aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/ide
diff options
context:
space:
mode:
authorBartlomiej Zolnierkiewicz <bzolnier@gmail.com>2007-07-09 17:17:57 -0400
committerBartlomiej Zolnierkiewicz <bzolnier@gmail.com>2007-07-09 17:17:57 -0400
commit75b1d97535327d0428c6bffd9d5407e65546fd5d (patch)
tree3271a13a27ed2a7896b7018bc2fceac62eba1b2e /drivers/ide
parent15a4f943e729d8ba215ee551df6d7988ba14ac00 (diff)
ide: convert ide_find_best_mode() users to use ide_max_dma_mode()
ide-timing.h: * remove handling of DMA modes from ide_find_best_mode() and rename it to ide_find_best_pio_mode() * drop no longer needed "map" argument from ide_find_best_pio_mode() and delete needless ->id check * remove no longer needed XFER_SWDMA and XFER_UDMA* defines au1xxx-ide.c: * use ide_max_dma_mode() instead of ide_find_best_mode() * remove needless CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA #ifdef amd74xx.c: * store UDMA masks in amd_ide_chip[] and while at it make "base" field to be u8 instead of unsigned long * convert the driver to use UDMA masks from amd_ide_chip[] * use ide_max_dma_mode() and ide_find_best_pio_mode() instead of ide_find_best_mode() * delete stale comment from amd74xx_ide_dma_check() * remove no longer needed AMD_UDMA* defines via82cxxx.c: * remove unused DISPLAY_VIA_TIMINGS define * store UDMA masks in via_isa_bridges[] and while at it make "flags" field to be u8 instead of u16 * convert the driver to use UDMA masks from via_isa_bridges[] * use ide_max_dma_mode() and ide_find_best_pio_mode() instead of ide_find_best_mode() * remove no longer needed VIA_UDMA* defines pmac.c: * use ide_max_dma_mode() instead of ide_find_best_mode() There should be no functionality changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Reviewed-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Diffstat (limited to 'drivers/ide')
-rw-r--r--drivers/ide/ide-timing.h56
-rw-r--r--drivers/ide/mips/au1xxx-ide.c7
-rw-r--r--drivers/ide/pci/amd74xx.c118
-rw-r--r--drivers/ide/pci/via82cxxx.c132
-rw-r--r--drivers/ide/ppc/pmac.c25
5 files changed, 123 insertions, 215 deletions
diff --git a/drivers/ide/ide-timing.h b/drivers/ide/ide-timing.h
index c0864b1e9228..e6cb8593b5ba 100644
--- a/drivers/ide/ide-timing.h
+++ b/drivers/ide/ide-timing.h
@@ -102,66 +102,16 @@ static struct ide_timing ide_timing[] = {
102#define EZ(v,unit) ((v)?ENOUGH(v,unit):0) 102#define EZ(v,unit) ((v)?ENOUGH(v,unit):0)
103 103
104#define XFER_MODE 0xf0 104#define XFER_MODE 0xf0
105#define XFER_UDMA_133 0x48
106#define XFER_UDMA_100 0x44
107#define XFER_UDMA_66 0x42
108#define XFER_UDMA 0x40
109#define XFER_MWDMA 0x20 105#define XFER_MWDMA 0x20
110#define XFER_SWDMA 0x10
111#define XFER_EPIO 0x01 106#define XFER_EPIO 0x01
112#define XFER_PIO 0x00 107#define XFER_PIO 0x00
113 108
114static short ide_find_best_mode(ide_drive_t *drive, int map) 109static short ide_find_best_pio_mode(ide_drive_t *drive)
115{ 110{
116 struct hd_driveid *id = drive->id; 111 struct hd_driveid *id = drive->id;
117 short best = 0; 112 short best = 0;
118 113
119 if (!id) 114 if (id->field_valid & 2) { /* EIDE PIO modes */
120 return XFER_PIO_SLOW;
121
122 if ((map & XFER_UDMA) && (id->field_valid & 4)) { /* Want UDMA and UDMA bitmap valid */
123
124 if ((map & XFER_UDMA_133) == XFER_UDMA_133)
125 if ((best = (id->dma_ultra & 0x0040) ? XFER_UDMA_6 : 0)) return best;
126
127 if ((map & XFER_UDMA_100) == XFER_UDMA_100)
128 if ((best = (id->dma_ultra & 0x0020) ? XFER_UDMA_5 : 0)) return best;
129
130 if ((map & XFER_UDMA_66) == XFER_UDMA_66)
131 if ((best = (id->dma_ultra & 0x0010) ? XFER_UDMA_4 :
132 (id->dma_ultra & 0x0008) ? XFER_UDMA_3 : 0)) return best;
133
134 if ((best = (id->dma_ultra & 0x0004) ? XFER_UDMA_2 :
135 (id->dma_ultra & 0x0002) ? XFER_UDMA_1 :
136 (id->dma_ultra & 0x0001) ? XFER_UDMA_0 : 0)) return best;
137 }
138
139 if ((map & XFER_MWDMA) && (id->field_valid & 2)) { /* Want MWDMA and drive has EIDE fields */
140
141 if ((best = (id->dma_mword & 0x0004) ? XFER_MW_DMA_2 :
142 (id->dma_mword & 0x0002) ? XFER_MW_DMA_1 :
143 (id->dma_mword & 0x0001) ? XFER_MW_DMA_0 : 0)) return best;
144 }
145
146 if (map & XFER_SWDMA) { /* Want SWDMA */
147
148 if (id->field_valid & 2) { /* EIDE SWDMA */
149
150 if ((best = (id->dma_1word & 0x0004) ? XFER_SW_DMA_2 :
151 (id->dma_1word & 0x0002) ? XFER_SW_DMA_1 :
152 (id->dma_1word & 0x0001) ? XFER_SW_DMA_0 : 0)) return best;
153 }
154
155 if (id->capability & 1) { /* Pre-EIDE style SWDMA */
156
157 if ((best = (id->tDMA == 2) ? XFER_SW_DMA_2 :
158 (id->tDMA == 1) ? XFER_SW_DMA_1 :
159 (id->tDMA == 0) ? XFER_SW_DMA_0 : 0)) return best;
160 }
161 }
162
163
164 if ((map & XFER_EPIO) && (id->field_valid & 2)) { /* EIDE PIO modes */
165 115
166 if ((best = (drive->id->eide_pio_modes & 4) ? XFER_PIO_5 : 116 if ((best = (drive->id->eide_pio_modes & 4) ? XFER_PIO_5 :
167 (drive->id->eide_pio_modes & 2) ? XFER_PIO_4 : 117 (drive->id->eide_pio_modes & 2) ? XFER_PIO_4 :
@@ -262,7 +212,7 @@ static int ide_timing_compute(ide_drive_t *drive, short speed, struct ide_timing
262 */ 212 */
263 213
264 if ((speed & XFER_MODE) != XFER_PIO) { 214 if ((speed & XFER_MODE) != XFER_PIO) {
265 ide_timing_compute(drive, ide_find_best_mode(drive, XFER_PIO | XFER_EPIO), &p, T, UT); 215 ide_timing_compute(drive, ide_find_best_pio_mode(drive), &p, T, UT);
266 ide_timing_merge(&p, t, t, IDE_TIMING_ALL); 216 ide_timing_merge(&p, t, t, IDE_TIMING_ALL);
267 } 217 }
268 218
diff --git a/drivers/ide/mips/au1xxx-ide.c b/drivers/ide/mips/au1xxx-ide.c
index 405903c42ba1..2e7013a2a7f6 100644
--- a/drivers/ide/mips/au1xxx-ide.c
+++ b/drivers/ide/mips/au1xxx-ide.c
@@ -381,9 +381,7 @@ static int auide_dma_setup(ide_drive_t *drive)
381 381
382static int auide_dma_check(ide_drive_t *drive) 382static int auide_dma_check(ide_drive_t *drive)
383{ 383{
384 u8 speed; 384 u8 speed = ide_max_dma_mode(drive);
385
386#ifdef CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA
387 385
388 if( dbdma_init_done == 0 ){ 386 if( dbdma_init_done == 0 ){
389 auide_hwif.white_list = ide_in_drive_list(drive->id, 387 auide_hwif.white_list = ide_in_drive_list(drive->id,
@@ -394,7 +392,6 @@ static int auide_dma_check(ide_drive_t *drive)
394 auide_ddma_init(&auide_hwif); 392 auide_ddma_init(&auide_hwif);
395 dbdma_init_done = 1; 393 dbdma_init_done = 1;
396 } 394 }
397#endif
398 395
399 /* Is the drive in our DMA black list? */ 396 /* Is the drive in our DMA black list? */
400 397
@@ -409,8 +406,6 @@ static int auide_dma_check(ide_drive_t *drive)
409 else 406 else
410 drive->using_dma = 1; 407 drive->using_dma = 1;
411 408
412 speed = ide_find_best_mode(drive, XFER_PIO | XFER_MWDMA);
413
414 if (drive->autodma && (speed & XFER_MODE) != XFER_PIO) 409 if (drive->autodma && (speed & XFER_MODE) != XFER_PIO)
415 return 0; 410 return 0;
416 411
diff --git a/drivers/ide/pci/amd74xx.c b/drivers/ide/pci/amd74xx.c
index a2be65fcf89c..a7443f15b27a 100644
--- a/drivers/ide/pci/amd74xx.c
+++ b/drivers/ide/pci/amd74xx.c
@@ -1,10 +1,11 @@
1/* 1/*
2 * Version 2.16 2 * Version 2.20
3 * 3 *
4 * AMD 755/756/766/8111 and nVidia nForce/2/2s/3/3s/CK804/MCP04 4 * AMD 755/756/766/8111 and nVidia nForce/2/2s/3/3s/CK804/MCP04
5 * IDE driver for Linux. 5 * IDE driver for Linux.
6 * 6 *
7 * Copyright (c) 2000-2002 Vojtech Pavlik 7 * Copyright (c) 2000-2002 Vojtech Pavlik
8 * Copyright (c) 2007 Bartlomiej Zolnierkiewicz
8 * 9 *
9 * Based on the work of: 10 * Based on the work of:
10 * Andre Hedrick 11 * Andre Hedrick
@@ -37,11 +38,6 @@
37#define AMD_ADDRESS_SETUP (0x0c + amd_config->base) 38#define AMD_ADDRESS_SETUP (0x0c + amd_config->base)
38#define AMD_UDMA_TIMING (0x10 + amd_config->base) 39#define AMD_UDMA_TIMING (0x10 + amd_config->base)
39 40
40#define AMD_UDMA 0x07
41#define AMD_UDMA_33 0x01
42#define AMD_UDMA_66 0x02
43#define AMD_UDMA_100 0x03
44#define AMD_UDMA_133 0x04
45#define AMD_CHECK_SWDMA 0x08 41#define AMD_CHECK_SWDMA 0x08
46#define AMD_BAD_SWDMA 0x10 42#define AMD_BAD_SWDMA 0x10
47#define AMD_BAD_FIFO 0x20 43#define AMD_BAD_FIFO 0x20
@@ -53,32 +49,33 @@
53 49
54static struct amd_ide_chip { 50static struct amd_ide_chip {
55 unsigned short id; 51 unsigned short id;
56 unsigned long base; 52 u8 base;
57 unsigned char flags; 53 u8 udma_mask;
54 u8 flags;
58} amd_ide_chips[] = { 55} amd_ide_chips[] = {
59 { PCI_DEVICE_ID_AMD_COBRA_7401, 0x40, AMD_UDMA_33 | AMD_BAD_SWDMA }, 56 { PCI_DEVICE_ID_AMD_COBRA_7401, 0x40, ATA_UDMA2, AMD_BAD_SWDMA },
60 { PCI_DEVICE_ID_AMD_VIPER_7409, 0x40, AMD_UDMA_66 | AMD_CHECK_SWDMA }, 57 { PCI_DEVICE_ID_AMD_VIPER_7409, 0x40, ATA_UDMA4, AMD_CHECK_SWDMA },
61 { PCI_DEVICE_ID_AMD_VIPER_7411, 0x40, AMD_UDMA_100 | AMD_BAD_FIFO }, 58 { PCI_DEVICE_ID_AMD_VIPER_7411, 0x40, ATA_UDMA5, AMD_BAD_FIFO },
62 { PCI_DEVICE_ID_AMD_OPUS_7441, 0x40, AMD_UDMA_100 }, 59 { PCI_DEVICE_ID_AMD_OPUS_7441, 0x40, ATA_UDMA5, },
63 { PCI_DEVICE_ID_AMD_8111_IDE, 0x40, AMD_UDMA_133 | AMD_CHECK_SERENADE }, 60 { PCI_DEVICE_ID_AMD_8111_IDE, 0x40, ATA_UDMA6, AMD_CHECK_SERENADE },
64 { PCI_DEVICE_ID_NVIDIA_NFORCE_IDE, 0x50, AMD_UDMA_100 }, 61 { PCI_DEVICE_ID_NVIDIA_NFORCE_IDE, 0x50, ATA_UDMA5, },
65 { PCI_DEVICE_ID_NVIDIA_NFORCE2_IDE, 0x50, AMD_UDMA_133 }, 62 { PCI_DEVICE_ID_NVIDIA_NFORCE2_IDE, 0x50, ATA_UDMA6, },
66 { PCI_DEVICE_ID_NVIDIA_NFORCE2S_IDE, 0x50, AMD_UDMA_133 }, 63 { PCI_DEVICE_ID_NVIDIA_NFORCE2S_IDE, 0x50, ATA_UDMA6, },
67 { PCI_DEVICE_ID_NVIDIA_NFORCE2S_SATA, 0x50, AMD_UDMA_133 }, 64 { PCI_DEVICE_ID_NVIDIA_NFORCE2S_SATA, 0x50, ATA_UDMA6, },
68 { PCI_DEVICE_ID_NVIDIA_NFORCE3_IDE, 0x50, AMD_UDMA_133 }, 65 { PCI_DEVICE_ID_NVIDIA_NFORCE3_IDE, 0x50, ATA_UDMA6, },
69 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_IDE, 0x50, AMD_UDMA_133 }, 66 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_IDE, 0x50, ATA_UDMA6, },
70 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA, 0x50, AMD_UDMA_133 }, 67 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA, 0x50, ATA_UDMA6, },
71 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA2, 0x50, AMD_UDMA_133 }, 68 { PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA2, 0x50, ATA_UDMA6, },
72 { PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_IDE, 0x50, AMD_UDMA_133 }, 69 { PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_IDE, 0x50, ATA_UDMA6, },
73 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_IDE, 0x50, AMD_UDMA_133 }, 70 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_IDE, 0x50, ATA_UDMA6, },
74 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_IDE, 0x50, AMD_UDMA_133 }, 71 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_IDE, 0x50, ATA_UDMA6, },
75 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_IDE, 0x50, AMD_UDMA_133 }, 72 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_IDE, 0x50, ATA_UDMA6, },
76 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_IDE, 0x50, AMD_UDMA_133 }, 73 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP61_IDE, 0x50, ATA_UDMA6, },
77 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP65_IDE, 0x50, AMD_UDMA_133 }, 74 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP65_IDE, 0x50, ATA_UDMA6, },
78 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_IDE, 0x50, AMD_UDMA_133 }, 75 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_IDE, 0x50, ATA_UDMA6, },
79 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE, 0x50, AMD_UDMA_133 }, 76 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE, 0x50, ATA_UDMA6, },
80 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE, 0x50, AMD_UDMA_133 }, 77 { PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE, 0x50, ATA_UDMA6, },
81 { PCI_DEVICE_ID_AMD_CS5536_IDE, 0x40, AMD_UDMA_100 }, 78 { PCI_DEVICE_ID_AMD_CS5536_IDE, 0x40, ATA_UDMA5, },
82 { 0 } 79 { 0 }
83}; 80};
84 81
@@ -87,7 +84,7 @@ static ide_pci_device_t *amd_chipset;
87static unsigned int amd_80w; 84static unsigned int amd_80w;
88static unsigned int amd_clock; 85static unsigned int amd_clock;
89 86
90static char *amd_dma[] = { "MWDMA16", "UDMA33", "UDMA66", "UDMA100", "UDMA133" }; 87static char *amd_dma[] = { "16", "25", "33", "44", "66", "100", "133" };
91static unsigned char amd_cyc2udma[] = { 6, 6, 5, 4, 0, 1, 1, 2, 2, 3, 3, 3, 3, 3, 3, 7 }; 88static unsigned char amd_cyc2udma[] = { 6, 6, 5, 4, 0, 1, 1, 2, 2, 3, 3, 3, 3, 3, 3, 7 };
92 89
93/* 90/*
@@ -128,7 +125,7 @@ static int amd74xx_get_info(char *buffer, char **addr, off_t offset, int count)
128 125
129 pci_read_config_byte(dev, PCI_REVISION_ID, &t); 126 pci_read_config_byte(dev, PCI_REVISION_ID, &t);
130 amd_print("Revision: IDE %#x", t); 127 amd_print("Revision: IDE %#x", t);
131 amd_print("Highest DMA rate: %s", amd_dma[amd_config->flags & AMD_UDMA]); 128 amd_print("Highest DMA rate: UDMA%s", amd_dma[fls(amd_config->udma_mask) - 1]);
132 129
133 amd_print("BM-DMA base: %#lx", amd_base); 130 amd_print("BM-DMA base: %#lx", amd_base);
134 amd_print("PCI clock: %d.%dMHz", amd_clock / 1000, amd_clock / 100 % 10); 131 amd_print("PCI clock: %d.%dMHz", amd_clock / 1000, amd_clock / 100 % 10);
@@ -221,12 +218,12 @@ static void amd_set_speed(struct pci_dev *dev, unsigned char dn, struct ide_timi
221 pci_write_config_byte(dev, AMD_DRIVE_TIMING + (3 - dn), 218 pci_write_config_byte(dev, AMD_DRIVE_TIMING + (3 - dn),
222 ((FIT(timing->active, 1, 16) - 1) << 4) | (FIT(timing->recover, 1, 16) - 1)); 219 ((FIT(timing->active, 1, 16) - 1) << 4) | (FIT(timing->recover, 1, 16) - 1));
223 220
224 switch (amd_config->flags & AMD_UDMA) { 221 switch (amd_config->udma_mask) {
225 case AMD_UDMA_33: t = timing->udma ? (0xc0 | (FIT(timing->udma, 2, 5) - 2)) : 0x03; break; 222 case ATA_UDMA2: t = timing->udma ? (0xc0 | (FIT(timing->udma, 2, 5) - 2)) : 0x03; break;
226 case AMD_UDMA_66: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 2, 10)]) : 0x03; break; 223 case ATA_UDMA4: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 2, 10)]) : 0x03; break;
227 case AMD_UDMA_100: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 1, 10)]) : 0x03; break; 224 case ATA_UDMA5: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 1, 10)]) : 0x03; break;
228 case AMD_UDMA_133: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 1, 15)]) : 0x03; break; 225 case ATA_UDMA6: t = timing->udma ? (0xc0 | amd_cyc2udma[FIT(timing->udma, 1, 15)]) : 0x03; break;
229 default: return; 226 default: return;
230 } 227 }
231 228
232 pci_write_config_byte(dev, AMD_UDMA_TIMING + (3 - dn), t); 229 pci_write_config_byte(dev, AMD_UDMA_TIMING + (3 - dn), t);
@@ -248,7 +245,7 @@ static int amd_set_drive(ide_drive_t *drive, u8 speed)
248 ide_config_drive_speed(drive, speed); 245 ide_config_drive_speed(drive, speed);
249 246
250 T = 1000000000 / amd_clock; 247 T = 1000000000 / amd_clock;
251 UT = T / min_t(int, max_t(int, amd_config->flags & AMD_UDMA, 1), 2); 248 UT = (amd_config->udma_mask == ATA_UDMA2) ? T : (T / 2);
252 249
253 ide_timing_compute(drive, speed, &t, T, UT); 250 ide_timing_compute(drive, speed, &t, T, UT);
254 251
@@ -277,29 +274,19 @@ static int amd_set_drive(ide_drive_t *drive, u8 speed)
277static void amd74xx_tune_drive(ide_drive_t *drive, u8 pio) 274static void amd74xx_tune_drive(ide_drive_t *drive, u8 pio)
278{ 275{
279 if (pio == 255) { 276 if (pio == 255) {
280 amd_set_drive(drive, ide_find_best_mode(drive, XFER_PIO | XFER_EPIO)); 277 amd_set_drive(drive, ide_find_best_pio_mode(drive));
281 return; 278 return;
282 } 279 }
283 280
284 amd_set_drive(drive, XFER_PIO_0 + min_t(byte, pio, 5)); 281 amd_set_drive(drive, XFER_PIO_0 + min_t(byte, pio, 5));
285} 282}
286 283
287/*
288 * amd74xx_dmaproc() is a callback from upper layers that can do
289 * a lot, but we use it for DMA/PIO tuning only, delegating everything
290 * else to the default ide_dmaproc().
291 */
292
293static int amd74xx_ide_dma_check(ide_drive_t *drive) 284static int amd74xx_ide_dma_check(ide_drive_t *drive)
294{ 285{
295 int w80 = HWIF(drive)->udma_four; 286 u8 speed = ide_max_dma_mode(drive);
296 287
297 u8 speed = ide_find_best_mode(drive, 288 if (speed == 0)
298 XFER_PIO | XFER_EPIO | XFER_MWDMA | XFER_UDMA | 289 speed = ide_find_best_pio_mode(drive);
299 ((amd_config->flags & AMD_BAD_SWDMA) ? 0 : XFER_SWDMA) |
300 (w80 && (amd_config->flags & AMD_UDMA) >= AMD_UDMA_66 ? XFER_UDMA_66 : 0) |
301 (w80 && (amd_config->flags & AMD_UDMA) >= AMD_UDMA_100 ? XFER_UDMA_100 : 0) |
302 (w80 && (amd_config->flags & AMD_UDMA) >= AMD_UDMA_133 ? XFER_UDMA_133 : 0));
303 290
304 amd_set_drive(drive, speed); 291 amd_set_drive(drive, speed);
305 292
@@ -334,10 +321,10 @@ static unsigned int __devinit init_chipset_amd74xx(struct pci_dev *dev, const ch
334 * Check 80-wire cable presence. 321 * Check 80-wire cable presence.
335 */ 322 */
336 323
337 switch (amd_config->flags & AMD_UDMA) { 324 switch (amd_config->udma_mask) {
338 325
339 case AMD_UDMA_133: 326 case ATA_UDMA6:
340 case AMD_UDMA_100: 327 case ATA_UDMA5:
341 pci_read_config_byte(dev, AMD_CABLE_DETECT, &t); 328 pci_read_config_byte(dev, AMD_CABLE_DETECT, &t);
342 pci_read_config_dword(dev, AMD_UDMA_TIMING, &u); 329 pci_read_config_dword(dev, AMD_UDMA_TIMING, &u);
343 amd_80w = ((t & 0x3) ? 1 : 0) | ((t & 0xc) ? 2 : 0); 330 amd_80w = ((t & 0x3) ? 1 : 0) | ((t & 0xc) ? 2 : 0);
@@ -349,7 +336,7 @@ static unsigned int __devinit init_chipset_amd74xx(struct pci_dev *dev, const ch
349 } 336 }
350 break; 337 break;
351 338
352 case AMD_UDMA_66: 339 case ATA_UDMA4:
353 /* no host side cable detection */ 340 /* no host side cable detection */
354 amd_80w = 0x03; 341 amd_80w = 0x03;
355 break; 342 break;
@@ -370,7 +357,7 @@ static unsigned int __devinit init_chipset_amd74xx(struct pci_dev *dev, const ch
370 if ((amd_config->flags & AMD_CHECK_SERENADE) && 357 if ((amd_config->flags & AMD_CHECK_SERENADE) &&
371 dev->subsystem_vendor == PCI_VENDOR_ID_AMD && 358 dev->subsystem_vendor == PCI_VENDOR_ID_AMD &&
372 dev->subsystem_device == PCI_DEVICE_ID_AMD_SERENADE) 359 dev->subsystem_device == PCI_DEVICE_ID_AMD_SERENADE)
373 amd_config->flags = AMD_UDMA_100; 360 amd_config->udma_mask = ATA_UDMA5;
374 361
375/* 362/*
376 * Determine the system bus clock. 363 * Determine the system bus clock.
@@ -395,8 +382,9 @@ static unsigned int __devinit init_chipset_amd74xx(struct pci_dev *dev, const ch
395 */ 382 */
396 383
397 pci_read_config_byte(dev, PCI_REVISION_ID, &t); 384 pci_read_config_byte(dev, PCI_REVISION_ID, &t);
398 printk(KERN_INFO "%s: %s (rev %02x) %s controller\n", 385 printk(KERN_INFO "%s: %s (rev %02x) UDMA%s controller\n",
399 amd_chipset->name, pci_name(dev), t, amd_dma[amd_config->flags & AMD_UDMA]); 386 amd_chipset->name, pci_name(dev), t,
387 amd_dma[fls(amd_config->udma_mask) - 1]);
400 388
401/* 389/*
402 * Register /proc/ide/amd74xx entry 390 * Register /proc/ide/amd74xx entry
@@ -437,9 +425,11 @@ static void __devinit init_hwif_amd74xx(ide_hwif_t *hwif)
437 return; 425 return;
438 426
439 hwif->atapi_dma = 1; 427 hwif->atapi_dma = 1;
440 hwif->ultra_mask = 0x7f; 428
441 hwif->mwdma_mask = 0x07; 429 hwif->ultra_mask = amd_config->udma_mask;
442 hwif->swdma_mask = 0x07; 430 hwif->mwdma_mask = 0x07;
431 if ((amd_config->flags & AMD_BAD_SWDMA) == 0)
432 hwif->swdma_mask = 0x07;
443 433
444 if (!hwif->udma_four) 434 if (!hwif->udma_four)
445 hwif->udma_four = (amd_80w >> hwif->channel) & 1; 435 hwif->udma_four = (amd_80w >> hwif->channel) & 1;
diff --git a/drivers/ide/pci/via82cxxx.c b/drivers/ide/pci/via82cxxx.c
index a508550c4095..49bd1c645fb2 100644
--- a/drivers/ide/pci/via82cxxx.c
+++ b/drivers/ide/pci/via82cxxx.c
@@ -1,6 +1,6 @@
1/* 1/*
2 * 2 *
3 * Version 3.38 3 * Version 3.40
4 * 4 *
5 * VIA IDE driver for Linux. Supported southbridges: 5 * VIA IDE driver for Linux. Supported southbridges:
6 * 6 *
@@ -9,6 +9,7 @@
9 * vt8235, vt8237, vt8237a 9 * vt8235, vt8237, vt8237a
10 * 10 *
11 * Copyright (c) 2000-2002 Vojtech Pavlik 11 * Copyright (c) 2000-2002 Vojtech Pavlik
12 * Copyright (c) 2007 Bartlomiej Zolnierkiewicz
12 * 13 *
13 * Based on the work of: 14 * Based on the work of:
14 * Michel Aubry 15 * Michel Aubry
@@ -41,8 +42,6 @@
41 42
42#include "ide-timing.h" 43#include "ide-timing.h"
43 44
44#define DISPLAY_VIA_TIMINGS
45
46#define VIA_IDE_ENABLE 0x40 45#define VIA_IDE_ENABLE 0x40
47#define VIA_IDE_CONFIG 0x41 46#define VIA_IDE_CONFIG 0x41
48#define VIA_FIFO_CONFIG 0x43 47#define VIA_FIFO_CONFIG 0x43
@@ -54,18 +53,12 @@
54#define VIA_ADDRESS_SETUP 0x4c 53#define VIA_ADDRESS_SETUP 0x4c
55#define VIA_UDMA_TIMING 0x50 54#define VIA_UDMA_TIMING 0x50
56 55
57#define VIA_UDMA 0x007 56#define VIA_BAD_PREQ 0x01 /* Crashes if PREQ# till DDACK# set */
58#define VIA_UDMA_NONE 0x000 57#define VIA_BAD_CLK66 0x02 /* 66 MHz clock doesn't work correctly */
59#define VIA_UDMA_33 0x001 58#define VIA_SET_FIFO 0x04 /* Needs to have FIFO split set */
60#define VIA_UDMA_66 0x002 59#define VIA_NO_UNMASK 0x08 /* Doesn't work with IRQ unmasking on */
61#define VIA_UDMA_100 0x003 60#define VIA_BAD_ID 0x10 /* Has wrong vendor ID (0x1107) */
62#define VIA_UDMA_133 0x004 61#define VIA_BAD_AST 0x20 /* Don't touch Address Setup Timing */
63#define VIA_BAD_PREQ 0x010 /* Crashes if PREQ# till DDACK# set */
64#define VIA_BAD_CLK66 0x020 /* 66 MHz clock doesn't work correctly */
65#define VIA_SET_FIFO 0x040 /* Needs to have FIFO split set */
66#define VIA_NO_UNMASK 0x080 /* Doesn't work with IRQ unmasking on */
67#define VIA_BAD_ID 0x100 /* Has wrong vendor ID (0x1107) */
68#define VIA_BAD_AST 0x200 /* Don't touch Address Setup Timing */
69 62
70/* 63/*
71 * VIA SouthBridge chips. 64 * VIA SouthBridge chips.
@@ -76,36 +69,37 @@ static struct via_isa_bridge {
76 u16 id; 69 u16 id;
77 u8 rev_min; 70 u8 rev_min;
78 u8 rev_max; 71 u8 rev_max;
79 u16 flags; 72 u8 udma_mask;
73 u8 flags;
80} via_isa_bridges[] = { 74} via_isa_bridges[] = {
81 { "cx700", PCI_DEVICE_ID_VIA_CX700, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 75 { "cx700", PCI_DEVICE_ID_VIA_CX700, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
82 { "vt8237s", PCI_DEVICE_ID_VIA_8237S, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 76 { "vt8237s", PCI_DEVICE_ID_VIA_8237S, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
83 { "vt6410", PCI_DEVICE_ID_VIA_6410, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 77 { "vt6410", PCI_DEVICE_ID_VIA_6410, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
84 { "vt8251", PCI_DEVICE_ID_VIA_8251, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 78 { "vt8251", PCI_DEVICE_ID_VIA_8251, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
85 { "vt8237", PCI_DEVICE_ID_VIA_8237, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 79 { "vt8237", PCI_DEVICE_ID_VIA_8237, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
86 { "vt8237a", PCI_DEVICE_ID_VIA_8237A, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 80 { "vt8237a", PCI_DEVICE_ID_VIA_8237A, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
87 { "vt8235", PCI_DEVICE_ID_VIA_8235, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 81 { "vt8235", PCI_DEVICE_ID_VIA_8235, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
88 { "vt8233a", PCI_DEVICE_ID_VIA_8233A, 0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST }, 82 { "vt8233a", PCI_DEVICE_ID_VIA_8233A, 0x00, 0x2f, ATA_UDMA6, VIA_BAD_AST },
89 { "vt8233c", PCI_DEVICE_ID_VIA_8233C_0, 0x00, 0x2f, VIA_UDMA_100 }, 83 { "vt8233c", PCI_DEVICE_ID_VIA_8233C_0, 0x00, 0x2f, ATA_UDMA5, },
90 { "vt8233", PCI_DEVICE_ID_VIA_8233_0, 0x00, 0x2f, VIA_UDMA_100 }, 84 { "vt8233", PCI_DEVICE_ID_VIA_8233_0, 0x00, 0x2f, ATA_UDMA5, },
91 { "vt8231", PCI_DEVICE_ID_VIA_8231, 0x00, 0x2f, VIA_UDMA_100 }, 85 { "vt8231", PCI_DEVICE_ID_VIA_8231, 0x00, 0x2f, ATA_UDMA5, },
92 { "vt82c686b", PCI_DEVICE_ID_VIA_82C686, 0x40, 0x4f, VIA_UDMA_100 }, 86 { "vt82c686b", PCI_DEVICE_ID_VIA_82C686, 0x40, 0x4f, ATA_UDMA5, },
93 { "vt82c686a", PCI_DEVICE_ID_VIA_82C686, 0x10, 0x2f, VIA_UDMA_66 }, 87 { "vt82c686a", PCI_DEVICE_ID_VIA_82C686, 0x10, 0x2f, ATA_UDMA4, },
94 { "vt82c686", PCI_DEVICE_ID_VIA_82C686, 0x00, 0x0f, VIA_UDMA_33 | VIA_BAD_CLK66 }, 88 { "vt82c686", PCI_DEVICE_ID_VIA_82C686, 0x00, 0x0f, ATA_UDMA2, VIA_BAD_CLK66 },
95 { "vt82c596b", PCI_DEVICE_ID_VIA_82C596, 0x10, 0x2f, VIA_UDMA_66 }, 89 { "vt82c596b", PCI_DEVICE_ID_VIA_82C596, 0x10, 0x2f, ATA_UDMA4, },
96 { "vt82c596a", PCI_DEVICE_ID_VIA_82C596, 0x00, 0x0f, VIA_UDMA_33 | VIA_BAD_CLK66 }, 90 { "vt82c596a", PCI_DEVICE_ID_VIA_82C596, 0x00, 0x0f, ATA_UDMA2, VIA_BAD_CLK66 },
97 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x47, 0x4f, VIA_UDMA_33 | VIA_SET_FIFO }, 91 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x47, 0x4f, ATA_UDMA2, VIA_SET_FIFO },
98 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x40, 0x46, VIA_UDMA_33 | VIA_SET_FIFO | VIA_BAD_PREQ }, 92 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x40, 0x46, ATA_UDMA2, VIA_SET_FIFO | VIA_BAD_PREQ },
99 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x30, 0x3f, VIA_UDMA_33 | VIA_SET_FIFO }, 93 { "vt82c586b", PCI_DEVICE_ID_VIA_82C586_0, 0x30, 0x3f, ATA_UDMA2, VIA_SET_FIFO },
100 { "vt82c586a", PCI_DEVICE_ID_VIA_82C586_0, 0x20, 0x2f, VIA_UDMA_33 | VIA_SET_FIFO }, 94 { "vt82c586a", PCI_DEVICE_ID_VIA_82C586_0, 0x20, 0x2f, ATA_UDMA2, VIA_SET_FIFO },
101 { "vt82c586", PCI_DEVICE_ID_VIA_82C586_0, 0x00, 0x0f, VIA_UDMA_NONE | VIA_SET_FIFO }, 95 { "vt82c586", PCI_DEVICE_ID_VIA_82C586_0, 0x00, 0x0f, 0x00, VIA_SET_FIFO },
102 { "vt82c576", PCI_DEVICE_ID_VIA_82C576, 0x00, 0x2f, VIA_UDMA_NONE | VIA_SET_FIFO | VIA_NO_UNMASK }, 96 { "vt82c576", PCI_DEVICE_ID_VIA_82C576, 0x00, 0x2f, 0x00, VIA_SET_FIFO | VIA_NO_UNMASK },
103 { "vt82c576", PCI_DEVICE_ID_VIA_82C576, 0x00, 0x2f, VIA_UDMA_NONE | VIA_SET_FIFO | VIA_NO_UNMASK | VIA_BAD_ID }, 97 { "vt82c576", PCI_DEVICE_ID_VIA_82C576, 0x00, 0x2f, 0x00, VIA_SET_FIFO | VIA_NO_UNMASK | VIA_BAD_ID },
104 { NULL } 98 { NULL }
105}; 99};
106 100
107static unsigned int via_clock; 101static unsigned int via_clock;
108static char *via_dma[] = { "MWDMA16", "UDMA33", "UDMA66", "UDMA100", "UDMA133" }; 102static char *via_dma[] = { "16", "25", "33", "44", "66", "100", "133" };
109 103
110struct via82cxxx_dev 104struct via82cxxx_dev
111{ 105{
@@ -140,12 +134,12 @@ static void via_set_speed(ide_hwif_t *hwif, u8 dn, struct ide_timing *timing)
140 pci_write_config_byte(dev, VIA_DRIVE_TIMING + (3 - dn), 134 pci_write_config_byte(dev, VIA_DRIVE_TIMING + (3 - dn),
141 ((FIT(timing->active, 1, 16) - 1) << 4) | (FIT(timing->recover, 1, 16) - 1)); 135 ((FIT(timing->active, 1, 16) - 1) << 4) | (FIT(timing->recover, 1, 16) - 1));
142 136
143 switch (vdev->via_config->flags & VIA_UDMA) { 137 switch (vdev->via_config->udma_mask) {
144 case VIA_UDMA_33: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 5) - 2)) : 0x03; break; 138 case ATA_UDMA2: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 5) - 2)) : 0x03; break;
145 case VIA_UDMA_66: t = timing->udma ? (0xe8 | (FIT(timing->udma, 2, 9) - 2)) : 0x0f; break; 139 case ATA_UDMA4: t = timing->udma ? (0xe8 | (FIT(timing->udma, 2, 9) - 2)) : 0x0f; break;
146 case VIA_UDMA_100: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 9) - 2)) : 0x07; break; 140 case ATA_UDMA5: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 9) - 2)) : 0x07; break;
147 case VIA_UDMA_133: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 9) - 2)) : 0x07; break; 141 case ATA_UDMA6: t = timing->udma ? (0xe0 | (FIT(timing->udma, 2, 9) - 2)) : 0x07; break;
148 default: return; 142 default: return;
149 } 143 }
150 144
151 pci_write_config_byte(dev, VIA_UDMA_TIMING + (3 - dn), t); 145 pci_write_config_byte(dev, VIA_UDMA_TIMING + (3 - dn), t);
@@ -173,12 +167,12 @@ static int via_set_drive(ide_drive_t *drive, u8 speed)
173 167
174 T = 1000000000 / via_clock; 168 T = 1000000000 / via_clock;
175 169
176 switch (vdev->via_config->flags & VIA_UDMA) { 170 switch (vdev->via_config->udma_mask) {
177 case VIA_UDMA_33: UT = T; break; 171 case ATA_UDMA2: UT = T; break;
178 case VIA_UDMA_66: UT = T/2; break; 172 case ATA_UDMA4: UT = T/2; break;
179 case VIA_UDMA_100: UT = T/3; break; 173 case ATA_UDMA5: UT = T/3; break;
180 case VIA_UDMA_133: UT = T/4; break; 174 case ATA_UDMA6: UT = T/4; break;
181 default: UT = T; 175 default: UT = T;
182 } 176 }
183 177
184 ide_timing_compute(drive, speed, &t, T, UT); 178 ide_timing_compute(drive, speed, &t, T, UT);
@@ -208,8 +202,7 @@ static int via_set_drive(ide_drive_t *drive, u8 speed)
208static void via82cxxx_tune_drive(ide_drive_t *drive, u8 pio) 202static void via82cxxx_tune_drive(ide_drive_t *drive, u8 pio)
209{ 203{
210 if (pio == 255) { 204 if (pio == 255) {
211 via_set_drive(drive, 205 via_set_drive(drive, ide_find_best_pio_mode(drive));
212 ide_find_best_mode(drive, XFER_PIO | XFER_EPIO));
213 return; 206 return;
214 } 207 }
215 208
@@ -226,16 +219,10 @@ static void via82cxxx_tune_drive(ide_drive_t *drive, u8 pio)
226 219
227static int via82cxxx_ide_dma_check (ide_drive_t *drive) 220static int via82cxxx_ide_dma_check (ide_drive_t *drive)
228{ 221{
229 ide_hwif_t *hwif = HWIF(drive); 222 u8 speed = ide_max_dma_mode(drive);
230 struct via82cxxx_dev *vdev = pci_get_drvdata(hwif->pci_dev);
231 u16 w80 = hwif->udma_four;
232 223
233 u16 speed = ide_find_best_mode(drive, 224 if (speed == 0)
234 XFER_PIO | XFER_EPIO | XFER_SWDMA | XFER_MWDMA | 225 speed = ide_find_best_pio_mode(drive);
235 (vdev->via_config->flags & VIA_UDMA ? XFER_UDMA : 0) |
236 (w80 && (vdev->via_config->flags & VIA_UDMA) >= VIA_UDMA_66 ? XFER_UDMA_66 : 0) |
237 (w80 && (vdev->via_config->flags & VIA_UDMA) >= VIA_UDMA_100 ? XFER_UDMA_100 : 0) |
238 (w80 && (vdev->via_config->flags & VIA_UDMA) >= VIA_UDMA_133 ? XFER_UDMA_133 : 0));
239 226
240 via_set_drive(drive, speed); 227 via_set_drive(drive, speed);
241 228
@@ -272,8 +259,8 @@ static void __devinit via_cable_detect(struct via82cxxx_dev *vdev, u32 u)
272{ 259{
273 int i; 260 int i;
274 261
275 switch (vdev->via_config->flags & VIA_UDMA) { 262 switch (vdev->via_config->udma_mask) {
276 case VIA_UDMA_66: 263 case ATA_UDMA4:
277 for (i = 24; i >= 0; i -= 8) 264 for (i = 24; i >= 0; i -= 8)
278 if (((u >> (i & 16)) & 8) && 265 if (((u >> (i & 16)) & 8) &&
279 ((u >> i) & 0x20) && 266 ((u >> i) & 0x20) &&
@@ -286,7 +273,7 @@ static void __devinit via_cable_detect(struct via82cxxx_dev *vdev, u32 u)
286 } 273 }
287 break; 274 break;
288 275
289 case VIA_UDMA_100: 276 case ATA_UDMA5:
290 for (i = 24; i >= 0; i -= 8) 277 for (i = 24; i >= 0; i -= 8)
291 if (((u >> i) & 0x10) || 278 if (((u >> i) & 0x10) ||
292 (((u >> i) & 0x20) && 279 (((u >> i) & 0x20) &&
@@ -298,7 +285,7 @@ static void __devinit via_cable_detect(struct via82cxxx_dev *vdev, u32 u)
298 } 285 }
299 break; 286 break;
300 287
301 case VIA_UDMA_133: 288 case ATA_UDMA6:
302 for (i = 24; i >= 0; i -= 8) 289 for (i = 24; i >= 0; i -= 8)
303 if (((u >> i) & 0x10) || 290 if (((u >> i) & 0x10) ||
304 (((u >> i) & 0x20) && 291 (((u >> i) & 0x20) &&
@@ -353,7 +340,7 @@ static unsigned int __devinit init_chipset_via82cxxx(struct pci_dev *dev, const
353 340
354 via_cable_detect(vdev, u); 341 via_cable_detect(vdev, u);
355 342
356 if ((via_config->flags & VIA_UDMA) == VIA_UDMA_66) { 343 if (via_config->udma_mask == ATA_UDMA4) {
357 /* Enable Clk66 */ 344 /* Enable Clk66 */
358 pci_write_config_dword(dev, VIA_UDMA_TIMING, u|0x80008); 345 pci_write_config_dword(dev, VIA_UDMA_TIMING, u|0x80008);
359 } else if (via_config->flags & VIA_BAD_CLK66) { 346 } else if (via_config->flags & VIA_BAD_CLK66) {
@@ -416,10 +403,12 @@ static unsigned int __devinit init_chipset_via82cxxx(struct pci_dev *dev, const
416 */ 403 */
417 404
418 pci_read_config_byte(isa, PCI_REVISION_ID, &t); 405 pci_read_config_byte(isa, PCI_REVISION_ID, &t);
419 printk(KERN_INFO "VP_IDE: VIA %s (rev %02x) IDE %s " 406 printk(KERN_INFO "VP_IDE: VIA %s (rev %02x) IDE %sDMA%s "
420 "controller on pci%s\n", 407 "controller on pci%s\n",
421 via_config->name, t, 408 via_config->name, t,
422 via_dma[via_config->flags & VIA_UDMA], 409 via_config->udma_mask ? "U" : "MW",
410 via_dma[via_config->udma_mask ?
411 (fls(via_config->udma_mask) - 1) : 0],
423 pci_name(dev)); 412 pci_name(dev));
424 413
425 pci_dev_put(isa); 414 pci_dev_put(isa);
@@ -454,7 +443,8 @@ static void __devinit init_hwif_via82cxxx(ide_hwif_t *hwif)
454 return; 443 return;
455 444
456 hwif->atapi_dma = 1; 445 hwif->atapi_dma = 1;
457 hwif->ultra_mask = 0x7f; 446
447 hwif->ultra_mask = vdev->via_config->udma_mask;
458 hwif->mwdma_mask = 0x07; 448 hwif->mwdma_mask = 0x07;
459 hwif->swdma_mask = 0x07; 449 hwif->swdma_mask = 0x07;
460 450
diff --git a/drivers/ide/ppc/pmac.c b/drivers/ide/ppc/pmac.c
index f9bada093d19..5e3077409457 100644
--- a/drivers/ide/ppc/pmac.c
+++ b/drivers/ide/ppc/pmac.c
@@ -1821,28 +1821,11 @@ pmac_ide_dma_check(ide_drive_t *drive)
1821 enable = 0; 1821 enable = 0;
1822 1822
1823 if (enable) { 1823 if (enable) {
1824 short mode; 1824 u8 mode = ide_max_dma_mode(drive);
1825 1825
1826 map = XFER_MWDMA; 1826 if (mode >= XFER_UDMA_0)
1827 if (pmif->kind == controller_kl_ata4
1828 || pmif->kind == controller_un_ata6
1829 || pmif->kind == controller_k2_ata6
1830 || pmif->kind == controller_sh_ata6) {
1831 map |= XFER_UDMA;
1832 if (pmif->cable_80) {
1833 map |= XFER_UDMA_66;
1834 if (pmif->kind == controller_un_ata6 ||
1835 pmif->kind == controller_k2_ata6 ||
1836 pmif->kind == controller_sh_ata6)
1837 map |= XFER_UDMA_100;
1838 if (pmif->kind == controller_sh_ata6)
1839 map |= XFER_UDMA_133;
1840 }
1841 }
1842 mode = ide_find_best_mode(drive, map);
1843 if (mode & XFER_UDMA)
1844 drive->using_dma = pmac_ide_udma_enable(drive, mode); 1827 drive->using_dma = pmac_ide_udma_enable(drive, mode);
1845 else if (mode & XFER_MWDMA) 1828 else if (mode >= XFER_MW_DMA_0)
1846 drive->using_dma = pmac_ide_mdma_enable(drive, mode); 1829 drive->using_dma = pmac_ide_mdma_enable(drive, mode);
1847 hwif->OUTB(0, IDE_CONTROL_REG); 1830 hwif->OUTB(0, IDE_CONTROL_REG);
1848 /* Apply settings to controller */ 1831 /* Apply settings to controller */
88' href='#n988'>988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585







                                                 

                                                        














                                                                      

                         
                     
                        
                           
                              
















                              
                        
                          
                          
 

























                                                                                            





                                                                        
                                                                        




                                                                            
                                                          




                                                                     
          
                                                                    
           
                                                                       
                                                             















































































                                                                         
                                               
                                                        
                                                          


                                                                    

                                                
                                                                        










                                                                       
                                 


































































































































                                                                                                           



                                                                         




























                                                                                                          
                                         










                                                                
                                                                           

                                                  


























                                                                                 


                                                                      
   

                                                                       
 
                                        




                                            






                                                          




                                                  

                                          


                     

                                                                      








                                                         

                                                                    






























                                                            
                                                                               
















                                                       
                       

                               
                                  

                                                       
                                                                




                                      

                                         
                                              
                                       
                                  
                               
                







                                                                               
                                         


                               
                                  
                                                              










                                                       
                                                                               
         




                                                                    
                                                

                           












                                                                              
                                       


















                                                                           
                                                                         






                                                                
























                                                                          

                                                         
                                                   






                                                                


                                                                       




                                                    
                                        
                                     











                                                                               



                                                              
                                                                        


                                                            
                                                   
                                                       

                                                                      
                                                         

                                                                      
                 
                           










                                                                               




                                                                               
                   
                                                                         


                                                                        


















                                                           




                                                               





                                                                         
                                                                     































                                                                               



                                                                 










                                                             
                                                          








                                                              

                                 
































































                                                                                                 
                                                     






































































                                                                            














                                                                               









































                                                                         
                                                                         


                  
                                                                                      








                                                            
                                                                             
                                 






















                                                           


                                                                     
                              
                                                                   








                                              















                                                                            

                                                                      


















                                                                         
                                                          








                                                                       
                                             



                                  

                                                                         



                 







                                                                               
                                                                            
 
                               























                                                                          

                 
                          
 



                                                                 
                                                                    

                                                                     
























                                                        
                                                        
                                                                
                                                             
                                                        
                         
                                                 








































































                                                                             
                                                              

















                                                                               
                                         




















































                                                                              
                                         




                                            
                                  
                                     

                                              










                                             
                                                                        
 
                                                                   
                  
                
 

                                                                           
 


                                                                              
 
                                      
                                     

 
                  
                                                                              
 
                                                               


                                                                     

                                                                     
 
                                                               








                                                                     
                                                           


















                                                         
                                                                    


                                    
                                          









                                                            
                                 













                                                        



                                                                                
                                                    






                                                              
                                                                      




                                                              

                                                                               

                              
                                         









                                                                               

                                                                            

                              
                                        







                                                

                                                                     

  
                                                                         

                                                                               
   







                                                                              
          


                                                                   
 



















                                                                   




                                                                                       
                                                              









                                                
                                    







                                                          
                                               










































































                                                                            
                                      




                                                                                                            
                                                           




























                                                                                 
                                                                         


























                                                                                
                        
                                            

                                             
















































                                                                                               
                                                                   
 
                                                              



                                       

                                      

                                                                   

                                 

                                                   

                                                          
                                        












                                                                          






                                                                            




                                                   
                 








                                                                        









                                                                          
                       





















                                                                                          
                                 










                                                                    
                         











                                                                                
                                         







                                                                    
                          








                                                                                   

                                    



















                                                                                                                           
                                            
                                   
                                    
                                   


























                                                                                       









                                                                    



























                                                                        
                                                                                  

                                                          
                    

 
                                                                           



                                                                           
                    

 
                                                                                     

                                       
                                           


                                         


         
                                                                        

                                                   

  
                                                                       



                                            

  































                                                                              
                                                            













                                                       












                                                                

                                                                
 
                            





                                          
 

                                                                 
                    
                                             


                            
                      































                                                                                
                                                          
                                           
                                          
                                             

  


                                                                    


                                       
















                                                                       
















































                                                                      
                                                       
                                                                        
                                             

















                                                                           

                                                      

                                                       



                             

                                                                     
                             
 






















                                                                        

                                            


                                        








                                                   








                                                   
                                     

                                 
                                  
                                                             
 
                   









                                                                     

                                                                         

                                       
                                            



                                 










                                                                

                                            

                               




                                                
                            



                                           
 

















                                                       
                                             



                                                              
                                                                                        










                                                                          
                                       


                                                            
                                                           


                                                                     
                                       
                             

                                
      





                                                                   
                                                          




                                    
                                               

 
                                                           
                                          
                                                        
                   
                                         

                                            
      
                                       

  
                                                             





                                              

                                                    


      
                                                               

                                              
                                               







                                              

  
                                                                   









                                        
      









                                              
                                                                       







                                              

  
                                                  











                                                   
                                      






                                           

                                                                          
 
                                                                         













                                                



                                                  








                                                              
 
                                                           












                                                                

                                             



















































                                                                           

                                                                  






























                                                                 
/*
 * Resizable virtual memory filesystem for Linux.
 *
 * Copyright (C) 2000 Linus Torvalds.
 *		 2000 Transmeta Corp.
 *		 2000-2001 Christoph Rohland
 *		 2000-2001 SAP AG
 *		 2002 Red Hat Inc.
 * Copyright (C) 2002-2005 Hugh Dickins.
 * Copyright (C) 2002-2005 VERITAS Software Corporation.
 * Copyright (C) 2004 Andi Kleen, SuSE Labs
 *
 * Extended attribute support for tmpfs:
 * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
 * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 *
 * This file is released under the GPL.
 */

/*
 * This virtual memory filesystem is heavily based on the ramfs. It
 * extends ramfs by the ability to use swap and honor resource limits
 * which makes it a completely usable filesystem.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/generic_acl.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>

#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>

/* This magic number is used in glibc for posix shared memory */
#define TMPFS_MAGIC	0x01021994

#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)

#define SHMEM_MAX_INDEX  (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
#define SHMEM_MAX_BYTES  ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)

#define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)

/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
#define SHMEM_PAGEIN	 VM_READ
#define SHMEM_TRUNCATE	 VM_WRITE

/* Definition to limit shmem_truncate's steps between cond_rescheds */
#define LATENCY_LIMIT	 64

/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20

/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
enum sgp_type {
	SGP_QUICK,	/* don't try more than file page cache lookup */
	SGP_READ,	/* don't exceed i_size, don't allocate page */
	SGP_CACHE,	/* don't exceed i_size, may allocate page */
	SGP_WRITE,	/* may exceed i_size, may allocate page */
	SGP_FAULT,	/* same as SGP_CACHE, return with page locked */
};

static int shmem_getpage(struct inode *inode, unsigned long idx,
			 struct page **pagep, enum sgp_type sgp, int *type);

static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
{
	/*
	 * The above definition of ENTRIES_PER_PAGE, and the use of
	 * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
	 * might be reconsidered if it ever diverges from PAGE_SIZE.
	 *
	 * Mobility flags are masked out as swap vectors cannot move
	 */
	return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO,
				PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static inline void shmem_dir_free(struct page *page)
{
	__free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static struct page **shmem_dir_map(struct page *page)
{
	return (struct page **)kmap_atomic(page, KM_USER0);
}

static inline void shmem_dir_unmap(struct page **dir)
{
	kunmap_atomic(dir, KM_USER0);
}

static swp_entry_t *shmem_swp_map(struct page *page)
{
	return (swp_entry_t *)kmap_atomic(page, KM_USER1);
}

static inline void shmem_swp_balance_unmap(void)
{
	/*
	 * When passing a pointer to an i_direct entry, to code which
	 * also handles indirect entries and so will shmem_swp_unmap,
	 * we must arrange for the preempt count to remain in balance.
	 * What kmap_atomic of a lowmem page does depends on config
	 * and architecture, so pretend to kmap_atomic some lowmem page.
	 */
	(void) kmap_atomic(ZERO_PAGE(0), KM_USER1);
}

static inline void shmem_swp_unmap(swp_entry_t *entry)
{
	kunmap_atomic(entry, KM_USER1);
}

static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

/*
 * shmem_file_setup pre-accounts the whole fixed size of a VM object,
 * for shared memory and for shared anonymous (/dev/zero) mappings
 * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
 * consistent with the pre-accounting of private mappings ...
 */
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
	return (flags & VM_ACCOUNT)?
		security_vm_enough_memory(VM_ACCT(size)): 0;
}

static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
	if (flags & VM_ACCOUNT)
		vm_unacct_memory(VM_ACCT(size));
}

/*
 * ... whereas tmpfs objects are accounted incrementally as
 * pages are allocated, in order to allow huge sparse files.
 * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
 * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
 */
static inline int shmem_acct_block(unsigned long flags)
{
	return (flags & VM_ACCOUNT)?
		0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE));
}

static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
	if (!(flags & VM_ACCOUNT))
		vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}

static const struct super_operations shmem_ops;
static const struct address_space_operations shmem_aops;
static const struct file_operations shmem_file_operations;
static const struct inode_operations shmem_inode_operations;
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static struct vm_operations_struct shmem_vm_ops;

static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
	.ra_pages	= 0,	/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
	.unplug_io_fn	= default_unplug_io_fn,
};

static LIST_HEAD(shmem_swaplist);
static DEFINE_SPINLOCK(shmem_swaplist_lock);

static void shmem_free_blocks(struct inode *inode, long pages)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	if (sbinfo->max_blocks) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_blocks += pages;
		inode->i_blocks -= pages*BLOCKS_PER_PAGE;
		spin_unlock(&sbinfo->stat_lock);
	}
}

/*
 * shmem_recalc_inode - recalculate the size of an inode
 *
 * @inode: inode to recalc
 *
 * We have to calculate the free blocks since the mm can drop
 * undirtied hole pages behind our back.
 *
 * But normally   info->alloced == inode->i_mapping->nrpages + info->swapped
 * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
 *
 * It has to be called with the spinlock held.
 */
static void shmem_recalc_inode(struct inode *inode)
{
	struct shmem_inode_info *info = SHMEM_I(inode);
	long freed;

	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
	if (freed > 0) {
		info->alloced -= freed;
		shmem_unacct_blocks(info->flags, freed);
		shmem_free_blocks(inode, freed);
	}
}

/*
 * shmem_swp_entry - find the swap vector position in the info structure
 *
 * @info:  info structure for the inode
 * @index: index of the page to find
 * @page:  optional page to add to the structure. Has to be preset to
 *         all zeros
 *
 * If there is no space allocated yet it will return NULL when
 * page is NULL, else it will use the page for the needed block,
 * setting it to NULL on return to indicate that it has been used.
 *
 * The swap vector is organized the following way:
 *
 * There are SHMEM_NR_DIRECT entries directly stored in the
 * shmem_inode_info structure. So small files do not need an addional
 * allocation.
 *
 * For pages with index > SHMEM_NR_DIRECT there is the pointer
 * i_indirect which points to a page which holds in the first half
 * doubly indirect blocks, in the second half triple indirect blocks:
 *
 * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the
 * following layout (for SHMEM_NR_DIRECT == 16):
 *
 * i_indirect -> dir --> 16-19
 * 	      |	     +-> 20-23
 * 	      |
 * 	      +-->dir2 --> 24-27
 * 	      |	       +-> 28-31
 * 	      |	       +-> 32-35
 * 	      |	       +-> 36-39
 * 	      |
 * 	      +-->dir3 --> 40-43
 * 	       	       +-> 44-47
 * 	      	       +-> 48-51
 * 	      	       +-> 52-55
 */
static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page)
{
	unsigned long offset;
	struct page **dir;
	struct page *subdir;

	if (index < SHMEM_NR_DIRECT) {
		shmem_swp_balance_unmap();
		return info->i_direct+index;
	}
	if (!info->i_indirect) {
		if (page) {
			info->i_indirect = *page;
			*page = NULL;
		}
		return NULL;			/* need another page */
	}

	index -= SHMEM_NR_DIRECT;
	offset = index % ENTRIES_PER_PAGE;
	index /= ENTRIES_PER_PAGE;
	dir = shmem_dir_map(info->i_indirect);

	if (index >= ENTRIES_PER_PAGE/2) {
		index -= ENTRIES_PER_PAGE/2;
		dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE;
		index %= ENTRIES_PER_PAGE;
		subdir = *dir;
		if (!subdir) {
			if (page) {
				*dir = *page;
				*page = NULL;
			}
			shmem_dir_unmap(dir);
			return NULL;		/* need another page */
		}
		shmem_dir_unmap(dir);
		dir = shmem_dir_map(subdir);
	}

	dir += index;
	subdir = *dir;
	if (!subdir) {
		if (!page || !(subdir = *page)) {
			shmem_dir_unmap(dir);
			return NULL;		/* need a page */
		}
		*dir = subdir;
		*page = NULL;
	}
	shmem_dir_unmap(dir);
	return shmem_swp_map(subdir) + offset;
}

static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value)
{
	long incdec = value? 1: -1;

	entry->val = value;
	info->swapped += incdec;
	if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) {
		struct page *page = kmap_atomic_to_page(entry);
		set_page_private(page, page_private(page) + incdec);
	}
}

/*
 * shmem_swp_alloc - get the position of the swap entry for the page.
 *                   If it does not exist allocate the entry.
 *
 * @info:	info structure for the inode
 * @index:	index of the page to find
 * @sgp:	check and recheck i_size? skip allocation?
 */
static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
{
	struct inode *inode = &info->vfs_inode;
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	struct page *page = NULL;
	swp_entry_t *entry;

	if (sgp != SGP_WRITE &&
	    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
		return ERR_PTR(-EINVAL);

	while (!(entry = shmem_swp_entry(info, index, &page))) {
		if (sgp == SGP_READ)
			return shmem_swp_map(ZERO_PAGE(0));
		/*
		 * Test free_blocks against 1 not 0, since we have 1 data
		 * page (and perhaps indirect index pages) yet to allocate:
		 * a waste to allocate index if we cannot allocate data.
		 */
		if (sbinfo->max_blocks) {
			spin_lock(&sbinfo->stat_lock);
			if (sbinfo->free_blocks <= 1) {
				spin_unlock(&sbinfo->stat_lock);
				return ERR_PTR(-ENOSPC);
			}
			sbinfo->free_blocks--;
			inode->i_blocks += BLOCKS_PER_PAGE;
			spin_unlock(&sbinfo->stat_lock);
		}

		spin_unlock(&info->lock);
		page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
		if (page)
			set_page_private(page, 0);
		spin_lock(&info->lock);

		if (!page) {
			shmem_free_blocks(inode, 1);
			return ERR_PTR(-ENOMEM);
		}
		if (sgp != SGP_WRITE &&
		    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
			entry = ERR_PTR(-EINVAL);
			break;
		}
		if (info->next_index <= index)
			info->next_index = index + 1;
	}
	if (page) {
		/* another task gave its page, or truncated the file */
		shmem_free_blocks(inode, 1);
		shmem_dir_free(page);
	}
	if (info->next_index <= index && !IS_ERR(entry))
		info->next_index = index + 1;
	return entry;
}

/*
 * shmem_free_swp - free some swap entries in a directory
 *
 * @dir:        pointer to the directory
 * @edir:       pointer after last entry of the directory
 * @punch_lock: pointer to spinlock when needed for the holepunch case
 */
static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir,
						spinlock_t *punch_lock)
{
	spinlock_t *punch_unlock = NULL;
	swp_entry_t *ptr;
	int freed = 0;

	for (ptr = dir; ptr < edir; ptr++) {
		if (ptr->val) {
			if (unlikely(punch_lock)) {
				punch_unlock = punch_lock;
				punch_lock = NULL;
				spin_lock(punch_unlock);
				if (!ptr->val)
					continue;
			}
			free_swap_and_cache(*ptr);
			*ptr = (swp_entry_t){0};
			freed++;
		}
	}
	if (punch_unlock)
		spin_unlock(punch_unlock);
	return freed;
}

static int shmem_map_and_free_swp(struct page *subdir, int offset,
		int limit, struct page ***dir, spinlock_t *punch_lock)
{
	swp_entry_t *ptr;
	int freed = 0;

	ptr = shmem_swp_map(subdir);
	for (; offset < limit; offset += LATENCY_LIMIT) {
		int size = limit - offset;
		if (size > LATENCY_LIMIT)
			size = LATENCY_LIMIT;
		freed += shmem_free_swp(ptr+offset, ptr+offset+size,
							punch_lock);
		if (need_resched()) {
			shmem_swp_unmap(ptr);
			if (*dir) {
				shmem_dir_unmap(*dir);
				*dir = NULL;
			}
			cond_resched();
			ptr = shmem_swp_map(subdir);
		}
	}
	shmem_swp_unmap(ptr);
	return freed;
}

static void shmem_free_pages(struct list_head *next)
{
	struct page *page;
	int freed = 0;

	do {
		page = container_of(next, struct page, lru);
		next = next->next;
		shmem_dir_free(page);
		freed++;
		if (freed >= LATENCY_LIMIT) {
			cond_resched();
			freed = 0;
		}
	} while (next);
}

static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
{
	struct shmem_inode_info *info = SHMEM_I(inode);
	unsigned long idx;
	unsigned long size;
	unsigned long limit;
	unsigned long stage;
	unsigned long diroff;
	struct page **dir;
	struct page *topdir;
	struct page *middir;
	struct page *subdir;
	swp_entry_t *ptr;
	LIST_HEAD(pages_to_free);
	long nr_pages_to_free = 0;
	long nr_swaps_freed = 0;
	int offset;
	int freed;
	int punch_hole;
	spinlock_t *needs_lock;
	spinlock_t *punch_lock;
	unsigned long upper_limit;

	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	if (idx >= info->next_index)
		return;

	spin_lock(&info->lock);
	info->flags |= SHMEM_TRUNCATE;
	if (likely(end == (loff_t) -1)) {
		limit = info->next_index;
		upper_limit = SHMEM_MAX_INDEX;
		info->next_index = idx;
		needs_lock = NULL;
		punch_hole = 0;
	} else {
		if (end + 1 >= inode->i_size) {	/* we may free a little more */
			limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >>
							PAGE_CACHE_SHIFT;
			upper_limit = SHMEM_MAX_INDEX;
		} else {
			limit = (end + 1) >> PAGE_CACHE_SHIFT;
			upper_limit = limit;
		}
		needs_lock = &info->lock;
		punch_hole = 1;
	}

	topdir = info->i_indirect;
	if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) {
		info->i_indirect = NULL;
		nr_pages_to_free++;
		list_add(&topdir->lru, &pages_to_free);
	}
	spin_unlock(&info->lock);

	if (info->swapped && idx < SHMEM_NR_DIRECT) {
		ptr = info->i_direct;
		size = limit;
		if (size > SHMEM_NR_DIRECT)
			size = SHMEM_NR_DIRECT;
		nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock);
	}

	/*
	 * If there are no indirect blocks or we are punching a hole
	 * below indirect blocks, nothing to be done.
	 */
	if (!topdir || limit <= SHMEM_NR_DIRECT)
		goto done2;

	/*
	 * The truncation case has already dropped info->lock, and we're safe
	 * because i_size and next_index have already been lowered, preventing
	 * access beyond.  But in the punch_hole case, we still need to take
	 * the lock when updating the swap directory, because there might be
	 * racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or
	 * shmem_writepage.  However, whenever we find we can remove a whole
	 * directory page (not at the misaligned start or end of the range),
	 * we first NULLify its pointer in the level above, and then have no
	 * need to take the lock when updating its contents: needs_lock and
	 * punch_lock (either pointing to info->lock or NULL) manage this.
	 */

	upper_limit -= SHMEM_NR_DIRECT;
	limit -= SHMEM_NR_DIRECT;
	idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0;
	offset = idx % ENTRIES_PER_PAGE;
	idx -= offset;

	dir = shmem_dir_map(topdir);
	stage = ENTRIES_PER_PAGEPAGE/2;
	if (idx < ENTRIES_PER_PAGEPAGE/2) {
		middir = topdir;
		diroff = idx/ENTRIES_PER_PAGE;
	} else {
		dir += ENTRIES_PER_PAGE/2;
		dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE;
		while (stage <= idx)
			stage += ENTRIES_PER_PAGEPAGE;
		middir = *dir;
		if (*dir) {
			diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
				ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
			if (!diroff && !offset && upper_limit >= stage) {
				if (needs_lock) {
					spin_lock(needs_lock);
					*dir = NULL;
					spin_unlock(needs_lock);
					needs_lock = NULL;
				} else
					*dir = NULL;
				nr_pages_to_free++;
				list_add(&middir->lru, &pages_to_free);
			}
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(middir);
		} else {
			diroff = 0;
			offset = 0;
			idx = stage;
		}
	}

	for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) {
		if (unlikely(idx == stage)) {
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(topdir) +
			    ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
			while (!*dir) {
				dir++;
				idx += ENTRIES_PER_PAGEPAGE;
				if (idx >= limit)
					goto done1;
			}
			stage = idx + ENTRIES_PER_PAGEPAGE;
			middir = *dir;
			if (punch_hole)
				needs_lock = &info->lock;
			if (upper_limit >= stage) {
				if (needs_lock) {
					spin_lock(needs_lock);
					*dir = NULL;
					spin_unlock(needs_lock);
					needs_lock = NULL;
				} else
					*dir = NULL;
				nr_pages_to_free++;
				list_add(&middir->lru, &pages_to_free);
			}
			shmem_dir_unmap(dir);
			cond_resched();
			dir = shmem_dir_map(middir);
			diroff = 0;
		}
		punch_lock = needs_lock;
		subdir = dir[diroff];
		if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) {
			if (needs_lock) {
				spin_lock(needs_lock);
				dir[diroff] = NULL;
				spin_unlock(needs_lock);
				punch_lock = NULL;
			} else
				dir[diroff] = NULL;
			nr_pages_to_free++;
			list_add(&subdir->lru, &pages_to_free);
		}
		if (subdir && page_private(subdir) /* has swap entries */) {
			size = limit - idx;
			if (size > ENTRIES_PER_PAGE)
				size = ENTRIES_PER_PAGE;
			freed = shmem_map_and_free_swp(subdir,
					offset, size, &dir, punch_lock);
			if (!dir)
				dir = shmem_dir_map(middir);
			nr_swaps_freed += freed;
			if (offset || punch_lock) {
				spin_lock(&info->lock);
				set_page_private(subdir,
					page_private(subdir) - freed);
				spin_unlock(&info->lock);
			} else
				BUG_ON(page_private(subdir) != freed);
		}
		offset = 0;
	}
done1:
	shmem_dir_unmap(dir);
done2:
	if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
		/*
		 * Call truncate_inode_pages again: racing shmem_unuse_inode
		 * may have swizzled a page in from swap since vmtruncate or
		 * generic_delete_inode did it, before we lowered next_index.
		 * Also, though shmem_getpage checks i_size before adding to
		 * cache, no recheck after: so fix the narrow window there too.
		 *
		 * Recalling truncate_inode_pages_range and unmap_mapping_range
		 * every time for punch_hole (which never got a chance to clear
		 * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
		 * yet hardly ever necessary: try to optimize them out later.
		 */
		truncate_inode_pages_range(inode->i_mapping, start, end);
		if (punch_hole)
			unmap_mapping_range(inode->i_mapping, start,
							end - start, 1);
	}

	spin_lock(&info->lock);
	info->flags &= ~SHMEM_TRUNCATE;
	info->swapped -= nr_swaps_freed;
	if (nr_pages_to_free)
		shmem_free_blocks(inode, nr_pages_to_free);
	shmem_recalc_inode(inode);
	spin_unlock(&info->lock);

	/*
	 * Empty swap vector directory pages to be freed?
	 */
	if (!list_empty(&pages_to_free)) {
		pages_to_free.prev->next = NULL;
		shmem_free_pages(pages_to_free.next);
	}
}

static void shmem_truncate(struct inode *inode)
{
	shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
}

static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct page *page = NULL;
	int error;

	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
		if (attr->ia_size < inode->i_size) {
			/*
			 * If truncating down to a partial page, then
			 * if that page is already allocated, hold it
			 * in memory until the truncation is over, so
			 * truncate_partial_page cannnot miss it were
			 * it assigned to swap.
			 */
			if (attr->ia_size & (PAGE_CACHE_SIZE-1)) {
				(void) shmem_getpage(inode,
					attr->ia_size>>PAGE_CACHE_SHIFT,
						&page, SGP_READ, NULL);
			}
			/*
			 * Reset SHMEM_PAGEIN flag so that shmem_truncate can
			 * detect if any pages might have been added to cache
			 * after truncate_inode_pages.  But we needn't bother
			 * if it's being fully truncated to zero-length: the
			 * nrpages check is efficient enough in that case.
			 */
			if (attr->ia_size) {
				struct shmem_inode_info *info = SHMEM_I(inode);
				spin_lock(&info->lock);
				info->flags &= ~SHMEM_PAGEIN;
				spin_unlock(&info->lock);
			}
		}
	}

	error = inode_change_ok(inode, attr);
	if (!error)
		error = inode_setattr(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
	if (!error && (attr->ia_valid & ATTR_MODE))
		error = generic_acl_chmod(inode, &shmem_acl_ops);
#endif
	if (page)
		page_cache_release(page);
	return error;
}

static void shmem_delete_inode(struct inode *inode)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	struct shmem_inode_info *info = SHMEM_I(inode);

	if (inode->i_op->truncate == shmem_truncate) {
		truncate_inode_pages(inode->i_mapping, 0);
		shmem_unacct_size(info->flags, inode->i_size);
		inode->i_size = 0;
		shmem_truncate(inode);
		if (!list_empty(&info->swaplist)) {
			spin_lock(&shmem_swaplist_lock);
			list_del_init(&info->swaplist);
			spin_unlock(&shmem_swaplist_lock);
		}
	}
	BUG_ON(inode->i_blocks);
	if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
	clear_inode(inode);
}

static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
{
	swp_entry_t *ptr;

	for (ptr = dir; ptr < edir; ptr++) {
		if (ptr->val == entry.val)
			return ptr - dir;
	}
	return -1;
}

static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
{
	struct inode *inode;
	unsigned long idx;
	unsigned long size;
	unsigned long limit;
	unsigned long stage;
	struct page **dir;
	struct page *subdir;
	swp_entry_t *ptr;
	int offset;

	idx = 0;
	ptr = info->i_direct;
	spin_lock(&info->lock);
	limit = info->next_index;
	size = limit;
	if (size > SHMEM_NR_DIRECT)
		size = SHMEM_NR_DIRECT;
	offset = shmem_find_swp(entry, ptr, ptr+size);
	if (offset >= 0) {
		shmem_swp_balance_unmap();
		goto found;
	}
	if (!info->i_indirect)
		goto lost2;

	dir = shmem_dir_map(info->i_indirect);
	stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2;

	for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
		if (unlikely(idx == stage)) {
			shmem_dir_unmap(dir-1);
			dir = shmem_dir_map(info->i_indirect) +
			    ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
			while (!*dir) {
				dir++;
				idx += ENTRIES_PER_PAGEPAGE;
				if (idx >= limit)
					goto lost1;
			}
			stage = idx + ENTRIES_PER_PAGEPAGE;
			subdir = *dir;
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(subdir);
		}
		subdir = *dir;
		if (subdir && page_private(subdir)) {
			ptr = shmem_swp_map(subdir);
			size = limit - idx;
			if (size > ENTRIES_PER_PAGE)
				size = ENTRIES_PER_PAGE;
			offset = shmem_find_swp(entry, ptr, ptr+size);
			if (offset >= 0) {
				shmem_dir_unmap(dir);
				goto found;
			}
			shmem_swp_unmap(ptr);
		}
	}
lost1:
	shmem_dir_unmap(dir-1);
lost2:
	spin_unlock(&info->lock);
	return 0;
found:
	idx += offset;
	inode = &info->vfs_inode;
	if (move_from_swap_cache(page, idx, inode->i_mapping) == 0) {
		info->flags |= SHMEM_PAGEIN;
		shmem_swp_set(info, ptr + offset, 0);
	}
	shmem_swp_unmap(ptr);
	spin_unlock(&info->lock);
	/*
	 * Decrement swap count even when the entry is left behind:
	 * try_to_unuse will skip over mms, then reincrement count.
	 */
	swap_free(entry);
	return 1;
}

/*
 * shmem_unuse() search for an eventually swapped out shmem page.
 */
int shmem_unuse(swp_entry_t entry, struct page *page)
{
	struct list_head *p, *next;
	struct shmem_inode_info *info;
	int found = 0;

	spin_lock(&shmem_swaplist_lock);
	list_for_each_safe(p, next, &shmem_swaplist) {
		info = list_entry(p, struct shmem_inode_info, swaplist);
		if (!info->swapped)
			list_del_init(&info->swaplist);
		else if (shmem_unuse_inode(info, entry, page)) {
			/* move head to start search for next from here */
			list_move_tail(&shmem_swaplist, &info->swaplist);
			found = 1;
			break;
		}
	}
	spin_unlock(&shmem_swaplist_lock);
	return found;
}

/*
 * Move the page from the page cache to the swap cache.
 */
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
	struct shmem_inode_info *info;
	swp_entry_t *entry, swap;
	struct address_space *mapping;
	unsigned long index;
	struct inode *inode;

	BUG_ON(!PageLocked(page));
	/*
	 * shmem_backing_dev_info's capabilities prevent regular writeback or
	 * sync from ever calling shmem_writepage; but a stacking filesystem
	 * may use the ->writepage of its underlying filesystem, in which case
	 * we want to do nothing when that underlying filesystem is tmpfs
	 * (writing out to swap is useful as a response to memory pressure, but
	 * of no use to stabilize the data) - just redirty the page, unlock it
	 * and claim success in this case.  AOP_WRITEPAGE_ACTIVATE, and the
	 * page_mapped check below, must be avoided unless we're in reclaim.
	 */
	if (!wbc->for_reclaim) {
		set_page_dirty(page);
		unlock_page(page);
		return 0;
	}
	BUG_ON(page_mapped(page));

	mapping = page->mapping;
	index = page->index;
	inode = mapping->host;
	info = SHMEM_I(inode);
	if (info->flags & VM_LOCKED)
		goto redirty;
	swap = get_swap_page();
	if (!swap.val)
		goto redirty;

	spin_lock(&info->lock);
	shmem_recalc_inode(inode);
	if (index >= info->next_index) {
		BUG_ON(!(info->flags & SHMEM_TRUNCATE));
		goto unlock;
	}
	entry = shmem_swp_entry(info, index, NULL);
	BUG_ON(!entry);
	BUG_ON(entry->val);

	if (move_to_swap_cache(page, swap) == 0) {
		shmem_swp_set(info, entry, swap.val);
		shmem_swp_unmap(entry);
		spin_unlock(&info->lock);
		if (list_empty(&info->swaplist)) {
			spin_lock(&shmem_swaplist_lock);
			/* move instead of add in case we're racing */
			list_move_tail(&info->swaplist, &shmem_swaplist);
			spin_unlock(&shmem_swaplist_lock);
		}
		unlock_page(page);
		return 0;
	}

	shmem_swp_unmap(entry);
unlock:
	spin_unlock(&info->lock);
	swap_free(swap);
redirty:
	set_page_dirty(page);
	return AOP_WRITEPAGE_ACTIVATE;	/* Return with the page locked */
}

#ifdef CONFIG_NUMA
static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
{
	char *nodelist = strchr(value, ':');
	int err = 1;

	if (nodelist) {
		/* NUL-terminate policy string */
		*nodelist++ = '\0';
		if (nodelist_parse(nodelist, *policy_nodes))
			goto out;
		if (!nodes_subset(*policy_nodes, node_states[N_HIGH_MEMORY]))
			goto out;
	}
	if (!strcmp(value, "default")) {
		*policy = MPOL_DEFAULT;
		/* Don't allow a nodelist */
		if (!nodelist)
			err = 0;
	} else if (!strcmp(value, "prefer")) {
		*policy = MPOL_PREFERRED;
		/* Insist on a nodelist of one node only */
		if (nodelist) {
			char *rest = nodelist;
			while (isdigit(*rest))
				rest++;
			if (!*rest)
				err = 0;
		}
	} else if (!strcmp(value, "bind")) {
		*policy = MPOL_BIND;
		/* Insist on a nodelist */
		if (nodelist)
			err = 0;
	} else if (!strcmp(value, "interleave")) {
		*policy = MPOL_INTERLEAVE;
		/*
		 * Default to online nodes with memory if no nodelist
		 */
		if (!nodelist)
			*policy_nodes = node_states[N_HIGH_MEMORY];
		err = 0;
	}
out:
	/* Restore string for error message */
	if (nodelist)
		*--nodelist = ':';
	return err;
}

static struct page *shmem_swapin_async(struct shared_policy *p,
				       swp_entry_t entry, unsigned long idx)
{
	struct page *page;
	struct vm_area_struct pvma;

	/* Create a pseudo vma that just contains the policy */
	memset(&pvma, 0, sizeof(struct vm_area_struct));
	pvma.vm_end = PAGE_SIZE;
	pvma.vm_pgoff = idx;
	pvma.vm_policy = mpol_shared_policy_lookup(p, idx);
	page = read_swap_cache_async(entry, &pvma, 0);
	mpol_free(pvma.vm_policy);
	return page;
}

static struct page *shmem_swapin(struct shmem_inode_info *info,
				 swp_entry_t entry, unsigned long idx)
{
	struct shared_policy *p = &info->policy;
	int i, num;
	struct page *page;
	unsigned long offset;

	num = valid_swaphandles(entry, &offset);
	for (i = 0; i < num; offset++, i++) {
		page = shmem_swapin_async(p,
				swp_entry(swp_type(entry), offset), idx);
		if (!page)
			break;
		page_cache_release(page);
	}
	lru_add_drain();	/* Push any new pages onto the LRU now */
	return shmem_swapin_async(p, entry, idx);
}

static struct page *
shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
		 unsigned long idx)
{
	struct vm_area_struct pvma;
	struct page *page;

	memset(&pvma, 0, sizeof(struct vm_area_struct));
	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
	pvma.vm_pgoff = idx;
	pvma.vm_end = PAGE_SIZE;
	page = alloc_page_vma(gfp, &pvma, 0);
	mpol_free(pvma.vm_policy);
	return page;
}
#else
static inline int shmem_parse_mpol(char *value, int *policy,
						nodemask_t *policy_nodes)
{
	return 1;
}

static inline struct page *
shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx)
{
	swapin_readahead(entry, 0, NULL);
	return read_swap_cache_async(entry, NULL, 0);
}

static inline struct page *
shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx)
{
	return alloc_page(gfp);
}
#endif

/*
 * shmem_getpage - either get the page from swap or allocate a new one
 *
 * If we allocate a new one we do not mark it dirty. That's up to the
 * vm. If we swap it in we mark it dirty since we also free the swap
 * entry since a page cannot live in both the swap and page cache
 */
static int shmem_getpage(struct inode *inode, unsigned long idx,
			struct page **pagep, enum sgp_type sgp, int *type)
{
	struct address_space *mapping = inode->i_mapping;
	struct shmem_inode_info *info = SHMEM_I(inode);
	struct shmem_sb_info *sbinfo;
	struct page *filepage = *pagep;
	struct page *swappage;
	swp_entry_t *entry;
	swp_entry_t swap;
	int error;

	if (idx >= SHMEM_MAX_INDEX)
		return -EFBIG;

	if (type)
		*type = 0;

	/*
	 * Normally, filepage is NULL on entry, and either found
	 * uptodate immediately, or allocated and zeroed, or read
	 * in under swappage, which is then assigned to filepage.
	 * But shmem_readpage and shmem_write_begin pass in a locked
	 * filepage, which may be found not uptodate by other callers
	 * too, and may need to be copied from the swappage read in.
	 */
repeat:
	if (!filepage)
		filepage = find_lock_page(mapping, idx);
	if (filepage && PageUptodate(filepage))
		goto done;
	error = 0;
	if (sgp == SGP_QUICK)
		goto failed;

	spin_lock(&info->lock);
	shmem_recalc_inode(inode);
	entry = shmem_swp_alloc(info, idx, sgp);
	if (IS_ERR(entry)) {
		spin_unlock(&info->lock);
		error = PTR_ERR(entry);
		goto failed;
	}
	swap = *entry;

	if (swap.val) {
		/* Look it up and read it in.. */
		swappage = lookup_swap_cache(swap);
		if (!swappage) {
			shmem_swp_unmap(entry);
			/* here we actually do the io */
			if (type && !(*type & VM_FAULT_MAJOR)) {
				__count_vm_event(PGMAJFAULT);
				*type |= VM_FAULT_MAJOR;
			}
			spin_unlock(&info->lock);
			swappage = shmem_swapin(info, swap, idx);
			if (!swappage) {
				spin_lock(&info->lock);
				entry = shmem_swp_alloc(info, idx, sgp);
				if (IS_ERR(entry))
					error = PTR_ERR(entry);
				else {
					if (entry->val == swap.val)
						error = -ENOMEM;
					shmem_swp_unmap(entry);
				}
				spin_unlock(&info->lock);
				if (error)
					goto failed;
				goto repeat;
			}
			wait_on_page_locked(swappage);
			page_cache_release(swappage);
			goto repeat;
		}

		/* We have to do this with page locked to prevent races */
		if (TestSetPageLocked(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			wait_on_page_locked(swappage);
			page_cache_release(swappage);
			goto repeat;
		}
		if (PageWriteback(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			wait_on_page_writeback(swappage);
			unlock_page(swappage);
			page_cache_release(swappage);
			goto repeat;
		}
		if (!PageUptodate(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			unlock_page(swappage);
			page_cache_release(swappage);
			error = -EIO;
			goto failed;
		}

		if (filepage) {
			shmem_swp_set(info, entry, 0);
			shmem_swp_unmap(entry);
			delete_from_swap_cache(swappage);
			spin_unlock(&info->lock);
			copy_highpage(filepage, swappage);
			unlock_page(swappage);
			page_cache_release(swappage);
			flush_dcache_page(filepage);
			SetPageUptodate(filepage);
			set_page_dirty(filepage);
			swap_free(swap);
		} else if (!(error = move_from_swap_cache(
				swappage, idx, mapping))) {
			info->flags |= SHMEM_PAGEIN;
			shmem_swp_set(info, entry, 0);
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			filepage = swappage;
			swap_free(swap);
		} else {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			unlock_page(swappage);
			page_cache_release(swappage);
			if (error == -ENOMEM) {
				/* let kswapd refresh zone for GFP_ATOMICs */
				congestion_wait(WRITE, HZ/50);
			}
			goto repeat;
		}
	} else if (sgp == SGP_READ && !filepage) {
		shmem_swp_unmap(entry);
		filepage = find_get_page(mapping, idx);
		if (filepage &&
		    (!PageUptodate(filepage) || TestSetPageLocked(filepage))) {
			spin_unlock(&info->lock);
			wait_on_page_locked(filepage);
			page_cache_release(filepage);
			filepage = NULL;
			goto repeat;
		}
		spin_unlock(&info->lock);
	} else {
		shmem_swp_unmap(entry);
		sbinfo = SHMEM_SB(inode->i_sb);
		if (sbinfo->max_blocks) {
			spin_lock(&sbinfo->stat_lock);
			if (sbinfo->free_blocks == 0 ||
			    shmem_acct_block(info->flags)) {
				spin_unlock(&sbinfo->stat_lock);
				spin_unlock(&info->lock);
				error = -ENOSPC;
				goto failed;
			}
			sbinfo->free_blocks--;
			inode->i_blocks += BLOCKS_PER_PAGE;
			spin_unlock(&sbinfo->stat_lock);
		} else if (shmem_acct_block(info->flags)) {
			spin_unlock(&info->lock);
			error = -ENOSPC;
			goto failed;
		}

		if (!filepage) {
			spin_unlock(&info->lock);
			filepage = shmem_alloc_page(mapping_gfp_mask(mapping),
						    info,
						    idx);
			if (!filepage) {
				shmem_unacct_blocks(info->flags, 1);
				shmem_free_blocks(inode, 1);
				error = -ENOMEM;
				goto failed;
			}

			spin_lock(&info->lock);
			entry = shmem_swp_alloc(info, idx, sgp);
			if (IS_ERR(entry))
				error = PTR_ERR(entry);
			else {
				swap = *entry;
				shmem_swp_unmap(entry);
			}
			if (error || swap.val || 0 != add_to_page_cache_lru(
					filepage, mapping, idx, GFP_ATOMIC)) {
				spin_unlock(&info->lock);
				page_cache_release(filepage);
				shmem_unacct_blocks(info->flags, 1);
				shmem_free_blocks(inode, 1);
				filepage = NULL;
				if (error)
					goto failed;
				goto repeat;
			}
			info->flags |= SHMEM_PAGEIN;
		}

		info->alloced++;
		spin_unlock(&info->lock);
		clear_highpage(filepage);
		flush_dcache_page(filepage);
		SetPageUptodate(filepage);
	}
done:
	if (*pagep != filepage) {
		*pagep = filepage;
		if (sgp != SGP_FAULT)
			unlock_page(filepage);

	}
	return 0;

failed:
	if (*pagep != filepage) {
		unlock_page(filepage);
		page_cache_release(filepage);
	}
	return error;
}

static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
	int error;
	int ret;

	if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
		return VM_FAULT_SIGBUS;

	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_FAULT, &ret);
	if (error)
		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);

	mark_page_accessed(vmf->page);
	return ret | VM_FAULT_LOCKED;
}

#ifdef CONFIG_NUMA
static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
{
	struct inode *i = vma->vm_file->f_path.dentry->d_inode;
	return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new);
}

static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
					  unsigned long addr)
{
	struct inode *i = vma->vm_file->f_path.dentry->d_inode;
	unsigned long idx;

	idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx);
}
#endif

int shmem_lock(struct file *file, int lock, struct user_struct *user)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct shmem_inode_info *info = SHMEM_I(inode);
	int retval = -ENOMEM;

	spin_lock(&info->lock);
	if (lock && !(info->flags & VM_LOCKED)) {
		if (!user_shm_lock(inode->i_size, user))
			goto out_nomem;
		info->flags |= VM_LOCKED;
	}
	if (!lock && (info->flags & VM_LOCKED) && user) {
		user_shm_unlock(inode->i_size, user);
		info->flags &= ~VM_LOCKED;
	}
	retval = 0;
out_nomem:
	spin_unlock(&info->lock);
	return retval;
}

static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
{
	file_accessed(file);
	vma->vm_ops = &shmem_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;
	return 0;
}

static struct inode *
shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
{
	struct inode *inode;
	struct shmem_inode_info *info;
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);

	if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return NULL;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	inode = new_inode(sb);
	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		inode->i_mapping->a_ops = &shmem_aops;
		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_generation = get_seconds();
		info = SHMEM_I(inode);
		memset(info, 0, (char *)inode - (char *)info);
		spin_lock_init(&info->lock);
		INIT_LIST_HEAD(&info->swaplist);

		switch (mode & S_IFMT) {
		default:
			inode->i_op = &shmem_special_inode_operations;
			init_special_inode(inode, mode, dev);
			break;
		case S_IFREG:
			inode->i_op = &shmem_inode_operations;
			inode->i_fop = &shmem_file_operations;
			mpol_shared_policy_init(&info->policy, sbinfo->policy,
							&sbinfo->policy_nodes);
			break;
		case S_IFDIR:
			inc_nlink(inode);
			/* Some things misbehave if size == 0 on a directory */
			inode->i_size = 2 * BOGO_DIRENT_SIZE;
			inode->i_op = &shmem_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;
			break;
		case S_IFLNK:
			/*
			 * Must not load anything in the rbtree,
			 * mpol_free_shared_policy will not be called.
			 */
			mpol_shared_policy_init(&info->policy, MPOL_DEFAULT,
						NULL);
			break;
		}
	} else if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
	return inode;
}

#ifdef CONFIG_TMPFS
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_symlink_inline_operations;

/*
 * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin;
 * but providing them allows a tmpfs file to be used for splice, sendfile, and
 * below the loop driver, in the generic fashion that many filesystems support.
 */
static int shmem_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL);
	unlock_page(page);
	return error;
}

static int
shmem_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	struct inode *inode = mapping->host;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
	*pagep = NULL;
	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
}

static int
shmem_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = mapping->host;

	set_page_dirty(page);
	page_cache_release(page);

	if (pos+copied > inode->i_size)
		i_size_write(inode, pos+copied);

	return copied;
}

static ssize_t
shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
	struct inode	*inode = file->f_path.dentry->d_inode;
	loff_t		pos;
	unsigned long	written;
	ssize_t		err;

	if ((ssize_t) count < 0)
		return -EINVAL;

	if (!access_ok(VERIFY_READ, buf, count))
		return -EFAULT;

	mutex_lock(&inode->i_mutex);

	pos = *ppos;
	written = 0;

	err = generic_write_checks(file, &pos, &count, 0);
	if (err || !count)
		goto out;

	err = remove_suid(file->f_path.dentry);
	if (err)
		goto out;

	inode->i_ctime = inode->i_mtime = CURRENT_TIME;

	do {
		struct page *page = NULL;
		unsigned long bytes, index, offset;
		char *kaddr;
		int left;

		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
		index = pos >> PAGE_CACHE_SHIFT;
		bytes = PAGE_CACHE_SIZE - offset;
		if (bytes > count)
			bytes = count;

		/*
		 * We don't hold page lock across copy from user -
		 * what would it guard against? - so no deadlock here.
		 * But it still may be a good idea to prefault below.
		 */

		err = shmem_getpage(inode, index, &page, SGP_WRITE, NULL);
		if (err)
			break;

		left = bytes;
		if (PageHighMem(page)) {
			volatile unsigned char dummy;
			__get_user(dummy, buf);
			__get_user(dummy, buf + bytes - 1);

			kaddr = kmap_atomic(page, KM_USER0);
			left = __copy_from_user_inatomic(kaddr + offset,
							buf, bytes);
			kunmap_atomic(kaddr, KM_USER0);
		}
		if (left) {
			kaddr = kmap(page);
			left = __copy_from_user(kaddr + offset, buf, bytes);
			kunmap(page);
		}

		written += bytes;
		count -= bytes;
		pos += bytes;
		buf += bytes;
		if (pos > inode->i_size)
			i_size_write(inode, pos);

		flush_dcache_page(page);
		set_page_dirty(page);
		mark_page_accessed(page);
		page_cache_release(page);

		if (left) {
			pos -= left;
			written -= left;
			err = -EFAULT;
			break;
		}

		/*
		 * Our dirty pages are not counted in nr_dirty,
		 * and we do not attempt to balance dirty pages.
		 */

		cond_resched();
	} while (count);

	*ppos = pos;
	if (written)
		err = written;
out:
	mutex_unlock(&inode->i_mutex);
	return err;
}

static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct address_space *mapping = inode->i_mapping;
	unsigned long index, offset;

	index = *ppos >> PAGE_CACHE_SHIFT;
	offset = *ppos & ~PAGE_CACHE_MASK;

	for (;;) {
		struct page *page = NULL;
		unsigned long end_index, nr, ret;
		loff_t i_size = i_size_read(inode);

		end_index = i_size >> PAGE_CACHE_SHIFT;
		if (index > end_index)
			break;
		if (index == end_index) {
			nr = i_size & ~PAGE_CACHE_MASK;
			if (nr <= offset)
				break;
		}

		desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL);
		if (desc->error) {
			if (desc->error == -EINVAL)
				desc->error = 0;
			break;
		}

		/*
		 * We must evaluate after, since reads (unlike writes)
		 * are called without i_mutex protection against truncate
		 */
		nr = PAGE_CACHE_SIZE;
		i_size = i_size_read(inode);
		end_index = i_size >> PAGE_CACHE_SHIFT;
		if (index == end_index) {
			nr = i_size & ~PAGE_CACHE_MASK;
			if (nr <= offset) {
				if (page)
					page_cache_release(page);
				break;
			}
		}
		nr -= offset;

		if (page) {
			/*
			 * If users can be writing to this page using arbitrary
			 * virtual addresses, take care about potential aliasing
			 * before reading the page on the kernel side.
			 */
			if (mapping_writably_mapped(mapping))
				flush_dcache_page(page);
			/*
			 * Mark the page accessed if we read the beginning.
			 */
			if (!offset)
				mark_page_accessed(page);
		} else {
			page = ZERO_PAGE(0);
			page_cache_get(page);
		}

		/*
		 * Ok, we have the page, and it's up-to-date, so
		 * now we can copy it to user space...
		 *
		 * The actor routine returns how many bytes were actually used..
		 * NOTE! This may not be the same as how much of a user buffer
		 * we filled up (we may be padding etc), so we can only update
		 * "pos" here (the actor routine has to update the user buffer
		 * pointers and the remaining count).
		 */
		ret = actor(desc, page, offset, nr);
		offset += ret;
		index += offset >> PAGE_CACHE_SHIFT;
		offset &= ~PAGE_CACHE_MASK;

		page_cache_release(page);
		if (ret != nr || !desc->count)
			break;

		cond_resched();
	}

	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
	file_accessed(filp);
}

static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
{
	read_descriptor_t desc;

	if ((ssize_t) count < 0)
		return -EINVAL;
	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT;
	if (!count)
		return 0;

	desc.written = 0;
	desc.count = count;
	desc.arg.buf = buf;
	desc.error = 0;

	do_shmem_file_read(filp, ppos, &desc, file_read_actor);
	if (desc.written)
		return desc.written;
	return desc.error;
}

static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);

	buf->f_type = TMPFS_MAGIC;
	buf->f_bsize = PAGE_CACHE_SIZE;
	buf->f_namelen = NAME_MAX;
	spin_lock(&sbinfo->stat_lock);
	if (sbinfo->max_blocks) {
		buf->f_blocks = sbinfo->max_blocks;
		buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
	}
	if (sbinfo->max_inodes) {
		buf->f_files = sbinfo->max_inodes;
		buf->f_ffree = sbinfo->free_inodes;
	}
	/* else leave those fields 0 like simple_statfs */
	spin_unlock(&sbinfo->stat_lock);
	return 0;
}

/*
 * File creation. Allocate an inode, and we're done..
 */
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
	struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
	int error = -ENOSPC;

	if (inode) {
		error = security_inode_init_security(inode, dir, NULL, NULL,
						     NULL);
		if (error) {
			if (error != -EOPNOTSUPP) {
				iput(inode);
				return error;
			}
		}
		error = shmem_acl_init(inode, dir);
		if (error) {
			iput(inode);
			return error;
		}
		if (dir->i_mode & S_ISGID) {
			inode->i_gid = dir->i_gid;
			if (S_ISDIR(mode))
				inode->i_mode |= S_ISGID;
		}
		dir->i_size += BOGO_DIRENT_SIZE;
		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
		d_instantiate(dentry, inode);
		dget(dentry); /* Extra count - pin the dentry in core */
	}
	return error;
}

static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int error;

	if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0)))
		return error;
	inc_nlink(dir);
	return 0;
}

static int shmem_create(struct inode *dir, struct dentry *dentry, int mode,
		struct nameidata *nd)
{
	return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
}

/*
 * Link a file..
 */
static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = old_dentry->d_inode;
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);

	/*
	 * No ordinary (disk based) filesystem counts links as inodes;
	 * but each new link needs a new dentry, pinning lowmem, and
	 * tmpfs dentries cannot be pruned until they are unlinked.
	 */
	if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return -ENOSPC;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	dir->i_size += BOGO_DIRENT_SIZE;
	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	inc_nlink(inode);
	atomic_inc(&inode->i_count);	/* New dentry reference */
	dget(dentry);		/* Extra pinning count for the created dentry */
	d_instantiate(dentry, inode);
	return 0;
}

static int shmem_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) {
		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
		if (sbinfo->max_inodes) {
			spin_lock(&sbinfo->stat_lock);
			sbinfo->free_inodes++;
			spin_unlock(&sbinfo->stat_lock);
		}
	}

	dir->i_size -= BOGO_DIRENT_SIZE;
	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	drop_nlink(inode);
	dput(dentry);	/* Undo the count from "create" - this does all the work */
	return 0;
}

static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
{
	if (!simple_empty(dentry))
		return -ENOTEMPTY;

	drop_nlink(dentry->d_inode);
	drop_nlink(dir);
	return shmem_unlink(dir, dentry);
}

/*
 * The VFS layer already does all the dentry stuff for rename,
 * we just have to decrement the usage count for the target if
 * it exists so that the VFS layer correctly free's it when it
 * gets overwritten.
 */
static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry)
{
	struct inode *inode = old_dentry->d_inode;
	int they_are_dirs = S_ISDIR(inode->i_mode);

	if (!simple_empty(new_dentry))
		return -ENOTEMPTY;

	if (new_dentry->d_inode) {
		(void) shmem_unlink(new_dir, new_dentry);
		if (they_are_dirs)
			drop_nlink(old_dir);
	} else if (they_are_dirs) {
		drop_nlink(old_dir);
		inc_nlink(new_dir);
	}

	old_dir->i_size -= BOGO_DIRENT_SIZE;
	new_dir->i_size += BOGO_DIRENT_SIZE;
	old_dir->i_ctime = old_dir->i_mtime =
	new_dir->i_ctime = new_dir->i_mtime =
	inode->i_ctime = CURRENT_TIME;
	return 0;
}

static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
	int error;
	int len;
	struct inode *inode;
	struct page *page = NULL;
	char *kaddr;
	struct shmem_inode_info *info;

	len = strlen(symname) + 1;
	if (len > PAGE_CACHE_SIZE)
		return -ENAMETOOLONG;

	inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
	if (!inode)
		return -ENOSPC;

	error = security_inode_init_security(inode, dir, NULL, NULL,
					     NULL);
	if (error) {
		if (error != -EOPNOTSUPP) {
			iput(inode);
			return error;
		}
		error = 0;
	}

	info = SHMEM_I(inode);
	inode->i_size = len-1;
	if (len <= (char *)inode - (char *)info) {
		/* do it inline */
		memcpy(info, symname, len);
		inode->i_op = &shmem_symlink_inline_operations;
	} else {
		error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
		if (error) {
			iput(inode);
			return error;
		}
		inode->i_op = &shmem_symlink_inode_operations;
		kaddr = kmap_atomic(page, KM_USER0);
		memcpy(kaddr, symname, len);
		kunmap_atomic(kaddr, KM_USER0);
		set_page_dirty(page);
		page_cache_release(page);
	}
	if (dir->i_mode & S_ISGID)
		inode->i_gid = dir->i_gid;
	dir->i_size += BOGO_DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
}

static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd)
{
	nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode));
	return NULL;
}

static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct page *page = NULL;
	int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL);
	nd_set_link(nd, res ? ERR_PTR(res) : kmap(page));
	return page;
}

static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
{
	if (!IS_ERR(nd_get_link(nd))) {
		struct page *page = cookie;
		kunmap(page);
		mark_page_accessed(page);
		page_cache_release(page);
	}
}

static const struct inode_operations shmem_symlink_inline_operations = {
	.readlink	= generic_readlink,
	.follow_link	= shmem_follow_link_inline,
};

static const struct inode_operations shmem_symlink_inode_operations = {
	.truncate	= shmem_truncate,
	.readlink	= generic_readlink,
	.follow_link	= shmem_follow_link,
	.put_link	= shmem_put_link,
};

#ifdef CONFIG_TMPFS_POSIX_ACL
/**
 * Superblocks without xattr inode operations will get security.* xattr
 * support from the VFS "for free". As soon as we have any other xattrs
 * like ACLs, we also need to implement the security.* handlers at
 * filesystem level, though.
 */

static size_t shmem_xattr_security_list(struct inode *inode, char *list,
					size_t list_len, const char *name,
					size_t name_len)
{
	return security_inode_listsecurity(inode, list, list_len);
}

static int shmem_xattr_security_get(struct inode *inode, const char *name,
				    void *buffer, size_t size)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return security_inode_getsecurity(inode, name, buffer, size,
					  -EOPNOTSUPP);
}

static int shmem_xattr_security_set(struct inode *inode, const char *name,
				    const void *value, size_t size, int flags)
{
	if (strcmp(name, "") == 0)
		return -EINVAL;
	return security_inode_setsecurity(inode, name, value, size, flags);
}

static struct xattr_handler shmem_xattr_security_handler = {
	.prefix = XATTR_SECURITY_PREFIX,
	.list   = shmem_xattr_security_list,
	.get    = shmem_xattr_security_get,
	.set    = shmem_xattr_security_set,
};

static struct xattr_handler *shmem_xattr_handlers[] = {
	&shmem_xattr_acl_access_handler,
	&shmem_xattr_acl_default_handler,
	&shmem_xattr_security_handler,
	NULL
};
#endif

static struct dentry *shmem_get_parent(struct dentry *child)
{
	return ERR_PTR(-ESTALE);
}

static int shmem_match(struct inode *ino, void *vfh)
{
	__u32 *fh = vfh;
	__u64 inum = fh[2];
	inum = (inum << 32) | fh[1];
	return ino->i_ino == inum && fh[0] == ino->i_generation;
}

static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
		struct fid *fid, int fh_len, int fh_type)
{
	struct inode *inode;
	struct dentry *dentry = NULL;
	u64 inum = fid->raw[2];
	inum = (inum << 32) | fid->raw[1];

	if (fh_len < 3)
		return NULL;

	inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
			shmem_match, fid->raw);
	if (inode) {
		dentry = d_find_alias(inode);
		iput(inode);
	}

	return dentry;
}

static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
				int connectable)
{
	struct inode *inode = dentry->d_inode;

	if (*len < 3)
		return 255;

	if (hlist_unhashed(&inode->i_hash)) {
		/* Unfortunately insert_inode_hash is not idempotent,
		 * so as we hash inodes here rather than at creation
		 * time, we need a lock to ensure we only try
		 * to do it once
		 */
		static DEFINE_SPINLOCK(lock);
		spin_lock(&lock);
		if (hlist_unhashed(&inode->i_hash))
			__insert_inode_hash(inode,
					    inode->i_ino + inode->i_generation);
		spin_unlock(&lock);
	}

	fh[0] = inode->i_generation;
	fh[1] = inode->i_ino;
	fh[2] = ((__u64)inode->i_ino) >> 32;

	*len = 3;
	return 1;
}

static const struct export_operations shmem_export_ops = {
	.get_parent     = shmem_get_parent,
	.encode_fh      = shmem_encode_fh,
	.fh_to_dentry	= shmem_fh_to_dentry,
};

static int shmem_parse_options(char *options, int *mode, uid_t *uid,
	gid_t *gid, unsigned long *blocks, unsigned long *inodes,
	int *policy, nodemask_t *policy_nodes)
{
	char *this_char, *value, *rest;

	while (options != NULL) {
		this_char = options;
		for (;;) {
			/*
			 * NUL-terminate this option: unfortunately,
			 * mount options form a comma-separated list,
			 * but mpol's nodelist may also contain commas.
			 */
			options = strchr(options, ',');
			if (options == NULL)
				break;
			options++;
			if (!isdigit(*options)) {
				options[-1] = '\0';
				break;
			}
		}
		if (!*this_char)
			continue;
		if ((value = strchr(this_char,'=')) != NULL) {
			*value++ = 0;
		} else {
			printk(KERN_ERR
			    "tmpfs: No value for mount option '%s'\n",
			    this_char);
			return 1;
		}

		if (!strcmp(this_char,"size")) {
			unsigned long long size;
			size = memparse(value,&rest);
			if (*rest == '%') {
				size <<= PAGE_SHIFT;
				size *= totalram_pages;
				do_div(size, 100);
				rest++;
			}
			if (*rest)
				goto bad_val;
			*blocks = size >> PAGE_CACHE_SHIFT;
		} else if (!strcmp(this_char,"nr_blocks")) {
			*blocks = memparse(value,&rest);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"nr_inodes")) {
			*inodes = memparse(value,&rest);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"mode")) {
			if (!mode)
				continue;
			*mode = simple_strtoul(value,&rest,8);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"uid")) {
			if (!uid)
				continue;
			*uid = simple_strtoul(value,&rest,0);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"gid")) {
			if (!gid)
				continue;
			*gid = simple_strtoul(value,&rest,0);
			if (*rest)
				goto bad_val;
		} else if (!strcmp(this_char,"mpol")) {
			if (shmem_parse_mpol(value,policy,policy_nodes))
				goto bad_val;
		} else {
			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
			       this_char);
			return 1;
		}
	}
	return 0;

bad_val:
	printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n",
	       value, this_char);
	return 1;

}

static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
	unsigned long max_blocks = sbinfo->max_blocks;
	unsigned long max_inodes = sbinfo->max_inodes;
	int policy = sbinfo->policy;
	nodemask_t policy_nodes = sbinfo->policy_nodes;
	unsigned long blocks;
	unsigned long inodes;
	int error = -EINVAL;

	if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks,
				&max_inodes, &policy, &policy_nodes))
		return error;

	spin_lock(&sbinfo->stat_lock);
	blocks = sbinfo->max_blocks - sbinfo->free_blocks;
	inodes = sbinfo->max_inodes - sbinfo->free_inodes;
	if (max_blocks < blocks)
		goto out;
	if (max_inodes < inodes)
		goto out;
	/*
	 * Those tests also disallow limited->unlimited while any are in
	 * use, so i_blocks will always be zero when max_blocks is zero;
	 * but we must separately disallow unlimited->limited, because
	 * in that case we have no record of how much is already in use.
	 */
	if (max_blocks && !sbinfo->max_blocks)
		goto out;
	if (max_inodes && !sbinfo->max_inodes)
		goto out;

	error = 0;
	sbinfo->max_blocks  = max_blocks;
	sbinfo->free_blocks = max_blocks - blocks;
	sbinfo->max_inodes  = max_inodes;
	sbinfo->free_inodes = max_inodes - inodes;
	sbinfo->policy = policy;
	sbinfo->policy_nodes = policy_nodes;
out:
	spin_unlock(&sbinfo->stat_lock);
	return error;
}
#endif

static void shmem_put_super(struct super_block *sb)
{
	kfree(sb->s_fs_info);
	sb->s_fs_info = NULL;
}

static int shmem_fill_super(struct super_block *sb,
			    void *data, int silent)
{
	struct inode *inode;
	struct dentry *root;
	int mode   = S_IRWXUGO | S_ISVTX;
	uid_t uid = current->fsuid;
	gid_t gid = current->fsgid;
	int err = -ENOMEM;
	struct shmem_sb_info *sbinfo;
	unsigned long blocks = 0;
	unsigned long inodes = 0;
	int policy = MPOL_DEFAULT;
	nodemask_t policy_nodes = node_states[N_HIGH_MEMORY];

#ifdef CONFIG_TMPFS
	/*
	 * Per default we only allow half of the physical ram per
	 * tmpfs instance, limiting inodes to one per page of lowmem;
	 * but the internal instance is left unlimited.
	 */
	if (!(sb->s_flags & MS_NOUSER)) {
		blocks = totalram_pages / 2;
		inodes = totalram_pages - totalhigh_pages;
		if (inodes > blocks)
			inodes = blocks;
		if (shmem_parse_options(data, &mode, &uid, &gid, &blocks,
					&inodes, &policy, &policy_nodes))
			return -EINVAL;
	}
	sb->s_export_op = &shmem_export_ops;
#else
	sb->s_flags |= MS_NOUSER;
#endif

	/* Round up to L1_CACHE_BYTES to resist false sharing */
	sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
				L1_CACHE_BYTES), GFP_KERNEL);
	if (!sbinfo)
		return -ENOMEM;

	spin_lock_init(&sbinfo->stat_lock);
	sbinfo->max_blocks = blocks;
	sbinfo->free_blocks = blocks;
	sbinfo->max_inodes = inodes;
	sbinfo->free_inodes = inodes;
	sbinfo->policy = policy;
	sbinfo->policy_nodes = policy_nodes;

	sb->s_fs_info = sbinfo;
	sb->s_maxbytes = SHMEM_MAX_BYTES;
	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = TMPFS_MAGIC;
	sb->s_op = &shmem_ops;
	sb->s_time_gran = 1;
#ifdef CONFIG_TMPFS_POSIX_ACL
	sb->s_xattr = shmem_xattr_handlers;
	sb->s_flags |= MS_POSIXACL;
#endif

	inode = shmem_get_inode(sb, S_IFDIR | mode, 0);
	if (!inode)
		goto failed;
	inode->i_uid = uid;
	inode->i_gid = gid;
	root = d_alloc_root(inode);
	if (!root)
		goto failed_iput;
	sb->s_root = root;
	return 0;

failed_iput:
	iput(inode);
failed:
	shmem_put_super(sb);
	return err;
}

static struct kmem_cache *shmem_inode_cachep;

static struct inode *shmem_alloc_inode(struct super_block *sb)
{
	struct shmem_inode_info *p;
	p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
	if (!p)
		return NULL;
	return &p->vfs_inode;
}

static void shmem_destroy_inode(struct inode *inode)
{
	if ((inode->i_mode & S_IFMT) == S_IFREG) {
		/* only struct inode is valid if it's an inline symlink */
		mpol_free_shared_policy(&SHMEM_I(inode)->policy);
	}
	shmem_acl_destroy_inode(inode);
	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}

static void init_once(struct kmem_cache *cachep, void *foo)
{
	struct shmem_inode_info *p = (struct shmem_inode_info *) foo;

	inode_init_once(&p->vfs_inode);
#ifdef CONFIG_TMPFS_POSIX_ACL
	p->i_acl = NULL;
	p->i_default_acl = NULL;
#endif
}

static int init_inodecache(void)
{
	shmem_inode_cachep = kmem_cache_create("shmem_inode_cache",
				sizeof(struct shmem_inode_info),
				0, SLAB_PANIC, init_once);
	return 0;
}

static void destroy_inodecache(void)
{
	kmem_cache_destroy(shmem_inode_cachep);
}

static const struct address_space_operations shmem_aops = {
	.writepage	= shmem_writepage,
	.set_page_dirty	= __set_page_dirty_no_writeback,
#ifdef CONFIG_TMPFS
	.readpage	= shmem_readpage,
	.write_begin	= shmem_write_begin,
	.write_end	= shmem_write_end,
#endif
	.migratepage	= migrate_page,
};

static const struct file_operations shmem_file_operations = {
	.mmap		= shmem_mmap,
#ifdef CONFIG_TMPFS
	.llseek		= generic_file_llseek,
	.read		= shmem_file_read,
	.write		= shmem_file_write,
	.fsync		= simple_sync_file,
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
#endif
};

static const struct inode_operations shmem_inode_operations = {
	.truncate	= shmem_truncate,
	.setattr	= shmem_notify_change,
	.truncate_range	= shmem_truncate_range,
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif

};

static const struct inode_operations shmem_dir_inode_operations = {
#ifdef CONFIG_TMPFS
	.create		= shmem_create,
	.lookup		= simple_lookup,
	.link		= shmem_link,
	.unlink		= shmem_unlink,
	.symlink	= shmem_symlink,
	.mkdir		= shmem_mkdir,
	.rmdir		= shmem_rmdir,
	.mknod		= shmem_mknod,
	.rename		= shmem_rename,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setattr	= shmem_notify_change,
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif
};

static const struct inode_operations shmem_special_inode_operations = {
#ifdef CONFIG_TMPFS_POSIX_ACL
	.setattr	= shmem_notify_change,
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= generic_listxattr,
	.removexattr	= generic_removexattr,
	.permission	= shmem_permission,
#endif
};

static const struct super_operations shmem_ops = {
	.alloc_inode	= shmem_alloc_inode,
	.destroy_inode	= shmem_destroy_inode,
#ifdef CONFIG_TMPFS
	.statfs		= shmem_statfs,
	.remount_fs	= shmem_remount_fs,
#endif
	.delete_inode	= shmem_delete_inode,
	.drop_inode	= generic_delete_inode,
	.put_super	= shmem_put_super,
};

static struct vm_operations_struct shmem_vm_ops = {
	.fault		= shmem_fault,
#ifdef CONFIG_NUMA
	.set_policy     = shmem_set_policy,
	.get_policy     = shmem_get_policy,
#endif
};


static int shmem_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt);
}

static struct file_system_type tmpfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "tmpfs",
	.get_sb		= shmem_get_sb,
	.kill_sb	= kill_litter_super,
};
static struct vfsmount *shm_mnt;

static int __init init_tmpfs(void)
{
	int error;

	error = bdi_init(&shmem_backing_dev_info);
	if (error)
		goto out4;

	error = init_inodecache();
	if (error)
		goto out3;

	error = register_filesystem(&tmpfs_fs_type);
	if (error) {
		printk(KERN_ERR "Could not register tmpfs\n");
		goto out2;
	}

	shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER,
				tmpfs_fs_type.name, NULL);
	if (IS_ERR(shm_mnt)) {
		error = PTR_ERR(shm_mnt);
		printk(KERN_ERR "Could not kern_mount tmpfs\n");
		goto out1;
	}
	return 0;

out1:
	unregister_filesystem(&tmpfs_fs_type);
out2:
	destroy_inodecache();
out3:
	bdi_destroy(&shmem_backing_dev_info);
out4:
	shm_mnt = ERR_PTR(error);
	return error;
}
module_init(init_tmpfs)

/*
 * shmem_file_setup - get an unlinked file living in tmpfs
 *
 * @name: name for dentry (to be seen in /proc/<pid>/maps
 * @size: size to be set for the file
 *
 */
struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
{
	int error;
	struct file *file;
	struct inode *inode;
	struct dentry *dentry, *root;
	struct qstr this;

	if (IS_ERR(shm_mnt))
		return (void *)shm_mnt;

	if (size < 0 || size > SHMEM_MAX_BYTES)
		return ERR_PTR(-EINVAL);

	if (shmem_acct_size(flags, size))
		return ERR_PTR(-ENOMEM);

	error = -ENOMEM;
	this.name = name;
	this.len = strlen(name);
	this.hash = 0; /* will go */
	root = shm_mnt->mnt_root;
	dentry = d_alloc(root, &this);
	if (!dentry)
		goto put_memory;

	error = -ENFILE;
	file = get_empty_filp();
	if (!file)
		goto put_dentry;

	error = -ENOSPC;
	inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
	if (!inode)
		goto close_file;

	SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
	d_instantiate(dentry, inode);
	inode->i_size = size;
	inode->i_nlink = 0;	/* It is unlinked */
	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
			&shmem_file_operations);
	return file;

close_file:
	put_filp(file);
put_dentry:
	dput(dentry);
put_memory:
	shmem_unacct_size(flags, size);
	return ERR_PTR(error);
}

/*
 * shmem_zero_setup - setup a shared anonymous mapping
 *
 * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
 */
int shmem_zero_setup(struct vm_area_struct *vma)
{
	struct file *file;
	loff_t size = vma->vm_end - vma->vm_start;

	file = shmem_file_setup("dev/zero", size, vma->vm_flags);
	if (IS_ERR(file))
		return PTR_ERR(file);

	if (vma->vm_file)
		fput(vma->vm_file);
	vma->vm_file = file;
	vma->vm_ops = &shmem_vm_ops;
	return 0;
}