x83126e98','0xfdf3b645',32,
		'0x83126e978d4fdf3c','0xfdf3b645a1cac083',64,
		64,125,
		'0xf4240000','0x1c0000',21,
		'0xf424000000000000','0x1c000000000000',53,
		15625,8,
		'0x8637bd06','0x3ffef39085f',42,
		'0x8637bd05af6c69b6','0x3ffef39085f4a1272c9',74,
		8,15625,
	], 1000 => [
		'0x80000000','0x0',31,
		'0x8000000000000000','0x0',63,
		1,1,
		'0x80000000','0x0',31,
		'0x8000000000000000','0x0',63,
		1,1,
		'0xfa000000','0x0',22,
		'0xfa00000000000000','0x0',54,
		1000,1,
		'0x83126e98','0x1ff7ced9168',41,
		'0x83126e978d4fdf3c','0x1ff7ced916872b020c4',73,
		1,1000,
	], 1024 => [
		'0xfa000000','0xfe000000',32,
		'0xfa00000000000000','0xfe00000000000000',64,
		125,128,
		'0x83126e98','0x7ef9db22',31,
		'0x83126e978d4fdf3c','0x7ef9db22d0e56041',63,
		128,125,
		'0xf4240000','0x3c0000',22,
		'0xf424000000000000','0x3c000000000000',54,
		15625,16,
		'0x8637bd06','0x1fff79c842f',41,
		'0x8637bd05af6c69b6','0x1fff79c842fa5093964',73,
		16,15625,
	], 1200 => [
		'0xd5555556','0xd5555555',32,
		'0xd555555555555556','0xd555555555555555',64,
		5,6,
		'0x9999999a','0x66666666',31,
		'0x999999999999999a','0x6666666666666666',63,
		6,5,
		'0xd0555556','0x2aaaaa',22,
		'0xd055555555555556','0x2aaaaaaaaaaaaa',54,
		2500,3,
		'0x9d495183','0x1ffcb923a29',41,
		'0x9d495182a9930be1','0x1ffcb923a29c779a6b5',73,
		3,2500,
	]
);

$has_bigint = eval 'use Math::BigInt qw(bgcd); 1;';

sub bint($)
{
	my($x) = @_;
	return Math::BigInt->new($x);
}

#
# Constants for division by reciprocal multiplication.
# (bits, numerator, denominator)
#
sub fmul($$$)
{
	my ($b,$n,$d) = @_;

	$n = bint($n);
	$d = bint($d);

	return scalar (($n << $b)+$d-bint(1))/$d;
}

sub fadj($$$)
{
	my($b,$n,$d) = @_;

	$n = bint($n);
	$d = bint($d);

	$d = $d/bgcd($n, $d);
	return scalar (($d-bint(1)) << $b)/$d;
}

sub fmuls($$$) {
	my($b,$n,$d) = @_;
	my($s,$m);
	my($thres) = bint(1) << ($b-1);

	$n = bint($n);
	$d = bint($d);

	for ($s = 0; 1; $s++) {
		$m = fmul($s,$n,$d);
		return $s if ($m >= $thres);
	}
	return 0;
}

# Provides mul, adj, and shr factors for a specific
# (bit, time, hz) combination
sub muladj($$$) {
	my($b, $t, $hz) = @_;
	my $s = fmuls($b, $t, $hz);
	my $m = fmul($s, $t, $hz);
	my $a = fadj($s, $t, $hz);
	return ($m->as_hex(), $a->as_hex(), $s);
}

# Provides numerator, denominator values
sub numden($$) {
	my($n, $d) = @_;
	my $g = bgcd($n, $d);
	return ($n/$g, $d/$g);
}

# All values for a specific (time, hz) combo
sub conversions($$) {
	my ($t, $hz) = @_;
	my @val = ();

	# HZ_TO_xx
	push(@val, muladj(32, $t, $hz));
	push(@val, muladj(64, $t, $hz));
	push(@val, numden($t, $hz));

	# xx_TO_HZ
	push(@val, muladj(32, $hz, $t));
	push(@val, muladj(64, $hz, $t));
	push(@val, numden($hz, $t));

	return @val;
}

sub compute_values($) {
	my($hz) = @_;
	my @val = ();
	my $s, $m, $a, $g;

	if (!$has_bigint) {
		die "$0: HZ == $hz not canned and ".
		    "Math::BigInt not available\n";
	}

	# MSEC conversions
	push(@val, conversions(1000, $hz));

	# USEC conversions
	push(@val, conversions(1000000, $hz));

	return @val;
}

sub output($@)
{
	my($hz, @val) = @_;
	my $pfx, $bit, $suf, $s, $m, $a;

	print "/* Automatically generated by kernel/timeconst.pl */\n";
	print "/* Conversion constants for HZ == $hz */\n";
	print "\n";
	print "#ifndef KERNEL_TIMECONST_H\n";
	print "#define KERNEL_TIMECONST_H\n";
	print "\n";

	print "#include <linux/param.h>\n";

	print "\n";
	print "#if HZ != $hz\n";
	print "#error \"kernel/timeconst.h has the wrong HZ value!\"\n";
	print "#endif\n";
	print "\n";

	foreach $pfx ('HZ_TO_MSEC','MSEC_TO_HZ',
		      'HZ_TO_USEC','USEC_TO_HZ') {
		foreach $bit (32, 64) {
			foreach $suf ('MUL', 'ADJ', 'SHR') {
				printf "#define %-23s %s\n",
					"${pfx}_$suf$bit", shift(@val);
			}
		}
		foreach $suf ('NUM', 'DEN') {
			printf "#define %-23s %s\n",
				"${pfx}_$suf", shift(@val);
		}
	}

	print "\n";
	print "#endif /* KERNEL_TIMECONST_H */\n";
}

($hz) = @ARGV;

# Use this to generate the %canned_values structure
if ($hz eq '--can') {
	shift(@ARGV);
	@hzlist = sort {$a <=> $b} (@ARGV);

	print "# Precomputed values for systems without Math::BigInt\n";
	print "# Generated by:\n";
	print "# timeconst.pl --can ", join(' ', @hzlist), "\n";
	print "\%canned_values = (\n";
	my $pf = "\t";
	foreach $hz (@hzlist) {
		my @values = compute_values($hz);
		print "$pf$hz => [\n";
		while (scalar(@values)) {
			my $bit;
			foreach $bit (32, 64) {
				my $m = shift(@values);
				my $a = shift(@values);
				my $s = shift(@values);
				print "\t\t\'",$m,"\',\'",$a,"\',",$s,",\n";
			}
			my $n = shift(@values);
			my $d = shift(@values);
			print "\t\t",$n,',',$d,",\n";
		}
		print "\t]";
		$pf = ', ';
	}
	print "\n);\n";
} else {
	$hz += 0;			# Force to number
	if ($hz < 1) {
		die "Usage: $0 HZ\n";
	}

	@val = @{$canned_values{$hz}};
	if (!defined(@val)) {
		@val = compute_values($hz);
	}
	output($hz, @val);
}
exit 0;
2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991
/*
 * Generic hugetlb support.
 * (C) William Irwin, April 2004
 */
#include <linux/list.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/io.h>

#include <linux/hugetlb.h>
#include <linux/node.h>
#include "internal.h"

const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;

static int max_hstate;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];

__initdata LIST_HEAD(huge_boot_pages);

/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;
static unsigned long __initdata default_hstate_size;

#define for_each_hstate(h) \
	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)

/*
 * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
 */
static DEFINE_SPINLOCK(hugetlb_lock);

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are protected by a combination of the mmap_sem
 * and the hugetlb_instantion_mutex.  To access or modify a region the caller
 * must either hold the mmap_sem for write, or the mmap_sem for read and
 * the hugetlb_instantiation mutex:
 *
 * 	down_write(&mm->mmap_sem);
 * or
 * 	down_read(&mm->mmap_sem);
 * 	mutex_lock(&hugetlb_instantiation_mutex);
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
};

static long region_add(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg, *trg;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;

	/* Check for and consume any regions we now overlap with. */
	nrg = rg;
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			break;

		/* If this area reaches higher then extend our area to
		 * include it completely.  If this is not the first area
		 * which we intend to reuse, free it. */
		if (rg->to > t)
			t = rg->to;
		if (rg != nrg) {
			list_del(&rg->link);
			kfree(rg);
		}
	}
	nrg->from = f;
	nrg->to = t;
	return 0;
}

static long region_chg(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg;
	long chg = 0;

	/* Locate the region we are before or in. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* If we are below the current region then a new region is required.
	 * Subtle, allocate a new region at the position but make it zero
	 * size such that we can guarantee to record the reservation. */
	if (&rg->link == head || t < rg->from) {
		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
		if (!nrg)
			return -ENOMEM;
		nrg->from = f;
		nrg->to   = f;
		INIT_LIST_HEAD(&nrg->link);
		list_add(&nrg->link, rg->link.prev);

		return t - f;
	}

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;
	chg = t - f;

	/* Check for and consume any regions we now overlap with. */
	list_for_each_entry(rg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			return chg;

		/* We overlap with this area, if it extends futher than
		 * us then we must extend ourselves.  Account for its
		 * existing reservation. */
		if (rg->to > t) {
			chg += rg->to - t;
			t = rg->to;
		}
		chg -= rg->to - rg->from;
	}
	return chg;
}

static long region_truncate(struct list_head *head, long end)
{
	struct file_region *rg, *trg;
	long chg = 0;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (end <= rg->to)
			break;
	if (&rg->link == head)
		return 0;

	/* If we are in the middle of a region then adjust it. */
	if (end > rg->from) {
		chg = rg->to - end;
		rg->to = end;
		rg = list_entry(rg->link.next, typeof(*rg), link);
	}

	/* Drop any remaining regions. */
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		chg += rg->to - rg->from;
		list_del(&rg->link);
		kfree(rg);
	}
	return chg;
}

static long region_count(struct list_head *head, long f, long t)
{
	struct file_region *rg;
	long chg = 0;

	/* Locate each segment we overlap with, and count that overlap. */
	list_for_each_entry(rg, head, link) {
		int seg_from;
		int seg_to;

		if (rg->to <= f)
			continue;
		if (rg->from >= t)
			break;

		seg_from = max(rg->from, f);
		seg_to = min(rg->to, t);

		chg += seg_to - seg_from;
	}

	return chg;
}

/*
 * Convert the address within this vma to the page offset within
 * the mapping, in pagecache page units; huge pages here.
 */
static pgoff_t vma_hugecache_offset(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	return ((address - vma->vm_start) >> huge_page_shift(h)) +
			(vma->vm_pgoff >> huge_page_order(h));
}

pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
				     unsigned long address)
{
	return vma_hugecache_offset(hstate_vma(vma), vma, address);
}

/*
 * Return the size of the pages allocated when backing a VMA. In the majority
 * cases this will be same size as used by the page table entries.
 */
unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
	struct hstate *hstate;

	if (!is_vm_hugetlb_page(vma))
		return PAGE_SIZE;

	hstate = hstate_vma(vma);

	return 1UL << (hstate->order + PAGE_SHIFT);
}
EXPORT_SYMBOL_GPL(vma_kernel_pagesize);

/*
 * Return the page size being used by the MMU to back a VMA. In the majority
 * of cases, the page size used by the kernel matches the MMU size. On
 * architectures where it differs, an architecture-specific version of this
 * function is required.
 */
#ifndef vma_mmu_pagesize
unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
	return vma_kernel_pagesize(vma);
}
#endif

/*
 * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
 * bits of the reservation map pointer, which are always clear due to
 * alignment.
 */
#define HPAGE_RESV_OWNER    (1UL << 0)
#define HPAGE_RESV_UNMAPPED (1UL << 1)
#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)

/*
 * These helpers are used to track how many pages are reserved for
 * faults in a MAP_PRIVATE mapping. Only the process that called mmap()
 * is guaranteed to have their future faults succeed.
 *
 * With the exception of reset_vma_resv_huge_pages() which is called at fork(),
 * the reserve counters are updated with the hugetlb_lock held. It is safe
 * to reset the VMA at fork() time as it is not in use yet and there is no
 * chance of the global counters getting corrupted as a result of the values.
 *
 * The private mapping reservation is represented in a subtly different
 * manner to a shared mapping.  A shared mapping has a region map associated
 * with the underlying file, this region map represents the backing file
 * pages which have ever had a reservation assigned which this persists even
 * after the page is instantiated.  A private mapping has a region map
 * associated with the original mmap which is attached to all VMAs which
 * reference it, this region map represents those offsets which have consumed
 * reservation ie. where pages have been instantiated.
 */
static unsigned long get_vma_private_data(struct vm_area_struct *vma)
{
	return (unsigned long)vma->vm_private_data;
}

static void set_vma_private_data(struct vm_area_struct *vma,
							unsigned long value)
{
	vma->vm_private_data = (void *)value;
}

struct resv_map {
	struct kref refs;
	struct list_head regions;
};

static struct resv_map *resv_map_alloc(void)
{
	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
	if (!resv_map)
		return NULL;

	kref_init(&resv_map->refs);
	INIT_LIST_HEAD(&resv_map->regions);

	return resv_map;
}

static void resv_map_release(struct kref *ref)
{
	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);

	/* Clear out any active regions before we release the map. */
	region_truncate(&resv_map->regions, 0);
	kfree(resv_map);
}

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_MAYSHARE))
		return (struct resv_map *)(get_vma_private_data(vma) &
							~HPAGE_RESV_MASK);
	return NULL;
}

static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, (get_vma_private_data(vma) &
				HPAGE_RESV_MASK) | (unsigned long)map);
}

static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}

static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));

	return (get_vma_private_data(vma) & flag) != 0;
}

/* Decrement the reserved pages in the hugepage pool by one */
static void decrement_hugepage_resv_vma(struct hstate *h,
			struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_NORESERVE)
		return;

	if (vma->vm_flags & VM_MAYSHARE) {
		/* Shared mappings always use reserves */
		h->resv_huge_pages--;
	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		/*
		 * Only the process that called mmap() has reserves for
		 * private mappings.
		 */
		h->resv_huge_pages--;
	}
}

/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_MAYSHARE))
		vma->vm_private_data = (void *)0;
}

/* Returns true if the VMA has associated reserve pages */
static int vma_has_reserves(struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_MAYSHARE)
		return 1;
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return 1;
	return 0;
}

static void clear_gigantic_page(struct page *page,
			unsigned long addr, unsigned long sz)
{
	int i;
	struct page *p = page;

	might_sleep();
	for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
		cond_resched();
		clear_user_highpage(p, addr + i * PAGE_SIZE);
	}
}
static void clear_huge_page(struct page *page,
			unsigned long addr, unsigned long sz)
{
	int i;

	if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
		clear_gigantic_page(page, addr, sz);
		return;
	}

	might_sleep();
	for (i = 0; i < sz/PAGE_SIZE; i++) {
		cond_resched();
		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
	}
}

static void copy_user_gigantic_page(struct page *dst, struct page *src,
			   unsigned long addr, struct vm_area_struct *vma)
{
	int i;
	struct hstate *h = hstate_vma(vma);
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < pages_per_huge_page(h); ) {
		cond_resched();
		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

static void copy_user_huge_page(struct page *dst, struct page *src,
			   unsigned long addr, struct vm_area_struct *vma)
{
	int i;
	struct hstate *h = hstate_vma(vma);

	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
		copy_user_gigantic_page(dst, src, addr, vma);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); i++) {
		cond_resched();
		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
	}
}

static void copy_gigantic_page(struct page *dst, struct page *src)
{
	int i;
	struct hstate *h = page_hstate(src);
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < pages_per_huge_page(h); ) {
		cond_resched();
		copy_highpage(dst, src);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

void copy_huge_page(struct page *dst, struct page *src)
{
	int i;
	struct hstate *h = page_hstate(src);

	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
		copy_gigantic_page(dst, src);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); i++) {
		cond_resched();
		copy_highpage(dst + i, src + i);
	}
}

static void enqueue_huge_page(struct hstate *h, struct page *page)
{
	int nid = page_to_nid(page);
	list_add(&page->lru, &h->hugepage_freelists[nid]);
	h->free_huge_pages++;
	h->free_huge_pages_node[nid]++;
}

static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	if (list_empty(&h->hugepage_freelists[nid]))
		return NULL;
	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
	list_del(&page->lru);
	set_page_refcounted(page);
	h->free_huge_pages--;
	h->free_huge_pages_node[nid]--;
	return page;
}

static struct page *dequeue_huge_page_vma(struct hstate *h,
				struct vm_area_struct *vma,
				unsigned long address, int avoid_reserve)
{
	struct page *page = NULL;
	struct mempolicy *mpol;
	nodemask_t *nodemask;
	struct zonelist *zonelist;
	struct zone *zone;
	struct zoneref *z;

	get_mems_allowed();
	zonelist = huge_zonelist(vma, address,
					htlb_alloc_mask, &mpol, &nodemask);
	/*
	 * A child process with MAP_PRIVATE mappings created by their parent
	 * have no page reserves. This check ensures that reservations are
	 * not "stolen". The child may still get SIGKILLed
	 */
	if (!vma_has_reserves(vma) &&
			h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;

	/* If reserves cannot be used, ensure enough pages are in the pool */
	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;;

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						MAX_NR_ZONES - 1, nodemask) {
		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
			page = dequeue_huge_page_node(h, zone_to_nid(zone));
			if (page) {
				if (!avoid_reserve)
					decrement_hugepage_resv_vma(h, vma);
				break;
			}
		}
	}
err:
	mpol_cond_put(mpol);
	put_mems_allowed();
	return page;
}

static void update_and_free_page(struct hstate *h, struct page *page)
{
	int i;

	VM_BUG_ON(h->order >= MAX_ORDER);

	h->nr_huge_pages--;
	h->nr_huge_pages_node[page_to_nid(page)]--;
	for (i = 0; i < pages_per_huge_page(h); i++) {
		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
				1 << PG_private | 1<< PG_writeback);
	}
	set_compound_page_dtor(page, NULL);
	set_page_refcounted(page);
	arch_release_hugepage(page);
	__free_pages(page, huge_page_order(h));
}

struct hstate *size_to_hstate(unsigned long size)
{
	struct hstate *h;

	for_each_hstate(h) {
		if (huge_page_size(h) == size)
			return h;
	}
	return NULL;
}

static void free_huge_page(struct page *page)
{
	/*
	 * Can't pass hstate in here because it is called from the
	 * compound page destructor.
	 */
	struct hstate *h = page_hstate(page);
	int nid = page_to_nid(page);
	struct address_space *mapping;

	mapping = (struct address_space *) page_private(page);
	set_page_private(page, 0);
	page->mapping = NULL;
	BUG_ON(page_count(page));
	BUG_ON(page_mapcount(page));
	INIT_LIST_HEAD(&page->lru);

	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
		update_and_free_page(h, page);
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	} else {
		enqueue_huge_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
	if (mapping)
		hugetlb_put_quota(mapping, 1);
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
	set_compound_page_dtor(page, free_huge_page);
	spin_lock(&hugetlb_lock);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;
	spin_unlock(&hugetlb_lock);
	put_page(page); /* free it into the hugepage allocator */
}

static void prep_compound_gigantic_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	/* we rely on prep_new_huge_page to set the destructor */
	set_compound_order(page, order);
	__SetPageHead(page);
	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		__SetPageTail(p);
		p->first_page = page;
	}
}

int PageHuge(struct page *page)
{
	compound_page_dtor *dtor;

	if (!PageCompound(page))
		return 0;

	page = compound_head(page);
	dtor = get_compound_page_dtor(page);

	return dtor == free_huge_page;
}

EXPORT_SYMBOL_GPL(PageHuge);

static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	if (h->order >= MAX_ORDER)
		return NULL;

	page = alloc_pages_exact_node(nid,
		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
						__GFP_REPEAT|__GFP_NOWARN,
		huge_page_order(h));
	if (page) {
		if (arch_prepare_hugepage(page)) {
			__free_pages(page, huge_page_order(h));
			return NULL;
		}
		prep_new_huge_page(h, page, nid);
	}

	return page;
}

/*
 * common helper functions for hstate_next_node_to_{alloc|free}.
 * We may have allocated or freed a huge page based on a different
 * nodes_allowed previously, so h->next_node_to_{alloc|free} might
 * be outside of *nodes_allowed.  Ensure that we use an allowed
 * node for alloc or free.
 */
static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	nid = next_node(nid, *nodes_allowed);
	if (nid == MAX_NUMNODES)
		nid = first_node(*nodes_allowed);
	VM_BUG_ON(nid >= MAX_NUMNODES);

	return nid;
}

static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	if (!node_isset(nid, *nodes_allowed))
		nid = next_node_allowed(nid, nodes_allowed);
	return nid;
}

/*
 * returns the previously saved node ["this node"] from which to
 * allocate a persistent huge page for the pool and advance the
 * next node from which to allocate, handling wrap at end of node
 * mask.
 */
static int hstate_next_node_to_alloc(struct hstate *h,
					nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);

	return nid;
}

static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
{
	struct page *page;
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	next_nid = start_nid;

	do {
		page = alloc_fresh_huge_page_node(h, next_nid);
		if (page) {
			ret = 1;
			break;
		}
		next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	} while (next_nid != start_nid);

	if (ret)
		count_vm_event(HTLB_BUDDY_PGALLOC);
	else
		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);

	return ret;
}

/*
 * helper for free_pool_huge_page() - return the previously saved
 * node ["this node"] from which to free a huge page.  Advance the
 * next node id whether or not we find a free huge page to free so
 * that the next attempt to free addresses the next node.
 */
static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
	h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);

	return nid;
}

/*
 * Free huge page from pool from next node to free.
 * Attempt to keep persistent huge pages more or less
 * balanced over allowed nodes.
 * Called with hugetlb_lock locked.
 */
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
							 bool acct_surplus)
{
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = hstate_next_node_to_free(h, nodes_allowed);
	next_nid = start_nid;

	do {
		/*
		 * If we're returning unused surplus pages, only examine
		 * nodes with surplus pages.
		 */
		if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) &&
		    !list_empty(&h->hugepage_freelists[next_nid])) {
			struct page *page =
				list_entry(h->hugepage_freelists[next_nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[next_nid]--;
			if (acct_surplus) {
				h->surplus_huge_pages--;
				h->surplus_huge_pages_node[next_nid]--;
			}
			update_and_free_page(h, page);
			ret = 1;
			break;
		}
		next_nid = hstate_next_node_to_free(h, nodes_allowed);
	} while (next_nid != start_nid);

	return ret;
}

static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
	struct page *page;
	unsigned int r_nid;

	if (h->order >= MAX_ORDER)
		return NULL;

	/*
	 * Assume we will successfully allocate the surplus page to
	 * prevent racing processes from causing the surplus to exceed
	 * overcommit
	 *
	 * This however introduces a different race, where a process B
	 * tries to grow the static hugepage pool while alloc_pages() is
	 * called by process A. B will only examine the per-node
	 * counters in determining if surplus huge pages can be
	 * converted to normal huge pages in adjust_pool_surplus(). A
	 * won't be able to increment the per-node counter, until the
	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
	 * no more huge pages can be converted from surplus to normal
	 * state (and doesn't try to convert again). Thus, we have a
	 * case where a surplus huge page exists, the pool is grown, and
	 * the surplus huge page still exists after, even though it
	 * should just have been converted to a normal huge page. This
	 * does not leak memory, though, as the hugepage will be freed
	 * once it is out of use. It also does not allow the counters to
	 * go out of whack in adjust_pool_surplus() as we don't modify
	 * the node values until we've gotten the hugepage and only the
	 * per-node value is checked there.
	 */
	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
		spin_unlock(&hugetlb_lock);
		return NULL;
	} else {
		h->nr_huge_pages++;
		h->surplus_huge_pages++;
	}
	spin_unlock(&hugetlb_lock);

	if (nid == NUMA_NO_NODE)
		page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
				   __GFP_REPEAT|__GFP_NOWARN,
				   huge_page_order(h));
	else
		page = alloc_pages_exact_node(nid,
			htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));

	if (page && arch_prepare_hugepage(page)) {
		__free_pages(page, huge_page_order(h));
		return NULL;
	}

	spin_lock(&hugetlb_lock);
	if (page) {
		r_nid = page_to_nid(page);
		set_compound_page_dtor(page, free_huge_page);
		/*
		 * We incremented the global counters already
		 */
		h->nr_huge_pages_node[r_nid]++;
		h->surplus_huge_pages_node[r_nid]++;
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	} else {
		h->nr_huge_pages--;
		h->surplus_huge_pages--;
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
	}
	spin_unlock(&hugetlb_lock);

	return page;
}

/*
 * This allocation function is useful in the context where vma is irrelevant.
 * E.g. soft-offlining uses this function because it only cares physical
 * address of error page.
 */
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_node(h, nid);
	spin_unlock(&hugetlb_lock);

	if (!page)
		page = alloc_buddy_huge_page(h, nid);

	return page;
}

/*
 * Increase the hugetlb pool such that it can accomodate a reservation
 * of size 'delta'.
 */
static int gather_surplus_pages(struct hstate *h, int delta)
{
	struct list_head surplus_list;
	struct page *page, *tmp;
	int ret, i;
	int needed, allocated;

	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
	if (needed <= 0) {
		h->resv_huge_pages += delta;
		return 0;
	}

	allocated = 0;
	INIT_LIST_HEAD(&surplus_list);

	ret = -ENOMEM;
retry:
	spin_unlock(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page)
			/*
			 * We were not able to allocate enough pages to
			 * satisfy the entire reservation so we free what
			 * we've allocated so far.
			 */
			goto free;

		list_add(&page->lru, &surplus_list);
	}
	allocated += needed;

	/*
	 * After retaking hugetlb_lock, we need to recalculate 'needed'
	 * because either resv_huge_pages or free_huge_pages may have changed.
	 */
	spin_lock(&hugetlb_lock);
	needed = (h->resv_huge_pages + delta) -
			(h->free_huge_pages + allocated);
	if (needed > 0)
		goto retry;

	/*
	 * The surplus_list now contains _at_least_ the number of extra pages
	 * needed to accomodate the reservation.  Add the appropriate number
	 * of pages to the hugetlb pool and free the extras back to the buddy
	 * allocator.  Commit the entire reservation here to prevent another
	 * process from stealing the pages as they are added to the pool but
	 * before they are reserved.
	 */
	needed += allocated;
	h->resv_huge_pages += delta;
	ret = 0;

	spin_unlock(&hugetlb_lock);
	/* Free the needed pages to the hugetlb pool */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
		if ((--needed) < 0)
			break;
		list_del(&page->lru);
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		put_page_testzero(page);
		VM_BUG_ON(page_count(page));
		enqueue_huge_page(h, page);
	}

	/* Free unnecessary surplus pages to the buddy allocator */
free:
	if (!list_empty(&surplus_list)) {
		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
			list_del(&page->lru);
			put_page(page);
		}
	}
	spin_lock(&hugetlb_lock);

	return ret;
}

/*
 * When releasing a hugetlb pool reservation, any surplus pages that were
 * allocated to satisfy the reservation must be explicitly freed if they were
 * never used.
 * Called with hugetlb_lock held.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	unsigned long nr_pages;

	/* Uncommit the reservation */
	h->resv_huge_pages -= unused_resv_pages;

	/* Cannot return gigantic pages currently */
	if (h->order >= MAX_ORDER)
		return;

	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);

	/*
	 * We want to release as many surplus pages as possible, spread
	 * evenly across all nodes with memory. Iterate across these nodes
	 * until we can no longer free unreserved surplus pages. This occurs
	 * when the nodes with surplus pages have no free pages.
	 * free_pool_huge_page() will balance the the freed pages across the
	 * on-line nodes with memory and will handle the hstate accounting.
	 */
	while (nr_pages--) {
		if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1))
			break;
	}
}

/*
 * Determine if the huge page at addr within the vma has an associated
 * reservation.  Where it does not we will need to logically increase
 * reservation and actually increase quota before an allocation can occur.
 * Where any new reservation would be required the reservation change is
 * prepared, but not committed.  Once the page has been quota'd allocated
 * an instantiated the change should be committed via vma_commit_reservation.
 * No action is required on failure.
 */
static long vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_MAYSHARE) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		return region_chg(&inode->i_mapping->private_list,
							idx, idx + 1);

	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		return 1;

	} else  {
		long err;
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		err = region_chg(&reservations->regions, idx, idx + 1);
		if (err < 0)
			return err;
		return 0;
	}
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_MAYSHARE) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		region_add(&inode->i_mapping->private_list, idx, idx + 1);

	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		/* Mark this page used in the map. */
		region_add(&reservations->regions, idx, idx + 1);
	}
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;
	long chg;

	/*
	 * Processes that did not create the mapping will have no reserves and
	 * will not have accounted against quota. Check that the quota can be
	 * made before satisfying the allocation
	 * MAP_NORESERVE mappings may also need pages and quota allocated
	 * if no reserve mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(chg);
	if (chg)
		if (hugetlb_get_quota(inode->i_mapping, chg))
			return ERR_PTR(-ENOSPC);

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
	spin_unlock(&hugetlb_lock);

	if (!page) {
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page) {
			hugetlb_put_quota(inode->i_mapping, chg);
			return ERR_PTR(-VM_FAULT_SIGBUS);
		}
	}

	set_page_private(page, (unsigned long) mapping);

	vma_commit_reservation(h, vma, addr);

	return page;
}

int __weak alloc_bootmem_huge_page(struct hstate *h)
{
	struct huge_bootmem_page *m;
	int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);

	while (nr_nodes) {
		void *addr;

		addr = __alloc_bootmem_node_nopanic(
				NODE_DATA(hstate_next_node_to_alloc(h,
						&node_states[N_HIGH_MEMORY])),
				huge_page_size(h), huge_page_size(h), 0);

		if (addr) {
			/*
			 * Use the beginning of the huge page to store the
			 * huge_bootmem_page struct (until gather_bootmem
			 * puts them into the mem_map).
			 */
			m = addr;
			goto found;
		}
		nr_nodes--;
	}
	return 0;

found:
	BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
	/* Put them into a private list first because mem_map is not up yet */
	list_add(&m->list, &huge_boot_pages);
	m->hstate = h;
	return 1;
}

static void prep_compound_huge_page(struct page *page, int order)
{
	if (unlikely(order > (MAX_ORDER - 1)))
		prep_compound_gigantic_page(page, order);
	else
		prep_compound_page(page, order);
}

/* Put bootmem huge pages into the standard lists after mem_map is up */
static void __init gather_bootmem_prealloc(void)
{
	struct huge_bootmem_page *m;

	list_for_each_entry(m, &huge_boot_pages, list) {
		struct page *page = virt_to_page(m);
		struct hstate *h = m->hstate;
		__ClearPageReserved(page);
		WARN_ON(page_count(page) != 1);
		prep_compound_huge_page(page, h->order);
		prep_new_huge_page(h, page, page_to_nid(page));
	}
}

static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
	unsigned long i;

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (h->order >= MAX_ORDER) {
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_fresh_huge_page(h,
					 &node_states[N_HIGH_MEMORY]))
			break;
	}
	h->max_huge_pages = i;
}

static void __init hugetlb_init_hstates(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		/* oversize hugepages were init'ed in early boot */
		if (h->order < MAX_ORDER)
			hugetlb_hstate_alloc_pages(h);
	}
}

static char * __init memfmt(char *buf, unsigned long n)
{
	if (n >= (1UL << 30))
		sprintf(buf, "%lu GB", n >> 30);
	else if (n >= (1UL << 20))
		sprintf(buf, "%lu MB", n >> 20);
	else
		sprintf(buf, "%lu KB", n >> 10);
	return buf;
}

static void __init report_hugepages(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		char buf[32];
		printk(KERN_INFO "HugeTLB registered %s page size, "
				 "pre-allocated %ld pages\n",
			memfmt(buf, huge_page_size(h)),
			h->free_huge_pages);
	}
}

#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	int i;

	if (h->order >= MAX_ORDER)
		return;

	for_each_node_mask(i, *nodes_allowed) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
}
#endif

/*
 * Increment or decrement surplus_huge_pages.  Keep node-specific counters
 * balanced by operating on them in a round-robin fashion.
 * Returns 1 if an adjustment was made.
 */
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
				int delta)
{
	int start_nid, next_nid;
	int ret = 0;

	VM_BUG_ON(delta != -1 && delta != 1);

	if (delta < 0)
		start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	else
		start_nid = hstate_next_node_to_free(h, nodes_allowed);
	next_nid = start_nid;

	do {
		int nid = next_nid;
		if (delta < 0)  {
			/*
			 * To shrink on this node, there must be a surplus page
			 */
			if (!h->surplus_huge_pages_node[nid]) {
				next_nid = hstate_next_node_to_alloc(h,
								nodes_allowed);
				continue;
			}
		}
		if (delta > 0) {
			/*
			 * Surplus cannot exceed the total number of pages
			 */
			if (h->surplus_huge_pages_node[nid] >=
						h->nr_huge_pages_node[nid]) {
				next_nid = hstate_next_node_to_free(h,
								nodes_allowed);
				continue;
			}
		}

		h->surplus_huge_pages += delta;
		h->surplus_huge_pages_node[nid] += delta;
		ret = 1;
		break;
	} while (next_nid != start_nid);

	return ret;
}

#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	unsigned long min_count, ret;

	if (h->order >= MAX_ORDER)
		return h->max_huge_pages;

	/*
	 * Increase the pool size
	 * First take pages out of surplus state.  Then make up the
	 * remaining difference by allocating fresh huge pages.
	 *
	 * We might race with alloc_buddy_huge_page() here and be unable
	 * to convert a surplus huge page to a normal huge page. That is
	 * not critical, though, it just means the overall size of the
	 * pool might be one hugepage larger than it needs to be, but
	 * within all the constraints specified by the sysctls.
	 */
	spin_lock(&hugetlb_lock);
	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, -1))
			break;
	}

	while (count > persistent_huge_pages(h)) {
		/*
		 * If this allocation races such that we no longer need the
		 * page, free_huge_page will handle it by freeing the page
		 * and reducing the surplus.
		 */
		spin_unlock(&hugetlb_lock);
		ret = alloc_fresh_huge_page(h, nodes_allowed);
		spin_lock(&hugetlb_lock);
		if (!ret)
			goto out;

		/* Bail for signals. Probably ctrl-c from user */
		if (signal_pending(current))
			goto out;
	}

	/*
	 * Decrease the pool size
	 * First return free pages to the buddy allocator (being careful
	 * to keep enough around to satisfy reservations).  Then place
	 * pages into surplus state as needed so the pool will shrink
	 * to the desired size as pages become free.
	 *
	 * By placing pages into the surplus state independent of the
	 * overcommit value, we are allowing the surplus pool size to
	 * exceed overcommit. There are few sane options here. Since
	 * alloc_buddy_huge_page() is checking the global counter,
	 * though, we'll note that we're not allowed to exceed surplus
	 * and won't grow the pool anywhere else. Not until one of the
	 * sysctls are changed, or the surplus pages go out of use.
	 */
	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
	min_count = max(count, min_count);
	try_to_free_low(h, min_count, nodes_allowed);
	while (min_count < persistent_huge_pages(h)) {
		if (!free_pool_huge_page(h, nodes_allowed, 0))
			break;
	}
	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, 1))
			break;
	}
out:
	ret = persistent_huge_pages(h);
	spin_unlock(&hugetlb_lock);
	return ret;
}

#define HSTATE_ATTR_RO(_name) \
	static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define HSTATE_ATTR(_name) \
	static struct kobj_attribute _name##_attr = \
		__ATTR(_name, 0644, _name##_show, _name##_store)

static struct kobject *hugepages_kobj;
static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);

static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
{
	int i;

	for (i = 0; i < HUGE_MAX_HSTATE; i++)
		if (hstate_kobjs[i] == kobj) {
			if (nidp)
				*nidp = NUMA_NO_NODE;
			return &hstates[i];
		}

	return kobj_to_node_hstate(kobj, nidp);
}

static ssize_t nr_hugepages_show_common(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long nr_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		nr_huge_pages = h->nr_huge_pages;
	else
		nr_huge_pages = h->nr_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", nr_huge_pages);
}
static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
			struct kobject *kobj, struct kobj_attribute *attr,
			const char *buf, size_t len)
{
	int err;
	int nid;
	unsigned long count;
	struct hstate *h;
	NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);

	err = strict_strtoul(buf, 10, &count);
	if (err)
		return 0;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE) {
		/*
		 * global hstate attribute
		 */
		if (!(obey_mempolicy &&
				init_nodemask_of_mempolicy(nodes_allowed))) {
			NODEMASK_FREE(nodes_allowed);
			nodes_allowed = &node_states[N_HIGH_MEMORY];
		}
	} else if (nodes_allowed) {
		/*
		 * per node hstate attribute: adjust count to global,
		 * but restrict alloc/free to the specified node.
		 */
		count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
		init_nodemask_of_node(nodes_allowed, nid);
	} else
		nodes_allowed = &node_states[N_HIGH_MEMORY];

	h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);

	if (nodes_allowed != &node_states[N_HIGH_MEMORY])
		NODEMASK_FREE(nodes_allowed);

	return len;
}

static ssize_t nr_hugepages_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(false, kobj, attr, buf, len);
}
HSTATE_ATTR(nr_hugepages);

#ifdef CONFIG_NUMA

/*
 * hstate attribute for optionally mempolicy-based constraint on persistent
 * huge page alloc/free.
 */
static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(true, kobj, attr, buf, len);
}
HSTATE_ATTR(nr_hugepages_mempolicy);
#endif


static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
}
static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	int err;
	unsigned long input;
	struct hstate *h = kobj_to_hstate(kobj, NULL);

	err = strict_strtoul(buf, 10, &input);
	if (err)
		return 0;

	spin_lock(&hugetlb_lock);
	h->nr_overcommit_huge_pages = input;
	spin_unlock(&hugetlb_lock);

	return count;
}
HSTATE_ATTR(nr_overcommit_hugepages);

static ssize_t free_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long free_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		free_huge_pages = h->free_huge_pages;
	else
		free_huge_pages = h->free_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", free_huge_pages);
}
HSTATE_ATTR_RO(free_hugepages);

static ssize_t resv_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->resv_huge_pages);
}
HSTATE_ATTR_RO(resv_hugepages);

static ssize_t surplus_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long surplus_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		surplus_huge_pages = h->surplus_huge_pages;
	else
		surplus_huge_pages = h->surplus_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", surplus_huge_pages);
}
HSTATE_ATTR_RO(surplus_hugepages);

static struct attribute *hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&nr_overcommit_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&resv_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
#ifdef CONFIG_NUMA
	&nr_hugepages_mempolicy_attr.attr,
#endif
	NULL,
};

static struct attribute_group hstate_attr_group = {
	.attrs = hstate_attrs,
};

static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
				    struct kobject **hstate_kobjs,
				    struct attribute_group *hstate_attr_group)
{
	int retval;
	int hi = h - hstates;

	hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
	if (!hstate_kobjs[hi])
		return -ENOMEM;

	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
	if (retval)
		kobject_put(hstate_kobjs[hi]);

	return retval;
}

static void __init hugetlb_sysfs_init(void)
{
	struct hstate *h;
	int err;

	hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
	if (!hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
					 hstate_kobjs, &hstate_attr_group);
		if (err)
			printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
								h->name);
	}
}

#ifdef CONFIG_NUMA

/*
 * node_hstate/s - associate per node hstate attributes, via their kobjects,
 * with node sysdevs in node_devices[] using a parallel array.  The array
 * index of a node sysdev or _hstate == node id.
 * This is here to avoid any static dependency of the node sysdev driver, in
 * the base kernel, on the hugetlb module.
 */
struct node_hstate {
	struct kobject		*hugepages_kobj;
	struct kobject		*hstate_kobjs[HUGE_MAX_HSTATE];
};
struct node_hstate node_hstates[MAX_NUMNODES];

/*
 * A subset of global hstate attributes for node sysdevs
 */
static struct attribute *per_node_hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
	NULL,
};

static struct attribute_group per_node_hstate_attr_group = {
	.attrs = per_node_hstate_attrs,
};

/*
 * kobj_to_node_hstate - lookup global hstate for node sysdev hstate attr kobj.
 * Returns node id via non-NULL nidp.
 */
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	int nid;

	for (nid = 0; nid < nr_node_ids; nid++) {
		struct node_hstate *nhs = &node_hstates[nid];
		int i;
		for (i = 0; i < HUGE_MAX_HSTATE; i++)
			if (nhs->hstate_kobjs[i] == kobj) {
				if (nidp)
					*nidp = nid;
				return &hstates[i];
			}
	}

	BUG();
	return NULL;
}

/*
 * Unregister hstate attributes from a single node sysdev.
 * No-op if no hstate attributes attached.
 */
void hugetlb_unregister_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->sysdev.id];

	if (!nhs->hugepages_kobj)
		return;		/* no hstate attributes */

	for_each_hstate(h)
		if (nhs->hstate_kobjs[h - hstates]) {
			kobject_put(nhs->hstate_kobjs[h - hstates]);
			nhs->hstate_kobjs[h - hstates] = NULL;
		}

	kobject_put(nhs->hugepages_kobj);
	nhs->hugepages_kobj = NULL;
}

/*
 * hugetlb module exit:  unregister hstate attributes from node sysdevs
 * that have them.
 */
static void hugetlb_unregister_all_nodes(void)
{
	int nid;

	/*
	 * disable node sysdev registrations.
	 */
	register_hugetlbfs_with_node(NULL, NULL);

	/*
	 * remove hstate attributes from any nodes that have them.
	 */
	for (nid = 0; nid < nr_node_ids; nid++)
		hugetlb_unregister_node(&node_devices[nid]);
}

/*
 * Register hstate attributes for a single node sysdev.
 * No-op if attributes already registered.
 */
void hugetlb_register_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->sysdev.id];
	int err;

	if (nhs->hugepages_kobj)
		return;		/* already allocated */

	nhs->hugepages_kobj = kobject_create_and_add("hugepages",
							&node->sysdev.kobj);
	if (!nhs->hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
						nhs->hstate_kobjs,
						&per_node_hstate_attr_group);
		if (err) {
			printk(KERN_ERR "Hugetlb: Unable to add hstate %s"
					" for node %d\n",
						h->name, node->sysdev.id);
			hugetlb_unregister_node(node);
			break;
		}
	}
}

/*
 * hugetlb init time:  register hstate attributes for all registered node
 * sysdevs of nodes that have memory.  All on-line nodes should have
 * registered their associated sysdev by this time.
 */
static void hugetlb_register_all_nodes(void)
{
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY) {
		struct node *node = &node_devices[nid];
		if (node->sysdev.id == nid)
			hugetlb_register_node(node);
	}

	/*
	 * Let the node sysdev driver know we're here so it can
	 * [un]register hstate attributes on node hotplug.
	 */
	register_hugetlbfs_with_node(hugetlb_register_node,
				     hugetlb_unregister_node);
}
#else	/* !CONFIG_NUMA */

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	BUG();
	if (nidp)
		*nidp = -1;
	return NULL;
}

static void hugetlb_unregister_all_nodes(void) { }

static void hugetlb_register_all_nodes(void) { }

#endif

static void __exit hugetlb_exit(void)
{
	struct hstate *h;

	hugetlb_unregister_all_nodes();

	for_each_hstate(h) {
		kobject_put(hstate_kobjs[h - hstates]);
	}

	kobject_put(hugepages_kobj);
}
module_exit(hugetlb_exit);

static int __init hugetlb_init(void)
{
	/* Some platform decide whether they support huge pages at boot
	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
	 * there is no such support
	 */
	if (HPAGE_SHIFT == 0)
		return 0;

	if (!size_to_hstate(default_hstate_size)) {
		default_hstate_size = HPAGE_SIZE;
		if (!size_to_hstate(default_hstate_size))
			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
	}
	default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
	if (default_hstate_max_huge_pages)
		default_hstate.max_huge_pages = default_hstate_max_huge_pages;

	hugetlb_init_hstates();

	gather_bootmem_prealloc();

	report_hugepages();

	hugetlb_sysfs_init();

	hugetlb_register_all_nodes();

	return 0;
}
module_init(hugetlb_init);

/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_add_hstate(unsigned order)
{
	struct hstate *h;
	unsigned long i;

	if (size_to_hstate(PAGE_SIZE << order)) {
		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
		return;
	}
	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
	BUG_ON(order == 0);
	h = &hstates[max_hstate++];
	h->order = order;
	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
	h->nr_huge_pages = 0;
	h->free_huge_pages = 0;
	for (i = 0; i < MAX_NUMNODES; ++i)
		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
	h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]);
	h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]);
	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
					huge_page_size(h)/1024);

	parsed_hstate = h;
}

static int __init hugetlb_nrpages_setup(char *s)
{
	unsigned long *mhp;
	static unsigned long *last_mhp;

	/*
	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
	 * so this hugepages= parameter goes to the "default hstate".
	 */
	if (!max_hstate)
		mhp = &default_hstate_max_huge_pages;
	else
		mhp = &parsed_hstate->max_huge_pages;

	if (mhp == last_mhp) {
		printk(KERN_WARNING "hugepages= specified twice without "
			"interleaving hugepagesz=, ignoring\n");
		return 1;
	}

	if (sscanf(s, "%lu", mhp) <= 0)
		*mhp = 0;

	/*
	 * Global state is always initialized later in hugetlb_init.
	 * But we need to allocate >= MAX_ORDER hstates here early to still
	 * use the bootmem allocator.
	 */
	if (max_hstate && parsed_hstate->order >= MAX_ORDER)
		hugetlb_hstate_alloc_pages(parsed_hstate);

	last_mhp = mhp;

	return 1;
}
__setup("hugepages=", hugetlb_nrpages_setup);

static int __init hugetlb_default_setup(char *s)
{
	default_hstate_size = memparse(s, &s);
	return 1;
}
__setup("default_hugepagesz=", hugetlb_default_setup);

static unsigned int cpuset_mems_nr(unsigned int *array)
{
	int node;
	unsigned int nr = 0;

	for_each_node_mask(node, cpuset_current_mems_allowed)
		nr += array[node];

	return nr;
}

#ifdef CONFIG_SYSCTL
static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
			 struct ctl_table *table, int write,
			 void __user *buffer, size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->max_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, buffer, length, ppos);

	if (write) {
		NODEMASK_ALLOC(nodemask_t, nodes_allowed,
						GFP_KERNEL | __GFP_NORETRY);
		if (!(obey_mempolicy &&
			       init_nodemask_of_mempolicy(nodes_allowed))) {
			NODEMASK_FREE(nodes_allowed);
			nodes_allowed = &node_states[N_HIGH_MEMORY];
		}
		h->max_huge_pages = set_max_huge_pages(h, tmp, nodes_allowed);

		if (nodes_allowed != &node_states[N_HIGH_MEMORY])
			NODEMASK_FREE(nodes_allowed);
	}

	return 0;
}

int hugetlb_sysctl_handler(struct ctl_table *table, int write,
			  void __user *buffer, size_t *length, loff_t *ppos)
{

	return hugetlb_sysctl_handler_common(false, table, write,
							buffer, length, ppos);
}

#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
			  void __user *buffer, size_t *length, loff_t *ppos)
{
	return hugetlb_sysctl_handler_common(true, table, write,
							buffer, length, ppos);
}
#endif /* CONFIG_NUMA */

int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
			void __user *buffer,
			size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, buffer, length, ppos);
	if (hugepages_treat_as_movable)
		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
	else
		htlb_alloc_mask = GFP_HIGHUSER;
	return 0;
}

int hugetlb_overcommit_handler(struct ctl_table *table, int write,
			void __user *buffer,
			size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->nr_overcommit_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, buffer, length, ppos);

	if (write) {
		spin_lock(&hugetlb_lock);
		h->nr_overcommit_huge_pages = tmp;
		spin_unlock(&hugetlb_lock);
	}

	return 0;
}

#endif /* CONFIG_SYSCTL */

void hugetlb_report_meminfo(struct seq_file *m)
{
	struct hstate *h = &default_hstate;
	seq_printf(m,
			"HugePages_Total:   %5lu\n"
			"HugePages_Free:    %5lu\n"
			"HugePages_Rsvd:    %5lu\n"
			"HugePages_Surp:    %5lu\n"
			"Hugepagesize:   %8lu kB\n",
			h->nr_huge_pages,
			h->free_huge_pages,
			h->resv_huge_pages,
			h->surplus_huge_pages,
			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

int hugetlb_report_node_meminfo(int nid, char *buf)
{
	struct hstate *h = &default_hstate;
	return sprintf(buf,
		"Node %d HugePages_Total: %5u\n"
		"Node %d HugePages_Free:  %5u\n"
		"Node %d HugePages_Surp:  %5u\n",
		nid, h->nr_huge_pages_node[nid],
		nid, h->free_huge_pages_node[nid],
		nid, h->surplus_huge_pages_node[nid]);
}

/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
	struct hstate *h = &default_hstate;
	return h->nr_huge_pages * pages_per_huge_page(h);
}

static int hugetlb_acct_memory(struct hstate *h, long delta)
{
	int ret = -ENOMEM;

	spin_lock(&hugetlb_lock);
	/*
	 * When cpuset is configured, it breaks the strict hugetlb page
	 * reservation as the accounting is done on a global variable. Such
	 * reservation is completely rubbish in the presence of cpuset because
	 * the reservation is not checked against page availability for the
	 * current cpuset. Application can still potentially OOM'ed by kernel
	 * with lack of free htlb page in cpuset that the task is in.
	 * Attempt to enforce strict accounting with cpuset is almost
	 * impossible (or too ugly) because cpuset is too fluid that
	 * task or memory node can be dynamically moved between cpusets.
	 *
	 * The change of semantics for shared hugetlb mapping with cpuset is
	 * undesirable. However, in order to preserve some of the semantics,
	 * we fall back to check against current free page availability as
	 * a best attempt and hopefully to minimize the impact of changing
	 * semantics that cpuset has.
	 */
	if (delta > 0) {
		if (gather_surplus_pages(h, delta) < 0)
			goto out;

		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
			return_unused_surplus_pages(h, delta);
			goto out;
		}
	}

	ret = 0;
	if (delta < 0)
		return_unused_surplus_pages(h, (unsigned long) -delta);

out:
	spin_unlock(&hugetlb_lock);
	return ret;
}

static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
	struct resv_map *reservations = vma_resv_map(vma);

	/*
	 * This new VMA should share its siblings reservation map if present.
	 * The VMA will only ever have a valid reservation map pointer where
	 * it is being copied for another still existing VMA.  As that VMA
	 * has a reference to the reservation map it cannot dissappear until
	 * after this open call completes.  It is therefore safe to take a
	 * new reference here without additional locking.
	 */
	if (reservations)
		kref_get(&reservations->refs);
}

static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
	struct hstate *h = hstate_vma(vma);
	struct resv_map *reservations = vma_resv_map(vma);
	unsigned long reserve;
	unsigned long start;
	unsigned long end;

	if (reservations) {
		start = vma_hugecache_offset(h, vma, vma->vm_start);
		end = vma_hugecache_offset(h, vma, vma->vm_end);

		reserve = (end - start) -
			region_count(&reservations->regions, start, end);

		kref_put(&reservations->refs, resv_map_release);

		if (reserve) {
			hugetlb_acct_memory(h, -reserve);
			hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
		}
	}
}

/*
 * We cannot handle pagefaults against hugetlb pages at all.  They cause
 * handle_mm_fault() to try to instantiate regular-sized pages in the
 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
 * this far.
 */
static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}

const struct vm_operations_struct hugetlb_vm_ops = {
	.fault = hugetlb_vm_op_fault,
	.open = hugetlb_vm_op_open,
	.close = hugetlb_vm_op_close,
};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
				int writable)
{
	pte_t entry;

	if (writable) {
		entry =
		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
	} else {
		entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
	}
	entry = pte_mkyoung(entry);
	entry = pte_mkhuge(entry);

	return entry;
}

static void set_huge_ptep_writable(struct vm_area_struct *vma,
				   unsigned long address, pte_t *ptep)
{
	pte_t entry;

	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
		update_mmu_cache(vma, address, ptep);
	}
}


int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			    struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr;
	int cow;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
		src_pte = huge_pte_offset(src, addr);
		if (!src_pte)
			continue;
		dst_pte = huge_pte_alloc(dst, addr, sz);
		if (!dst_pte)
			goto nomem;

		/* If the pagetables are shared don't copy or take references */
		if (dst_pte == src_pte)
			continue;

		spin_lock(&dst->page_table_lock);
		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
		if (!huge_pte_none(huge_ptep_get(src_pte))) {
			if (cow)
				huge_ptep_set_wrprotect(src, addr, src_pte);
			entry = huge_ptep_get(src_pte);
			ptepage = pte_page(entry);
			get_page(ptepage);
			page_dup_rmap(ptepage);
			set_huge_pte_at(dst, addr, dst_pte, entry);
		}
		spin_unlock(&src->page_table_lock);
		spin_unlock(&dst->page_table_lock);
	}
	return 0;

nomem:
	return -ENOMEM;
}

static int is_hugetlb_entry_migration(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_migration_entry(swp)) {
		return 1;
	} else
		return 0;
}

static int is_hugetlb_entry_hwpoisoned(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
		return 1;
	} else
		return 0;
}

void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			    unsigned long end, struct page *ref_page)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *ptep;
	pte_t pte;