summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSam Shih <sam.shih@mediatek.com>2019-09-19 18:49:05 -0400
committerThierry Reding <thierry.reding@gmail.com>2019-09-25 03:49:15 -0400
commit2503781c97fa66f1ee7ffac21f8c5c330b82b5eb (patch)
treea6437f16b3f2418e993797d7be45d98689274407
parentefecdeb82f21d4100566ce85bda2d7ffb9c9edff (diff)
pwm: mediatek: Use pwm_mediatek as common prefix
Use pwm_mediatek as common prefix to match the filename. No functional change intended. Signed-off-by: Ryder Lee <ryder.lee@mediatek.com> Signed-off-by: Sam Shih <sam.shih@mediatek.com> Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
Diffstat
-rw-r--r--drivers/pwm/pwm-mediatek.c117
1 files changed, 60 insertions, 57 deletions
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index db986b77e556..6b9a5857b5b6 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -35,13 +35,13 @@
35 35
36#define PWM_CLK_DIV_MAX 7 36#define PWM_CLK_DIV_MAX 7
37 37
38struct mtk_pwm_platform_data { 38struct pwm_mediatek_of_data {
39 unsigned int num_pwms; 39 unsigned int num_pwms;
40 bool pwm45_fixup; 40 bool pwm45_fixup;
41}; 41};
42 42
43/** 43/**
44 * struct mtk_pwm_chip - struct representing PWM chip 44 * struct pwm_mediatek_chip - struct representing PWM chip
45 * @chip: linux PWM chip representation 45 * @chip: linux PWM chip representation
46 * @regs: base address of PWM chip 46 * @regs: base address of PWM chip
47 * @clk_top: the top clock generator 47 * @clk_top: the top clock generator
@@ -49,27 +49,29 @@ struct mtk_pwm_platform_data {
49 * @clk_pwms: the clock used by each PWM channel 49 * @clk_pwms: the clock used by each PWM channel
50 * @clk_freq: the fix clock frequency of legacy MIPS SoC 50 * @clk_freq: the fix clock frequency of legacy MIPS SoC
51 */ 51 */
52struct mtk_pwm_chip { 52struct pwm_mediatek_chip {
53 struct pwm_chip chip; 53 struct pwm_chip chip;
54 void __iomem *regs; 54 void __iomem *regs;
55 struct clk *clk_top; 55 struct clk *clk_top;
56 struct clk *clk_main; 56 struct clk *clk_main;
57 struct clk **clk_pwms; 57 struct clk **clk_pwms;
58 const struct mtk_pwm_platform_data *soc; 58 const struct pwm_mediatek_of_data *soc;
59}; 59};
60 60
61static const unsigned int mtk_pwm_reg_offset[] = { 61static const unsigned int pwm_mediatek_reg_offset[] = {
62 0x0010, 0x0050, 0x0090, 0x00d0, 0x0110, 0x0150, 0x0190, 0x0220 62 0x0010, 0x0050, 0x0090, 0x00d0, 0x0110, 0x0150, 0x0190, 0x0220
63}; 63};
64 64
65static inline struct mtk_pwm_chip *to_mtk_pwm_chip(struct pwm_chip *chip) 65static inline struct pwm_mediatek_chip *
66to_pwm_mediatek_chip(struct pwm_chip *chip)
66{ 67{
67 return container_of(chip, struct mtk_pwm_chip, chip); 68 return container_of(chip, struct pwm_mediatek_chip, chip);
68} 69}
69 70
70static int mtk_pwm_clk_enable(struct pwm_chip *chip, struct pwm_device *pwm) 71static int pwm_mediatek_clk_enable(struct pwm_chip *chip,
72 struct pwm_device *pwm)
71{ 73{
72 struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip); 74 struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
73 int ret; 75 int ret;
74 76
75 ret = clk_prepare_enable(pc->clk_top); 77 ret = clk_prepare_enable(pc->clk_top);
@@ -94,45 +96,46 @@ disable_clk_top:
94 return ret; 96 return ret;
95} 97}
96 98
97static void mtk_pwm_clk_disable(struct pwm_chip *chip, struct pwm_device *pwm) 99static void pwm_mediatek_clk_disable(struct pwm_chip *chip,
100 struct pwm_device *pwm)
98{ 101{
99 struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip); 102 struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
100 103
101 clk_disable_unprepare(pc->clk_pwms[pwm->hwpwm]); 104 clk_disable_unprepare(pc->clk_pwms[pwm->hwpwm]);
102 clk_disable_unprepare(pc->clk_main); 105 clk_disable_unprepare(pc->clk_main);
103 clk_disable_unprepare(pc->clk_top); 106 clk_disable_unprepare(pc->clk_top);
104} 107}
105 108
106static inline u32 mtk_pwm_readl(struct mtk_pwm_chip *chip, unsigned int num, 109static inline u32 pwm_mediatek_readl(struct pwm_mediatek_chip *chip,
107 unsigned int offset) 110 unsigned int num, unsigned int offset)
108{ 111{
109 return readl(chip->regs + mtk_pwm_reg_offset[num] + offset); 112 return readl(chip->regs + pwm_mediatek_reg_offset[num] + offset);
110} 113}
111 114
112static inline void mtk_pwm_writel(struct mtk_pwm_chip *chip, 115static inline void pwm_mediatek_writel(struct pwm_mediatek_chip *chip,
113 unsigned int num, unsigned int offset, 116 unsigned int num, unsigned int offset,
114 u32 value) 117 u32 value)
115{ 118{
116 writel(value, chip->regs + mtk_pwm_reg_offset[num] + offset); 119 writel(value, chip->regs + pwm_mediatek_reg_offset[num] + offset);
117} 120}
118 121
119static int mtk_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, 122static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
120 int duty_ns, int period_ns) 123 int duty_ns, int period_ns)
121{ 124{
122 struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip); 125 struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
123 struct clk *clk = pc->clk_pwms[pwm->hwpwm];
124 u32 clkdiv = 0, cnt_period, cnt_duty, reg_width = PWMDWIDTH, 126 u32 clkdiv = 0, cnt_period, cnt_duty, reg_width = PWMDWIDTH,
125 reg_thres = PWMTHRES; 127 reg_thres = PWMTHRES;
126 u64 resolution; 128 u64 resolution;
127 int ret; 129 int ret;
128 130
129 ret = mtk_pwm_clk_enable(chip, pwm); 131 ret = pwm_mediatek_clk_enable(chip, pwm);
132
130 if (ret < 0) 133 if (ret < 0)
131 return ret; 134 return ret;
132 135
133 /* Using resolution in picosecond gets accuracy higher */ 136 /* Using resolution in picosecond gets accuracy higher */
134 resolution = (u64)NSEC_PER_SEC * 1000; 137 resolution = (u64)NSEC_PER_SEC * 1000;
135 do_div(resolution, clk_get_rate(clk)); 138 do_div(resolution, clk_get_rate(pc->clk_pwms[pwm->hwpwm]));
136 139
137 cnt_period = DIV_ROUND_CLOSEST_ULL((u64)period_ns * 1000, resolution); 140 cnt_period = DIV_ROUND_CLOSEST_ULL((u64)period_ns * 1000, resolution);
138 while (cnt_period > 8191) { 141 while (cnt_period > 8191) {
@@ -143,7 +146,7 @@ static int mtk_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
143 } 146 }
144 147
145 if (clkdiv > PWM_CLK_DIV_MAX) { 148 if (clkdiv > PWM_CLK_DIV_MAX) {
146 mtk_pwm_clk_disable(chip, pwm); 149 pwm_mediatek_clk_disable(chip, pwm);
147 dev_err(chip->dev, "period %d not supported\n", period_ns); 150 dev_err(chip->dev, "period %d not supported\n", period_ns);
148 return -EINVAL; 151 return -EINVAL;
149 } 152 }
@@ -158,22 +161,22 @@ static int mtk_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
158 } 161 }
159 162
160 cnt_duty = DIV_ROUND_CLOSEST_ULL((u64)duty_ns * 1000, resolution); 163 cnt_duty = DIV_ROUND_CLOSEST_ULL((u64)duty_ns * 1000, resolution);
161 mtk_pwm_writel(pc, pwm->hwpwm, PWMCON, BIT(15) | clkdiv); 164 pwm_mediatek_writel(pc, pwm->hwpwm, PWMCON, BIT(15) | clkdiv);
162 mtk_pwm_writel(pc, pwm->hwpwm, reg_width, cnt_period); 165 pwm_mediatek_writel(pc, pwm->hwpwm, reg_width, cnt_period);
163 mtk_pwm_writel(pc, pwm->hwpwm, reg_thres, cnt_duty); 166 pwm_mediatek_writel(pc, pwm->hwpwm, reg_thres, cnt_duty);
164 167
165 mtk_pwm_clk_disable(chip, pwm); 168 pwm_mediatek_clk_disable(chip, pwm);
166 169
167 return 0; 170 return 0;
168} 171}
169 172
170static int mtk_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) 173static int pwm_mediatek_enable(struct pwm_chip *chip, struct pwm_device *pwm)
171{ 174{
172 struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip); 175 struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
173 u32 value; 176 u32 value;
174 int ret; 177 int ret;
175 178
176 ret = mtk_pwm_clk_enable(chip, pwm); 179 ret = pwm_mediatek_clk_enable(chip, pwm);
177 if (ret < 0) 180 if (ret < 0)
178 return ret; 181 return ret;
179 182
@@ -184,28 +187,28 @@ static int mtk_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
184 return 0; 187 return 0;
185} 188}
186 189
187static void mtk_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) 190static void pwm_mediatek_disable(struct pwm_chip *chip, struct pwm_device *pwm)
188{ 191{
189 struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip); 192 struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
190 u32 value; 193 u32 value;
191 194
192 value = readl(pc->regs); 195 value = readl(pc->regs);
193 value &= ~BIT(pwm->hwpwm); 196 value &= ~BIT(pwm->hwpwm);
194 writel(value, pc->regs); 197 writel(value, pc->regs);
195 198
196 mtk_pwm_clk_disable(chip, pwm); 199 pwm_mediatek_clk_disable(chip, pwm);
197} 200}
198 201
199static const struct pwm_ops mtk_pwm_ops = { 202static const struct pwm_ops pwm_mediatek_ops = {
200 .config = mtk_pwm_config, 203 .config = pwm_mediatek_config,
201 .enable = mtk_pwm_enable, 204 .enable = pwm_mediatek_enable,
202 .disable = mtk_pwm_disable, 205 .disable = pwm_mediatek_disable,
203 .owner = THIS_MODULE, 206 .owner = THIS_MODULE,
204}; 207};
205 208
206static int mtk_pwm_probe(struct platform_device *pdev) 209static int pwm_mediatek_probe(struct platform_device *pdev)
207{ 210{
208 struct mtk_pwm_chip *pc; 211 struct pwm_mediatek_chip *pc;
209 struct resource *res; 212 struct resource *res;
210 unsigned int i; 213 unsigned int i;
211 int ret; 214 int ret;
@@ -256,7 +259,7 @@ static int mtk_pwm_probe(struct platform_device *pdev)
256 platform_set_drvdata(pdev, pc); 259 platform_set_drvdata(pdev, pc);
257 260
258 pc->chip.dev = &pdev->dev; 261 pc->chip.dev = &pdev->dev;
259 pc->chip.ops = &mtk_pwm_ops; 262 pc->chip.ops = &pwm_mediatek_ops;
260 pc->chip.base = -1; 263 pc->chip.base = -1;
261 pc->chip.npwm = pc->soc->num_pwms; 264 pc->chip.npwm = pc->soc->num_pwms;
262 265
@@ -269,39 +272,39 @@ static int mtk_pwm_probe(struct platform_device *pdev)
269 return 0; 272 return 0;
270} 273}
271 274
272static int mtk_pwm_remove(struct platform_device *pdev) 275static int pwm_mediatek_remove(struct platform_device *pdev)
273{ 276{
274 struct mtk_pwm_chip *pc = platform_get_drvdata(pdev); 277 struct pwm_mediatek_chip *pc = platform_get_drvdata(pdev);
275 278
276 return pwmchip_remove(&pc->chip); 279 return pwmchip_remove(&pc->chip);
277} 280}
278 281
279static const struct mtk_pwm_platform_data mt2712_pwm_data = { 282static const struct pwm_mediatek_of_data mt2712_pwm_data = {
280 .num_pwms = 8, 283 .num_pwms = 8,
281 .pwm45_fixup = false, 284 .pwm45_fixup = false,
282}; 285};
283 286
284static const struct mtk_pwm_platform_data mt7622_pwm_data = { 287static const struct pwm_mediatek_of_data mt7622_pwm_data = {
285 .num_pwms = 6, 288 .num_pwms = 6,
286 .pwm45_fixup = false, 289 .pwm45_fixup = false,
287}; 290};
288 291
289static const struct mtk_pwm_platform_data mt7623_pwm_data = { 292static const struct pwm_mediatek_of_data mt7623_pwm_data = {
290 .num_pwms = 5, 293 .num_pwms = 5,
291 .pwm45_fixup = true, 294 .pwm45_fixup = true,
292}; 295};
293 296
294static const struct mtk_pwm_platform_data mt7628_pwm_data = { 297static const struct pwm_mediatek_of_data mt7628_pwm_data = {
295 .num_pwms = 4, 298 .num_pwms = 4,
296 .pwm45_fixup = true, 299 .pwm45_fixup = true,
297}; 300};
298 301
299static const struct mtk_pwm_platform_data mt8516_pwm_data = { 302static const struct pwm_mediatek_of_data mt8516_pwm_data = {
300 .num_pwms = 5, 303 .num_pwms = 5,
301 .pwm45_fixup = false, 304 .pwm45_fixup = false,
302}; 305};
303 306
304static const struct of_device_id mtk_pwm_of_match[] = { 307static const struct of_device_id pwm_mediatek_of_match[] = {
305 { .compatible = "mediatek,mt2712-pwm", .data = &mt2712_pwm_data }, 308 { .compatible = "mediatek,mt2712-pwm", .data = &mt2712_pwm_data },
306 { .compatible = "mediatek,mt7622-pwm", .data = &mt7622_pwm_data }, 309 { .compatible = "mediatek,mt7622-pwm", .data = &mt7622_pwm_data },
307 { .compatible = "mediatek,mt7623-pwm", .data = &mt7623_pwm_data }, 310 { .compatible = "mediatek,mt7623-pwm", .data = &mt7623_pwm_data },
@@ -309,17 +312,17 @@ static const struct of_device_id mtk_pwm_of_match[] = {
309 { .compatible = "mediatek,mt8516-pwm", .data = &mt8516_pwm_data }, 312 { .compatible = "mediatek,mt8516-pwm", .data = &mt8516_pwm_data },
310 { }, 313 { },
311}; 314};
312MODULE_DEVICE_TABLE(of, mtk_pwm_of_match); 315MODULE_DEVICE_TABLE(of, pwm_mediatek_of_match);
313 316
314static struct platform_driver mtk_pwm_driver = { 317static struct platform_driver pwm_mediatek_driver = {
315 .driver = { 318 .driver = {
316 .name = "mtk-pwm", 319 .name = "pwm-mediatek",
317 .of_match_table = mtk_pwm_of_match, 320 .of_match_table = pwm_mediatek_of_match,
318 }, 321 },
319 .probe = mtk_pwm_probe, 322 .probe = pwm_mediatek_probe,
320 .remove = mtk_pwm_remove, 323 .remove = pwm_mediatek_remove,
321}; 324};
322module_platform_driver(mtk_pwm_driver); 325module_platform_driver(pwm_mediatek_driver);
323 326
324MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); 327MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
325MODULE_LICENSE("GPL"); 328MODULE_LICENSE("GPL");
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-11 01:05:12 -0400
' href='#n2889'>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 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 
/*
 *  Fast Userspace Mutexes (which I call "Futexes!").
 *  (C) Rusty Russell, IBM 2002
 *
 *  Generalized futexes, futex requeueing, misc fixes by Ingo Molnar
 *  (C) Copyright 2003 Red Hat Inc, All Rights Reserved
 *
 *  Removed page pinning, fix privately mapped COW pages and other cleanups
 *  (C) Copyright 2003, 2004 Jamie Lokier
 *
 *  Robust futex support started by Ingo Molnar
 *  (C) Copyright 2006 Red Hat Inc, All Rights Reserved
 *  Thanks to Thomas Gleixner for suggestions, analysis and fixes.
 *
 *  PI-futex support started by Ingo Molnar and Thomas Gleixner
 *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *  Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
 *
 *  PRIVATE futexes by Eric Dumazet
 *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
 *
 *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
 *  Copyright (C) IBM Corporation, 2009
 *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
 *
 *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
 *  enough at me, Linus for the original (flawed) idea, Matthew
 *  Kirkwood for proof-of-concept implementation.
 *
 *  "The futexes are also cursed."
 *  "But they come in a choice of three flavours!"
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/futex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/export.h>
#include <linux/magic.h>
#include <linux/pid.h>
#include <linux/nsproxy.h>
#include <linux/ptrace.h>
#include <linux/sched/rt.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/mm.h>
#include <linux/hugetlb.h>
#include <linux/freezer.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>

#include <asm/futex.h>

#include "locking/rtmutex_common.h"

/*
 * READ this before attempting to hack on futexes!
 *
 * Basic futex operation and ordering guarantees
 * =============================================
 *
 * The waiter reads the futex value in user space and calls
 * futex_wait(). This function computes the hash bucket and acquires
 * the hash bucket lock. After that it reads the futex user space value
 * again and verifies that the data has not changed. If it has not changed
 * it enqueues itself into the hash bucket, releases the hash bucket lock
 * and schedules.
 *
 * The waker side modifies the user space value of the futex and calls
 * futex_wake(). This function computes the hash bucket and acquires the
 * hash bucket lock. Then it looks for waiters on that futex in the hash
 * bucket and wakes them.
 *
 * In futex wake up scenarios where no tasks are blocked on a futex, taking
 * the hb spinlock can be avoided and simply return. In order for this
 * optimization to work, ordering guarantees must exist so that the waiter
 * being added to the list is acknowledged when the list is concurrently being
 * checked by the waker, avoiding scenarios like the following:
 *
 * CPU 0                               CPU 1
 * val = *futex;
 * sys_futex(WAIT, futex, val);
 *   futex_wait(futex, val);
 *   uval = *futex;
 *                                     *futex = newval;
 *                                     sys_futex(WAKE, futex);
 *                                       futex_wake(futex);
 *                                       if (queue_empty())
 *                                         return;
 *   if (uval == val)
 *      lock(hash_bucket(futex));
 *      queue();
 *     unlock(hash_bucket(futex));
 *     schedule();
 *
 * This would cause the waiter on CPU 0 to wait forever because it
 * missed the transition of the user space value from val to newval
 * and the waker did not find the waiter in the hash bucket queue.
 *
 * The correct serialization ensures that a waiter either observes
 * the changed user space value before blocking or is woken by a
 * concurrent waker:
 *
 * CPU 0                                 CPU 1
 * val = *futex;
 * sys_futex(WAIT, futex, val);
 *   futex_wait(futex, val);
 *
 *   waiters++; (a)
 *   smp_mb(); (A) <-- paired with -.
 *                                  |
 *   lock(hash_bucket(futex));      |
 *                                  |
 *   uval = *futex;                 |
 *                                  |        *futex = newval;
 *                                  |        sys_futex(WAKE, futex);
 *                                  |          futex_wake(futex);
 *                                  |
 *                                  `--------> smp_mb(); (B)
 *   if (uval == val)
 *     queue();
 *     unlock(hash_bucket(futex));
 *     schedule();                         if (waiters)
 *                                           lock(hash_bucket(futex));
 *   else                                    wake_waiters(futex);
 *     waiters--; (b)                        unlock(hash_bucket(futex));
 *
 * Where (A) orders the waiters increment and the futex value read through
 * atomic operations (see hb_waiters_inc) and where (B) orders the write
 * to futex and the waiters read -- this is done by the barriers for both
 * shared and private futexes in get_futex_key_refs().
 *
 * This yields the following case (where X:=waiters, Y:=futex):
 *
 *	X = Y = 0
 *
 *	w[X]=1		w[Y]=1
 *	MB		MB
 *	r[Y]=y		r[X]=x
 *
 * Which guarantees that x==0 && y==0 is impossible; which translates back into
 * the guarantee that we cannot both miss the futex variable change and the
 * enqueue.
 *
 * Note that a new waiter is accounted for in (a) even when it is possible that
 * the wait call can return error, in which case we backtrack from it in (b).
 * Refer to the comment in queue_lock().
 *
 * Similarly, in order to account for waiters being requeued on another
 * address we always increment the waiters for the destination bucket before
 * acquiring the lock. It then decrements them again  after releasing it -
 * the code that actually moves the futex(es) between hash buckets (requeue_futex)
 * will do the additional required waiter count housekeeping. This is done for
 * double_lock_hb() and double_unlock_hb(), respectively.
 */

#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
#define futex_cmpxchg_enabled 1
#else
static int  __read_mostly futex_cmpxchg_enabled;
#endif

/*
 * Futex flags used to encode options to functions and preserve them across
 * restarts.
 */
#ifdef CONFIG_MMU
# define FLAGS_SHARED		0x01
#else
/*
 * NOMMU does not have per process address space. Let the compiler optimize
 * code away.
 */
# define FLAGS_SHARED		0x00
#endif
#define FLAGS_CLOCKRT		0x02
#define FLAGS_HAS_TIMEOUT	0x04

/*
 * Priority Inheritance state:
 */
struct futex_pi_state {
	/*
	 * list of 'owned' pi_state instances - these have to be
	 * cleaned up in do_exit() if the task exits prematurely:
	 */
	struct list_head list;

	/*
	 * The PI object:
	 */
	struct rt_mutex pi_mutex;

	struct task_struct *owner;
	atomic_t refcount;

	union futex_key key;
} __randomize_layout;

/**
 * struct futex_q - The hashed futex queue entry, one per waiting task
 * @list:		priority-sorted list of tasks waiting on this futex
 * @task:		the task waiting on the futex
 * @lock_ptr:		the hash bucket lock
 * @key:		the key the futex is hashed on
 * @pi_state:		optional priority inheritance state
 * @rt_waiter:		rt_waiter storage for use with requeue_pi
 * @requeue_pi_key:	the requeue_pi target futex key
 * @bitset:		bitset for the optional bitmasked wakeup
 *
 * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
 * we can wake only the relevant ones (hashed queues may be shared).
 *
 * A futex_q has a woken state, just like tasks have TASK_RUNNING.
 * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
 * The order of wakeup is always to make the first condition true, then
 * the second.
 *
 * PI futexes are typically woken before they are removed from the hash list via
 * the rt_mutex code. See unqueue_me_pi().
 */
struct futex_q {
	struct plist_node list;

	struct task_struct *task;
	spinlock_t *lock_ptr;
	union futex_key key;
	struct futex_pi_state *pi_state;
	struct rt_mutex_waiter *rt_waiter;
	union futex_key *requeue_pi_key;
	u32 bitset;
} __randomize_layout;

static const struct futex_q futex_q_init = {
	/* list gets initialized in queue_me()*/
	.key = FUTEX_KEY_INIT,
	.bitset = FUTEX_BITSET_MATCH_ANY
};

/*
 * Hash buckets are shared by all the futex_keys that hash to the same
 * location.  Each key may have multiple futex_q structures, one for each task
 * waiting on a futex.
 */
struct futex_hash_bucket {
	atomic_t waiters;
	spinlock_t lock;
	struct plist_head chain;
} ____cacheline_aligned_in_smp;

/*
 * The base of the bucket array and its size are always used together
 * (after initialization only in hash_futex()), so ensure that they
 * reside in the same cacheline.
 */
static struct {
	struct futex_hash_bucket *queues;
	unsigned long            hashsize;
} __futex_data __read_mostly __aligned(2*sizeof(long));
#define futex_queues   (__futex_data.queues)
#define futex_hashsize (__futex_data.hashsize)


/*
 * Fault injections for futexes.
 */
#ifdef CONFIG_FAIL_FUTEX

static struct {
	struct fault_attr attr;

	bool ignore_private;
} fail_futex = {
	.attr = FAULT_ATTR_INITIALIZER,
	.ignore_private = false,
};

static int __init setup_fail_futex(char *str)
{
	return setup_fault_attr(&fail_futex.attr, str);
}
__setup("fail_futex=", setup_fail_futex);

static bool should_fail_futex(bool fshared)
{
	if (fail_futex.ignore_private && !fshared)
		return false;

	return should_fail(&fail_futex.attr, 1);
}

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

static int __init fail_futex_debugfs(void)
{
	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
	struct dentry *dir;

	dir = fault_create_debugfs_attr("fail_futex", NULL,
					&fail_futex.attr);
	if (IS_ERR(dir))
		return PTR_ERR(dir);

	if (!debugfs_create_bool("ignore-private", mode, dir,
				 &fail_futex.ignore_private)) {
		debugfs_remove_recursive(dir);
		return -ENOMEM;
	}

	return 0;
}

late_initcall(fail_futex_debugfs);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

#else
static inline bool should_fail_futex(bool fshared)
{
	return false;
}
#endif /* CONFIG_FAIL_FUTEX */

static inline void futex_get_mm(union futex_key *key)
{
	mmgrab(key->private.mm);
	/*
	 * Ensure futex_get_mm() implies a full barrier such that
	 * get_futex_key() implies a full barrier. This is relied upon
	 * as smp_mb(); (B), see the ordering comment above.
	 */
	smp_mb__after_atomic();
}

/*
 * Reflects a new waiter being added to the waitqueue.
 */
static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
	atomic_inc(&hb->waiters);
	/*
	 * Full barrier (A), see the ordering comment above.
	 */
	smp_mb__after_atomic();
#endif
}

/*
 * Reflects a waiter being removed from the waitqueue by wakeup
 * paths.
 */
static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
	atomic_dec(&hb->waiters);
#endif
}

static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
	return atomic_read(&hb->waiters);
#else
	return 1;
#endif
}

/**
 * hash_futex - Return the hash bucket in the global hash
 * @key:	Pointer to the futex key for which the hash is calculated
 *
 * We hash on the keys returned from get_futex_key (see below) and return the
 * corresponding hash bucket in the global hash.
 */
static struct futex_hash_bucket *hash_futex(union futex_key *key)
{
	u32 hash = jhash2((u32*)&key->both.word,
			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
			  key->both.offset);
	return &futex_queues[hash & (futex_hashsize - 1)];
}


/**
 * match_futex - Check whether two futex keys are equal
 * @key1:	Pointer to key1
 * @key2:	Pointer to key2
 *
 * Return 1 if two futex_keys are equal, 0 otherwise.
 */
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
	return (key1 && key2
		&& key1->both.word == key2->both.word
		&& key1->both.ptr == key2->both.ptr
		&& key1->both.offset == key2->both.offset);
}

/*
 * Take a reference to the resource addressed by a key.
 * Can be called while holding spinlocks.
 *
 */
static void get_futex_key_refs(union futex_key *key)
{
	if (!key->both.ptr)
		return;

	/*
	 * On MMU less systems futexes are always "private" as there is no per
	 * process address space. We need the smp wmb nevertheless - yes,
	 * arch/blackfin has MMU less SMP ...
	 */
	if (!IS_ENABLED(CONFIG_MMU)) {
		smp_mb(); /* explicit smp_mb(); (B) */
		return;
	}

	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
	case FUT_OFF_INODE:
		ihold(key->shared.inode); /* implies smp_mb(); (B) */
		break;
	case FUT_OFF_MMSHARED:
		futex_get_mm(key); /* implies smp_mb(); (B) */
		break;
	default:
		/*
		 * Private futexes do not hold reference on an inode or
		 * mm, therefore the only purpose of calling get_futex_key_refs
		 * is because we need the barrier for the lockless waiter check.
		 */
		smp_mb(); /* explicit smp_mb(); (B) */
	}
}

/*
 * Drop a reference to the resource addressed by a key.
 * The hash bucket spinlock must not be held. This is
 * a no-op for private futexes, see comment in the get
 * counterpart.
 */
static void drop_futex_key_refs(union futex_key *key)
{
	if (!key->both.ptr) {
		/* If we're here then we tried to put a key we failed to get */
		WARN_ON_ONCE(1);
		return;
	}

	if (!IS_ENABLED(CONFIG_MMU))
		return;

	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
	case FUT_OFF_INODE:
		iput(key->shared.inode);
		break;
	case FUT_OFF_MMSHARED:
		mmdrop(key->private.mm);
		break;
	}
}

enum futex_access {
	FUTEX_READ,
	FUTEX_WRITE
};

/**
 * get_futex_key() - Get parameters which are the keys for a futex
 * @uaddr:	virtual address of the futex
 * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
 * @key:	address where result is stored.
 * @rw:		mapping needs to be read/write (values: FUTEX_READ,
 *              FUTEX_WRITE)
 *
 * Return: a negative error code or 0
 *
 * The key words are stored in @key on success.
 *
 * For shared mappings, it's (page->index, file_inode(vma->vm_file),
 * offset_within_page).  For private mappings, it's (uaddr, current->mm).
 * We can usually work out the index without swapping in the page.
 *
 * lock_page() might sleep, the caller should not hold a spinlock.
 */
static int
get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_access rw)
{
	unsigned long address = (unsigned long)uaddr;
	struct mm_struct *mm = current->mm;
	struct page *page, *tail;
	struct address_space *mapping;
	int err, ro = 0;

	/*
	 * The futex address must be "naturally" aligned.
	 */
	key->both.offset = address % PAGE_SIZE;
	if (unlikely((address % sizeof(u32)) != 0))
		return -EINVAL;
	address -= key->both.offset;

	if (unlikely(!access_ok(uaddr, sizeof(u32))))
		return -EFAULT;

	if (unlikely(should_fail_futex(fshared)))
		return -EFAULT;

	/*
	 * PROCESS_PRIVATE futexes are fast.
	 * As the mm cannot disappear under us and the 'key' only needs
	 * virtual address, we dont even have to find the underlying vma.
	 * Note : We do have to check 'uaddr' is a valid user address,
	 *        but access_ok() should be faster than find_vma()
	 */
	if (!fshared) {
		key->private.mm = mm;
		key->private.address = address;
		get_futex_key_refs(key);  /* implies smp_mb(); (B) */
		return 0;
	}

again:
	/* Ignore any VERIFY_READ mapping (futex common case) */
	if (unlikely(should_fail_futex(fshared)))
		return -EFAULT;

	err = get_user_pages_fast(address, 1, 1, &page);
	/*
	 * If write access is not required (eg. FUTEX_WAIT), try
	 * and get read-only access.
	 */
	if (err == -EFAULT && rw == FUTEX_READ) {
		err = get_user_pages_fast(address, 1, 0, &page);
		ro = 1;
	}
	if (err < 0)
		return err;
	else
		err = 0;

	/*
	 * The treatment of mapping from this point on is critical. The page
	 * lock protects many things but in this context the page lock
	 * stabilizes mapping, prevents inode freeing in the shared
	 * file-backed region case and guards against movement to swap cache.
	 *
	 * Strictly speaking the page lock is not needed in all cases being
	 * considered here and page lock forces unnecessarily serialization
	 * From this point on, mapping will be re-verified if necessary and
	 * page lock will be acquired only if it is unavoidable
	 *
	 * Mapping checks require the head page for any compound page so the
	 * head page and mapping is looked up now. For anonymous pages, it
	 * does not matter if the page splits in the future as the key is
	 * based on the address. For filesystem-backed pages, the tail is
	 * required as the index of the page determines the key. For
	 * base pages, there is no tail page and tail == page.
	 */
	tail = page;
	page = compound_head(page);
	mapping = READ_ONCE(page->mapping);

	/*
	 * If page->mapping is NULL, then it cannot be a PageAnon
	 * page; but it might be the ZERO_PAGE or in the gate area or
	 * in a special mapping (all cases which we are happy to fail);
	 * or it may have been a good file page when get_user_pages_fast
	 * found it, but truncated or holepunched or subjected to
	 * invalidate_complete_page2 before we got the page lock (also
	 * cases which we are happy to fail).  And we hold a reference,
	 * so refcount care in invalidate_complete_page's remove_mapping
	 * prevents drop_caches from setting mapping to NULL beneath us.
	 *
	 * The case we do have to guard against is when memory pressure made
	 * shmem_writepage move it from filecache to swapcache beneath us:
	 * an unlikely race, but we do need to retry for page->mapping.
	 */
	if (unlikely(!mapping)) {
		int shmem_swizzled;

		/*
		 * Page lock is required to identify which special case above
		 * applies. If this is really a shmem page then the page lock
		 * will prevent unexpected transitions.
		 */
		lock_page(page);
		shmem_swizzled = PageSwapCache(page) || page->mapping;
		unlock_page(page);
		put_page(page);

		if (shmem_swizzled)
			goto again;

		return -EFAULT;
	}

	/*
	 * Private mappings are handled in a simple way.
	 *
	 * If the futex key is stored on an anonymous page, then the associated
	 * object is the mm which is implicitly pinned by the calling process.
	 *
	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
	 * it's a read-only handle, it's expected that futexes attach to
	 * the object not the particular process.
	 */
	if (PageAnon(page)) {
		/*
		 * A RO anonymous page will never change and thus doesn't make
		 * sense for futex operations.
		 */
		if (unlikely(should_fail_futex(fshared)) || ro) {
			err = -EFAULT;
			goto out;
		}

		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
		key->private.mm = mm;
		key->private.address = address;

		get_futex_key_refs(key); /* implies smp_mb(); (B) */

	} else {
		struct inode *inode;

		/*
		 * The associated futex object in this case is the inode and
		 * the page->mapping must be traversed. Ordinarily this should
		 * be stabilised under page lock but it's not strictly
		 * necessary in this case as we just want to pin the inode, not
		 * update the radix tree or anything like that.
		 *
		 * The RCU read lock is taken as the inode is finally freed
		 * under RCU. If the mapping still matches expectations then the
		 * mapping->host can be safely accessed as being a valid inode.
		 */
		rcu_read_lock();

		if (READ_ONCE(page->mapping) != mapping) {
			rcu_read_unlock();
			put_page(page);

			goto again;
		}

		inode = READ_ONCE(mapping->host);
		if (!inode) {
			rcu_read_unlock();
			put_page(page);

			goto again;
		}

		/*
		 * Take a reference unless it is about to be freed. Previously
		 * this reference was taken by ihold under the page lock
		 * pinning the inode in place so i_lock was unnecessary. The
		 * only way for this check to fail is if the inode was
		 * truncated in parallel which is almost certainly an
		 * application bug. In such a case, just retry.
		 *
		 * We are not calling into get_futex_key_refs() in file-backed
		 * cases, therefore a successful atomic_inc return below will
		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
		 */
		if (!atomic_inc_not_zero(&inode->i_count)) {
			rcu_read_unlock();
			put_page(page);

			goto again;
		}

		/* Should be impossible but lets be paranoid for now */
		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
			err = -EFAULT;
			rcu_read_unlock();
			iput(inode);

			goto out;
		}

		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
		key->shared.inode = inode;
		key->shared.pgoff = basepage_index(tail);
		rcu_read_unlock();
	}

out:
	put_page(page);
	return err;
}

static inline void put_futex_key(union futex_key *key)
{
	drop_futex_key_refs(key);
}

/**
 * fault_in_user_writeable() - Fault in user address and verify RW access
 * @uaddr:	pointer to faulting user space address
 *
 * Slow path to fixup the fault we just took in the atomic write
 * access to @uaddr.
 *
 * We have no generic implementation of a non-destructive write to the
 * user address. We know that we faulted in the atomic pagefault
 * disabled section so we can as well avoid the #PF overhead by
 * calling get_user_pages() right away.
 */
static int fault_in_user_writeable(u32 __user *uaddr)
{
	struct mm_struct *mm = current->mm;
	int ret;

	down_read(&mm->mmap_sem);
	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
			       FAULT_FLAG_WRITE, NULL);
	up_read(&mm->mmap_sem);

	return ret < 0 ? ret : 0;
}

/**
 * futex_top_waiter() - Return the highest priority waiter on a futex
 * @hb:		the hash bucket the futex_q's reside in
 * @key:	the futex key (to distinguish it from other futex futex_q's)
 *
 * Must be called with the hb lock held.
 */
static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
					union futex_key *key)
{
	struct futex_q *this;

	plist_for_each_entry(this, &hb->chain, list) {
		if (match_futex(&this->key, key))
			return this;
	}
	return NULL;
}

static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
				      u32 uval, u32 newval)
{
	int ret;

	pagefault_disable();
	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
	pagefault_enable();

	return ret;
}

static int get_futex_value_locked(u32 *dest, u32 __user *from)
{
	int ret;

	pagefault_disable();
	ret = __get_user(*dest, from);
	pagefault_enable();

	return ret ? -EFAULT : 0;
}


/*
 * PI code:
 */
static int refill_pi_state_cache(void)
{
	struct futex_pi_state *pi_state;

	if (likely(current->pi_state_cache))
		return 0;

	pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL);

	if (!pi_state)
		return -ENOMEM;

	INIT_LIST_HEAD(&pi_state->list);
	/* pi_mutex gets initialized later */
	pi_state->owner = NULL;
	atomic_set(&pi_state->refcount, 1);
	pi_state->key = FUTEX_KEY_INIT;

	current->pi_state_cache = pi_state;

	return 0;
}

static struct futex_pi_state *alloc_pi_state(void)
{
	struct futex_pi_state *pi_state = current->pi_state_cache;

	WARN_ON(!pi_state);
	current->pi_state_cache = NULL;

	return pi_state;
}

static void get_pi_state(struct futex_pi_state *pi_state)
{
	WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
}

/*
 * Drops a reference to the pi_state object and frees or caches it
 * when the last reference is gone.
 */
static void put_pi_state(struct futex_pi_state *pi_state)
{
	if (!pi_state)
		return;

	if (!atomic_dec_and_test(&pi_state->refcount))
		return;

	/*
	 * If pi_state->owner is NULL, the owner is most probably dying
	 * and has cleaned up the pi_state already
	 */
	if (pi_state->owner) {
		struct task_struct *owner;

		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
		owner = pi_state->owner;
		if (owner) {
			raw_spin_lock(&owner->pi_lock);
			list_del_init(&pi_state->list);
			raw_spin_unlock(&owner->pi_lock);
		}
		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
	}

	if (current->pi_state_cache) {
		kfree(pi_state);
	} else {
		/*
		 * pi_state->list is already empty.
		 * clear pi_state->owner.
		 * refcount is at 0 - put it back to 1.
		 */
		pi_state->owner = NULL;
		atomic_set(&pi_state->refcount, 1);
		current->pi_state_cache = pi_state;
	}
}

#ifdef CONFIG_FUTEX_PI

/*
 * This task is holding PI mutexes at exit time => bad.
 * Kernel cleans up PI-state, but userspace is likely hosed.
 * (Robust-futex cleanup is separate and might save the day for userspace.)
 */
void exit_pi_state_list(struct task_struct *curr)
{
	struct list_head *next, *head = &curr->pi_state_list;
	struct futex_pi_state *pi_state;
	struct futex_hash_bucket *hb;
	union futex_key key = FUTEX_KEY_INIT;

	if (!futex_cmpxchg_enabled)
		return;
	/*
	 * We are a ZOMBIE and nobody can enqueue itself on
	 * pi_state_list anymore, but we have to be careful
	 * versus waiters unqueueing themselves:
	 */
	raw_spin_lock_irq(&curr->pi_lock);
	while (!list_empty(head)) {
		next = head->next;
		pi_state = list_entry(next, struct futex_pi_state, list);
		key = pi_state->key;
		hb = hash_futex(&key);

		/*
		 * We can race against put_pi_state() removing itself from the
		 * list (a waiter going away). put_pi_state() will first
		 * decrement the reference count and then modify the list, so
		 * its possible to see the list entry but fail this reference
		 * acquire.
		 *
		 * In that case; drop the locks to let put_pi_state() make
		 * progress and retry the loop.
		 */
		if (!atomic_inc_not_zero(&pi_state->refcount)) {
			raw_spin_unlock_irq(&curr->pi_lock);
			cpu_relax();
			raw_spin_lock_irq(&curr->pi_lock);
			continue;
		}
		raw_spin_unlock_irq(&curr->pi_lock);

		spin_lock(&hb->lock);
		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
		raw_spin_lock(&curr->pi_lock);
		/*
		 * We dropped the pi-lock, so re-check whether this
		 * task still owns the PI-state:
		 */
		if (head->next != next) {
			/* retain curr->pi_lock for the loop invariant */
			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
			spin_unlock(&hb->lock);
			put_pi_state(pi_state);
			continue;
		}

		WARN_ON(pi_state->owner != curr);
		WARN_ON(list_empty(&pi_state->list));
		list_del_init(&pi_state->list);
		pi_state->owner = NULL;

		raw_spin_unlock(&curr->pi_lock);
		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
		spin_unlock(&hb->lock);

		rt_mutex_futex_unlock(&pi_state->pi_mutex);
		put_pi_state(pi_state);

		raw_spin_lock_irq(&curr->pi_lock);
	}
	raw_spin_unlock_irq(&curr->pi_lock);
}

#endif

/*
 * We need to check the following states:
 *
 *      Waiter | pi_state | pi->owner | uTID      | uODIED | ?
 *
 * [1]  NULL   | ---      | ---       | 0         | 0/1    | Valid
 * [2]  NULL   | ---      | ---       | >0        | 0/1    | Valid
 *
 * [3]  Found  | NULL     | --        | Any       | 0/1    | Invalid
 *
 * [4]  Found  | Found    | NULL      | 0         | 1      | Valid
 * [5]  Found  | Found    | NULL      | >0        | 1      | Invalid
 *
 * [6]  Found  | Found    | task      | 0         | 1      | Valid
 *
 * [7]  Found  | Found    | NULL      | Any       | 0      | Invalid
 *
 * [8]  Found  | Found    | task      | ==taskTID | 0/1    | Valid
 * [9]  Found  | Found    | task      | 0         | 0      | Invalid
 * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
 *
 * [1]	Indicates that the kernel can acquire the futex atomically. We
 *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
 *
 * [2]	Valid, if TID does not belong to a kernel thread. If no matching
 *      thread is found then it indicates that the owner TID has died.
 *
 * [3]	Invalid. The waiter is queued on a non PI futex
 *
 * [4]	Valid state after exit_robust_list(), which sets the user space
 *	value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
 *
 * [5]	The user space value got manipulated between exit_robust_list()
 *	and exit_pi_state_list()
 *
 * [6]	Valid state after exit_pi_state_list() which sets the new owner in
 *	the pi_state but cannot access the user space value.
 *
 * [7]	pi_state->owner can only be NULL when the OWNER_DIED bit is set.
 *
 * [8]	Owner and user space value match
 *
 * [9]	There is no transient state which sets the user space TID to 0
 *	except exit_robust_list(), but this is indicated by the
 *	FUTEX_OWNER_DIED bit. See [4]
 *
 * [10] There is no transient state which leaves owner and user space
 *	TID out of sync.
 *
 *
 * Serialization and lifetime rules:
 *
 * hb->lock:
 *
 *	hb -> futex_q, relation
 *	futex_q -> pi_state, relation
 *
 *	(cannot be raw because hb can contain arbitrary amount
 *	 of futex_q's)
 *
 * pi_mutex->wait_lock:
 *
 *	{uval, pi_state}
 *
 *	(and pi_mutex 'obviously')
 *
 * p->pi_lock:
 *
 *	p->pi_state_list -> pi_state->list, relation
 *
 * pi_state->refcount:
 *
 *	pi_state lifetime
 *
 *
 * Lock order:
 *
 *   hb->lock
 *     pi_mutex->wait_lock
 *       p->pi_lock
 *
 */

/*
 * Validate that the existing waiter has a pi_state and sanity check
 * the pi_state against the user space value. If correct, attach to
 * it.
 */
static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
			      struct futex_pi_state *pi_state,
			      struct futex_pi_state **ps)
{
	pid_t pid = uval & FUTEX_TID_MASK;
	u32 uval2;
	int ret;

	/*
	 * Userspace might have messed up non-PI and PI futexes [3]
	 */
	if (unlikely(!pi_state))
		return -EINVAL;

	/*
	 * We get here with hb->lock held, and having found a
	 * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
	 * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
	 * which in turn means that futex_lock_pi() still has a reference on
	 * our pi_state.
	 *
	 * The waiter holding a reference on @pi_state also protects against
	 * the unlocked put_pi_state() in futex_unlock_pi(), futex_lock_pi()
	 * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
	 * free pi_state before we can take a reference ourselves.
	 */
	WARN_ON(!atomic_read(&pi_state->refcount));

	/*
	 * Now that we have a pi_state, we can acquire wait_lock
	 * and do the state validation.
	 */
	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);

	/*
	 * Since {uval, pi_state} is serialized by wait_lock, and our current
	 * uval was read without holding it, it can have changed. Verify it
	 * still is what we expect it to be, otherwise retry the entire
	 * operation.
	 */
	if (get_futex_value_locked(&uval2, uaddr))
		goto out_efault;

	if (uval != uval2)
		goto out_eagain;

	/*
	 * Handle the owner died case:
	 */
	if (uval & FUTEX_OWNER_DIED) {
		/*
		 * exit_pi_state_list sets owner to NULL and wakes the
		 * topmost waiter. The task which acquires the
		 * pi_state->rt_mutex will fixup owner.
		 */
		if (!pi_state->owner) {
			/*
			 * No pi state owner, but the user space TID
			 * is not 0. Inconsistent state. [5]
			 */
			if (pid)
				goto out_einval;
			/*
			 * Take a ref on the state and return success. [4]
			 */
			goto out_attach;
		}

		/*
		 * If TID is 0, then either the dying owner has not
		 * yet executed exit_pi_state_list() or some waiter
		 * acquired the rtmutex in the pi state, but did not
		 * yet fixup the TID in user space.
		 *
		 * Take a ref on the state and return success. [6]
		 */
		if (!pid)
			goto out_attach;
	} else {
		/*
		 * If the owner died bit is not set, then the pi_state
		 * must have an owner. [7]
		 */
		if (!pi_state->owner)
			goto out_einval;
	}

	/*
	 * Bail out if user space manipulated the futex value. If pi
	 * state exists then the owner TID must be the same as the
	 * user space TID. [9/10]
	 */
	if (pid != task_pid_vnr(pi_state->owner))
		goto out_einval;

out_attach:
	get_pi_state(pi_state);
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
	*ps = pi_state;
	return 0;

out_einval:
	ret = -EINVAL;
	goto out_error;

out_eagain:
	ret = -EAGAIN;
	goto out_error;

out_efault:
	ret = -EFAULT;
	goto out_error;

out_error:
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
	return ret;
}

static int handle_exit_race(u32 __user *uaddr, u32 uval,
			    struct task_struct *tsk)
{
	u32 uval2;

	/*
	 * If PF_EXITPIDONE is not yet set, then try again.
	 */
	if (tsk && !(tsk->flags & PF_EXITPIDONE))
		return -EAGAIN;

	/*
	 * Reread the user space value to handle the following situation:
	 *
	 * CPU0				CPU1
	 *
	 * sys_exit()			sys_futex()
	 *  do_exit()			 futex_lock_pi()
	 *                                futex_lock_pi_atomic()
	 *   exit_signals(tsk)		    No waiters:
	 *    tsk->flags |= PF_EXITING;	    *uaddr == 0x00000PID
	 *  mm_release(tsk)		    Set waiter bit
	 *   exit_robust_list(tsk) {	    *uaddr = 0x80000PID;
	 *      Set owner died		    attach_to_pi_owner() {
	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
	 *   }				     if (!tsk->flags & PF_EXITING) {
	 *  ...				       attach();
	 *  tsk->flags |= PF_EXITPIDONE;     } else {
	 *				       if (!(tsk->flags & PF_EXITPIDONE))
	 *				         return -EAGAIN;
	 *				       return -ESRCH; <--- FAIL
	 *				     }
	 *
	 * Returning ESRCH unconditionally is wrong here because the
	 * user space value has been changed by the exiting task.
	 *
	 * The same logic applies to the case where the exiting task is
	 * already gone.
	 */
	if (get_futex_value_locked(&uval2, uaddr))
		return -EFAULT;

	/* If the user space value has changed, try again. */
	if (uval2 != uval)
		return -EAGAIN;

	/*
	 * The exiting task did not have a robust list, the robust list was
	 * corrupted or the user space value in *uaddr is simply bogus.
	 * Give up and tell user space.
	 */
	return -ESRCH;
}

/*
 * Lookup the task for the TID provided from user space and attach to
 * it after doing proper sanity checks.
 */
static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
			      struct futex_pi_state **ps)
{
	pid_t pid = uval & FUTEX_TID_MASK;
	struct futex_pi_state *pi_state;
	struct task_struct *p;

	/*
	 * We are the first waiter - try to look up the real owner and attach
	 * the new pi_state to it, but bail out when TID = 0 [1]
	 *
	 * The !pid check is paranoid. None of the call sites should end up
	 * with pid == 0, but better safe than sorry. Let the caller retry
	 */
	if (!pid)
		return -EAGAIN;
	p = find_get_task_by_vpid(pid);
	if (!p)
		return handle_exit_race(uaddr, uval, NULL);

	if (unlikely(p->flags & PF_KTHREAD)) {
		put_task_struct(p);
		return -EPERM;
	}

	/*
	 * We need to look at the task state flags to figure out,
	 * whether the task is exiting. To protect against the do_exit
	 * change of the task flags, we do this protected by
	 * p->pi_lock:
	 */
	raw_spin_lock_irq(&p->pi_lock);
	if (unlikely(p->flags & PF_EXITING)) {
		/*
		 * The task is on the way out. When PF_EXITPIDONE is
		 * set, we know that the task has finished the
		 * cleanup:
		 */
		int ret = handle_exit_race(uaddr, uval, p);

		raw_spin_unlock_irq(&p->pi_lock);
		put_task_struct(p);
		return ret;
	}

	/*
	 * No existing pi state. First waiter. [2]
	 *
	 * This creates pi_state, we have hb->lock held, this means nothing can
	 * observe this state, wait_lock is irrelevant.
	 */
	pi_state = alloc_pi_state();

	/*
	 * Initialize the pi_mutex in locked state and make @p
	 * the owner of it:
	 */
	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);

	/* Store the key for possible exit cleanups: */
	pi_state->key = *key;

	WARN_ON(!list_empty(&pi_state->list));
	list_add(&pi_state->list, &p->pi_state_list);
	/*
	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
	 * because there is no concurrency as the object is not published yet.
	 */
	pi_state->owner = p;
	raw_spin_unlock_irq(&p->pi_lock);

	put_task_struct(p);

	*ps = pi_state;

	return 0;
}

static int lookup_pi_state(u32 __user *uaddr, u32 uval,
			   struct futex_hash_bucket *hb,
			   union futex_key *key, struct futex_pi_state **ps)
{
	struct futex_q *top_waiter = futex_top_waiter(hb, key);

	/*
	 * If there is a waiter on that futex, validate it and
	 * attach to the pi_state when the validation succeeds.
	 */
	if (top_waiter)
		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);

	/*
	 * We are the first waiter - try to look up the owner based on
	 * @uval and attach to it.
	 */
	return attach_to_pi_owner(uaddr, uval, key, ps);
}

static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
{
	u32 uninitialized_var(curval);

	if (unlikely(should_fail_futex(true)))
		return -EFAULT;

	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
		return -EFAULT;

	/* If user space value changed, let the caller retry */
	return curval != uval ? -EAGAIN : 0;
}

/**
 * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
 * @uaddr:		the pi futex user address
 * @hb:			the pi futex hash bucket
 * @key:		the futex key associated with uaddr and hb
 * @ps:			the pi_state pointer where we store the result of the
 *			lookup
 * @task:		the task to perform the atomic lock work for.  This will
 *			be "current" except in the case of requeue pi.
 * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
 *
 * Return:
 *  -  0 - ready to wait;
 *  -  1 - acquired the lock;
 *  - <0 - error
 *
 * The hb->lock and futex_key refs shall be held by the caller.
 */
static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
				union futex_key *key,
				struct futex_pi_state **ps,
				struct task_struct *task, int set_waiters)
{
	u32 uval, newval, vpid = task_pid_vnr(task);
	struct futex_q *top_waiter;
	int ret;

	/*
	 * Read the user space value first so we can validate a few
	 * things before proceeding further.
	 */
	if (get_futex_value_locked(&uval, uaddr))
		return -EFAULT;

	if (unlikely(should_fail_futex(true)))
		return -EFAULT;

	/*
	 * Detect deadlocks.
	 */
	if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
		return -EDEADLK;

	if ((unlikely(should_fail_futex(true))))
		return -EDEADLK;

	/*
	 * Lookup existing state first. If it exists, try to attach to
	 * its pi_state.
	 */
	top_waiter = futex_top_waiter(hb, key);
	if (top_waiter)
		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);

	/*
	 * No waiter and user TID is 0. We are here because the
	 * waiters or the owner died bit is set or called from
	 * requeue_cmp_pi or for whatever reason something took the
	 * syscall.
	 */
	if (!(uval & FUTEX_TID_MASK)) {
		/*
		 * We take over the futex. No other waiters and the user space
		 * TID is 0. We preserve the owner died bit.
		 */
		newval = uval & FUTEX_OWNER_DIED;
		newval |= vpid;

		/* The futex requeue_pi code can enforce the waiters bit */
		if (set_waiters)
			newval |= FUTEX_WAITERS;

		ret = lock_pi_update_atomic(uaddr, uval, newval);
		/* If the take over worked, return 1 */
		return ret < 0 ? ret : 1;
	}

	/*
	 * First waiter. Set the waiters bit before attaching ourself to
	 * the owner. If owner tries to unlock, it will be forced into
	 * the kernel and blocked on hb->lock.
	 */
	newval = uval | FUTEX_WAITERS;
	ret = lock_pi_update_atomic(uaddr, uval, newval);
	if (ret)
		return ret;
	/*
	 * If the update of the user space value succeeded, we try to
	 * attach to the owner. If that fails, no harm done, we only
	 * set the FUTEX_WAITERS bit in the user space variable.
	 */
	return attach_to_pi_owner(uaddr, newval, key, ps);
}

/**
 * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
 * @q:	The futex_q to unqueue
 *
 * The q->lock_ptr must not be NULL and must be held by the caller.
 */
static void __unqueue_futex(struct futex_q *q)
{
	struct futex_hash_bucket *hb;

	if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list)))
		return;
	lockdep_assert_held(q->lock_ptr);

	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
	plist_del(&q->list, &hb->chain);
	hb_waiters_dec(hb);
}

/*
 * The hash bucket lock must be held when this is called.
 * Afterwards, the futex_q must not be accessed. Callers
 * must ensure to later call wake_up_q() for the actual
 * wakeups to occur.
 */
static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
{
	struct task_struct *p = q->task;

	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
		return;

	/*
	 * Queue the task for later wakeup for after we've released
	 * the hb->lock. wake_q_add() grabs reference to p.
	 */
	wake_q_add(wake_q, p);
	__unqueue_futex(q);
	/*
	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
	 * is written, without taking any locks. This is possible in the event
	 * of a spurious wakeup, for example. A memory barrier is required here
	 * to prevent the following store to lock_ptr from getting ahead of the
	 * plist_del in __unqueue_futex().
	 */
	smp_store_release(&q->lock_ptr, NULL);
}

/*
 * Caller must hold a reference on @pi_state.
 */
static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
{
	u32 uninitialized_var(curval), newval;
	struct task_struct *new_owner;
	bool postunlock = false;
	DEFINE_WAKE_Q(wake_q);
	int ret = 0;

	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
	if (WARN_ON_ONCE(!new_owner)) {
		/*
		 * As per the comment in futex_unlock_pi() this should not happen.
		 *
		 * When this happens, give up our locks and try again, giving
		 * the futex_lock_pi() instance time to complete, either by
		 * waiting on the rtmutex or removing itself from the futex
		 * queue.
		 */
		ret = -EAGAIN;
		goto out_unlock;
	}

	/*
	 * We pass it to the next owner. The WAITERS bit is always kept
	 * enabled while there is PI state around. We cleanup the owner
	 * died bit, because we are the owner.
	 */
	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);

	if (unlikely(should_fail_futex(true)))
		ret = -EFAULT;

	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
		ret = -EFAULT;

	} else if (curval != uval) {
		/*
		 * If a unconditional UNLOCK_PI operation (user space did not
		 * try the TID->0 transition) raced with a waiter setting the
		 * FUTEX_WAITERS flag between get_user() and locking the hash
		 * bucket lock, retry the operation.
		 */
		if ((FUTEX_TID_MASK & curval) == uval)
			ret = -EAGAIN;
		else
			ret = -EINVAL;
	}

	if (ret)
		goto out_unlock;

	/*
	 * This is a point of no return; once we modify the uval there is no
	 * going back and subsequent operations must not fail.
	 */

	raw_spin_lock(&pi_state->owner->pi_lock);
	WARN_ON(list_empty(&pi_state->list));
	list_del_init(&pi_state->list);
	raw_spin_unlock(&pi_state->owner->pi_lock);

	raw_spin_lock(&new_owner->pi_lock);
	WARN_ON(!list_empty(&pi_state->list));
	list_add(&pi_state->list, &new_owner->pi_state_list);
	pi_state->owner = new_owner;
	raw_spin_unlock(&new_owner->pi_lock);

	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);

out_unlock:
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);

	if (postunlock)
		rt_mutex_postunlock(&wake_q);

	return ret;
}

/*
 * Express the locking dependencies for lockdep:
 */
static inline void
double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
{
	if (hb1 <= hb2) {
		spin_lock(&hb1->lock);
		if (hb1 < hb2)
			spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
	} else { /* hb1 > hb2 */
		spin_lock(&hb2->lock);
		spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING);
	}
}

static inline void
double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
{
	spin_unlock(&hb1->lock);
	if (hb1 != hb2)
		spin_unlock(&hb2->lock);
}

/*
 * Wake up waiters matching bitset queued on this futex (uaddr).
 */
static int
futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
	struct futex_hash_bucket *hb;
	struct futex_q *this, *next;
	union futex_key key = FUTEX_KEY_INIT;
	int ret;
	DEFINE_WAKE_Q(wake_q);

	if (!bitset)
		return -EINVAL;

	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ);
	if (unlikely(ret != 0))
		goto out;

	hb = hash_futex(&key);

	/* Make sure we really have tasks to wakeup */
	if (!hb_waiters_pending(hb))
		goto out_put_key;

	spin_lock(&hb->lock);

	plist_for_each_entry_safe(this, next, &hb->chain, list) {
		if (match_futex (&this->key, &key)) {
			if (this->pi_state || this->rt_waiter) {
				ret = -EINVAL;
				break;
			}

			/* Check if one of the bits is set in both bitsets */
			if (!(this->bitset & bitset))
				continue;

			mark_wake_futex(&wake_q, this);
			if (++ret >= nr_wake)
				break;
		}
	}

	spin_unlock(&hb->lock);
	wake_up_q(&wake_q);
out_put_key:
	put_futex_key(&key);
out:
	return ret;
}

static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
{
	unsigned int op =	  (encoded_op & 0x70000000) >> 28;
	unsigned int cmp =	  (encoded_op & 0x0f000000) >> 24;
	int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
	int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
	int oldval, ret;

	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
		if (oparg < 0 || oparg > 31) {
			char comm[sizeof(current->comm)];
			/*
			 * kill this print and return -EINVAL when userspace
			 * is sane again
			 */
			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
					get_task_comm(comm, current), oparg);
			oparg &= 31;
		}
		oparg = 1 << oparg;
	}

	if (!access_ok(uaddr, sizeof(u32)))
		return -EFAULT;

	ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
	if (ret)
		return ret;

	switch (cmp) {
	case FUTEX_OP_CMP_EQ:
		return oldval == cmparg;
	case FUTEX_OP_CMP_NE:
		return oldval != cmparg;
	case FUTEX_OP_CMP_LT:
		return oldval < cmparg;
	case FUTEX_OP_CMP_GE:
		return oldval >= cmparg;
	case FUTEX_OP_CMP_LE:
		return oldval <= cmparg;
	case FUTEX_OP_CMP_GT:
		return oldval > cmparg;
	default:
		return -ENOSYS;
	}
}

/*
 * Wake up all waiters hashed on the physical page that is mapped
 * to this virtual address:
 */
static int
futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
	      int nr_wake, int nr_wake2, int op)
{
	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
	struct futex_hash_bucket *hb1, *hb2;
	struct futex_q *this, *next;
	int ret, op_ret;
	DEFINE_WAKE_Q(wake_q);

retry:
	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
	if (unlikely(ret != 0))
		goto out;
	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
	if (unlikely(ret != 0))
		goto out_put_key1;

	hb1 = hash_futex(&key1);
	hb2 = hash_futex(&key2);

retry_private:
	double_lock_hb(hb1, hb2);
	op_ret = futex_atomic_op_inuser(op, uaddr2);
	if (unlikely(op_ret < 0)) {

		double_unlock_hb(hb1, hb2);

#ifndef CONFIG_MMU
		/*
		 * we don't get EFAULT from MMU faults if we don't have an MMU,
		 * but we might get them from range checking
		 */
		ret = op_ret;
		goto out_put_keys;
#endif

		if (unlikely(op_ret != -EFAULT)) {
			ret = op_ret;
			goto out_put_keys;
		}

		ret = fault_in_user_writeable(uaddr2);
		if (ret)
			goto out_put_keys;

		if (!(flags & FLAGS_SHARED))
			goto retry_private;

		put_futex_key(&key2);
		put_futex_key(&key1);
		goto retry;
	}

	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
		if (match_futex (&this->key, &key1)) {
			if (this->pi_state || this->rt_waiter) {
				ret = -EINVAL;
				goto out_unlock;
			}
			mark_wake_futex(&wake_q, this);
			if (++ret >= nr_wake)
				break;
		}
	}

	if (op_ret > 0) {
		op_ret = 0;
		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
			if (match_futex (&this->key, &key2)) {
				if (this->pi_state || this->rt_waiter) {
					ret = -EINVAL;
					goto out_unlock;
				}
				mark_wake_futex(&wake_q, this);
				if (++op_ret >= nr_wake2)
					break;
			}
		}
		ret += op_ret;
	}

out_unlock:
	double_unlock_hb(hb1, hb2);
	wake_up_q(&wake_q);
out_put_keys:
	put_futex_key(&key2);
out_put_key1:
	put_futex_key(&key1);
out:
	return ret;
}

/**
 * requeue_futex() - Requeue a futex_q from one hb to another
 * @q:		the futex_q to requeue
 * @hb1:	the source hash_bucket
 * @hb2:	the target hash_bucket
 * @key2:	the new key for the requeued futex_q
 */
static inline
void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
		   struct futex_hash_bucket *hb2, union futex_key *key2)
{

	/*
	 * If key1 and key2 hash to the same bucket, no need to
	 * requeue.
	 */
	if (likely(&hb1->chain != &hb2->chain)) {
		plist_del(&q->list, &hb1->chain);
		hb_waiters_dec(hb1);
		hb_waiters_inc(hb2);
		plist_add(&q->list, &hb2->chain);
		q->lock_ptr = &hb2->lock;
	}
	get_futex_key_refs(key2);
	q->key = *key2;
}

/**
 * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
 * @q:		the futex_q
 * @key:	the key of the requeue target futex
 * @hb:		the hash_bucket of the requeue target futex
 *
 * During futex_requeue, with requeue_pi=1, it is possible to acquire the
 * target futex if it is uncontended or via a lock steal.  Set the futex_q key
 * to the requeue target futex so the waiter can detect the wakeup on the right
 * futex, but remove it from the hb and NULL the rt_waiter so it can detect
 * atomic lock acquisition.  Set the q->lock_ptr to the requeue target hb->lock
 * to protect access to the pi_state to fixup the owner later.  Must be called
 * with both q->lock_ptr and hb->lock held.
 */
static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
			   struct futex_hash_bucket *hb)
{
	get_futex_key_refs(key);
	q->key = *key;

	__unqueue_futex(q);

	WARN_ON(!q->rt_waiter);
	q->rt_waiter = NULL;

	q->lock_ptr = &hb->lock;

	wake_up_state(q->task, TASK_NORMAL);
}

/**
 * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
 * @pifutex:		the user address of the to futex
 * @hb1:		the from futex hash bucket, must be locked by the caller
 * @hb2:		the to futex hash bucket, must be locked by the caller
 * @key1:		the from futex key
 * @key2:		the to futex key
 * @ps:			address to store the pi_state pointer
 * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
 *
 * Try and get the lock on behalf of the top waiter if we can do it atomically.
 * Wake the top waiter if we succeed.  If the caller specified set_waiters,
 * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
 * hb1 and hb2 must be held by the caller.
 *
 * Return:
 *  -  0 - failed to acquire the lock atomically;
 *  - >0 - acquired the lock, return value is vpid of the top_waiter
 *  - <0 - error
 */
static int futex_proxy_trylock_atomic(u32 __user *pifutex,
				 struct futex_hash_bucket *hb1,
				 struct futex_hash_bucket *hb2,
				 union futex_key *key1, union futex_key *key2,
				 struct futex_pi_state **ps, int set_waiters)
{
	struct futex_q *top_waiter = NULL;
	u32 curval;
	int ret, vpid;

	if (get_futex_value_locked(&curval, pifutex))
		return -EFAULT;

	if (unlikely(should_fail_futex(true)))
		return -EFAULT;

	/*
	 * Find the top_waiter and determine if there are additional waiters.
	 * If the caller intends to requeue more than 1 waiter to pifutex,
	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
	 * as we have means to handle the possible fault.  If not, don't set
	 * the bit unecessarily as it will force the subsequent unlock to enter
	 * the kernel.
	 */
	top_waiter = futex_top_waiter(hb1, key1);

	/* There are no waiters, nothing for us to do. */
	if (!top_waiter)
		return 0;

	/* Ensure we requeue to the expected futex. */
	if (!match_futex(top_waiter->requeue_pi_key, key2))
		return -EINVAL;

	/*
	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
	 * the contended case or if set_waiters is 1.  The pi_state is returned
	 * in ps in contended cases.
	 */
	vpid = task_pid_vnr(top_waiter->task);
	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
				   set_waiters);
	if (ret == 1) {
		requeue_pi_wake_futex(top_waiter, key2, hb2);
		return vpid;
	}
	return ret;
}

/**
 * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
 * @uaddr1:	source futex user address
 * @flags:	futex flags (FLAGS_SHARED, etc.)
 * @uaddr2:	target futex user address
 * @nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
 * @nr_requeue:	number of waiters to requeue (0-INT_MAX)
 * @cmpval:	@uaddr1 expected value (or %NULL)
 * @requeue_pi:	if we are attempting to requeue from a non-pi futex to a
 *		pi futex (pi to pi requeue is not supported)
 *
 * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
 * uaddr2 atomically on behalf of the top waiter.
 *
 * Return:
 *  - >=0 - on success, the number of tasks requeued or woken;
 *  -  <0 - on error
 */
static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
			 u32 __user *uaddr2, int nr_wake, int nr_requeue,
			 u32 *cmpval, int requeue_pi)
{
	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
	int drop_count = 0, task_count = 0, ret;
	struct futex_pi_state *pi_state = NULL;
	struct futex_hash_bucket *hb1, *hb2;
	struct futex_q *this, *next;
	DEFINE_WAKE_Q(wake_q);

	if (nr_wake < 0 || nr_requeue < 0)
		return -EINVAL;

	/*
	 * When PI not supported: return -ENOSYS if requeue_pi is true,
	 * consequently the compiler knows requeue_pi is always false past
	 * this point which will optimize away all the conditional code
	 * further down.
	 */
	if (!IS_ENABLED(CONFIG_FUTEX_PI) && requeue_pi)
		return -ENOSYS;

	if (requeue_pi) {
		/*
		 * Requeue PI only works on two distinct uaddrs. This
		 * check is only valid for private futexes. See below.
		 */
		if (uaddr1 == uaddr2)
			return -EINVAL;

		/*
		 * requeue_pi requires a pi_state, try to allocate it now
		 * without any locks in case it fails.
		 */
		if (refill_pi_state_cache())
			return -ENOMEM;
		/*
		 * requeue_pi must wake as many tasks as it can, up to nr_wake
		 * + nr_requeue, since it acquires the rt_mutex prior to
		 * returning to userspace, so as to not leave the rt_mutex with
		 * waiters and no owner.  However, second and third wake-ups
		 * cannot be predicted as they involve race conditions with the
		 * first wake and a fault while looking up the pi_state.  Both
		 * pthread_cond_signal() and pthread_cond_broadcast() should
		 * use nr_wake=1.
		 */
		if (nr_wake != 1)
			return -EINVAL;
	}

retry:
	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
	if (unlikely(ret != 0))
		goto out;
	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
			    requeue_pi ? FUTEX_WRITE : FUTEX_READ);
	if (unlikely(ret != 0))
		goto out_put_key1;

	/*
	 * The check above which compares uaddrs is not sufficient for
	 * shared futexes. We need to compare the keys:
	 */
	if (requeue_pi && match_futex(&key1, &key2)) {
		ret = -EINVAL;
		goto out_put_keys;
	}

	hb1 = hash_futex(&key1);
	hb2 = hash_futex(&key2);

retry_private:
	hb_waiters_inc(hb2);
	double_lock_hb(hb1, hb2);

	if (likely(cmpval != NULL)) {
		u32 curval;

		ret = get_futex_value_locked(&curval, uaddr1);

		if (unlikely(ret)) {
			double_unlock_hb(hb1, hb2);
			hb_waiters_dec(hb2);

			ret = get_user(curval, uaddr1);
			if (ret)
				goto out_put_keys;

			if (!(flags & FLAGS_SHARED))
				goto retry_private;

			put_futex_key(&key2);
			put_futex_key(&key1);
			goto retry;
		}
		if (curval != *cmpval) {
			ret = -EAGAIN;
			goto out_unlock;
		}
	}

	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
		/*
		 * Attempt to acquire uaddr2 and wake the top waiter. If we
		 * intend to requeue waiters, force setting the FUTEX_WAITERS
		 * bit.  We force this here where we are able to easily handle
		 * faults rather in the requeue loop below.
		 */
		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
						 &key2, &pi_state, nr_requeue);

		/*
		 * At this point the top_waiter has either taken uaddr2 or is
		 * waiting on it.  If the former, then the pi_state will not
		 * exist yet, look it up one more time to ensure we have a
		 * reference to it. If the lock was taken, ret contains the
		 * vpid of the top waiter task.
		 * If the lock was not taken, we have pi_state and an initial
		 * refcount on it. In case of an error we have nothing.
		 */
		if (ret > 0) {
			WARN_ON(pi_state);
			drop_count++;
			task_count++;
			/*
			 * If we acquired the lock, then the user space value
			 * of uaddr2 should be vpid. It cannot be changed by
			 * the top waiter as it is blocked on hb2 lock if it
			 * tries to do so. If something fiddled with it behind
			 * our back the pi state lookup might unearth it. So
			 * we rather use the known value than rereading and
			 * handing potential crap to lookup_pi_state.
			 *
			 * If that call succeeds then we have pi_state and an
			 * initial refcount on it.
			 */
			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
		}

		switch (ret) {
		case 0:
			/* We hold a reference on the pi state. */
			break;

			/* If the above failed, then pi_state is NULL */
		case -EFAULT:
			double_unlock_hb(hb1, hb2);
			hb_waiters_dec(hb2);
			put_futex_key(&key2);
			put_futex_key(&key1);
			ret = fault_in_user_writeable(uaddr2);
			if (!ret)
				goto retry;
			goto out;
		case -EAGAIN:
			/*
			 * Two reasons for this:
			 * - Owner is exiting and we just wait for the
			 *   exit to complete.
			 * - The user space value changed.
			 */
			double_unlock_hb(hb1, hb2);
			hb_waiters_dec(hb2);
			put_futex_key(&key2);
			put_futex_key(&key1);
			cond_resched();
			goto retry;
		default:
			goto out_unlock;
		}
	}

	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
		if (task_count - nr_wake >= nr_requeue)
			break;

		if (!match_futex(&this->key, &key1))
			continue;

		/*
		 * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
		 * be paired with each other and no other futex ops.
		 *
		 * We should never be requeueing a futex_q with a pi_state,
		 * which is awaiting a futex_unlock_pi().
		 */
		if ((requeue_pi && !this->rt_waiter) ||
		    (!requeue_pi && this->rt_waiter) ||
		    this->pi_state) {
			ret = -EINVAL;
			break;
		}

		/*
		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
		 * lock, we already woke the top_waiter.  If not, it will be
		 * woken by futex_unlock_pi().
		 */
		if (++task_count <= nr_wake && !requeue_pi) {
			mark_wake_futex(&wake_q, this);
			continue;
		}

		/* Ensure we requeue to the expected futex for requeue_pi. */
		if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) {
			ret = -EINVAL;
			break;
		}

		/*
		 * Requeue nr_requeue waiters and possibly one more in the case
		 * of requeue_pi if we couldn't acquire the lock atomically.
		 */
		if (requeue_pi) {
			/*
			 * Prepare the waiter to take the rt_mutex. Take a
			 * refcount on the pi_state and store the pointer in
			 * the futex_q object of the waiter.
			 */
			get_pi_state(pi_state);
			this->pi_state = pi_state;
			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
							this->rt_waiter,
							this->task);
			if (ret == 1) {
				/*
				 * We got the lock. We do neither drop the
				 * refcount on pi_state nor clear
				 * this->pi_state because the waiter needs the
				 * pi_state for cleaning up the user space
				 * value. It will drop the refcount after
				 * doing so.
				 */
				requeue_pi_wake_futex(this, &key2, hb2);
				drop_count++;
				continue;
			} else if (ret) {
				/*
				 * rt_mutex_start_proxy_lock() detected a
				 * potential deadlock when we tried to queue
				 * that waiter. Drop the pi_state reference
				 * which we took above and remove the pointer
				 * to the state from the waiters futex_q
				 * object.
				 */
				this->pi_state = NULL;
				put_pi_state(pi_state);
				/*
				 * We stop queueing more waiters and let user
				 * space deal with the mess.
				 */
				break;
			}
		}
		requeue_futex(this, hb1, hb2, &key2);
		drop_count++;
	}

	/*
	 * We took an extra initial reference to the pi_state either
	 * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We
	 * need to drop it here again.
	 */
	put_pi_state(pi_state);

out_unlock:
	double_unlock_hb(hb1, hb2);
	wake_up_q(&wake_q);
	hb_waiters_dec(hb2);

	/*
	 * drop_futex_key_refs() must be called outside the spinlocks. During
	 * the requeue we moved futex_q's from the hash bucket at key1 to the
	 * one at key2 and updated their key pointer.  We no longer need to
	 * hold the references to key1.
	 */
	while (--drop_count >= 0)
		drop_futex_key_refs(&key1);

out_put_keys:
	put_futex_key(&key2);
out_put_key1:
	put_futex_key(&key1);
out:
	return ret ? ret : task_count;
}

/* The key must be already stored in q->key. */
static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
	__acquires(&hb->lock)
{
	struct futex_hash_bucket *hb;

	hb = hash_futex(&q->key);

	/*
	 * Increment the counter before taking the lock so that
	 * a potential waker won't miss a to-be-slept task that is
	 * waiting for the spinlock. This is safe as all queue_lock()
	 * users end up calling queue_me(). Similarly, for housekeeping,
	 * decrement the counter at queue_unlock() when some error has
	 * occurred and we don't end up adding the task to the list.
	 */
	hb_waiters_inc(hb);

	q->lock_ptr = &hb->lock;

	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
	return hb;
}

static inline void
queue_unlock(struct futex_hash_bucket *hb)
	__releases(&hb->lock)
{
	spin_unlock(&hb->lock);
	hb_waiters_dec(hb);
}

static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
{
	int prio;

	/*
	 * The priority used to register this element is
	 * - either the real thread-priority for the real-time threads
	 * (i.e. threads with a priority lower than MAX_RT_PRIO)
	 * - or MAX_RT_PRIO for non-RT threads.
	 * Thus, all RT-threads are woken first in priority order, and
	 * the others are woken last, in FIFO order.
	 */
	prio = min(current->normal_prio, MAX_RT_PRIO);

	plist_node_init(&q->list, prio);
	plist_add(&q->list, &hb->chain);
	q->task = current;
}

/**
 * queue_me() - Enqueue the futex_q on the futex_hash_bucket
 * @q:	The futex_q to enqueue
 * @hb:	The destination hash bucket
 *
 * The hb->lock must be held by the caller, and is released here. A call to
 * queue_me() is typically paired with exactly one call to unqueue_me().  The
 * exceptions involve the PI related operations, which may use unqueue_me_pi()
 * or nothing if the unqueue is done as part of the wake process and the unqueue
 * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
 * an example).
 */
static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
	__releases(&hb->lock)
{
	__queue_me(q, hb);
	spin_unlock(&hb->lock);
}

/**
 * unqueue_me() - Remove the futex_q from its futex_hash_bucket
 * @q:	The futex_q to unqueue
 *
 * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
 * be paired with exactly one earlier call to queue_me().
 *
 * Return:
 *  - 1 - if the futex_q was still queued (and we removed unqueued it);
 *  - 0 - if the futex_q was already removed by the waking thread
 */
static int unqueue_me(struct futex_q *q)
{
	spinlock_t *lock_ptr;
	int ret = 0;

	/* In the common case we don't take the spinlock, which is nice. */
retry:
	/*
	 * q->lock_ptr can change between this read and the following spin_lock.
	 * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
	 * optimizing lock_ptr out of the logic below.
	 */
	lock_ptr = READ_ONCE(q->lock_ptr);
	if (lock_ptr != NULL) {
		spin_lock(lock_ptr);
		/*
		 * q->lock_ptr can change between reading it and
		 * spin_lock(), causing us to take the wrong lock.  This
		 * corrects the race condition.
		 *
		 * Reasoning goes like this: if we have the wrong lock,
		 * q->lock_ptr must have changed (maybe several times)
		 * between reading it and the spin_lock().  It can
		 * change again after the spin_lock() but only if it was
		 * already changed before the spin_lock().  It cannot,
		 * however, change back to the original value.  Therefore
		 * we can detect whether we acquired the correct lock.
		 */
		if (unlikely(lock_ptr != q->lock_ptr)) {
			spin_unlock(lock_ptr);
			goto retry;
		}
		__unqueue_futex(q);

		BUG_ON(q->pi_state);

		spin_unlock(lock_ptr);
		ret = 1;
	}

	drop_futex_key_refs(&q->key);
	return ret;
}

/*
 * PI futexes can not be requeued and must remove themself from the
 * hash bucket. The hash bucket lock (i.e. lock_ptr) is held on entry
 * and dropped here.
 */
static void unqueue_me_pi(struct futex_q *q)
	__releases(q->lock_ptr)
{
	__unqueue_futex(q);

	BUG_ON(!q->pi_state);
	put_pi_state(q->pi_state);
	q->pi_state = NULL;

	spin_unlock(q->lock_ptr);
}

static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
				struct task_struct *argowner)
{
	struct futex_pi_state *pi_state = q->pi_state;
	u32 uval, uninitialized_var(curval), newval;
	struct task_struct *oldowner, *newowner;
	u32 newtid;
	int ret;

	lockdep_assert_held(q->lock_ptr);

	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);

	oldowner = pi_state->owner;

	/*
	 * We are here because either:
	 *
	 *  - we stole the lock and pi_state->owner needs updating to reflect
	 *    that (@argowner == current),
	 *
	 * or:
	 *
	 *  - someone stole our lock and we need to fix things to point to the
	 *    new owner (@argowner == NULL).
	 *
	 * Either way, we have to replace the TID in the user space variable.
	 * This must be atomic as we have to preserve the owner died bit here.
	 *
	 * Note: We write the user space value _before_ changing the pi_state
	 * because we can fault here. Imagine swapped out pages or a fork
	 * that marked all the anonymous memory readonly for cow.
	 *
	 * Modifying pi_state _before_ the user space value would leave the
	 * pi_state in an inconsistent state when we fault here, because we
	 * need to drop the locks to handle the fault. This might be observed
	 * in the PID check in lookup_pi_state.
	 */
retry:
	if (!argowner) {
		if (oldowner != current) {
			/*
			 * We raced against a concurrent self; things are
			 * already fixed up. Nothing to do.
			 */
			ret = 0;
			goto out_unlock;
		}

		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
			/* We got the lock after all, nothing to fix. */
			ret = 0;
			goto out_unlock;
		}

		/*
		 * Since we just failed the trylock; there must be an owner.
		 */
		newowner = rt_mutex_owner(&pi_state->pi_mutex);
		BUG_ON(!newowner);
	} else {
		WARN_ON_ONCE(argowner != current);
		if (oldowner == current) {
			/*
			 * We raced against a concurrent self; things are
			 * already fixed up. Nothing to do.
			 */
			ret = 0;
			goto out_unlock;
		}
		newowner = argowner;
	}

	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
	/* Owner died? */
	if (!pi_state->owner)
		newtid |= FUTEX_OWNER_DIED;

	if (get_futex_value_locked(&uval, uaddr))
		goto handle_fault;

	for (;;) {
		newval = (uval & FUTEX_OWNER_DIED) | newtid;

		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
			goto handle_fault;
		if (curval == uval)
			break;
		uval = curval;
	}

	/*
	 * We fixed up user space. Now we need to fix the pi_state
	 * itself.
	 */
	if (pi_state->owner != NULL) {
		raw_spin_lock(&pi_state->owner->pi_lock);
		WARN_ON(list_empty(&pi_state->list));
		list_del_init(&pi_state->list);
		raw_spin_unlock(&pi_state->owner->pi_lock);
	}

	pi_state->owner = newowner;

	raw_spin_lock(&newowner->pi_lock);
	WARN_ON(!list_empty(&pi_state->list));
	list_add(&pi_state->list, &newowner->pi_state_list);
	raw_spin_unlock(&newowner->pi_lock);
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);

	return 0;

	/*
	 * To handle the page fault we need to drop the locks here. That gives
	 * the other task (either the highest priority waiter itself or the
	 * task which stole the rtmutex) the chance to try the fixup of the
	 * pi_state. So once we are back from handling the fault we need to
	 * check the pi_state after reacquiring the locks and before trying to
	 * do another fixup. When the fixup has been done already we simply
	 * return.
	 *
	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
	 * drop hb->lock since the caller owns the hb -> futex_q relation.
	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
	 */
handle_fault:
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
	spin_unlock(q->lock_ptr);

	ret = fault_in_user_writeable(uaddr);

	spin_lock(q->lock_ptr);
	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);

	/*
	 * Check if someone else fixed it for us:
	 */
	if (pi_state->owner != oldowner) {
		ret = 0;
		goto out_unlock;
	}

	if (ret)
		goto out_unlock;

	goto retry;

out_unlock:
	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
	return ret;
}

static long futex_wait_restart(struct restart_block *restart);

/**
 * fixup_owner() - Post lock pi_state and corner case management
 * @uaddr:	user address of the futex
 * @q:		futex_q (contains pi_state and access to the rt_mutex)
 * @locked:	if the attempt to take the rt_mutex succeeded (1) or not (0)
 *
 * After attempting to lock an rt_mutex, this function is called to cleanup
 * the pi_state owner as well as handle race conditions that may allow us to
 * acquire the lock. Must be called with the hb lock held.
 *
 * Return:
 *  -  1 - success, lock taken;
 *  -  0 - success, lock not taken;
 *  - <0 - on error (-EFAULT)
 */
static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
{
	int ret = 0;

	if (locked) {
		/*
		 * Got the lock. We might not be the anticipated owner if we
		 * did a lock-steal - fix up the PI-state in that case:
		 *
		 * Speculative pi_state->owner read (we don't hold wait_lock);
		 * since we own the lock pi_state->owner == current is the
		 * stable state, anything else needs more attention.
		 */
		if (q->pi_state->owner != current)
			ret = fixup_pi_state_owner(uaddr, q, current);
		goto out;
	}

	/*
	 * If we didn't get the lock; check if anybody stole it from us. In
	 * that case, we need to fix up the uval to point to them instead of
	 * us, otherwise bad things happen. [10]
	 *
	 * Another speculative read; pi_state->owner == current is unstable
	 * but needs our attention.
	 */
	if (q->pi_state->owner == current) {
		ret = fixup_pi_state_owner(uaddr, q, NULL);
		goto out;
	}

	/*
	 * Paranoia check. If we did not take the lock, then we should not be
	 * the owner of the rt_mutex.
	 */
	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
				"pi-state %p\n", ret,
				q->pi_state->pi_mutex.owner,
				q->pi_state->owner);
	}

out:
	return ret ? ret : locked;
}

/**
 * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal
 * @hb:		the futex hash bucket, must be locked by the caller
 * @q:		the futex_q to queue up on
 * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
 */
static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
				struct hrtimer_sleeper *timeout)
{
	/*
	 * The task state is guaranteed to be set before another task can
	 * wake it. set_current_state() is implemented using smp_store_mb() and
	 * queue_me() calls spin_unlock() upon completion, both serializing
	 * access to the hash list and forcing another memory barrier.
	 */
	set_current_state(TASK_INTERRUPTIBLE);
	queue_me(q, hb);

	/* Arm the timer */
	if (timeout)
		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);

	/*
	 * If we have been removed from the hash list, then another task
	 * has tried to wake us, and we can skip the call to schedule().
	 */
	if (likely(!plist_node_empty(&q->list))) {
		/*
		 * If the timer has already expired, current will already be
		 * flagged for rescheduling. Only call schedule if there
		 * is no timeout, or if it has yet to expire.
		 */
		if (!timeout || timeout->task)
			freezable_schedule();
	}
	__set_current_state(TASK_RUNNING);
}

/**
 * futex_wait_setup() - Prepare to wait on a futex
 * @uaddr:	the futex userspace address
 * @val:	the expected value
 * @flags:	futex flags (FLAGS_SHARED, etc.)
 * @q:		the associated futex_q
 * @hb:		storage for hash_bucket pointer to be returned to caller
 *
 * Setup the futex_q and locate the hash_bucket.  Get the futex value and
 * compare it with the expected value.  Handle atomic faults internally.
 * Return with the hb lock held and a q.key reference on success, and unlocked
 * with no q.key reference on failure.
 *
 * Return:
 *  -  0 - uaddr contains val and hb has been locked;
 *  - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
 */
static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
			   struct futex_q *q, struct futex_hash_bucket **hb)
{
	u32 uval;
	int ret;

	/*
	 * Access the page AFTER the hash-bucket is locked.
	 * Order is important:
	 *
	 *   Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
	 *   Userspace waker:  if (cond(var)) { var = new; futex_wake(&var); }
	 *
	 * The basic logical guarantee of a futex is that it blocks ONLY
	 * if cond(var) is known to be true at the time of blocking, for
	 * any cond.  If we locked the hash-bucket after testing *uaddr, that
	 * would open a race condition where we could block indefinitely with
	 * cond(var) false, which would violate the guarantee.
	 *
	 * On the other hand, we insert q and release the hash-bucket only
	 * after testing *uaddr.  This guarantees that futex_wait() will NOT
	 * absorb a wakeup if *uaddr does not match the desired values
	 * while the syscall executes.
	 */
retry:
	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, FUTEX_READ);
	if (unlikely(ret != 0))
		return ret;

retry_private:
	*hb = queue_lock(q);

	ret = get_futex_value_locked(&uval, uaddr);

	if (ret) {
		queue_unlock(*hb);

		ret = get_user(uval, uaddr);
		if (ret)
			goto out;

		if (!(flags & FLAGS_SHARED))
			goto retry_private;

		put_futex_key(&q->key);
		goto retry;
	}

	if (uval != val) {
		queue_unlock(*hb);
		ret = -EWOULDBLOCK;
	}

out:
	if (ret)
		put_futex_key(&q->key);
	return ret;
}

static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
		      ktime_t *abs_time, u32 bitset)
{
	struct hrtimer_sleeper timeout, *to = NULL;
	struct restart_block *restart;
	struct futex_hash_bucket *hb;
	struct futex_q q = futex_q_init;
	int ret;

	if (!bitset)
		return -EINVAL;
	q.bitset = bitset;

	if (abs_time) {
		to = &timeout;

		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
				      CLOCK_REALTIME : CLOCK_MONOTONIC,
				      HRTIMER_MODE_ABS);
		hrtimer_init_sleeper(to, current);
		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
					     current->timer_slack_ns);
	}

retry:
	/*
	 * Prepare to wait on uaddr. On success, holds hb lock and increments
	 * q.key refs.
	 */
	ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
	if (ret)
		goto out;

	/* queue_me and wait for wakeup, timeout, or a signal. */
	futex_wait_queue_me(hb, &q, to);

	/* If we were woken (and unqueued), we succeeded, whatever. */
	ret = 0;
	/* unqueue_me() drops q.key ref */
	if (!unqueue_me(&q))
		goto out;
	ret = -ETIMEDOUT;
	if (to && !to->task)
		goto out;

	/*
	 * We expect signal_pending(current), but we might be the
	 * victim of a spurious wakeup as well.
	 */
	if (!signal_pending(current))
		goto retry;

	ret = -ERESTARTSYS;
	if (!abs_time)
		goto out;

	restart = &current->restart_block;
	restart->fn = futex_wait_restart;
	restart->futex.uaddr = uaddr;
	restart->futex.val = val;
	restart->futex.time = *abs_time;
	restart->futex.bitset = bitset;
	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;

	ret = -ERESTART_RESTARTBLOCK;

out:
	if (to) {
		hrtimer_cancel(&to->timer);
		destroy_hrtimer_on_stack(&to->timer);
	}
	return ret;
}


static long futex_wait_restart(struct restart_block *restart)
{
	u32 __user *uaddr = restart->futex.uaddr;
	ktime_t t, *tp = NULL;

	if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
		t = restart->futex.time;
		tp = &t;
	}
	restart->fn = do_no_restart_syscall;

	return (long)futex_wait(uaddr, restart->futex.flags,
				restart->futex.val, tp, restart->futex.bitset);
}


/*
 * Userspace tried a 0 -> TID atomic transition of the futex value
 * and failed. The kernel side here does the whole locking operation:
 * if there are waiters then it will block as a consequence of relying
 * on rt-mutexes, it does PI, etc. (Due to races the kernel might see
 * a 0 value of the futex too.).
 *
 * Also serves as futex trylock_pi()'ing, and due semantics.
 */
static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
			 ktime_t *time, int trylock)
{
	struct hrtimer_sleeper timeout, *to = NULL;
	struct futex_pi_state *pi_state = NULL;
	struct rt_mutex_waiter rt_waiter;
	struct futex_hash_bucket *hb;
	struct futex_q q = futex_q_init;
	int res, ret;

	if (!IS_ENABLED(CONFIG_FUTEX_PI))
		return -ENOSYS;

	if (refill_pi_state_cache())
		return -ENOMEM;

	if (time) {
		to = &timeout;
		hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
				      HRTIMER_MODE_ABS);
		hrtimer_init_sleeper(to, current);
		hrtimer_set_expires(&to->timer, *time);
	}

retry:
	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, FUTEX_WRITE);
	if (unlikely(ret != 0))
		goto out;

retry_private:
	hb = queue_lock(&q);

	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
	if (unlikely(ret)) {
		/*
		 * Atomic work succeeded and we got the lock,
		 * or failed. Either way, we do _not_ block.
		 */
		switch (ret) {
		case 1:
			/* We got the lock. */
			ret = 0;
			goto out_unlock_put_key;
		case -EFAULT:
			goto uaddr_faulted;
		case -EAGAIN:
			/*
			 * Two reasons for this:
			 * - Task is exiting and we just wait for the
			 *   exit to complete.
			 * - The user space value changed.
			 */
			queue_unlock(hb);
			put_futex_key(&q.key);
			cond_resched();
			goto retry;
		default:
			goto out_unlock_put_key;
		}
	}

	WARN_ON(!q.pi_state);

	/*
	 * Only actually queue now that the atomic ops are done:
	 */
	__queue_me(&q, hb);

	if (trylock) {
		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
		/* Fixup the trylock return value: */
		ret = ret ? 0 : -EWOULDBLOCK;
		goto no_block;
	}

	rt_mutex_init_waiter(&rt_waiter);

	/*
	 * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
	 * hold it while doing rt_mutex_start_proxy(), because then it will
	 * include hb->lock in the blocking chain, even through we'll not in
	 * fact hold it while blocking. This will lead it to report -EDEADLK
	 * and BUG when futex_unlock_pi() interleaves with this.
	 *
	 * Therefore acquire wait_lock while holding hb->lock, but drop the
	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
	 * serializes against futex_unlock_pi() as that does the exact same
	 * lock handoff sequence.
	 */
	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
	spin_unlock(q.lock_ptr);
	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);

	if (ret) {
		if (ret == 1)
			ret = 0;

		spin_lock(q.lock_ptr);
		goto no_block;
	}


	if (unlikely(to))
		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);

	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);

	spin_lock(q.lock_ptr);
	/*
	 * If we failed to acquire the lock (signal/timeout), we must
	 * first acquire the hb->lock before removing the lock from the
	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
	 * wait lists consistent.
	 *
	 * In particular; it is important that futex_unlock_pi() can not
	 * observe this inconsistency.
	 */
	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
		ret = 0;

no_block:
	/*
	 * Fixup the pi_state owner and possibly acquire the lock if we
	 * haven't already.
	 */
	res = fixup_owner(uaddr, &q, !ret);
	/*
	 * If fixup_owner() returned an error, proprogate that.  If it acquired
	 * the lock, clear our -ETIMEDOUT or -EINTR.
	 */
	if (res)
		ret = (res < 0) ? res : 0;

	/*
	 * If fixup_owner() faulted and was unable to handle the fault, unlock
	 * it and return the fault to userspace.
	 */
	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
		pi_state = q.pi_state;
		get_pi_state(pi_state);
	}

	/* Unqueue and drop the lock */
	unqueue_me_pi(&q);

	if (pi_state) {
		rt_mutex_futex_unlock(&pi_state->pi_mutex);
		put_pi_state(pi_state);
	}

	goto out_put_key;

out_unlock_put_key:
	queue_unlock(hb);

out_put_key:
	put_futex_key(&q.key);
out:
	if (to) {
		hrtimer_cancel(&to->timer);
		destroy_hrtimer_on_stack(&to->timer);
	}
	return ret != -EINTR ? ret : -ERESTARTNOINTR;

uaddr_faulted:
	queue_unlock(hb);

	ret = fault_in_user_writeable(uaddr);
	if (ret)
		goto out_put_key;

	if (!(flags & FLAGS_SHARED))
		goto retry_private;

	put_futex_key(&q.key);
	goto retry;
}

/*
 * Userspace attempted a TID -> 0 atomic transition, and failed.
 * This is the in-kernel slowpath: we look up the PI state (if any),
 * and do the rt-mutex unlock.
 */
static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
	union futex_key key = FUTEX_KEY_INIT;
	struct futex_hash_bucket *hb;
	struct futex_q *top_waiter;
	int ret;

	if (!IS_ENABLED(CONFIG_FUTEX_PI))
		return -ENOSYS;

retry:
	if (get_user(uval, uaddr))
		return -EFAULT;
	/*
	 * We release only a lock we actually own:
	 */
	if ((uval & FUTEX_TID_MASK) != vpid)
		return -EPERM;

	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_WRITE);
	if (ret)
		return ret;

	hb = hash_futex(&key);
	spin_lock(&hb->lock);

	/*
	 * Check waiters first. We do not trust user space values at
	 * all and we at least want to know if user space fiddled
	 * with the futex value instead of blindly unlocking.
	 */
	top_waiter = futex_top_waiter(hb, &key);
	if (top_waiter) {
		struct futex_pi_state *pi_state = top_waiter->pi_state;

		ret = -EINVAL;
		if (!pi_state)
			goto out_unlock;

		/*
		 * If current does not own the pi_state then the futex is
		 * inconsistent and user space fiddled with the futex value.
		 */
		if (pi_state->owner != current)
			goto out_unlock;

		get_pi_state(pi_state);
		/*
		 * By taking wait_lock while still holding hb->lock, we ensure
		 * there is no point where we hold neither; and therefore
		 * wake_futex_pi() must observe a state consistent with what we
		 * observed.
		 */
		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
		spin_unlock(&hb->lock);

		/* drops pi_state->pi_mutex.wait_lock */
		ret = wake_futex_pi(uaddr, uval, pi_state);

		put_pi_state(pi_state);

		/*
		 * Success, we're done! No tricky corner cases.
		 */
		if (!ret)
			goto out_putkey;
		/*
		 * The atomic access to the futex value generated a
		 * pagefault, so retry the user-access and the wakeup:
		 */
		if (ret == -EFAULT)
			goto pi_faulted;
		/*
		 * A unconditional UNLOCK_PI op raced against a waiter
		 * setting the FUTEX_WAITERS bit. Try again.
		 */
		if (ret == -EAGAIN) {
			put_futex_key(&key);
			goto retry;
		}
		/*
		 * wake_futex_pi has detected invalid state. Tell user
		 * space.
		 */
		goto out_putkey;
	}

	/*
	 * We have no kernel internal state, i.e. no waiters in the
	 * kernel. Waiters which are about to queue themselves are stuck
	 * on hb->lock. So we can safely ignore them. We do neither
	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
	 * owner.
	 */
	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
		spin_unlock(&hb->lock);
		goto pi_faulted;
	}

	/*
	 * If uval has changed, let user space handle it.
	 */
	ret = (curval == uval) ? 0 : -EAGAIN;

out_unlock:
	spin_unlock(&hb->lock);
out_putkey:
	put_futex_key(&key);
	return ret;

pi_faulted:
	put_futex_key(&key);

	ret = fault_in_user_writeable(uaddr);
	if (!ret)
		goto retry;

	return ret;
}

/**
 * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex
 * @hb:		the hash_bucket futex_q was original enqueued on
 * @q:		the futex_q woken while waiting to be requeued
 * @key2:	the futex_key of the requeue target futex
 * @timeout:	the timeout associated with the wait (NULL if none)
 *
 * Detect if the task was woken on the initial futex as opposed to the requeue
 * target futex.  If so, determine if it was a timeout or a signal that caused
 * the wakeup and return the appropriate error code to the caller.  Must be
 * called with the hb lock held.
 *
 * Return:
 *  -  0 = no early wakeup detected;
 *  - <0 = -ETIMEDOUT or -ERESTARTNOINTR
 */
static inline
int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
				   struct futex_q *q, union futex_key *key2,
				   struct hrtimer_sleeper *timeout)
{
	int ret = 0;

	/*
	 * With the hb lock held, we avoid races while we process the wakeup.
	 * We only need to hold hb (and not hb2) to ensure atomicity as the
	 * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb.
	 * It can't be requeued from uaddr2 to something else since we don't
	 * support a PI aware source futex for requeue.
	 */
	if (!match_futex(&q->key, key2)) {
		WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr));
		/*
		 * We were woken prior to requeue by a timeout or a signal.
		 * Unqueue the futex_q and determine which it was.
		 */
		plist_del(&q->list, &hb->chain);
		hb_waiters_dec(hb);

		/* Handle spurious wakeups gracefully */
		ret = -EWOULDBLOCK;
		if (timeout && !timeout->task)
			ret = -ETIMEDOUT;
		else if (signal_pending(current))
			ret = -ERESTARTNOINTR;
	}
	return ret;
}

/**
 * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
 * @uaddr:	the futex we initially wait on (non-pi)
 * @flags:	futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be
 *		the same type, no requeueing from private to shared, etc.
 * @val:	the expected value of uaddr
 * @abs_time:	absolute timeout
 * @bitset:	32 bit wakeup bitset set by userspace, defaults to all
 * @uaddr2:	the pi futex we will take prior to returning to user-space
 *
 * The caller will wait on uaddr and will be requeued by futex_requeue() to
 * uaddr2 which must be PI aware and unique from uaddr.  Normal wakeup will wake
 * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
 * userspace.  This ensures the rt_mutex maintains an owner when it has waiters;
 * without one, the pi logic would not know which task to boost/deboost, if
 * there was a need to.
 *
 * We call schedule in futex_wait_queue_me() when we enqueue and return there
 * via the following--
 * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
 * 2) wakeup on uaddr2 after a requeue
 * 3) signal
 * 4) timeout
 *
 * If 3, cleanup and return -ERESTARTNOINTR.
 *
 * If 2, we may then block on trying to take the rt_mutex and return via:
 * 5) successful lock
 * 6) signal
 * 7) timeout
 * 8) other lock acquisition failure
 *
 * If 6, return -EWOULDBLOCK (restarting the syscall would do the same).
 *
 * If 4 or 7, we cleanup and return with -ETIMEDOUT.
 *
 * Return:
 *  -  0 - On success;
 *  - <0 - On error
 */
static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
				 u32 val, ktime_t *abs_time, u32 bitset,
				 u32 __user *uaddr2)
{
	struct hrtimer_sleeper timeout, *to = NULL;
	struct futex_pi_state *pi_state = NULL;
	struct rt_mutex_waiter rt_waiter;
	struct futex_hash_bucket *hb;
	union futex_key key2 = FUTEX_KEY_INIT;
	struct futex_q q = futex_q_init;
	int res, ret;

	if (!IS_ENABLED(CONFIG_FUTEX_PI))
		return -ENOSYS;

	if (uaddr == uaddr2)
		return -EINVAL;

	if (!bitset)
		return -EINVAL;

	if (abs_time) {
		to = &timeout;
		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
				      CLOCK_REALTIME : CLOCK_MONOTONIC,
				      HRTIMER_MODE_ABS);
		hrtimer_init_sleeper(to, current);
		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
					     current->timer_slack_ns);
	}

	/*
	 * The waiter is allocated on our stack, manipulated by the requeue
	 * code while we sleep on uaddr.
	 */
	rt_mutex_init_waiter(&rt_waiter);

	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
	if (unlikely(ret != 0))
		goto out;

	q.bitset = bitset;
	q.rt_waiter = &rt_waiter;
	q.requeue_pi_key = &key2;

	/*
	 * Prepare to wait on uaddr. On success, increments q.key (key1) ref
	 * count.
	 */
	ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
	if (ret)
		goto out_key2;

	/*
	 * The check above which compares uaddrs is not sufficient for
	 * shared futexes. We need to compare the keys:
	 */
	if (match_futex(&q.key, &key2)) {
		queue_unlock(hb);
		ret = -EINVAL;
		goto out_put_keys;
	}

	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
	futex_wait_queue_me(hb, &q, to);

	spin_lock(&hb->lock);
	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
	spin_unlock(&hb->lock);
	if (ret)
		goto out_put_keys;

	/*
	 * In order for us to be here, we know our q.key == key2, and since
	 * we took the hb->lock above, we also know that futex_requeue() has
	 * completed and we no longer have to concern ourselves with a wakeup
	 * race with the atomic proxy lock acquisition by the requeue code. The
	 * futex_requeue dropped our key1 reference and incremented our key2
	 * reference count.
	 */

	/* Check if the requeue code acquired the second futex for us. */
	if (!q.rt_waiter) {
		/*
		 * Got the lock. We might not be the anticipated owner if we
		 * did a lock-steal - fix up the PI-state in that case.
		 */
		if (q.pi_state && (q.pi_state->owner != current)) {
			spin_lock(q.lock_ptr);
			ret = fixup_pi_state_owner(uaddr2, &q, current);
			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
				pi_state = q.pi_state;
				get_pi_state(pi_state);
			}
			/*
			 * Drop the reference to the pi state which
			 * the requeue_pi() code acquired for us.
			 */
			put_pi_state(q.pi_state);
			spin_unlock(q.lock_ptr);
		}
	} else {
		struct rt_mutex *pi_mutex;

		/*
		 * We have been woken up by futex_unlock_pi(), a timeout, or a
		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
		 * the pi_state.
		 */
		WARN_ON(!q.pi_state);
		pi_mutex = &q.pi_state->pi_mutex;
		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);

		spin_lock(q.lock_ptr);
		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
			ret = 0;

		debug_rt_mutex_free_waiter(&rt_waiter);
		/*
		 * Fixup the pi_state owner and possibly acquire the lock if we
		 * haven't already.
		 */
		res = fixup_owner(uaddr2, &q, !ret);
		/*
		 * If fixup_owner() returned an error, proprogate that.  If it
		 * acquired the lock, clear -ETIMEDOUT or -EINTR.
		 */
		if (res)
			ret = (res < 0) ? res : 0;

		/*
		 * If fixup_pi_state_owner() faulted and was unable to handle
		 * the fault, unlock the rt_mutex and return the fault to
		 * userspace.
		 */
		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
			pi_state = q.pi_state;
			get_pi_state(pi_state);
		}

		/* Unqueue and drop the lock. */
		unqueue_me_pi(&q);
	}

	if (pi_state) {
		rt_mutex_futex_unlock(&pi_state->pi_mutex);
		put_pi_state(pi_state);
	}

	if (ret == -EINTR) {
		/*
		 * We've already been requeued, but cannot restart by calling
		 * futex_lock_pi() directly. We could restart this syscall, but
		 * it would detect that the user space "val" changed and return
		 * -EWOULDBLOCK.  Save the overhead of the restart and return
		 * -EWOULDBLOCK directly.
		 */
		ret = -EWOULDBLOCK;
	}

out_put_keys:
	put_futex_key(&q.key);
out_key2:
	put_futex_key(&key2);

out:
	if (to) {
		hrtimer_cancel(&to->timer);
		destroy_hrtimer_on_stack(&to->timer);
	}
	return ret;
}

/*
 * Support for robust futexes: the kernel cleans up held futexes at
 * thread exit time.
 *
 * Implementation: user-space maintains a per-thread list of locks it
 * is holding. Upon do_exit(), the kernel carefully walks this list,
 * and marks all locks that are owned by this thread with the
 * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is
 * always manipulated with the lock held, so the list is private and
 * per-thread. Userspace also maintains a per-thread 'list_op_pending'
 * field, to allow the kernel to clean up if the thread dies after
 * acquiring the lock, but just before it could have added itself to
 * the list. There can only be one such pending lock.
 */

/**
 * sys_set_robust_list() - Set the robust-futex list head of a task
 * @head:	pointer to the list-head
 * @len:	length of the list-head, as userspace expects
 */
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
		size_t, len)
{
	if (!futex_cmpxchg_enabled)
		return -ENOSYS;
	/*
	 * The kernel knows only one size for now:
	 */
	if (unlikely(len != sizeof(*head)))
		return -EINVAL;

	current->robust_list = head;

	return 0;
}

/**
 * sys_get_robust_list() - Get the robust-futex list head of a task
 * @pid:	pid of the process [zero for current task]
 * @head_ptr:	pointer to a list-head pointer, the kernel fills it in
 * @len_ptr:	pointer to a length field, the kernel fills in the header size
 */
SYSCALL_DEFINE3(get_robust_list, int, pid,
		struct robust_list_head __user * __user *, head_ptr,
		size_t __user *, len_ptr)
{
	struct robust_list_head __user *head;
	unsigned long ret;
	struct task_struct *p;

	if (!futex_cmpxchg_enabled)
		return -ENOSYS;

	rcu_read_lock();

	ret = -ESRCH;
	if (!pid)
		p = current;
	else {
		p = find_task_by_vpid(pid);
		if (!p)
			goto err_unlock;
	}

	ret = -EPERM;
	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
		goto err_unlock;

	head = p->robust_list;
	rcu_read_unlock();

	if (put_user(sizeof(*head), len_ptr))
		return -EFAULT;
	return put_user(head, head_ptr);

err_unlock:
	rcu_read_unlock();

	return ret;
}

/*
 * Process a futex-list entry, check whether it's owned by the
 * dying task, and do notification if so:
 */
static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
{
	u32 uval, uninitialized_var(nval), mval;

retry:
	if (get_user(uval, uaddr))
		return -1;

	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
		/*
		 * Ok, this dying thread is truly holding a futex
		 * of interest. Set the OWNER_DIED bit atomically
		 * via cmpxchg, and if the value had FUTEX_WAITERS
		 * set, wake up a waiter (if any). (We have to do a
		 * futex_wake() even if OWNER_DIED is already set -
		 * to handle the rare but possible case of recursive
		 * thread-death.) The rest of the cleanup is done in
		 * userspace.
		 */
		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
		/*
		 * We are not holding a lock here, but we want to have
		 * the pagefault_disable/enable() protection because
		 * we want to handle the fault gracefully. If the
		 * access fails we try to fault in the futex with R/W
		 * verification via get_user_pages. get_user() above
		 * does not guarantee R/W access. If that fails we
		 * give up and leave the futex locked.
		 */
		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
			if (fault_in_user_writeable(uaddr))
				return -1;
			goto retry;
		}
		if (nval != uval)
			goto retry;

		/*
		 * Wake robust non-PI futexes here. The wakeup of
		 * PI futexes happens in exit_pi_state():
		 */
		if (!pi && (uval & FUTEX_WAITERS))
			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
	}
	return 0;
}

/*
 * Fetch a robust-list pointer. Bit 0 signals PI futexes:
 */
static inline int fetch_robust_entry(struct robust_list __user **entry,
				     struct robust_list __user * __user *head,
				     unsigned int *pi)
{
	unsigned long uentry;

	if (get_user(uentry, (unsigned long __user *)head))
		return -EFAULT;

	*entry = (void __user *)(uentry & ~1UL);
	*pi = uentry & 1;

	return 0;
}

/*
 * Walk curr->robust_list (very carefully, it's a userspace list!)
 * and mark any locks found there dead, and notify any waiters.
 *
 * We silently return on any sign of list-walking problem.
 */
void exit_robust_list(struct task_struct *curr)
{
	struct robust_list_head __user *head = curr->robust_list;
	struct robust_list __user *entry, *next_entry, *pending;
	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
	unsigned int uninitialized_var(next_pi);
	unsigned long futex_offset;
	int rc;

	if (!futex_cmpxchg_enabled)
		return;

	/*
	 * Fetch the list head (which was registered earlier, via
	 * sys_set_robust_list()):
	 */
	if (fetch_robust_entry(&entry, &head->list.next, &pi))
		return;
	/*
	 * Fetch the relative futex offset:
	 */
	if (get_user(futex_offset, &head->futex_offset))
		return;
	/*
	 * Fetch any possibly pending lock-add first, and handle it
	 * if it exists:
	 */
	if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
		return;

	next_entry = NULL;	/* avoid warning with gcc */
	while (entry != &head->list) {
		/*
		 * Fetch the next entry in the list before calling
		 * handle_futex_death:
		 */
		rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi);
		/*
		 * A pending lock might already be on the list, so
		 * don't process it twice:
		 */
		if (entry != pending)
			if (handle_futex_death((void __user *)entry + futex_offset,
						curr, pi))
				return;
		if (rc)
			return;
		entry = next_entry;
		pi = next_pi;
		/*
		 * Avoid excessively long or circular lists:
		 */
		if (!--limit)
			break;

		cond_resched();
	}

	if (pending)
		handle_futex_death((void __user *)pending + futex_offset,
				   curr, pip);
}

long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
		u32 __user *uaddr2, u32 val2, u32 val3)
{
	int cmd = op & FUTEX_CMD_MASK;
	unsigned int flags = 0;

	if (!(op & FUTEX_PRIVATE_FLAG))
		flags |= FLAGS_SHARED;

	if (op & FUTEX_CLOCK_REALTIME) {
		flags |= FLAGS_CLOCKRT;
		if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \
		    cmd != FUTEX_WAIT_REQUEUE_PI)
			return -ENOSYS;
	}

	switch (cmd) {
	case FUTEX_LOCK_PI:
	case FUTEX_UNLOCK_PI:
	case FUTEX_TRYLOCK_PI:
	case FUTEX_WAIT_REQUEUE_PI:
	case FUTEX_CMP_REQUEUE_PI:
		if (!futex_cmpxchg_enabled)
			return -ENOSYS;
	}

	switch (cmd) {
	case FUTEX_WAIT:
		val3 = FUTEX_BITSET_MATCH_ANY;
		/* fall through */
	case FUTEX_WAIT_BITSET:
		return futex_wait(uaddr, flags, val, timeout, val3);
	case FUTEX_WAKE:
		val3 = FUTEX_BITSET_MATCH_ANY;
		/* fall through */
	case FUTEX_WAKE_BITSET:
		return futex_wake(uaddr, flags, val, val3);
	case FUTEX_REQUEUE:
		return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
	case FUTEX_CMP_REQUEUE:
		return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
	case FUTEX_WAKE_OP:
		return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
	case FUTEX_LOCK_PI:
		return futex_lock_pi(uaddr, flags, timeout, 0);
	case FUTEX_UNLOCK_PI:
		return futex_unlock_pi(uaddr, flags);
	case FUTEX_TRYLOCK_PI:
		return futex_lock_pi(uaddr, flags, NULL, 1);
	case FUTEX_WAIT_REQUEUE_PI:
		val3 = FUTEX_BITSET_MATCH_ANY;
		return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
					     uaddr2);
	case FUTEX_CMP_REQUEUE_PI:
		return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
	}
	return -ENOSYS;
}


SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
		struct __kernel_timespec __user *, utime, u32 __user *, uaddr2,
		u32, val3)
{
	struct timespec64 ts;
	ktime_t t, *tp = NULL;
	u32 val2 = 0;
	int cmd = op & FUTEX_CMD_MASK;

	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
		      cmd == FUTEX_WAIT_BITSET ||
		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
		if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
			return -EFAULT;
		if (get_timespec64(&ts, utime))
			return -EFAULT;
		if (!timespec64_valid(&ts))
			return -EINVAL;

		t = timespec64_to_ktime(ts);
		if (cmd == FUTEX_WAIT)
			t = ktime_add_safe(ktime_get(), t);
		tp = &t;
	}
	/*
	 * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*.
	 * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP.
	 */
	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
		val2 = (u32) (unsigned long) utime;

	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}

#ifdef CONFIG_COMPAT
/*
 * Fetch a robust-list pointer. Bit 0 signals PI futexes:
 */
static inline int
compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
		   compat_uptr_t __user *head, unsigned int *pi)
{
	if (get_user(*uentry, head))
		return -EFAULT;

	*entry = compat_ptr((*uentry) & ~1);
	*pi = (unsigned int)(*uentry) & 1;

	return 0;
}

static void __user *futex_uaddr(struct robust_list __user *entry,
				compat_long_t futex_offset)
{
	compat_uptr_t base = ptr_to_compat(entry);
	void __user *uaddr = compat_ptr(base + futex_offset);

	return uaddr;
}

/*
 * Walk curr->robust_list (very carefully, it's a userspace list!)
 * and mark any locks found there dead, and notify any waiters.
 *
 * We silently return on any sign of list-walking problem.
 */
void compat_exit_robust_list(struct task_struct *curr)
{
	struct compat_robust_list_head __user *head = curr->compat_robust_list;
	struct robust_list __user *entry, *next_entry, *pending;
	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
	unsigned int uninitialized_var(next_pi);
	compat_uptr_t uentry, next_uentry, upending;
	compat_long_t futex_offset;
	int rc;

	if (!futex_cmpxchg_enabled)
		return;

	/*
	 * Fetch the list head (which was registered earlier, via
	 * sys_set_robust_list()):
	 */
	if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
		return;
	/*
	 * Fetch the relative futex offset:
	 */
	if (get_user(futex_offset, &head->futex_offset))
		return;
	/*
	 * Fetch any possibly pending lock-add first, and handle it
	 * if it exists:
	 */
	if (compat_fetch_robust_entry(&upending, &pending,
			       &head->list_op_pending, &pip))
		return;

	next_entry = NULL;	/* avoid warning with gcc */
	while (entry != (struct robust_list __user *) &head->list) {
		/*
		 * Fetch the next entry in the list before calling
		 * handle_futex_death:
		 */
		rc = compat_fetch_robust_entry(&next_uentry, &next_entry,
			(compat_uptr_t __user *)&entry->next, &next_pi);
		/*
		 * A pending lock might already be on the list, so
		 * dont process it twice:
		 */
		if (entry != pending) {
			void __user *uaddr = futex_uaddr(entry, futex_offset);

			if (handle_futex_death(uaddr, curr, pi))
				return;
		}
		if (rc)
			return;
		uentry = next_uentry;
		entry = next_entry;
		pi = next_pi;
		/*
		 * Avoid excessively long or circular lists:
		 */
		if (!--limit)
			break;

		cond_resched();
	}
	if (pending) {
		void __user *uaddr = futex_uaddr(pending, futex_offset);

		handle_futex_death(uaddr, curr, pip);
	}
}

COMPAT_SYSCALL_DEFINE2(set_robust_list,
		struct compat_robust_list_head __user *, head,
		compat_size_t, len)
{
	if (!futex_cmpxchg_enabled)
		return -ENOSYS;

	if (unlikely(len != sizeof(*head)))
		return -EINVAL;

	current->compat_robust_list = head;

	return 0;
}

COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
			compat_uptr_t __user *, head_ptr,
			compat_size_t __user *, len_ptr)
{
	struct compat_robust_list_head __user *head;
	unsigned long ret;
	struct task_struct *p;

	if (!futex_cmpxchg_enabled)
		return -ENOSYS;

	rcu_read_lock();

	ret = -ESRCH;
	if (!pid)
		p = current;
	else {
		p = find_task_by_vpid(pid);
		if (!p)
			goto err_unlock;
	}

	ret = -EPERM;
	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
		goto err_unlock;

	head = p->compat_robust_list;
	rcu_read_unlock();

	if (put_user(sizeof(*head), len_ptr))
		return -EFAULT;
	return put_user(ptr_to_compat(head), head_ptr);

err_unlock:
	rcu_read_unlock();

	return ret;
}
#endif /* CONFIG_COMPAT */

#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
		struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
		u32, val3)
{
	struct timespec64 ts;
	ktime_t t, *tp = NULL;
	int val2 = 0;
	int cmd = op & FUTEX_CMD_MASK;

	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
		      cmd == FUTEX_WAIT_BITSET ||
		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
		if (get_old_timespec32(&ts, utime))
			return -EFAULT;
		if (!timespec64_valid(&ts))
			return -EINVAL;

		t = timespec64_to_ktime(ts);
		if (cmd == FUTEX_WAIT)
			t = ktime_add_safe(ktime_get(), t);
		tp = &t;
	}
	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
		val2 = (int) (unsigned long) utime;

	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
#endif /* CONFIG_COMPAT_32BIT_TIME */

static void __init futex_detect_cmpxchg(void)
{
#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
	u32 curval;

	/*
	 * This will fail and we want it. Some arch implementations do
	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
	 * functionality. We want to know that before we call in any
	 * of the complex code paths. Also we want to prevent
	 * registration of robust lists in that case. NULL is
	 * guaranteed to fault and we get -EFAULT on functional
	 * implementation, the non-functional ones will return
	 * -ENOSYS.
	 */
	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
		futex_cmpxchg_enabled = 1;
#endif
}

static int __init futex_init(void)
{
	unsigned int futex_shift;
	unsigned long i;

#if CONFIG_BASE_SMALL
	futex_hashsize = 16;
#else
	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
#endif

	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
					       futex_hashsize, 0,
					       futex_hashsize < 256 ? HASH_SMALL : 0,
					       &futex_shift, NULL,
					       futex_hashsize, futex_hashsize);
	futex_hashsize = 1UL << futex_shift;

	futex_detect_cmpxchg();

	for (i = 0; i < futex_hashsize; i++) {
		atomic_set(&futex_queues[i].waiters, 0);
		plist_head_init(&futex_queues[i].chain);
		spin_lock_init(&futex_queues[i].lock);
	}

	return 0;
}
core_initcall(futex_init);
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-11 01:05:12 -0400