aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/isdn/hisax/asuscom.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/isdn/hisax/asuscom.c')
-rw-r--r--drivers/isdn/hisax/asuscom.c427
1 files changed, 427 insertions, 0 deletions
diff --git a/drivers/isdn/hisax/asuscom.c b/drivers/isdn/hisax/asuscom.c
new file mode 100644
index 000000000000..7546e2e4a94e
--- /dev/null
+++ b/drivers/isdn/hisax/asuscom.c
@@ -0,0 +1,427 @@
1/* $Id: asuscom.c,v 1.14.2.4 2004/01/13 23:48:39 keil Exp $
2 *
3 * low level stuff for ASUSCOM NETWORK INC. ISDNLink cards
4 *
5 * Author Karsten Keil
6 * Copyright by Karsten Keil <keil@isdn4linux.de>
7 *
8 * This software may be used and distributed according to the terms
9 * of the GNU General Public License, incorporated herein by reference.
10 *
11 * Thanks to ASUSCOM NETWORK INC. Taiwan and Dynalink NL for information
12 *
13 */
14
15#include <linux/init.h>
16#include <linux/isapnp.h>
17#include "hisax.h"
18#include "isac.h"
19#include "ipac.h"
20#include "hscx.h"
21#include "isdnl1.h"
22
23extern const char *CardType[];
24
25const char *Asuscom_revision = "$Revision: 1.14.2.4 $";
26
27#define byteout(addr,val) outb(val,addr)
28#define bytein(addr) inb(addr)
29
30#define ASUS_ISAC 0
31#define ASUS_HSCX 1
32#define ASUS_ADR 2
33#define ASUS_CTRL_U7 3
34#define ASUS_CTRL_POTS 5
35
36#define ASUS_IPAC_ALE 0
37#define ASUS_IPAC_DATA 1
38
39#define ASUS_ISACHSCX 1
40#define ASUS_IPAC 2
41
42/* CARD_ADR (Write) */
43#define ASUS_RESET 0x80 /* Bit 7 Reset-Leitung */
44
45static inline u_char
46readreg(unsigned int ale, unsigned int adr, u_char off)
47{
48 register u_char ret;
49
50 byteout(ale, off);
51 ret = bytein(adr);
52 return (ret);
53}
54
55static inline void
56readfifo(unsigned int ale, unsigned int adr, u_char off, u_char * data, int size)
57{
58 byteout(ale, off);
59 insb(adr, data, size);
60}
61
62
63static inline void
64writereg(unsigned int ale, unsigned int adr, u_char off, u_char data)
65{
66 byteout(ale, off);
67 byteout(adr, data);
68}
69
70static inline void
71writefifo(unsigned int ale, unsigned int adr, u_char off, u_char * data, int size)
72{
73 byteout(ale, off);
74 outsb(adr, data, size);
75}
76
77/* Interface functions */
78
79static u_char
80ReadISAC(struct IsdnCardState *cs, u_char offset)
81{
82 return (readreg(cs->hw.asus.adr, cs->hw.asus.isac, offset));
83}
84
85static void
86WriteISAC(struct IsdnCardState *cs, u_char offset, u_char value)
87{
88 writereg(cs->hw.asus.adr, cs->hw.asus.isac, offset, value);
89}
90
91static void
92ReadISACfifo(struct IsdnCardState *cs, u_char * data, int size)
93{
94 readfifo(cs->hw.asus.adr, cs->hw.asus.isac, 0, data, size);
95}
96
97static void
98WriteISACfifo(struct IsdnCardState *cs, u_char * data, int size)
99{
100 writefifo(cs->hw.asus.adr, cs->hw.asus.isac, 0, data, size);
101}
102
103static u_char
104ReadISAC_IPAC(struct IsdnCardState *cs, u_char offset)
105{
106 return (readreg(cs->hw.asus.adr, cs->hw.asus.isac, offset|0x80));
107}
108
109static void
110WriteISAC_IPAC(struct IsdnCardState *cs, u_char offset, u_char value)
111{
112 writereg(cs->hw.asus.adr, cs->hw.asus.isac, offset|0x80, value);
113}
114
115static void
116ReadISACfifo_IPAC(struct IsdnCardState *cs, u_char * data, int size)
117{
118 readfifo(cs->hw.asus.adr, cs->hw.asus.isac, 0x80, data, size);
119}
120
121static void
122WriteISACfifo_IPAC(struct IsdnCardState *cs, u_char * data, int size)
123{
124 writefifo(cs->hw.asus.adr, cs->hw.asus.isac, 0x80, data, size);
125}
126
127static u_char
128ReadHSCX(struct IsdnCardState *cs, int hscx, u_char offset)
129{
130 return (readreg(cs->hw.asus.adr,
131 cs->hw.asus.hscx, offset + (hscx ? 0x40 : 0)));
132}
133
134static void
135WriteHSCX(struct IsdnCardState *cs, int hscx, u_char offset, u_char value)
136{
137 writereg(cs->hw.asus.adr,
138 cs->hw.asus.hscx, offset + (hscx ? 0x40 : 0), value);
139}
140
141/*
142 * fast interrupt HSCX stuff goes here
143 */
144
145#define READHSCX(cs, nr, reg) readreg(cs->hw.asus.adr, \
146 cs->hw.asus.hscx, reg + (nr ? 0x40 : 0))
147#define WRITEHSCX(cs, nr, reg, data) writereg(cs->hw.asus.adr, \
148 cs->hw.asus.hscx, reg + (nr ? 0x40 : 0), data)
149
150#define READHSCXFIFO(cs, nr, ptr, cnt) readfifo(cs->hw.asus.adr, \
151 cs->hw.asus.hscx, (nr ? 0x40 : 0), ptr, cnt)
152
153#define WRITEHSCXFIFO(cs, nr, ptr, cnt) writefifo(cs->hw.asus.adr, \
154 cs->hw.asus.hscx, (nr ? 0x40 : 0), ptr, cnt)
155
156#include "hscx_irq.c"
157
158static irqreturn_t
159asuscom_interrupt(int intno, void *dev_id, struct pt_regs *regs)
160{
161 struct IsdnCardState *cs = dev_id;
162 u_char val;
163 u_long flags;
164
165 spin_lock_irqsave(&cs->lock, flags);
166 val = readreg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_ISTA + 0x40);
167 Start_HSCX:
168 if (val)
169 hscx_int_main(cs, val);
170 val = readreg(cs->hw.asus.adr, cs->hw.asus.isac, ISAC_ISTA);
171 Start_ISAC:
172 if (val)
173 isac_interrupt(cs, val);
174 val = readreg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_ISTA + 0x40);
175 if (val) {
176 if (cs->debug & L1_DEB_HSCX)
177 debugl1(cs, "HSCX IntStat after IntRoutine");
178 goto Start_HSCX;
179 }
180 val = readreg(cs->hw.asus.adr, cs->hw.asus.isac, ISAC_ISTA);
181 if (val) {
182 if (cs->debug & L1_DEB_ISAC)
183 debugl1(cs, "ISAC IntStat after IntRoutine");
184 goto Start_ISAC;
185 }
186 writereg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_MASK, 0xFF);
187 writereg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_MASK + 0x40, 0xFF);
188 writereg(cs->hw.asus.adr, cs->hw.asus.isac, ISAC_MASK, 0xFF);
189 writereg(cs->hw.asus.adr, cs->hw.asus.isac, ISAC_MASK, 0x0);
190 writereg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_MASK, 0x0);
191 writereg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_MASK + 0x40, 0x0);
192 spin_unlock_irqrestore(&cs->lock, flags);
193 return IRQ_HANDLED;
194}
195
196static irqreturn_t
197asuscom_interrupt_ipac(int intno, void *dev_id, struct pt_regs *regs)
198{
199 struct IsdnCardState *cs = dev_id;
200 u_char ista, val, icnt = 5;
201 u_long flags;
202
203 spin_lock_irqsave(&cs->lock, flags);
204 ista = readreg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_ISTA);
205Start_IPAC:
206 if (cs->debug & L1_DEB_IPAC)
207 debugl1(cs, "IPAC ISTA %02X", ista);
208 if (ista & 0x0f) {
209 val = readreg(cs->hw.asus.adr, cs->hw.asus.hscx, HSCX_ISTA + 0x40);
210 if (ista & 0x01)
211 val |= 0x01;
212 if (ista & 0x04)
213 val |= 0x02;
214 if (ista & 0x08)
215 val |= 0x04;
216 if (val)
217 hscx_int_main(cs, val);
218 }
219 if (ista & 0x20) {
220 val = 0xfe & readreg(cs->hw.asus.adr, cs->hw.asus.isac, ISAC_ISTA | 0x80);
221 if (val) {
222 isac_interrupt(cs, val);
223 }
224 }
225 if (ista & 0x10) {
226 val = 0x01;
227 isac_interrupt(cs, val);
228 }
229 ista = readreg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_ISTA);
230 if ((ista & 0x3f) && icnt) {
231 icnt--;
232 goto Start_IPAC;
233 }
234 if (!icnt)
235 printk(KERN_WARNING "ASUS IRQ LOOP\n");
236 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_MASK, 0xFF);
237 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_MASK, 0xC0);
238 spin_unlock_irqrestore(&cs->lock, flags);
239 return IRQ_HANDLED;
240}
241
242void
243release_io_asuscom(struct IsdnCardState *cs)
244{
245 int bytecnt = 8;
246
247 if (cs->hw.asus.cfg_reg)
248 release_region(cs->hw.asus.cfg_reg, bytecnt);
249}
250
251static void
252reset_asuscom(struct IsdnCardState *cs)
253{
254 if (cs->subtyp == ASUS_IPAC)
255 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_POTA2, 0x20);
256 else
257 byteout(cs->hw.asus.adr, ASUS_RESET); /* Reset On */
258 mdelay(10);
259 if (cs->subtyp == ASUS_IPAC)
260 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_POTA2, 0x0);
261 else
262 byteout(cs->hw.asus.adr, 0); /* Reset Off */
263 mdelay(10);
264 if (cs->subtyp == ASUS_IPAC) {
265 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_CONF, 0x0);
266 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_ACFG, 0xff);
267 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_AOE, 0x0);
268 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_MASK, 0xc0);
269 writereg(cs->hw.asus.adr, cs->hw.asus.isac, IPAC_PCFG, 0x12);
270 }
271}
272
273static int
274Asus_card_msg(struct IsdnCardState *cs, int mt, void *arg)
275{
276 u_long flags;
277
278 switch (mt) {
279 case CARD_RESET:
280 spin_lock_irqsave(&cs->lock, flags);
281 reset_asuscom(cs);
282 spin_unlock_irqrestore(&cs->lock, flags);
283 return(0);
284 case CARD_RELEASE:
285 release_io_asuscom(cs);
286 return(0);
287 case CARD_INIT:
288 spin_lock_irqsave(&cs->lock, flags);
289 cs->debug |= L1_DEB_IPAC;
290 inithscxisac(cs, 3);
291 spin_unlock_irqrestore(&cs->lock, flags);
292 return(0);
293 case CARD_TEST:
294 return(0);
295 }
296 return(0);
297}
298
299#ifdef __ISAPNP__
300static struct isapnp_device_id asus_ids[] __initdata = {
301 { ISAPNP_VENDOR('A', 'S', 'U'), ISAPNP_FUNCTION(0x1688),
302 ISAPNP_VENDOR('A', 'S', 'U'), ISAPNP_FUNCTION(0x1688),
303 (unsigned long) "Asus1688 PnP" },
304 { ISAPNP_VENDOR('A', 'S', 'U'), ISAPNP_FUNCTION(0x1690),
305 ISAPNP_VENDOR('A', 'S', 'U'), ISAPNP_FUNCTION(0x1690),
306 (unsigned long) "Asus1690 PnP" },
307 { ISAPNP_VENDOR('S', 'I', 'E'), ISAPNP_FUNCTION(0x0020),
308 ISAPNP_VENDOR('S', 'I', 'E'), ISAPNP_FUNCTION(0x0020),
309 (unsigned long) "Isurf2 PnP" },
310 { ISAPNP_VENDOR('E', 'L', 'F'), ISAPNP_FUNCTION(0x0000),
311 ISAPNP_VENDOR('E', 'L', 'F'), ISAPNP_FUNCTION(0x0000),
312 (unsigned long) "Iscas TE320" },
313 { 0, }
314};
315
316static struct isapnp_device_id *ipid __initdata = &asus_ids[0];
317static struct pnp_card *pnp_c __devinitdata = NULL;
318#endif
319
320int __init
321setup_asuscom(struct IsdnCard *card)
322{
323 int bytecnt;
324 struct IsdnCardState *cs = card->cs;
325 u_char val;
326 char tmp[64];
327
328 strcpy(tmp, Asuscom_revision);
329 printk(KERN_INFO "HiSax: Asuscom ISDNLink driver Rev. %s\n", HiSax_getrev(tmp));
330 if (cs->typ != ISDN_CTYPE_ASUSCOM)
331 return (0);
332#ifdef __ISAPNP__
333 if (!card->para[1] && isapnp_present()) {
334 struct pnp_dev *pnp_d;
335 while(ipid->card_vendor) {
336 if ((pnp_c = pnp_find_card(ipid->card_vendor,
337 ipid->card_device, pnp_c))) {
338 pnp_d = NULL;
339 if ((pnp_d = pnp_find_dev(pnp_c,
340 ipid->vendor, ipid->function, pnp_d))) {
341 int err;
342
343 printk(KERN_INFO "HiSax: %s detected\n",
344 (char *)ipid->driver_data);
345 pnp_disable_dev(pnp_d);
346 err = pnp_activate_dev(pnp_d);
347 if (err<0) {
348 printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
349 __FUNCTION__, err);
350 return(0);
351 }
352 card->para[1] = pnp_port_start(pnp_d, 0);
353 card->para[0] = pnp_irq(pnp_d, 0);
354 if (!card->para[0] || !card->para[1]) {
355 printk(KERN_ERR "AsusPnP:some resources are missing %ld/%lx\n",
356 card->para[0], card->para[1]);
357 pnp_disable_dev(pnp_d);
358 return(0);
359 }
360 break;
361 } else {
362 printk(KERN_ERR "AsusPnP: PnP error card found, no device\n");
363 }
364 }
365 ipid++;
366 pnp_c = NULL;
367 }
368 if (!ipid->card_vendor) {
369 printk(KERN_INFO "AsusPnP: no ISAPnP card found\n");
370 return(0);
371 }
372 }
373#endif
374 bytecnt = 8;
375 cs->hw.asus.cfg_reg = card->para[1];
376 cs->irq = card->para[0];
377 if (!request_region(cs->hw.asus.cfg_reg, bytecnt, "asuscom isdn")) {
378 printk(KERN_WARNING
379 "HiSax: %s config port %x-%x already in use\n",
380 CardType[card->typ],
381 cs->hw.asus.cfg_reg,
382 cs->hw.asus.cfg_reg + bytecnt);
383 return (0);
384 }
385 printk(KERN_INFO "ISDNLink: defined at 0x%x IRQ %d\n",
386 cs->hw.asus.cfg_reg, cs->irq);
387 setup_isac(cs);
388 cs->BC_Read_Reg = &ReadHSCX;
389 cs->BC_Write_Reg = &WriteHSCX;
390 cs->BC_Send_Data = &hscx_fill_fifo;
391 cs->cardmsg = &Asus_card_msg;
392 val = readreg(cs->hw.asus.cfg_reg + ASUS_IPAC_ALE,
393 cs->hw.asus.cfg_reg + ASUS_IPAC_DATA, IPAC_ID);
394 if ((val == 1) || (val == 2)) {
395 cs->subtyp = ASUS_IPAC;
396 cs->hw.asus.adr = cs->hw.asus.cfg_reg + ASUS_IPAC_ALE;
397 cs->hw.asus.isac = cs->hw.asus.cfg_reg + ASUS_IPAC_DATA;
398 cs->hw.asus.hscx = cs->hw.asus.cfg_reg + ASUS_IPAC_DATA;
399 test_and_set_bit(HW_IPAC, &cs->HW_Flags);
400 cs->readisac = &ReadISAC_IPAC;
401 cs->writeisac = &WriteISAC_IPAC;
402 cs->readisacfifo = &ReadISACfifo_IPAC;
403 cs->writeisacfifo = &WriteISACfifo_IPAC;
404 cs->irq_func = &asuscom_interrupt_ipac;
405 printk(KERN_INFO "Asus: IPAC version %x\n", val);
406 } else {
407 cs->subtyp = ASUS_ISACHSCX;
408 cs->hw.asus.adr = cs->hw.asus.cfg_reg + ASUS_ADR;
409 cs->hw.asus.isac = cs->hw.asus.cfg_reg + ASUS_ISAC;
410 cs->hw.asus.hscx = cs->hw.asus.cfg_reg + ASUS_HSCX;
411 cs->hw.asus.u7 = cs->hw.asus.cfg_reg + ASUS_CTRL_U7;
412 cs->hw.asus.pots = cs->hw.asus.cfg_reg + ASUS_CTRL_POTS;
413 cs->readisac = &ReadISAC;
414 cs->writeisac = &WriteISAC;
415 cs->readisacfifo = &ReadISACfifo;
416 cs->writeisacfifo = &WriteISACfifo;
417 cs->irq_func = &asuscom_interrupt;
418 ISACVersion(cs, "ISDNLink:");
419 if (HscxVersion(cs, "ISDNLink:")) {
420 printk(KERN_WARNING
421 "ISDNLink: wrong HSCX versions check IO address\n");
422 release_io_asuscom(cs);
423 return (0);
424 }
425 }
426 return (1);
427}
generated by cgit v1.2.2 (git 2.25.0) at 2025-03-01 07:30:28 -0500
4' href='#n3284'>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 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 
/*
 * Copyright (C) 2008 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * 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 021110-1307, USA.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/list_sort.h>
#include "ctree.h"
#include "transaction.h"
#include "disk-io.h"
#include "locking.h"
#include "print-tree.h"
#include "backref.h"
#include "tree-log.h"
#include "hash.h"

/* magic values for the inode_only field in btrfs_log_inode:
 *
 * LOG_INODE_ALL means to log everything
 * LOG_INODE_EXISTS means to log just enough to recreate the inode
 * during log replay
 */
#define LOG_INODE_ALL 0
#define LOG_INODE_EXISTS 1

/*
 * directory trouble cases
 *
 * 1) on rename or unlink, if the inode being unlinked isn't in the fsync
 * log, we must force a full commit before doing an fsync of the directory
 * where the unlink was done.
 * ---> record transid of last unlink/rename per directory
 *
 * mkdir foo/some_dir
 * normal commit
 * rename foo/some_dir foo2/some_dir
 * mkdir foo/some_dir
 * fsync foo/some_dir/some_file
 *
 * The fsync above will unlink the original some_dir without recording
 * it in its new location (foo2).  After a crash, some_dir will be gone
 * unless the fsync of some_file forces a full commit
 *
 * 2) we must log any new names for any file or dir that is in the fsync
 * log. ---> check inode while renaming/linking.
 *
 * 2a) we must log any new names for any file or dir during rename
 * when the directory they are being removed from was logged.
 * ---> check inode and old parent dir during rename
 *
 *  2a is actually the more important variant.  With the extra logging
 *  a crash might unlink the old name without recreating the new one
 *
 * 3) after a crash, we must go through any directories with a link count
 * of zero and redo the rm -rf
 *
 * mkdir f1/foo
 * normal commit
 * rm -rf f1/foo
 * fsync(f1)
 *
 * The directory f1 was fully removed from the FS, but fsync was never
 * called on f1, only its parent dir.  After a crash the rm -rf must
 * be replayed.  This must be able to recurse down the entire
 * directory tree.  The inode link count fixup code takes care of the
 * ugly details.
 */

/*
 * stages for the tree walking.  The first
 * stage (0) is to only pin down the blocks we find
 * the second stage (1) is to make sure that all the inodes
 * we find in the log are created in the subvolume.
 *
 * The last stage is to deal with directories and links and extents
 * and all the other fun semantics
 */
#define LOG_WALK_PIN_ONLY 0
#define LOG_WALK_REPLAY_INODES 1
#define LOG_WALK_REPLAY_DIR_INDEX 2
#define LOG_WALK_REPLAY_ALL 3

static int btrfs_log_inode(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root, struct inode *inode,
			     int inode_only);
static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
			     struct btrfs_root *root,
			     struct btrfs_path *path, u64 objectid);
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
				       struct btrfs_root *root,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
				       u64 dirid, int del_all);

/*
 * tree logging is a special write ahead log used to make sure that
 * fsyncs and O_SYNCs can happen without doing full tree commits.
 *
 * Full tree commits are expensive because they require commonly
 * modified blocks to be recowed, creating many dirty pages in the
 * extent tree an 4x-6x higher write load than ext3.
 *
 * Instead of doing a tree commit on every fsync, we use the
 * key ranges and transaction ids to find items for a given file or directory
 * that have changed in this transaction.  Those items are copied into
 * a special tree (one per subvolume root), that tree is written to disk
 * and then the fsync is considered complete.
 *
 * After a crash, items are copied out of the log-tree back into the
 * subvolume tree.  Any file data extents found are recorded in the extent
 * allocation tree, and the log-tree freed.
 *
 * The log tree is read three times, once to pin down all the extents it is
 * using in ram and once, once to create all the inodes logged in the tree
 * and once to do all the other items.
 */

/*
 * start a sub transaction and setup the log tree
 * this increments the log tree writer count to make the people
 * syncing the tree wait for us to finish
 */
static int start_log_trans(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root)
{
	int ret;

	mutex_lock(&root->log_mutex);
	if (root->log_root) {
		if (!root->log_start_pid) {
			root->log_start_pid = current->pid;
			root->log_multiple_pids = false;
		} else if (root->log_start_pid != current->pid) {
			root->log_multiple_pids = true;
		}

		atomic_inc(&root->log_batch);
		atomic_inc(&root->log_writers);
		mutex_unlock(&root->log_mutex);
		return 0;
	}

	ret = 0;
	mutex_lock(&root->fs_info->tree_log_mutex);
	if (!root->fs_info->log_root_tree)
		ret = btrfs_init_log_root_tree(trans, root->fs_info);
	mutex_unlock(&root->fs_info->tree_log_mutex);
	if (ret)
		goto out;

	if (!root->log_root) {
		ret = btrfs_add_log_tree(trans, root);
		if (ret)
			goto out;
	}
	root->log_multiple_pids = false;
	root->log_start_pid = current->pid;
	atomic_inc(&root->log_batch);
	atomic_inc(&root->log_writers);
out:
	mutex_unlock(&root->log_mutex);
	return ret;
}

/*
 * returns 0 if there was a log transaction running and we were able
 * to join, or returns -ENOENT if there were not transactions
 * in progress
 */
static int join_running_log_trans(struct btrfs_root *root)
{
	int ret = -ENOENT;

	smp_mb();
	if (!root->log_root)
		return -ENOENT;

	mutex_lock(&root->log_mutex);
	if (root->log_root) {
		ret = 0;
		atomic_inc(&root->log_writers);
	}
	mutex_unlock(&root->log_mutex);
	return ret;
}

/*
 * This either makes the current running log transaction wait
 * until you call btrfs_end_log_trans() or it makes any future
 * log transactions wait until you call btrfs_end_log_trans()
 */
int btrfs_pin_log_trans(struct btrfs_root *root)
{
	int ret = -ENOENT;

	mutex_lock(&root->log_mutex);
	atomic_inc(&root->log_writers);
	mutex_unlock(&root->log_mutex);
	return ret;
}

/*
 * indicate we're done making changes to the log tree
 * and wake up anyone waiting to do a sync
 */
void btrfs_end_log_trans(struct btrfs_root *root)
{
	if (atomic_dec_and_test(&root->log_writers)) {
		smp_mb();
		if (waitqueue_active(&root->log_writer_wait))
			wake_up(&root->log_writer_wait);
	}
}


/*
 * the walk control struct is used to pass state down the chain when
 * processing the log tree.  The stage field tells us which part
 * of the log tree processing we are currently doing.  The others
 * are state fields used for that specific part
 */
struct walk_control {
	/* should we free the extent on disk when done?  This is used
	 * at transaction commit time while freeing a log tree
	 */
	int free;

	/* should we write out the extent buffer?  This is used
	 * while flushing the log tree to disk during a sync
	 */
	int write;

	/* should we wait for the extent buffer io to finish?  Also used
	 * while flushing the log tree to disk for a sync
	 */
	int wait;

	/* pin only walk, we record which extents on disk belong to the
	 * log trees
	 */
	int pin;

	/* what stage of the replay code we're currently in */
	int stage;

	/* the root we are currently replaying */
	struct btrfs_root *replay_dest;

	/* the trans handle for the current replay */
	struct btrfs_trans_handle *trans;

	/* the function that gets used to process blocks we find in the
	 * tree.  Note the extent_buffer might not be up to date when it is
	 * passed in, and it must be checked or read if you need the data
	 * inside it
	 */
	int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
			    struct walk_control *wc, u64 gen);
};

/*
 * process_func used to pin down extents, write them or wait on them
 */
static int process_one_buffer(struct btrfs_root *log,
			      struct extent_buffer *eb,
			      struct walk_control *wc, u64 gen)
{
	int ret = 0;

	/*
	 * If this fs is mixed then we need to be able to process the leaves to
	 * pin down any logged extents, so we have to read the block.
	 */
	if (btrfs_fs_incompat(log->fs_info, MIXED_GROUPS)) {
		ret = btrfs_read_buffer(eb, gen);
		if (ret)
			return ret;
	}

	if (wc->pin)
		ret = btrfs_pin_extent_for_log_replay(log->fs_info->extent_root,
						      eb->start, eb->len);

	if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) {
		if (wc->pin && btrfs_header_level(eb) == 0)
			ret = btrfs_exclude_logged_extents(log, eb);
		if (wc->write)
			btrfs_write_tree_block(eb);
		if (wc->wait)
			btrfs_wait_tree_block_writeback(eb);
	}
	return ret;
}

/*
 * Item overwrite used by replay and tree logging.  eb, slot and key all refer
 * to the src data we are copying out.
 *
 * root is the tree we are copying into, and path is a scratch
 * path for use in this function (it should be released on entry and
 * will be released on exit).
 *
 * If the key is already in the destination tree the existing item is
 * overwritten.  If the existing item isn't big enough, it is extended.
 * If it is too large, it is truncated.
 *
 * If the key isn't in the destination yet, a new item is inserted.
 */
static noinline int overwrite_item(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_path *path,
				   struct extent_buffer *eb, int slot,
				   struct btrfs_key *key)
{
	int ret;
	u32 item_size;
	u64 saved_i_size = 0;
	int save_old_i_size = 0;
	unsigned long src_ptr;
	unsigned long dst_ptr;
	int overwrite_root = 0;
	bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;

	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
		overwrite_root = 1;

	item_size = btrfs_item_size_nr(eb, slot);
	src_ptr = btrfs_item_ptr_offset(eb, slot);

	/* look for the key in the destination tree */
	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
	if (ret < 0)
		return ret;

	if (ret == 0) {
		char *src_copy;
		char *dst_copy;
		u32 dst_size = btrfs_item_size_nr(path->nodes[0],
						  path->slots[0]);
		if (dst_size != item_size)
			goto insert;

		if (item_size == 0) {
			btrfs_release_path(path);
			return 0;
		}
		dst_copy = kmalloc(item_size, GFP_NOFS);
		src_copy = kmalloc(item_size, GFP_NOFS);
		if (!dst_copy || !src_copy) {
			btrfs_release_path(path);
			kfree(dst_copy);
			kfree(src_copy);
			return -ENOMEM;
		}

		read_extent_buffer(eb, src_copy, src_ptr, item_size);

		dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
		read_extent_buffer(path->nodes[0], dst_copy, dst_ptr,
				   item_size);
		ret = memcmp(dst_copy, src_copy, item_size);

		kfree(dst_copy);
		kfree(src_copy);
		/*
		 * they have the same contents, just return, this saves
		 * us from cowing blocks in the destination tree and doing
		 * extra writes that may not have been done by a previous
		 * sync
		 */
		if (ret == 0) {
			btrfs_release_path(path);
			return 0;
		}

		/*
		 * We need to load the old nbytes into the inode so when we
		 * replay the extents we've logged we get the right nbytes.
		 */
		if (inode_item) {
			struct btrfs_inode_item *item;
			u64 nbytes;
			u32 mode;

			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
					      struct btrfs_inode_item);
			nbytes = btrfs_inode_nbytes(path->nodes[0], item);
			item = btrfs_item_ptr(eb, slot,
					      struct btrfs_inode_item);
			btrfs_set_inode_nbytes(eb, item, nbytes);

			/*
			 * If this is a directory we need to reset the i_size to
			 * 0 so that we can set it up properly when replaying
			 * the rest of the items in this log.
			 */
			mode = btrfs_inode_mode(eb, item);
			if (S_ISDIR(mode))
				btrfs_set_inode_size(eb, item, 0);
		}
	} else if (inode_item) {
		struct btrfs_inode_item *item;
		u32 mode;

		/*
		 * New inode, set nbytes to 0 so that the nbytes comes out
		 * properly when we replay the extents.
		 */
		item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
		btrfs_set_inode_nbytes(eb, item, 0);

		/*
		 * If this is a directory we need to reset the i_size to 0 so
		 * that we can set it up properly when replaying the rest of
		 * the items in this log.
		 */
		mode = btrfs_inode_mode(eb, item);
		if (S_ISDIR(mode))
			btrfs_set_inode_size(eb, item, 0);
	}
insert:
	btrfs_release_path(path);
	/* try to insert the key into the destination tree */
	ret = btrfs_insert_empty_item(trans, root, path,
				      key, item_size);

	/* make sure any existing item is the correct size */
	if (ret == -EEXIST) {
		u32 found_size;
		found_size = btrfs_item_size_nr(path->nodes[0],
						path->slots[0]);
		if (found_size > item_size)
			btrfs_truncate_item(root, path, item_size, 1);
		else if (found_size < item_size)
			btrfs_extend_item(root, path,
					  item_size - found_size);
	} else if (ret) {
		return ret;
	}
	dst_ptr = btrfs_item_ptr_offset(path->nodes[0],
					path->slots[0]);

	/* don't overwrite an existing inode if the generation number
	 * was logged as zero.  This is done when the tree logging code
	 * is just logging an inode to make sure it exists after recovery.
	 *
	 * Also, don't overwrite i_size on directories during replay.
	 * log replay inserts and removes directory items based on the
	 * state of the tree found in the subvolume, and i_size is modified
	 * as it goes
	 */
	if (key->type == BTRFS_INODE_ITEM_KEY && ret == -EEXIST) {
		struct btrfs_inode_item *src_item;
		struct btrfs_inode_item *dst_item;

		src_item = (struct btrfs_inode_item *)src_ptr;
		dst_item = (struct btrfs_inode_item *)dst_ptr;

		if (btrfs_inode_generation(eb, src_item) == 0)
			goto no_copy;

		if (overwrite_root &&
		    S_ISDIR(btrfs_inode_mode(eb, src_item)) &&
		    S_ISDIR(btrfs_inode_mode(path->nodes[0], dst_item))) {
			save_old_i_size = 1;
			saved_i_size = btrfs_inode_size(path->nodes[0],
							dst_item);
		}
	}

	copy_extent_buffer(path->nodes[0], eb, dst_ptr,
			   src_ptr, item_size);

	if (save_old_i_size) {
		struct btrfs_inode_item *dst_item;
		dst_item = (struct btrfs_inode_item *)dst_ptr;
		btrfs_set_inode_size(path->nodes[0], dst_item, saved_i_size);
	}

	/* make sure the generation is filled in */
	if (key->type == BTRFS_INODE_ITEM_KEY) {
		struct btrfs_inode_item *dst_item;
		dst_item = (struct btrfs_inode_item *)dst_ptr;
		if (btrfs_inode_generation(path->nodes[0], dst_item) == 0) {
			btrfs_set_inode_generation(path->nodes[0], dst_item,
						   trans->transid);
		}
	}
no_copy:
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_release_path(path);
	return 0;
}

/*
 * simple helper to read an inode off the disk from a given root
 * This can only be called for subvolume roots and not for the log
 */
static noinline struct inode *read_one_inode(struct btrfs_root *root,
					     u64 objectid)
{
	struct btrfs_key key;
	struct inode *inode;

	key.objectid = objectid;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;
	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
	if (IS_ERR(inode)) {
		inode = NULL;
	} else if (is_bad_inode(inode)) {
		iput(inode);
		inode = NULL;
	}
	return inode;
}

/* replays a single extent in 'eb' at 'slot' with 'key' into the
 * subvolume 'root'.  path is released on entry and should be released
 * on exit.
 *
 * extents in the log tree have not been allocated out of the extent
 * tree yet.  So, this completes the allocation, taking a reference
 * as required if the extent already exists or creating a new extent
 * if it isn't in the extent allocation tree yet.
 *
 * The extent is inserted into the file, dropping any existing extents
 * from the file that overlap the new one.
 */
static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      struct extent_buffer *eb, int slot,
				      struct btrfs_key *key)
{
	int found_type;
	u64 extent_end;
	u64 start = key->offset;
	u64 nbytes = 0;
	struct btrfs_file_extent_item *item;
	struct inode *inode = NULL;
	unsigned long size;
	int ret = 0;

	item = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
	found_type = btrfs_file_extent_type(eb, item);

	if (found_type == BTRFS_FILE_EXTENT_REG ||
	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
		nbytes = btrfs_file_extent_num_bytes(eb, item);
		extent_end = start + nbytes;

		/*
		 * We don't add to the inodes nbytes if we are prealloc or a
		 * hole.
		 */
		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
			nbytes = 0;
	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
		size = btrfs_file_extent_inline_len(eb, slot, item);
		nbytes = btrfs_file_extent_ram_bytes(eb, item);
		extent_end = ALIGN(start + size, root->sectorsize);
	} else {
		ret = 0;
		goto out;
	}

	inode = read_one_inode(root, key->objectid);
	if (!inode) {
		ret = -EIO;
		goto out;
	}

	/*
	 * first check to see if we already have this extent in the
	 * file.  This must be done before the btrfs_drop_extents run
	 * so we don't try to drop this extent.
	 */
	ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
				       start, 0);

	if (ret == 0 &&
	    (found_type == BTRFS_FILE_EXTENT_REG ||
	     found_type == BTRFS_FILE_EXTENT_PREALLOC)) {
		struct btrfs_file_extent_item cmp1;
		struct btrfs_file_extent_item cmp2;
		struct btrfs_file_extent_item *existing;
		struct extent_buffer *leaf;

		leaf = path->nodes[0];
		existing = btrfs_item_ptr(leaf, path->slots[0],
					  struct btrfs_file_extent_item);

		read_extent_buffer(eb, &cmp1, (unsigned long)item,
				   sizeof(cmp1));
		read_extent_buffer(leaf, &cmp2, (unsigned long)existing,
				   sizeof(cmp2));

		/*
		 * we already have a pointer to this exact extent,
		 * we don't have to do anything
		 */
		if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) {
			btrfs_release_path(path);
			goto out;
		}
	}
	btrfs_release_path(path);

	/* drop any overlapping extents */
	ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1);
	if (ret)
		goto out;

	if (found_type == BTRFS_FILE_EXTENT_REG ||
	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
		u64 offset;
		unsigned long dest_offset;
		struct btrfs_key ins;

		ret = btrfs_insert_empty_item(trans, root, path, key,
					      sizeof(*item));
		if (ret)
			goto out;
		dest_offset = btrfs_item_ptr_offset(path->nodes[0],
						    path->slots[0]);
		copy_extent_buffer(path->nodes[0], eb, dest_offset,
				(unsigned long)item,  sizeof(*item));

		ins.objectid = btrfs_file_extent_disk_bytenr(eb, item);
		ins.offset = btrfs_file_extent_disk_num_bytes(eb, item);
		ins.type = BTRFS_EXTENT_ITEM_KEY;
		offset = key->offset - btrfs_file_extent_offset(eb, item);

		if (ins.objectid > 0) {
			u64 csum_start;
			u64 csum_end;
			LIST_HEAD(ordered_sums);
			/*
			 * is this extent already allocated in the extent
			 * allocation tree?  If so, just add a reference
			 */
			ret = btrfs_lookup_extent(root, ins.objectid,
						ins.offset);
			if (ret == 0) {
				ret = btrfs_inc_extent_ref(trans, root,
						ins.objectid, ins.offset,
						0, root->root_key.objectid,
						key->objectid, offset, 0);
				if (ret)
					goto out;
			} else {
				/*
				 * insert the extent pointer in the extent
				 * allocation tree
				 */
				ret = btrfs_alloc_logged_file_extent(trans,
						root, root->root_key.objectid,
						key->objectid, offset, &ins);
				if (ret)
					goto out;
			}
			btrfs_release_path(path);

			if (btrfs_file_extent_compression(eb, item)) {
				csum_start = ins.objectid;
				csum_end = csum_start + ins.offset;
			} else {
				csum_start = ins.objectid +
					btrfs_file_extent_offset(eb, item);
				csum_end = csum_start +
					btrfs_file_extent_num_bytes(eb, item);
			}

			ret = btrfs_lookup_csums_range(root->log_root,
						csum_start, csum_end - 1,
						&ordered_sums, 0);
			if (ret)
				goto out;
			while (!list_empty(&ordered_sums)) {
				struct btrfs_ordered_sum *sums;
				sums = list_entry(ordered_sums.next,
						struct btrfs_ordered_sum,
						list);
				if (!ret)
					ret = btrfs_csum_file_blocks(trans,
						root->fs_info->csum_root,
						sums);
				list_del(&sums->list);
				kfree(sums);
			}
			if (ret)
				goto out;
		} else {
			btrfs_release_path(path);
		}
	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
		/* inline extents are easy, we just overwrite them */
		ret = overwrite_item(trans, root, path, eb, slot, key);
		if (ret)
			goto out;
	}

	inode_add_bytes(inode, nbytes);
	ret = btrfs_update_inode(trans, root, inode);
out:
	if (inode)
		iput(inode);
	return ret;
}

/*
 * when cleaning up conflicts between the directory names in the
 * subvolume, directory names in the log and directory names in the
 * inode back references, we may have to unlink inodes from directories.
 *
 * This is a helper function to do the unlink of a specific directory
 * item
 */
static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      struct inode *dir,
				      struct btrfs_dir_item *di)
{
	struct inode *inode;
	char *name;
	int name_len;
	struct extent_buffer *leaf;
	struct btrfs_key location;
	int ret;

	leaf = path->nodes[0];

	btrfs_dir_item_key_to_cpu(leaf, di, &location);
	name_len = btrfs_dir_name_len(leaf, di);
	name = kmalloc(name_len, GFP_NOFS);
	if (!name)
		return -ENOMEM;

	read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
	btrfs_release_path(path);

	inode = read_one_inode(root, location.objectid);
	if (!inode) {
		ret = -EIO;
		goto out;
	}

	ret = link_to_fixup_dir(trans, root, path, location.objectid);
	if (ret)
		goto out;

	ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
	if (ret)
		goto out;
	else
		ret = btrfs_run_delayed_items(trans, root);
out:
	kfree(name);
	iput(inode);
	return ret;
}

/*
 * helper function to see if a given name and sequence number found
 * in an inode back reference are already in a directory and correctly
 * point to this inode
 */
static noinline int inode_in_dir(struct btrfs_root *root,
				 struct btrfs_path *path,
				 u64 dirid, u64 objectid, u64 index,
				 const char *name, int name_len)
{
	struct btrfs_dir_item *di;
	struct btrfs_key location;
	int match = 0;

	di = btrfs_lookup_dir_index_item(NULL, root, path, dirid,
					 index, name, name_len, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
		if (location.objectid != objectid)
			goto out;
	} else
		goto out;
	btrfs_release_path(path);

	di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
		if (location.objectid != objectid)
			goto out;
	} else
		goto out;
	match = 1;
out:
	btrfs_release_path(path);
	return match;
}

/*
 * helper function to check a log tree for a named back reference in
 * an inode.  This is used to decide if a back reference that is
 * found in the subvolume conflicts with what we find in the log.
 *
 * inode backreferences may have multiple refs in a single item,
 * during replay we process one reference at a time, and we don't
 * want to delete valid links to a file from the subvolume if that
 * link is also in the log.
 */
static noinline int backref_in_log(struct btrfs_root *log,
				   struct btrfs_key *key,
				   u64 ref_objectid,
				   char *name, int namelen)
{
	struct btrfs_path *path;
	struct btrfs_inode_ref *ref;
	unsigned long ptr;
	unsigned long ptr_end;
	unsigned long name_ptr;
	int found_name_len;
	int item_size;
	int ret;
	int match = 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
	if (ret != 0)
		goto out;

	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);

	if (key->type == BTRFS_INODE_EXTREF_KEY) {
		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
						   name, namelen, NULL))
			match = 1;

		goto out;
	}

	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
	ptr_end = ptr + item_size;
	while (ptr < ptr_end) {
		ref = (struct btrfs_inode_ref *)ptr;
		found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
		if (found_name_len == namelen) {
			name_ptr = (unsigned long)(ref + 1);
			ret = memcmp_extent_buffer(path->nodes[0], name,
						   name_ptr, namelen);
			if (ret == 0) {
				match = 1;
				goto out;
			}
		}
		ptr = (unsigned long)(ref + 1) + found_name_len;
	}
out:
	btrfs_free_path(path);
	return match;
}

static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
				  struct btrfs_root *root,
				  struct btrfs_path *path,
				  struct btrfs_root *log_root,
				  struct inode *dir, struct inode *inode,
				  struct extent_buffer *eb,
				  u64 inode_objectid, u64 parent_objectid,
				  u64 ref_index, char *name, int namelen,
				  int *search_done)
{
	int ret;
	char *victim_name;
	int victim_name_len;
	struct extent_buffer *leaf;
	struct btrfs_dir_item *di;
	struct btrfs_key search_key;
	struct btrfs_inode_extref *extref;

again:
	/* Search old style refs */
	search_key.objectid = inode_objectid;
	search_key.type = BTRFS_INODE_REF_KEY;
	search_key.offset = parent_objectid;
	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
	if (ret == 0) {
		struct btrfs_inode_ref *victim_ref;
		unsigned long ptr;
		unsigned long ptr_end;

		leaf = path->nodes[0];

		/* are we trying to overwrite a back ref for the root directory
		 * if so, just jump out, we're done
		 */
		if (search_key.objectid == search_key.offset)
			return 1;

		/* check all the names in this back reference to see
		 * if they are in the log.  if so, we allow them to stay
		 * otherwise they must be unlinked as a conflict
		 */
		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
		ptr_end = ptr + btrfs_item_size_nr(leaf, path->slots[0]);
		while (ptr < ptr_end) {
			victim_ref = (struct btrfs_inode_ref *)ptr;
			victim_name_len = btrfs_inode_ref_name_len(leaf,
								   victim_ref);
			victim_name = kmalloc(victim_name_len, GFP_NOFS);
			if (!victim_name)
				return -ENOMEM;

			read_extent_buffer(leaf, victim_name,
					   (unsigned long)(victim_ref + 1),
					   victim_name_len);

			if (!backref_in_log(log_root, &search_key,
					    parent_objectid,
					    victim_name,
					    victim_name_len)) {
				inc_nlink(inode);
				btrfs_release_path(path);

				ret = btrfs_unlink_inode(trans, root, dir,
							 inode, victim_name,
							 victim_name_len);
				kfree(victim_name);
				if (ret)
					return ret;
				ret = btrfs_run_delayed_items(trans, root);
				if (ret)
					return ret;
				*search_done = 1;
				goto again;
			}
			kfree(victim_name);

			ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
		}

		/*
		 * NOTE: we have searched root tree and checked the
		 * coresponding ref, it does not need to check again.
		 */
		*search_done = 1;
	}
	btrfs_release_path(path);

	/* Same search but for extended refs */
	extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
					   inode_objectid, parent_objectid, 0,
					   0);
	if (!IS_ERR_OR_NULL(extref)) {
		u32 item_size;
		u32 cur_offset = 0;
		unsigned long base;
		struct inode *victim_parent;

		leaf = path->nodes[0];

		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
		base = btrfs_item_ptr_offset(leaf, path->slots[0]);

		while (cur_offset < item_size) {
			extref = (struct btrfs_inode_extref *)base + cur_offset;

			victim_name_len = btrfs_inode_extref_name_len(leaf, extref);

			if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid)
				goto next;

			victim_name = kmalloc(victim_name_len, GFP_NOFS);
			if (!victim_name)
				return -ENOMEM;
			read_extent_buffer(leaf, victim_name, (unsigned long)&extref->name,
					   victim_name_len);

			search_key.objectid = inode_objectid;
			search_key.type = BTRFS_INODE_EXTREF_KEY;
			search_key.offset = btrfs_extref_hash(parent_objectid,
							      victim_name,
							      victim_name_len);
			ret = 0;
			if (!backref_in_log(log_root, &search_key,
					    parent_objectid, victim_name,
					    victim_name_len)) {
				ret = -ENOENT;
				victim_parent = read_one_inode(root,
							       parent_objectid);
				if (victim_parent) {
					inc_nlink(inode);
					btrfs_release_path(path);

					ret = btrfs_unlink_inode(trans, root,
								 victim_parent,
								 inode,
								 victim_name,
								 victim_name_len);
					if (!ret)
						ret = btrfs_run_delayed_items(
								  trans, root);
				}
				iput(victim_parent);
				kfree(victim_name);
				if (ret)
					return ret;
				*search_done = 1;
				goto again;
			}
			kfree(victim_name);
			if (ret)
				return ret;
next:
			cur_offset += victim_name_len + sizeof(*extref);
		}
		*search_done = 1;
	}
	btrfs_release_path(path);

	/* look for a conflicting sequence number */
	di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
					 ref_index, name, namelen, 0);
	if (di && !IS_ERR(di)) {
		ret = drop_one_dir_item(trans, root, path, dir, di);
		if (ret)
			return ret;
	}
	btrfs_release_path(path);

	/* look for a conflicing name */
	di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
				   name, namelen, 0);
	if (di && !IS_ERR(di)) {
		ret = drop_one_dir_item(trans, root, path, dir, di);
		if (ret)
			return ret;
	}
	btrfs_release_path(path);

	return 0;
}

static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
			     u32 *namelen, char **name, u64 *index,
			     u64 *parent_objectid)
{
	struct btrfs_inode_extref *extref;

	extref = (struct btrfs_inode_extref *)ref_ptr;

	*namelen = btrfs_inode_extref_name_len(eb, extref);
	*name = kmalloc(*namelen, GFP_NOFS);
	if (*name == NULL)
		return -ENOMEM;

	read_extent_buffer(eb, *name, (unsigned long)&extref->name,
			   *namelen);

	*index = btrfs_inode_extref_index(eb, extref);
	if (parent_objectid)
		*parent_objectid = btrfs_inode_extref_parent(eb, extref);

	return 0;
}

static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
			  u32 *namelen, char **name, u64 *index)
{
	struct btrfs_inode_ref *ref;

	ref = (struct btrfs_inode_ref *)ref_ptr;

	*namelen = btrfs_inode_ref_name_len(eb, ref);
	*name = kmalloc(*namelen, GFP_NOFS);
	if (*name == NULL)
		return -ENOMEM;

	read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);

	*index = btrfs_inode_ref_index(eb, ref);

	return 0;
}

/*
 * replay one inode back reference item found in the log tree.
 * eb, slot and key refer to the buffer and key found in the log tree.
 * root is the destination we are replaying into, and path is for temp
 * use by this function.  (it should be released on return).
 */
static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
				  struct btrfs_root *root,
				  struct btrfs_root *log,
				  struct btrfs_path *path,
				  struct extent_buffer *eb, int slot,
				  struct btrfs_key *key)
{
	struct inode *dir = NULL;
	struct inode *inode = NULL;
	unsigned long ref_ptr;
	unsigned long ref_end;
	char *name = NULL;
	int namelen;
	int ret;
	int search_done = 0;
	int log_ref_ver = 0;
	u64 parent_objectid;
	u64 inode_objectid;
	u64 ref_index = 0;
	int ref_struct_size;

	ref_ptr = btrfs_item_ptr_offset(eb, slot);
	ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);

	if (key->type == BTRFS_INODE_EXTREF_KEY) {
		struct btrfs_inode_extref *r;

		ref_struct_size = sizeof(struct btrfs_inode_extref);
		log_ref_ver = 1;
		r = (struct btrfs_inode_extref *)ref_ptr;
		parent_objectid = btrfs_inode_extref_parent(eb, r);
	} else {
		ref_struct_size = sizeof(struct btrfs_inode_ref);
		parent_objectid = key->offset;
	}
	inode_objectid = key->objectid;

	/*
	 * it is possible that we didn't log all the parent directories
	 * for a given inode.  If we don't find the dir, just don't
	 * copy the back ref in.  The link count fixup code will take
	 * care of the rest
	 */
	dir = read_one_inode(root, parent_objectid);
	if (!dir) {
		ret = -ENOENT;
		goto out;
	}

	inode = read_one_inode(root, inode_objectid);
	if (!inode) {
		ret = -EIO;
		goto out;
	}

	while (ref_ptr < ref_end) {
		if (log_ref_ver) {
			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
						&ref_index, &parent_objectid);
			/*
			 * parent object can change from one array
			 * item to another.
			 */
			if (!dir)
				dir = read_one_inode(root, parent_objectid);
			if (!dir) {
				ret = -ENOENT;
				goto out;
			}
		} else {
			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
					     &ref_index);
		}
		if (ret)
			goto out;

		/* if we already have a perfect match, we're done */
		if (!inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode),
				  ref_index, name, namelen)) {
			/*
			 * look for a conflicting back reference in the
			 * metadata. if we find one we have to unlink that name
			 * of the file before we add our new link.  Later on, we
			 * overwrite any existing back reference, and we don't
			 * want to create dangling pointers in the directory.
			 */

			if (!search_done) {
				ret = __add_inode_ref(trans, root, path, log,
						      dir, inode, eb,
						      inode_objectid,
						      parent_objectid,
						      ref_index, name, namelen,
						      &search_done);
				if (ret) {
					if (ret == 1)
						ret = 0;
					goto out;
				}
			}

			/* insert our name */
			ret = btrfs_add_link(trans, dir, inode, name, namelen,
					     0, ref_index);
			if (ret)
				goto out;

			btrfs_update_inode(trans, root, inode);
		}

		ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen;
		kfree(name);
		name = NULL;
		if (log_ref_ver) {
			iput(dir);
			dir = NULL;
		}
	}

	/* finally write the back reference in the inode */
	ret = overwrite_item(trans, root, path, eb, slot, key);
out:
	btrfs_release_path(path);
	kfree(name);
	iput(dir);
	iput(inode);
	return ret;
}

static int insert_orphan_item(struct btrfs_trans_handle *trans,
			      struct btrfs_root *root, u64 offset)
{
	int ret;
	ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID,
			offset, BTRFS_ORPHAN_ITEM_KEY, NULL);
	if (ret > 0)
		ret = btrfs_insert_orphan_item(trans, root, offset);
	return ret;
}

static int count_inode_extrefs(struct btrfs_root *root,
			       struct inode *inode, struct btrfs_path *path)
{
	int ret = 0;
	int name_len;
	unsigned int nlink = 0;
	u32 item_size;
	u32 cur_offset = 0;
	u64 inode_objectid = btrfs_ino(inode);
	u64 offset = 0;
	unsigned long ptr;
	struct btrfs_inode_extref *extref;
	struct extent_buffer *leaf;

	while (1) {
		ret = btrfs_find_one_extref(root, inode_objectid, offset, path,
					    &extref, &offset);
		if (ret)
			break;

		leaf = path->nodes[0];
		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);

		while (cur_offset < item_size) {
			extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
			name_len = btrfs_inode_extref_name_len(leaf, extref);

			nlink++;

			cur_offset += name_len + sizeof(*extref);
		}

		offset++;
		btrfs_release_path(path);
	}
	btrfs_release_path(path);

	if (ret < 0)
		return ret;
	return nlink;
}

static int count_inode_refs(struct btrfs_root *root,
			       struct inode *inode, struct btrfs_path *path)
{
	int ret;
	struct btrfs_key key;
	unsigned int nlink = 0;
	unsigned long ptr;
	unsigned long ptr_end;
	int name_len;
	u64 ino = btrfs_ino(inode);

	key.objectid = ino;
	key.type = BTRFS_INODE_REF_KEY;
	key.offset = (u64)-1;

	while (1) {
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0)
			break;
		if (ret > 0) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}
process_slot:
		btrfs_item_key_to_cpu(path->nodes[0], &key,
				      path->slots[0]);
		if (key.objectid != ino ||
		    key.type != BTRFS_INODE_REF_KEY)
			break;
		ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
		ptr_end = ptr + btrfs_item_size_nr(path->nodes[0],
						   path->slots[0]);
		while (ptr < ptr_end) {
			struct btrfs_inode_ref *ref;

			ref = (struct btrfs_inode_ref *)ptr;
			name_len = btrfs_inode_ref_name_len(path->nodes[0],
							    ref);
			ptr = (unsigned long)(ref + 1) + name_len;
			nlink++;
		}

		if (key.offset == 0)
			break;
		if (path->slots[0] > 0) {
			path->slots[0]--;
			goto process_slot;
		}
		key.offset--;
		btrfs_release_path(path);
	}
	btrfs_release_path(path);

	return nlink;
}

/*
 * There are a few corners where the link count of the file can't
 * be properly maintained during replay.  So, instead of adding
 * lots of complexity to the log code, we just scan the backrefs
 * for any file that has been through replay.
 *
 * The scan will update the link count on the inode to reflect the
 * number of back refs found.  If it goes down to zero, the iput
 * will free the inode.
 */
static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
					   struct btrfs_root *root,
					   struct inode *inode)
{
	struct btrfs_path *path;
	int ret;
	u64 nlink = 0;
	u64 ino = btrfs_ino(inode);

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = count_inode_refs(root, inode, path);
	if (ret < 0)
		goto out;

	nlink = ret;

	ret = count_inode_extrefs(root, inode, path);
	if (ret == -ENOENT)
		ret = 0;

	if (ret < 0)
		goto out;

	nlink += ret;

	ret = 0;

	if (nlink != inode->i_nlink) {
		set_nlink(inode, nlink);
		btrfs_update_inode(trans, root, inode);
	}
	BTRFS_I(inode)->index_cnt = (u64)-1;

	if (inode->i_nlink == 0) {
		if (S_ISDIR(inode->i_mode)) {
			ret = replay_dir_deletes(trans, root, NULL, path,
						 ino, 1);
			if (ret)
				goto out;
		}
		ret = insert_orphan_item(trans, root, ino);
	}

out:
	btrfs_free_path(path);
	return ret;
}

static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
					    struct btrfs_root *root,
					    struct btrfs_path *path)
{
	int ret;
	struct btrfs_key key;
	struct inode *inode;

	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = (u64)-1;
	while (1) {
		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
		if (ret < 0)
			break;

		if (ret == 1) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID ||
		    key.type != BTRFS_ORPHAN_ITEM_KEY)
			break;

		ret = btrfs_del_item(trans, root, path);
		if (ret)
			goto out;

		btrfs_release_path(path);
		inode = read_one_inode(root, key.offset);
		if (!inode)
			return -EIO;

		ret = fixup_inode_link_count(trans, root, inode);
		iput(inode);
		if (ret)
			goto out;

		/*
		 * fixup on a directory may create new entries,
		 * make sure we always look for the highset possible
		 * offset
		 */
		key.offset = (u64)-1;
	}
	ret = 0;
out:
	btrfs_release_path(path);
	return ret;
}


/*
 * record a given inode in the fixup dir so we can check its link
 * count when replay is done.  The link count is incremented here
 * so the inode won't go away until we check it
 */
static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_path *path,
				      u64 objectid)
{
	struct btrfs_key key;
	int ret = 0;
	struct inode *inode;

	inode = read_one_inode(root, objectid);
	if (!inode)
		return -EIO;

	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
	key.offset = objectid;

	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);

	btrfs_release_path(path);
	if (ret == 0) {
		if (!inode->i_nlink)
			set_nlink(inode, 1);
		else
			inc_nlink(inode);
		ret = btrfs_update_inode(trans, root, inode);
	} else if (ret == -EEXIST) {
		ret = 0;
	} else {
		BUG(); /* Logic Error */
	}
	iput(inode);

	return ret;
}

/*
 * when replaying the log for a directory, we only insert names
 * for inodes that actually exist.  This means an fsync on a directory
 * does not implicitly fsync all the new files in it
 */
static noinline int insert_one_name(struct btrfs_trans_handle *trans,
				    struct btrfs_root *root,
				    struct btrfs_path *path,
				    u64 dirid, u64 index,
				    char *name, int name_len, u8 type,
				    struct btrfs_key *location)
{
	struct inode *inode;
	struct inode *dir;
	int ret;

	inode = read_one_inode(root, location->objectid);
	if (!inode)
		return -ENOENT;

	dir = read_one_inode(root, dirid);
	if (!dir) {
		iput(inode);
		return -EIO;
	}

	ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index);

	/* FIXME, put inode into FIXUP list */

	iput(inode);
	iput(dir);
	return ret;
}

/*
 * take a single entry in a log directory item and replay it into
 * the subvolume.
 *
 * if a conflicting item exists in the subdirectory already,
 * the inode it points to is unlinked and put into the link count
 * fix up tree.
 *
 * If a name from the log points to a file or directory that does
 * not exist in the FS, it is skipped.  fsyncs on directories
 * do not force down inodes inside that directory, just changes to the
 * names or unlinks in a directory.
 */
static noinline int replay_one_name(struct btrfs_trans_handle *trans,
				    struct btrfs_root *root,
				    struct btrfs_path *path,
				    struct extent_buffer *eb,
				    struct btrfs_dir_item *di,
				    struct btrfs_key *key)
{
	char *name;
	int name_len;
	struct btrfs_dir_item *dst_di;
	struct btrfs_key found_key;
	struct btrfs_key log_key;
	struct inode *dir;
	u8 log_type;
	int exists;
	int ret = 0;
	bool update_size = (key->type == BTRFS_DIR_INDEX_KEY);

	dir = read_one_inode(root, key->objectid);
	if (!dir)
		return -EIO;

	name_len = btrfs_dir_name_len(eb, di);
	name = kmalloc(name_len, GFP_NOFS);
	if (!name) {
		ret = -ENOMEM;
		goto out;
	}

	log_type = btrfs_dir_type(eb, di);
	read_extent_buffer(eb, name, (unsigned long)(di + 1),
		   name_len);

	btrfs_dir_item_key_to_cpu(eb, di, &log_key);
	exists = btrfs_lookup_inode(trans, root, path, &log_key, 0);
	if (exists == 0)
		exists = 1;
	else
		exists = 0;
	btrfs_release_path(path);

	if (key->type == BTRFS_DIR_ITEM_KEY) {
		dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid,
				       name, name_len, 1);
	} else if (key->type == BTRFS_DIR_INDEX_KEY) {
		dst_di = btrfs_lookup_dir_index_item(trans, root, path,
						     key->objectid,
						     key->offset, name,
						     name_len, 1);
	} else {
		/* Corruption */
		ret = -EINVAL;
		goto out;
	}
	if (IS_ERR_OR_NULL(dst_di)) {
		/* we need a sequence number to insert, so we only
		 * do inserts for the BTRFS_DIR_INDEX_KEY types
		 */
		if (key->type != BTRFS_DIR_INDEX_KEY)
			goto out;
		goto insert;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], dst_di, &found_key);
	/* the existing item matches the logged item */
	if (found_key.objectid == log_key.objectid &&
	    found_key.type == log_key.type &&
	    found_key.offset == log_key.offset &&
	    btrfs_dir_type(path->nodes[0], dst_di) == log_type) {
		goto out;
	}

	/*
	 * don't drop the conflicting directory entry if the inode
	 * for the new entry doesn't exist
	 */
	if (!exists)
		goto out;

	ret = drop_one_dir_item(trans, root, path, dir, dst_di);
	if (ret)
		goto out;

	if (key->type == BTRFS_DIR_INDEX_KEY)
		goto insert;
out:
	btrfs_release_path(path);
	if (!ret && update_size) {
		btrfs_i_size_write(dir, dir->i_size + name_len * 2);
		ret = btrfs_update_inode(trans, root, dir);
	}
	kfree(name);
	iput(dir);
	return ret;

insert:
	btrfs_release_path(path);
	ret = insert_one_name(trans, root, path, key->objectid, key->offset,
			      name, name_len, log_type, &log_key);
	if (ret && ret != -ENOENT)
		goto out;
	update_size = false;
	ret = 0;
	goto out;
}

/*
 * find all the names in a directory item and reconcile them into
 * the subvolume.  Only BTRFS_DIR_ITEM_KEY types will have more than
 * one name in a directory item, but the same code gets used for
 * both directory index types
 */
static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
					struct btrfs_root *root,
					struct btrfs_path *path,
					struct extent_buffer *eb, int slot,
					struct btrfs_key *key)
{
	int ret;
	u32 item_size = btrfs_item_size_nr(eb, slot);
	struct btrfs_dir_item *di;
	int name_len;
	unsigned long ptr;
	unsigned long ptr_end;

	ptr = btrfs_item_ptr_offset(eb, slot);
	ptr_end = ptr + item_size;
	while (ptr < ptr_end) {
		di = (struct btrfs_dir_item *)ptr;
		if (verify_dir_item(root, eb, di))
			return -EIO;
		name_len = btrfs_dir_name_len(eb, di);
		ret = replay_one_name(trans, root, path, eb, di, key);
		if (ret)
			return ret;
		ptr = (unsigned long)(di + 1);
		ptr += name_len;
	}
	return 0;
}

/*
 * directory replay has two parts.  There are the standard directory
 * items in the log copied from the subvolume, and range items
 * created in the log while the subvolume was logged.
 *
 * The range items tell us which parts of the key space the log
 * is authoritative for.  During replay, if a key in the subvolume
 * directory is in a logged range item, but not actually in the log
 * that means it was deleted from the directory before the fsync
 * and should be removed.
 */
static noinline int find_dir_range(struct btrfs_root *root,
				   struct btrfs_path *path,
				   u64 dirid, int key_type,
				   u64 *start_ret, u64 *end_ret)
{
	struct btrfs_key key;
	u64 found_end;
	struct btrfs_dir_log_item *item;
	int ret;
	int nritems;

	if (*start_ret == (u64)-1)
		return 1;

	key.objectid = dirid;
	key.type = key_type;
	key.offset = *start_ret;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	if (ret > 0) {
		if (path->slots[0] == 0)
			goto out;
		path->slots[0]--;
	}
	if (ret != 0)
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != key_type || key.objectid != dirid) {
		ret = 1;
		goto next;
	}
	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	found_end = btrfs_dir_log_end(path->nodes[0], item);

	if (*start_ret >= key.offset && *start_ret <= found_end) {
		ret = 0;
		*start_ret = key.offset;
		*end_ret = found_end;
		goto out;
	}
	ret = 1;
next:
	/* check the next slot in the tree to see if it is a valid item */
	nritems = btrfs_header_nritems(path->nodes[0]);
	if (path->slots[0] >= nritems) {
		ret = btrfs_next_leaf(root, path);
		if (ret)
			goto out;
	} else {
		path->slots[0]++;
	}

	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

	if (key.type != key_type || key.objectid != dirid) {
		ret = 1;
		goto out;
	}
	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	found_end = btrfs_dir_log_end(path->nodes[0], item);
	*start_ret = key.offset;
	*end_ret = found_end;
	ret = 0;
out:
	btrfs_release_path(path);
	return ret;
}

/*
 * this looks for a given directory item in the log.  If the directory
 * item is not in the log, the item is removed and the inode it points
 * to is unlinked
 */
static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
				      struct btrfs_root *root,
				      struct btrfs_root *log,
				      struct btrfs_path *path,
				      struct btrfs_path *log_path,
				      struct inode *dir,
				      struct btrfs_key *dir_key)
{
	int ret;
	struct extent_buffer *eb;
	int slot;
	u32 item_size;
	struct btrfs_dir_item *di;
	struct btrfs_dir_item *log_di;
	int name_len;
	unsigned long ptr;
	unsigned long ptr_end;
	char *name;
	struct inode *inode;
	struct btrfs_key location;

again:
	eb = path->nodes[0];
	slot = path->slots[0];
	item_size = btrfs_item_size_nr(eb, slot);
	ptr = btrfs_item_ptr_offset(eb, slot);
	ptr_end = ptr + item_size;
	while (ptr < ptr_end) {
		di = (struct btrfs_dir_item *)ptr;
		if (verify_dir_item(root, eb, di)) {
			ret = -EIO;
			goto out;
		}

		name_len = btrfs_dir_name_len(eb, di);
		name = kmalloc(name_len, GFP_NOFS);
		if (!name) {
			ret = -ENOMEM;
			goto out;
		}
		read_extent_buffer(eb, name, (unsigned long)(di + 1),
				  name_len);
		log_di = NULL;
		if (log && dir_key->type == BTRFS_DIR_ITEM_KEY) {
			log_di = btrfs_lookup_dir_item(trans, log, log_path,
						       dir_key->objectid,
						       name, name_len, 0);
		} else if (log && dir_key->type == BTRFS_DIR_INDEX_KEY) {
			log_di = btrfs_lookup_dir_index_item(trans, log,
						     log_path,
						     dir_key->objectid,
						     dir_key->offset,
						     name, name_len, 0);
		}
		if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) {
			btrfs_dir_item_key_to_cpu(eb, di, &location);
			btrfs_release_path(path);
			btrfs_release_path(log_path);
			inode = read_one_inode(root, location.objectid);
			if (!inode) {
				kfree(name);
				return -EIO;
			}

			ret = link_to_fixup_dir(trans, root,
						path, location.objectid);
			if (ret) {
				kfree(name);
				iput(inode);
				goto out;
			}

			inc_nlink(inode);
			ret = btrfs_unlink_inode(trans, root, dir, inode,
						 name, name_len);
			if (!ret)
				ret = btrfs_run_delayed_items(trans, root);
			kfree(name);
			iput(inode);
			if (ret)
				goto out;

			/* there might still be more names under this key
			 * check and repeat if required
			 */
			ret = btrfs_search_slot(NULL, root, dir_key, path,
						0, 0);
			if (ret == 0)
				goto again;
			ret = 0;
			goto out;
		} else if (IS_ERR(log_di)) {
			kfree(name);
			return PTR_ERR(log_di);
		}
		btrfs_release_path(log_path);
		kfree(name);

		ptr = (unsigned long)(di + 1);
		ptr += name_len;
	}
	ret = 0;
out:
	btrfs_release_path(path);
	btrfs_release_path(log_path);
	return ret;
}

/*
 * deletion replay happens before we copy any new directory items
 * out of the log or out of backreferences from inodes.  It
 * scans the log to find ranges of keys that log is authoritative for,
 * and then scans the directory to find items in those ranges that are
 * not present in the log.
 *
 * Anything we don't find in the log is unlinked and removed from the
 * directory.
 */
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
				       struct btrfs_root *root,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
				       u64 dirid, int del_all)
{
	u64 range_start;
	u64 range_end;
	int key_type = BTRFS_DIR_LOG_ITEM_KEY;
	int ret = 0;
	struct btrfs_key dir_key;
	struct btrfs_key found_key;
	struct btrfs_path *log_path;
	struct inode *dir;

	dir_key.objectid = dirid;
	dir_key.type = BTRFS_DIR_ITEM_KEY;
	log_path = btrfs_alloc_path();
	if (!log_path)
		return -ENOMEM;

	dir = read_one_inode(root, dirid);
	/* it isn't an error if the inode isn't there, that can happen
	 * because we replay the deletes before we copy in the inode item
	 * from the log
	 */
	if (!dir) {
		btrfs_free_path(log_path);
		return 0;
	}
again:
	range_start = 0;
	range_end = 0;
	while (1) {
		if (del_all)
			range_end = (u64)-1;
		else {
			ret = find_dir_range(log, path, dirid, key_type,
					     &range_start, &range_end);
			if (ret != 0)
				break;
		}

		dir_key.offset = range_start;
		while (1) {
			int nritems;
			ret = btrfs_search_slot(NULL, root, &dir_key, path,
						0, 0);
			if (ret < 0)
				goto out;

			nritems = btrfs_header_nritems(path->nodes[0]);
			if (path->slots[0] >= nritems) {
				ret = btrfs_next_leaf(root, path);
				if (ret)
					break;
			}
			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
					      path->slots[0]);
			if (found_key.objectid != dirid ||
			    found_key.type != dir_key.type)
				goto next_type;

			if (found_key.offset > range_end)
				break;

			ret = check_item_in_log(trans, root, log, path,
						log_path, dir,
						&found_key);
			if (ret)
				goto out;
			if (found_key.offset == (u64)-1)
				break;
			dir_key.offset = found_key.offset + 1;
		}
		btrfs_release_path(path);
		if (range_end == (u64)-1)
			break;
		range_start = range_end + 1;
	}

next_type:
	ret = 0;
	if (key_type == BTRFS_DIR_LOG_ITEM_KEY) {
		key_type = BTRFS_DIR_LOG_INDEX_KEY;
		dir_key.type = BTRFS_DIR_INDEX_KEY;
		btrfs_release_path(path);
		goto again;
	}
out:
	btrfs_release_path(path);
	btrfs_free_path(log_path);
	iput(dir);
	return ret;
}

/*
 * the process_func used to replay items from the log tree.  This
 * gets called in two different stages.  The first stage just looks
 * for inodes and makes sure they are all copied into the subvolume.
 *
 * The second stage copies all the other item types from the log into
 * the subvolume.  The two stage approach is slower, but gets rid of
 * lots of complexity around inodes referencing other inodes that exist
 * only in the log (references come from either directory items or inode
 * back refs).
 */
static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
			     struct walk_control *wc, u64 gen)
{
	int nritems;
	struct btrfs_path *path;
	struct btrfs_root *root = wc->replay_dest;
	struct btrfs_key key;
	int level;
	int i;
	int ret;

	ret = btrfs_read_buffer(eb, gen);
	if (ret)
		return ret;

	level = btrfs_header_level(eb);

	if (level != 0)
		return 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	nritems = btrfs_header_nritems(eb);
	for (i = 0; i < nritems; i++) {
		btrfs_item_key_to_cpu(eb, &key, i);

		/* inode keys are done during the first stage */
		if (key.type == BTRFS_INODE_ITEM_KEY &&
		    wc->stage == LOG_WALK_REPLAY_INODES) {
			struct btrfs_inode_item *inode_item;
			u32 mode;

			inode_item = btrfs_item_ptr(eb, i,
					    struct btrfs_inode_item);
			mode = btrfs_inode_mode(eb, inode_item);
			if (S_ISDIR(mode)) {
				ret = replay_dir_deletes(wc->trans,
					 root, log, path, key.objectid, 0);
				if (ret)
					break;
			}
			ret = overwrite_item(wc->trans, root, path,
					     eb, i, &key);
			if (ret)
				break;

			/* for regular files, make sure corresponding
			 * orhpan item exist. extents past the new EOF
			 * will be truncated later by orphan cleanup.
			 */
			if (S_ISREG(mode)) {
				ret = insert_orphan_item(wc->trans, root,
							 key.objectid);
				if (ret)
					break;
			}

			ret = link_to_fixup_dir(wc->trans, root,
						path, key.objectid);
			if (ret)
				break;
		}

		if (key.type == BTRFS_DIR_INDEX_KEY &&
		    wc->stage == LOG_WALK_REPLAY_DIR_INDEX) {
			ret = replay_one_dir_item(wc->trans, root, path,
						  eb, i, &key);
			if (ret)
				break;
		}

		if (wc->stage < LOG_WALK_REPLAY_ALL)
			continue;

		/* these keys are simply copied */
		if (key.type == BTRFS_XATTR_ITEM_KEY) {
			ret = overwrite_item(wc->trans, root, path,
					     eb, i, &key);
			if (ret)
				break;
		} else if (key.type == BTRFS_INODE_REF_KEY ||
			   key.type == BTRFS_INODE_EXTREF_KEY) {
			ret = add_inode_ref(wc->trans, root, log, path,
					    eb, i, &key);
			if (ret && ret != -ENOENT)
				break;
			ret = 0;
		} else if (key.type == BTRFS_EXTENT_DATA_KEY) {
			ret = replay_one_extent(wc->trans, root, path,
						eb, i, &key);
			if (ret)
				break;
		} else if (key.type == BTRFS_DIR_ITEM_KEY) {
			ret = replay_one_dir_item(wc->trans, root, path,
						  eb, i, &key);
			if (ret)
				break;
		}
	}
	btrfs_free_path(path);
	return ret;
}

static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_path *path, int *level,
				   struct walk_control *wc)
{
	u64 root_owner;
	u64 bytenr;
	u64 ptr_gen;
	struct extent_buffer *next;
	struct extent_buffer *cur;
	struct extent_buffer *parent;
	u32 blocksize;
	int ret = 0;

	WARN_ON(*level < 0);
	WARN_ON(*level >= BTRFS_MAX_LEVEL);

	while (*level > 0) {
		WARN_ON(*level < 0);
		WARN_ON(*level >= BTRFS_MAX_LEVEL);
		cur = path->nodes[*level];

		WARN_ON(btrfs_header_level(cur) != *level);

		if (path->slots[*level] >=
		    btrfs_header_nritems(cur))
			break;

		bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
		ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
		blocksize = btrfs_level_size(root, *level - 1);

		parent = path->nodes[*level];
		root_owner = btrfs_header_owner(parent);

		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
		if (!next)
			return -ENOMEM;

		if (*level == 1) {
			ret = wc->process_func(root, next, wc, ptr_gen);
			if (ret) {
				free_extent_buffer(next);
				return ret;
			}

			path->slots[*level]++;
			if (wc->free) {
				ret = btrfs_read_buffer(next, ptr_gen);
				if (ret) {
					free_extent_buffer(next);
					return ret;
				}

				if (trans) {
					btrfs_tree_lock(next);
					btrfs_set_lock_blocking(next);
					clean_tree_block(trans, root, next);
					btrfs_wait_tree_block_writeback(next);
					btrfs_tree_unlock(next);
				}

				WARN_ON(root_owner !=
					BTRFS_TREE_LOG_OBJECTID);
				ret = btrfs_free_and_pin_reserved_extent(root,
							 bytenr, blocksize);
				if (ret) {
					free_extent_buffer(next);
					return ret;
				}
			}
			free_extent_buffer(next);
			continue;
		}
		ret = btrfs_read_buffer(next, ptr_gen);
		if (ret) {
			free_extent_buffer(next);
			return ret;
		}

		WARN_ON(*level <= 0);
		if (path->nodes[*level-1])
			free_extent_buffer(path->nodes[*level-1]);
		path->nodes[*level-1] = next;
		*level = btrfs_header_level(next);
		path->slots[*level] = 0;
		cond_resched();
	}
	WARN_ON(*level < 0);
	WARN_ON(*level >= BTRFS_MAX_LEVEL);

	path->slots[*level] = btrfs_header_nritems(path->nodes[*level]);

	cond_resched();
	return 0;
}

static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 struct btrfs_path *path, int *level,
				 struct walk_control *wc)
{
	u64 root_owner;
	int i;
	int slot;
	int ret;

	for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
		slot = path->slots[i];
		if (slot + 1 < btrfs_header_nritems(path->nodes[i])) {
			path->slots[i]++;
			*level = i;
			WARN_ON(*level == 0);
			return 0;
		} else {
			struct extent_buffer *parent;
			if (path->nodes[*level] == root->node)
				parent = path->nodes[*level];
			else
				parent = path->nodes[*level + 1];

			root_owner = btrfs_header_owner(parent);
			ret = wc->process_func(root, path->nodes[*level], wc,
				 btrfs_header_generation(path->nodes[*level]));
			if (ret)
				return ret;

			if (wc->free) {
				struct extent_buffer *next;

				next = path->nodes[*level];

				if (trans) {
					btrfs_tree_lock(next);
					btrfs_set_lock_blocking(next);
					clean_tree_block(trans, root, next);
					btrfs_wait_tree_block_writeback(next);
					btrfs_tree_unlock(next);
				}

				WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
				ret = btrfs_free_and_pin_reserved_extent(root,
						path->nodes[*level]->start,
						path->nodes[*level]->len);
				if (ret)
					return ret;
			}
			free_extent_buffer(path->nodes[*level]);
			path->nodes[*level] = NULL;
			*level = i + 1;
		}
	}
	return 1;
}

/*
 * drop the reference count on the tree rooted at 'snap'.  This traverses
 * the tree freeing any blocks that have a ref count of zero after being
 * decremented.
 */
static int walk_log_tree(struct btrfs_trans_handle *trans,
			 struct btrfs_root *log, struct walk_control *wc)
{
	int ret = 0;
	int wret;
	int level;
	struct btrfs_path *path;
	int orig_level;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	level = btrfs_header_level(log->node);
	orig_level = level;
	path->nodes[level] = log->node;
	extent_buffer_get(log->node);
	path->slots[level] = 0;

	while (1) {
		wret = walk_down_log_tree(trans, log, path, &level, wc);
		if (wret > 0)
			break;
		if (wret < 0) {
			ret = wret;
			goto out;
		}

		wret = walk_up_log_tree(trans, log, path, &level, wc);
		if (wret > 0)
			break;
		if (wret < 0) {
			ret = wret;
			goto out;
		}
	}

	/* was the root node processed? if not, catch it here */
	if (path->nodes[orig_level]) {
		ret = wc->process_func(log, path->nodes[orig_level], wc,
			 btrfs_header_generation(path->nodes[orig_level]));
		if (ret)
			goto out;
		if (wc->free) {
			struct extent_buffer *next;

			next = path->nodes[orig_level];

			if (trans) {
				btrfs_tree_lock(next);
				btrfs_set_lock_blocking(next);
				clean_tree_block(trans, log, next);
				btrfs_wait_tree_block_writeback(next);
				btrfs_tree_unlock(next);
			}

			WARN_ON(log->root_key.objectid !=
				BTRFS_TREE_LOG_OBJECTID);
			ret = btrfs_free_and_pin_reserved_extent(log, next->start,
							 next->len);
			if (ret)
				goto out;
		}
	}

out:
	btrfs_free_path(path);
	return ret;
}

/*
 * helper function to update the item for a given subvolumes log root
 * in the tree of log roots
 */
static int update_log_root(struct btrfs_trans_handle *trans,
			   struct btrfs_root *log)
{
	int ret;

	if (log->log_transid == 1) {
		/* insert root item on the first sync */
		ret = btrfs_insert_root(trans, log->fs_info->log_root_tree,
				&log->root_key, &log->root_item);
	} else {
		ret = btrfs_update_root(trans, log->fs_info->log_root_tree,
				&log->root_key, &log->root_item);
	}
	return ret;
}

static int wait_log_commit(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root, unsigned long transid)
{
	DEFINE_WAIT(wait);
	int index = transid % 2;
	int ret = 0;

	/*
	 * we only allow two pending log transactions at a time,
	 * so we know that if ours is more than 2 older than the
	 * current transaction, we're done
	 */
	do {
		if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
		    trans->transid) {
			ret = -EAGAIN;
			break;
		}

		prepare_to_wait(&root->log_commit_wait[index],
				&wait, TASK_UNINTERRUPTIBLE);
		mutex_unlock(&root->log_mutex);

		if (root->log_transid < transid + 2 &&
		    atomic_read(&root->log_commit[index]))
			schedule();

		finish_wait(&root->log_commit_wait[index], &wait);
		mutex_lock(&root->log_mutex);
	} while (root->log_transid < transid + 2 &&
		 atomic_read(&root->log_commit[index]));

	return ret;
}

static void wait_for_writer(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root)
{
	DEFINE_WAIT(wait);
	while (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) !=
	       trans->transid && atomic_read(&root->log_writers)) {
		prepare_to_wait(&root->log_writer_wait,
				&wait, TASK_UNINTERRUPTIBLE);
		mutex_unlock(&root->log_mutex);
		if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) !=
		    trans->transid && atomic_read(&root->log_writers))
			schedule();
		mutex_lock(&root->log_mutex);
		finish_wait(&root->log_writer_wait, &wait);
	}
}

/*
 * btrfs_sync_log does sends a given tree log down to the disk and
 * updates the super blocks to record it.  When this call is done,
 * you know that any inodes previously logged are safely on disk only
 * if it returns 0.
 *
 * Any other return value means you need to call btrfs_commit_transaction.
 * Some of the edge cases for fsyncing directories that have had unlinks
 * or renames done in the past mean that sometimes the only safe
 * fsync is to commit the whole FS.  When btrfs_sync_log returns -EAGAIN,
 * that has happened.
 */
int btrfs_sync_log(struct btrfs_trans_handle *trans,
		   struct btrfs_root *root)
{
	int index1;
	int index2;
	int mark;
	int ret;
	struct btrfs_root *log = root->log_root;
	struct btrfs_root *log_root_tree = root->fs_info->log_root_tree;
	unsigned long log_transid = 0;
	struct blk_plug plug;

	mutex_lock(&root->log_mutex);
	log_transid = root->log_transid;
	index1 = root->log_transid % 2;
	if (atomic_read(&root->log_commit[index1])) {
		ret = wait_log_commit(trans, root, root->log_transid);
		mutex_unlock(&root->log_mutex);
		return ret;
	}
	atomic_set(&root->log_commit[index1], 1);

	/* wait for previous tree log sync to complete */
	if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
		wait_log_commit(trans, root, root->log_transid - 1);

	while (1) {
		int batch = atomic_read(&root->log_batch);
		/* when we're on an ssd, just kick the log commit out */
		if (!btrfs_test_opt(root, SSD) && root->log_multiple_pids) {
			mutex_unlock(&root->log_mutex);
			schedule_timeout_uninterruptible(1);
			mutex_lock(&root->log_mutex);
		}
		wait_for_writer(trans, root);
		if (batch == atomic_read(&root->log_batch))
			break;
	}

	/* bail out if we need to do a full commit */
	if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
	    trans->transid) {
		ret = -EAGAIN;
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&root->log_mutex);
		goto out;
	}

	if (log_transid % 2 == 0)
		mark = EXTENT_DIRTY;
	else
		mark = EXTENT_NEW;

	/* we start IO on  all the marked extents here, but we don't actually
	 * wait for them until later.
	 */
	blk_start_plug(&plug);
	ret = btrfs_write_marked_extents(log, &log->dirty_log_pages, mark);
	if (ret) {
		blk_finish_plug(&plug);
		btrfs_abort_transaction(trans, root, ret);
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&root->log_mutex);
		goto out;
	}

	btrfs_set_root_node(&log->root_item, log->node);

	root->log_transid++;
	log->log_transid = root->log_transid;
	root->log_start_pid = 0;
	smp_mb();
	/*
	 * IO has been started, blocks of the log tree have WRITTEN flag set
	 * in their headers. new modifications of the log will be written to
	 * new positions. so it's safe to allow log writers to go in.
	 */
	mutex_unlock(&root->log_mutex);

	mutex_lock(&log_root_tree->log_mutex);
	atomic_inc(&log_root_tree->log_batch);
	atomic_inc(&log_root_tree->log_writers);
	mutex_unlock(&log_root_tree->log_mutex);

	ret = update_log_root(trans, log);

	mutex_lock(&log_root_tree->log_mutex);
	if (atomic_dec_and_test(&log_root_tree->log_writers)) {
		smp_mb();
		if (waitqueue_active(&log_root_tree->log_writer_wait))
			wake_up(&log_root_tree->log_writer_wait);
	}

	if (ret) {
		blk_finish_plug(&plug);
		if (ret != -ENOSPC) {
			btrfs_abort_transaction(trans, root, ret);
			mutex_unlock(&log_root_tree->log_mutex);
			goto out;
		}
		ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
								trans->transid;
		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&log_root_tree->log_mutex);
		ret = -EAGAIN;
		goto out;
	}

	index2 = log_root_tree->log_transid % 2;
	if (atomic_read(&log_root_tree->log_commit[index2])) {
		blk_finish_plug(&plug);
		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
		ret = wait_log_commit(trans, log_root_tree,
				      log_root_tree->log_transid);
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&log_root_tree->log_mutex);
		goto out;
	}
	atomic_set(&log_root_tree->log_commit[index2], 1);

	if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) {
		wait_log_commit(trans, log_root_tree,
				log_root_tree->log_transid - 1);
	}

	wait_for_writer(trans, log_root_tree);

	/*
	 * now that we've moved on to the tree of log tree roots,
	 * check the full commit flag again
	 */
	if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
	    trans->transid) {
		blk_finish_plug(&plug);
		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&log_root_tree->log_mutex);
		ret = -EAGAIN;
		goto out_wake_log_root;
	}

	ret = btrfs_write_marked_extents(log_root_tree,
					 &log_root_tree->dirty_log_pages,
					 EXTENT_DIRTY | EXTENT_NEW);
	blk_finish_plug(&plug);
	if (ret) {
		btrfs_abort_transaction(trans, root, ret);
		btrfs_free_logged_extents(log, log_transid);
		mutex_unlock(&log_root_tree->log_mutex);
		goto out_wake_log_root;
	}
	btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
	btrfs_wait_marked_extents(log_root_tree,
				  &log_root_tree->dirty_log_pages,
				  EXTENT_NEW | EXTENT_DIRTY);
	btrfs_wait_logged_extents(log, log_transid);

	btrfs_set_super_log_root(root->fs_info->super_for_commit,
				log_root_tree->node->start);
	btrfs_set_super_log_root_level(root->fs_info->super_for_commit,
				btrfs_header_level(log_root_tree->node));

	log_root_tree->log_transid++;
	smp_mb();

	mutex_unlock(&log_root_tree->log_mutex);

	/*
	 * nobody else is going to jump in and write the the ctree
	 * super here because the log_commit atomic below is protecting
	 * us.  We must be called with a transaction handle pinning
	 * the running transaction open, so a full commit can't hop
	 * in and cause problems either.
	 */
	ret = write_ctree_super(trans, root->fs_info->tree_root, 1);
	if (ret) {
		btrfs_abort_transaction(trans, root, ret);
		goto out_wake_log_root;
	}

	mutex_lock(&root->log_mutex);
	if (root->last_log_commit < log_transid)
		root->last_log_commit = log_transid;
	mutex_unlock(&root->log_mutex);

out_wake_log_root:
	atomic_set(&log_root_tree->log_commit[index2], 0);
	smp_mb();
	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
		wake_up(&log_root_tree->log_commit_wait[index2]);
out:
	atomic_set(&root->log_commit[index1], 0);
	smp_mb();
	if (waitqueue_active(&root->log_commit_wait[index1]))
		wake_up(&root->log_commit_wait[index1]);
	return ret;
}

static void free_log_tree(struct btrfs_trans_handle *trans,
			  struct btrfs_root *log)
{
	int ret;
	u64 start;
	u64 end;
	struct walk_control wc = {
		.free = 1,
		.process_func = process_one_buffer
	};

	ret = walk_log_tree(trans, log, &wc);
	/* I don't think this can happen but just in case */
	if (ret)
		btrfs_abort_transaction(trans, log, ret);

	while (1) {
		ret = find_first_extent_bit(&log->dirty_log_pages,
				0, &start, &end, EXTENT_DIRTY | EXTENT_NEW,
				NULL);
		if (ret)
			break;

		clear_extent_bits(&log->dirty_log_pages, start, end,
				  EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS);
	}

	/*
	 * We may have short-circuited the log tree with the full commit logic
	 * and left ordered extents on our list, so clear these out to keep us
	 * from leaking inodes and memory.
	 */
	btrfs_free_logged_extents(log, 0);
	btrfs_free_logged_extents(log, 1);

	free_extent_buffer(log->node);
	kfree(log);
}

/*
 * free all the extents used by the tree log.  This should be called
 * at commit time of the full transaction
 */
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root)
{
	if (root->log_root) {
		free_log_tree(trans, root->log_root);
		root->log_root = NULL;
	}
	return 0;
}

int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
			     struct btrfs_fs_info *fs_info)
{
	if (fs_info->log_root_tree) {
		free_log_tree(trans, fs_info->log_root_tree);
		fs_info->log_root_tree = NULL;
	}
	return 0;
}

/*
 * If both a file and directory are logged, and unlinks or renames are
 * mixed in, we have a few interesting corners:
 *
 * create file X in dir Y
 * link file X to X.link in dir Y
 * fsync file X
 * unlink file X but leave X.link
 * fsync dir Y
 *
 * After a crash we would expect only X.link to exist.  But file X
 * didn't get fsync'd again so the log has back refs for X and X.link.
 *
 * We solve this by removing directory entries and inode backrefs from the
 * log when a file that was logged in the current transaction is
 * unlinked.  Any later fsync will include the updated log entries, and
 * we'll be able to reconstruct the proper directory items from backrefs.
 *
 * This optimizations allows us to avoid relogging the entire inode
 * or the entire directory.
 */
int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 const char *name, int name_len,
				 struct inode *dir, u64 index)
{
	struct btrfs_root *log;
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	int ret;
	int err = 0;
	int bytes_del = 0;
	u64 dir_ino = btrfs_ino(dir);

	if (BTRFS_I(dir)->logged_trans < trans->transid)
		return 0;

	ret = join_running_log_trans(root);
	if (ret)
		return 0;

	mutex_lock(&BTRFS_I(dir)->log_mutex);

	log = root->log_root;
	path = btrfs_alloc_path();
	if (!path) {
		err = -ENOMEM;
		goto out_unlock;
	}

	di = btrfs_lookup_dir_item(trans, log, path, dir_ino,
				   name, name_len, -1);
	if (IS_ERR(di)) {
		err = PTR_ERR(di);
		goto fail;
	}
	if (di) {
		ret = btrfs_delete_one_dir_name(trans, log, path, di);
		bytes_del += name_len;
		if (ret) {
			err = ret;
			goto fail;
		}
	}
	btrfs_release_path(path);
	di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino,
					 index, name, name_len, -1);
	if (IS_ERR(di)) {
		err = PTR_ERR(di);
		goto fail;
	}
	if (di) {
		ret = btrfs_delete_one_dir_name(trans, log, path, di);
		bytes_del += name_len;
		if (ret) {
			err = ret;
			goto fail;
		}
	}

	/* update the directory size in the log to reflect the names
	 * we have removed
	 */
	if (bytes_del) {
		struct btrfs_key key;

		key.objectid = dir_ino;
		key.offset = 0;
		key.type = BTRFS_INODE_ITEM_KEY;
		btrfs_release_path(path);

		ret = btrfs_search_slot(trans, log, &key, path, 0, 1);
		if (ret < 0) {
			err = ret;
			goto fail;
		}
		if (ret == 0) {
			struct btrfs_inode_item *item;
			u64 i_size;

			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
					      struct btrfs_inode_item);
			i_size = btrfs_inode_size(path->nodes[0], item);
			if (i_size > bytes_del)
				i_size -= bytes_del;
			else
				i_size = 0;
			btrfs_set_inode_size(path->nodes[0], item, i_size);
			btrfs_mark_buffer_dirty(path->nodes[0]);
		} else
			ret = 0;
		btrfs_release_path(path);
	}
fail:
	btrfs_free_path(path);
out_unlock:
	mutex_unlock(&BTRFS_I(dir)->log_mutex);
	if (ret == -ENOSPC) {
		root->fs_info->last_trans_log_full_commit = trans->transid;
		ret = 0;
	} else if (ret < 0)
		btrfs_abort_transaction(trans, root, ret);

	btrfs_end_log_trans(root);

	return err;
}

/* see comments for btrfs_del_dir_entries_in_log */
int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root,
			       const char *name, int name_len,
			       struct inode *inode, u64 dirid)
{
	struct btrfs_root *log;
	u64 index;
	int ret;

	if (BTRFS_I(inode)->logged_trans < trans->transid)
		return 0;

	ret = join_running_log_trans(root);
	if (ret)
		return 0;
	log = root->log_root;
	mutex_lock(&BTRFS_I(inode)->log_mutex);

	ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode),
				  dirid, &index);
	mutex_unlock(&BTRFS_I(inode)->log_mutex);
	if (ret == -ENOSPC) {
		root->fs_info->last_trans_log_full_commit = trans->transid;
		ret = 0;
	} else if (ret < 0 && ret != -ENOENT)
		btrfs_abort_transaction(trans, root, ret);
	btrfs_end_log_trans(root);

	return ret;
}

/*
 * creates a range item in the log for 'dirid'.  first_offset and
 * last_offset tell us which parts of the key space the log should
 * be considered authoritative for.
 */
static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
				       struct btrfs_root *log,
				       struct btrfs_path *path,
				       int key_type, u64 dirid,
				       u64 first_offset, u64 last_offset)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_dir_log_item *item;

	key.objectid = dirid;
	key.offset = first_offset;
	if (key_type == BTRFS_DIR_ITEM_KEY)
		key.type = BTRFS_DIR_LOG_ITEM_KEY;
	else
		key.type = BTRFS_DIR_LOG_INDEX_KEY;
	ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item));
	if (ret)
		return ret;

	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
			      struct btrfs_dir_log_item);
	btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_release_path(path);
	return 0;
}

/*
 * log all the items included in the current transaction for a given
 * directory.  This also creates the range items in the log tree required
 * to replay anything deleted before the fsync
 */
static noinline int log_dir_items(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct inode *inode,
			  struct btrfs_path *path,
			  struct btrfs_path *dst_path, int key_type,
			  u64 min_offset, u64 *last_offset_ret)
{
	struct btrfs_key min_key;
	struct btrfs_root *log = root->log_root;
	struct extent_buffer *src;
	int err = 0;
	int ret;
	int i;
	int nritems;
	u64 first_offset = min_offset;
	u64 last_offset = (u64)-1;
	u64 ino = btrfs_ino(inode);

	log = root->log_root;

	min_key.objectid = ino;
	min_key.type = key_type;
	min_key.offset = min_offset;

	path->keep_locks = 1;

	ret = btrfs_search_forward(root, &min_key, path, trans->transid);

	/*
	 * we didn't find anything from this transaction, see if there
	 * is anything at all
	 */
	if (ret != 0 || min_key.objectid != ino || min_key.type != key_type) {
		min_key.objectid = ino;
		min_key.type = key_type;
		min_key.offset = (u64)-1;
		btrfs_release_path(path);
		ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
		if (ret < 0) {
			btrfs_release_path(path);
			return ret;
		}
		ret = btrfs_previous_item(root, path, ino, key_type);

		/* if ret == 0 there are items for this type,
		 * create a range to tell us the last key of this type.
		 * otherwise, there are no items in this directory after
		 * *min_offset, and we create a range to indicate that.
		 */
		if (ret == 0) {
			struct btrfs_key tmp;
			btrfs_item_key_to_cpu(path->nodes[0], &tmp,
					      path->slots[0]);
			if (key_type == tmp.type)
				first_offset = max(min_offset, tmp.offset) + 1;
		}
		goto done;
	}

	/* go backward to find any previous key */
	ret = btrfs_previous_item(root, path, ino, key_type);
	if (ret == 0) {
		struct btrfs_key tmp;
		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
		if (key_type == tmp.type) {
			first_offset = tmp.offset;
			ret = overwrite_item(trans, log, dst_path,
					     path->nodes[0], path->slots[0],
					     &tmp);
			if (ret) {
				err = ret;
				goto done;
			}
		}
	}
	btrfs_release_path(path);

	/* find the first key from this transaction again */
	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
	if (WARN_ON(ret != 0))
		goto done;

	/*
	 * we have a block from this transaction, log every item in it
	 * from our directory
	 */
	while (1) {
		struct btrfs_key tmp;
		src = path->nodes[0];
		nritems = btrfs_header_nritems(src);
		for (i = path->slots[0]; i < nritems; i++) {
			btrfs_item_key_to_cpu(src, &min_key, i);

			if (min_key.objectid != ino || min_key.type != key_type)
				goto done;
			ret = overwrite_item(trans, log, dst_path, src, i,
					     &min_key);
			if (ret) {
				err = ret;
				goto done;
			}
		}
		path->slots[0] = nritems;

		/*
		 * look ahead to the next item and see if it is also
		 * from this directory and from this transaction
		 */
		ret = btrfs_next_leaf(root, path);
		if (ret == 1) {
			last_offset = (u64)-1;
			goto done;
		}
		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
		if (tmp.objectid != ino || tmp.type != key_type) {
			last_offset = (u64)-1;
			goto done;
		}
		if (btrfs_header_generation(path->nodes[0]) != trans->transid) {
			ret = overwrite_item(trans, log, dst_path,
					     path->nodes[0], path->slots[0],
					     &tmp);
			if (ret)
				err = ret;
			else
				last_offset = tmp.offset;
			goto done;
		}
	}
done:
	btrfs_release_path(path);
	btrfs_release_path(dst_path);

	if (err == 0) {
		*last_offset_ret = last_offset;
		/*
		 * insert the log range keys to indicate where the log
		 * is valid
		 */
		ret = insert_dir_log_key(trans, log, path, key_type,
					 ino, first_offset, last_offset);
		if (ret)
			err = ret;
	}
	return err;
}

/*
 * logging directories is very similar to logging inodes, We find all the items
 * from the current transaction and write them to the log.
 *
 * The recovery code scans the directory in the subvolume, and if it finds a
 * key in the range logged that is not present in the log tree, then it means
 * that dir entry was unlinked during the transaction.
 *
 * In order for that scan to work, we must include one key smaller than
 * the smallest logged by this transaction and one key larger than the largest
 * key logged by this transaction.
 */
static noinline int log_directory_changes(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct inode *inode,
			  struct btrfs_path *path,
			  struct btrfs_path *dst_path)
{
	u64 min_key;
	u64 max_key;
	int ret;
	int key_type = BTRFS_DIR_ITEM_KEY;

again:
	min_key = 0;
	max_key = 0;
	while (1) {
		ret = log_dir_items(trans, root, inode, path,
				    dst_path, key_type, min_key,
				    &max_key);
		if (ret)
			return ret;
		if (max_key == (u64)-1)
			break;
		min_key = max_key + 1;
	}

	if (key_type == BTRFS_DIR_ITEM_KEY) {
		key_type = BTRFS_DIR_INDEX_KEY;
		goto again;
	}
	return 0;
}

/*
 * a helper function to drop items from the log before we relog an
 * inode.  max_key_type indicates the highest item type to remove.
 * This cannot be run for file data extents because it does not
 * free the extents they point to.
 */
static int drop_objectid_items(struct btrfs_trans_handle *trans,
				  struct btrfs_root *log,
				  struct btrfs_path *path,
				  u64 objectid, int max_key_type)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_key found_key;
	int start_slot;

	key.objectid = objectid;
	key.type = max_key_type;
	key.offset = (u64)-1;

	while (1) {
		ret = btrfs_search_slot(trans, log, &key, path, -1, 1);
		BUG_ON(ret == 0); /* Logic error */
		if (ret < 0)
			break;

		if (path->slots[0] == 0)
			break;

		path->slots[0]--;
		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
				      path->slots[0]);

		if (found_key.objectid != objectid)
			break;

		found_key.offset = 0;
		found_key.type = 0;
		ret = btrfs_bin_search(path->nodes[0], &found_key, 0,
				       &start_slot);

		ret = btrfs_del_items(trans, log, path, start_slot,
				      path->slots[0] - start_slot + 1);
		/*
		 * If start slot isn't 0 then we don't need to re-search, we've
		 * found the last guy with the objectid in this tree.
		 */
		if (ret || start_slot != 0)
			break;
		btrfs_release_path(path);
	}
	btrfs_release_path(path);
	if (ret > 0)
		ret = 0;
	return ret;
}

static void fill_inode_item(struct btrfs_trans_handle *trans,
			    struct extent_buffer *leaf,
			    struct btrfs_inode_item *item,
			    struct inode *inode, int log_inode_only)
{
	struct btrfs_map_token token;

	btrfs_init_map_token(&token);

	if (log_inode_only) {
		/* set the generation to zero so the recover code
		 * can tell the difference between an logging
		 * just to say 'this inode exists' and a logging
		 * to say 'update this inode with these values'
		 */
		btrfs_set_token_inode_generation(leaf, item, 0, &token);
		btrfs_set_token_inode_size(leaf, item, 0, &token);
	} else {
		btrfs_set_token_inode_generation(leaf, item,
						 BTRFS_I(inode)->generation,
						 &token);
		btrfs_set_token_inode_size(leaf, item, inode->i_size, &token);
	}

	btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
	btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);

	btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
				     inode->i_atime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
				      inode->i_atime.tv_nsec, &token);

	btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
				     inode->i_mtime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
				      inode->i_mtime.tv_nsec, &token);

	btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
				     inode->i_ctime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
				      inode->i_ctime.tv_nsec, &token);

	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
				     &token);

	btrfs_set_token_inode_sequence(leaf, item, inode->i_version, &token);
	btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
	btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
	btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
	btrfs_set_token_inode_block_group(leaf, item, 0, &token);
}

static int log_inode_item(struct btrfs_trans_handle *trans,
			  struct btrfs_root *log, struct btrfs_path *path,
			  struct inode *inode)
{
	struct btrfs_inode_item *inode_item;
	int ret;

	ret = btrfs_insert_empty_item(trans, log, path,
				      &BTRFS_I(inode)->location,
				      sizeof(*inode_item));
	if (ret && ret != -EEXIST)
		return ret;
	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
				    struct btrfs_inode_item);
	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0);
	btrfs_release_path(path);
	return 0;
}

static noinline int copy_items(struct btrfs_trans_handle *trans,
			       struct inode *inode,
			       struct btrfs_path *dst_path,
			       struct btrfs_path *src_path, u64 *last_extent,
			       int start_slot, int nr, int inode_only)
{
	unsigned long src_offset;
	unsigned long dst_offset;
	struct btrfs_root *log = BTRFS_I(inode)->root->log_root;
	struct btrfs_file_extent_item *extent;
	struct btrfs_inode_item *inode_item;
	struct extent_buffer *src = src_path->nodes[0];
	struct btrfs_key first_key, last_key, key;
	int ret;
	struct btrfs_key *ins_keys;
	u32 *ins_sizes;
	char *ins_data;
	int i;
	struct list_head ordered_sums;
	int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
	bool has_extents = false;
	bool need_find_last_extent = (*last_extent == 0);
	bool done = false;

	INIT_LIST_HEAD(&ordered_sums);

	ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
			   nr * sizeof(u32), GFP_NOFS);
	if (!ins_data)
		return -ENOMEM;

	first_key.objectid = (u64)-1;

	ins_sizes = (u32 *)ins_data;
	ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));

	for (i = 0; i < nr; i++) {
		ins_sizes[i] = btrfs_item_size_nr(src, i + start_slot);
		btrfs_item_key_to_cpu(src, ins_keys + i, i + start_slot);
	}
	ret = btrfs_insert_empty_items(trans, log, dst_path,
				       ins_keys, ins_sizes, nr);
	if (ret) {
		kfree(ins_data);
		return ret;
	}

	for (i = 0; i < nr; i++, dst_path->slots[0]++) {
		dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0],
						   dst_path->slots[0]);

		src_offset = btrfs_item_ptr_offset(src, start_slot + i);

		if ((i == (nr - 1)))
			last_key = ins_keys[i];

		if (ins_keys[i].type == BTRFS_INODE_ITEM_KEY) {
			inode_item = btrfs_item_ptr(dst_path->nodes[0],
						    dst_path->slots[0],
						    struct btrfs_inode_item);
			fill_inode_item(trans, dst_path->nodes[0], inode_item,
					inode, inode_only == LOG_INODE_EXISTS);
		} else {
			copy_extent_buffer(dst_path->nodes[0], src, dst_offset,
					   src_offset, ins_sizes[i]);
		}

		/*
		 * We set need_find_last_extent here in case we know we were
		 * processing other items and then walk into the first extent in
		 * the inode.  If we don't hit an extent then nothing changes,
		 * we'll do the last search the next time around.
		 */
		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
			has_extents = true;
			if (need_find_last_extent &&
			    first_key.objectid == (u64)-1)
				first_key = ins_keys[i];
		} else {
			need_find_last_extent = false;
		}

		/* take a reference on file data extents so that truncates
		 * or deletes of this inode don't have to relog the inode
		 * again
		 */
		if (btrfs_key_type(ins_keys + i) == BTRFS_EXTENT_DATA_KEY &&
		    !skip_csum) {
			int found_type;
			extent = btrfs_item_ptr(src, start_slot + i,
						struct btrfs_file_extent_item);

			if (btrfs_file_extent_generation(src, extent) < trans->transid)
				continue;

			found_type = btrfs_file_extent_type(src, extent);
			if (found_type == BTRFS_FILE_EXTENT_REG) {
				u64 ds, dl, cs, cl;
				ds = btrfs_file_extent_disk_bytenr(src,
								extent);
				/* ds == 0 is a hole */
				if (ds == 0)
					continue;

				dl = btrfs_file_extent_disk_num_bytes(src,
								extent);
				cs = btrfs_file_extent_offset(src, extent);
				cl = btrfs_file_extent_num_bytes(src,
								extent);
				if (btrfs_file_extent_compression(src,
								  extent)) {
					cs = 0;
					cl = dl;
				}

				ret = btrfs_lookup_csums_range(
						log->fs_info->csum_root,
						ds + cs, ds + cs + cl - 1,
						&ordered_sums, 0);
				if (ret) {
					btrfs_release_path(dst_path);
					kfree(ins_data);
					return ret;
				}
			}
		}
	}

	btrfs_mark_buffer_dirty(dst_path->nodes[0]);
	btrfs_release_path(dst_path);
	kfree(ins_data);

	/*
	 * we have to do this after the loop above to avoid changing the
	 * log tree while trying to change the log tree.
	 */
	ret = 0;
	while (!list_empty(&ordered_sums)) {
		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
						   struct btrfs_ordered_sum,
						   list);
		if (!ret)
			ret = btrfs_csum_file_blocks(trans, log, sums);
		list_del(&sums->list);
		kfree(sums);
	}

	if (!has_extents)
		return ret;

	/*
	 * Because we use btrfs_search_forward we could skip leaves that were
	 * not modified and then assume *last_extent is valid when it really
	 * isn't.  So back up to the previous leaf and read the end of the last
	 * extent before we go and fill in holes.
	 */
	if (need_find_last_extent) {
		u64 len;

		ret = btrfs_prev_leaf(BTRFS_I(inode)->root, src_path);
		if (ret < 0)
			return ret;
		if (ret)
			goto fill_holes;
		if (src_path->slots[0])
			src_path->slots[0]--;
		src = src_path->nodes[0];
		btrfs_item_key_to_cpu(src, &key, src_path->slots[0]);
		if (key.objectid != btrfs_ino(inode) ||
		    key.type != BTRFS_EXTENT_DATA_KEY)
			goto fill_holes;
		extent = btrfs_item_ptr(src, src_path->slots[0],
					struct btrfs_file_extent_item);
		if (btrfs_file_extent_type(src, extent) ==
		    BTRFS_FILE_EXTENT_INLINE) {
			len = btrfs_file_extent_inline_len(src,
							   src_path->slots[0],
							   extent);
			*last_extent = ALIGN(key.offset + len,
					     log->sectorsize);
		} else {
			len = btrfs_file_extent_num_bytes(src, extent);
			*last_extent = key.offset + len;
		}
	}
fill_holes:
	/* So we did prev_leaf, now we need to move to the next leaf, but a few
	 * things could have happened
	 *
	 * 1) A merge could have happened, so we could currently be on a leaf
	 * that holds what we were copying in the first place.
	 * 2) A split could have happened, and now not all of the items we want
	 * are on the same leaf.
	 *
	 * So we need to adjust how we search for holes, we need to drop the
	 * path and re-search for the first extent key we found, and then walk
	 * forward until we hit the last one we copied.
	 */
	if (need_find_last_extent) {
		/* btrfs_prev_leaf could return 1 without releasing the path */
		btrfs_release_path(src_path);
		ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &first_key,
					src_path, 0, 0);
		if (ret < 0)
			return ret;
		ASSERT(ret == 0);
		src = src_path->nodes[0];
		i = src_path->slots[0];
	} else {
		i = start_slot;
	}

	/*
	 * Ok so here we need to go through and fill in any holes we may have
	 * to make sure that holes are punched for those areas in case they had
	 * extents previously.
	 */
	while (!done) {
		u64 offset, len;
		u64 extent_end;

		if (i >= btrfs_header_nritems(src_path->nodes[0])) {
			ret = btrfs_next_leaf(BTRFS_I(inode)->root, src_path);
			if (ret < 0)
				return ret;
			ASSERT(ret == 0);
			src = src_path->nodes[0];
			i = 0;
		}

		btrfs_item_key_to_cpu(src, &key, i);
		if (!btrfs_comp_cpu_keys(&key, &last_key))
			done = true;
		if (key.objectid != btrfs_ino(inode) ||
		    key.type != BTRFS_EXTENT_DATA_KEY) {
			i++;
			continue;
		}