diff options
51 files changed, 908 insertions, 287 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index ceddcff4082a..e638e15a8895 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -1,3 +1,46 @@ +What: /sys/bus/pci/drivers/.../bind +Date: December 2003 +Contact: linux-pci@vger.kernel.org +Description: + Writing a device location to this file will cause + the driver to attempt to bind to the device found at + this location. This is useful for overriding default + bindings. The format for the location is: DDDD:BB:DD.F. + That is Domain:Bus:Device.Function and is the same as + found in /sys/bus/pci/devices/. For example: + # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind + (Note: kernels before 2.6.28 may require echo -n). + +What: /sys/bus/pci/drivers/.../unbind +Date: December 2003 +Contact: linux-pci@vger.kernel.org +Description: + Writing a device location to this file will cause the + driver to attempt to unbind from the device found at + this location. This may be useful when overriding default + bindings. The format for the location is: DDDD:BB:DD.F. + That is Domain:Bus:Device.Function and is the same as + found in /sys/bus/pci/devices/. For example: + # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind + (Note: kernels before 2.6.28 may require echo -n). + +What: /sys/bus/pci/drivers/.../new_id +Date: December 2003 +Contact: linux-pci@vger.kernel.org +Description: + Writing a device ID to this file will attempt to + dynamically add a new device ID to a PCI device driver. + This may allow the driver to support more hardware than + was included in the driver's static device ID support + table at compile time. The format for the device ID is: + VVVV DDDD SVVV SDDD CCCC MMMM PPPP. That is Vendor ID, + Device ID, Subsystem Vendor ID, Subsystem Device ID, + Class, Class Mask, and Private Driver Data. The Vendor ID + and Device ID fields are required, the rest are optional. + Upon successfully adding an ID, the driver will probe + for the device and attempt to bind to it. For example: + # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id + What: /sys/bus/pci/devices/.../vpd Date: February 2008 Contact: Ben Hutchings <bhutchings@solarflare.com> diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index ada06924a423..73cb6a3229ae 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -367,27 +367,24 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, unsigned int flags) { - char *ptr = (char *) ¤t->thread.TS_FPR(reg); - int i, ret; + char *ptr0 = (char *) ¤t->thread.TS_FPR(reg); + char *ptr1 = (char *) ¤t->thread.TS_FPR(reg+1); + int i, ret, sw = 0; if (!(flags & F)) return 0; if (reg & 1) return 0; /* invalid form: FRS/FRT must be even */ - if (!(flags & SW)) { - /* not byte-swapped - easy */ - if (!(flags & ST)) - ret = __copy_from_user(ptr, addr, 16); - else - ret = __copy_to_user(addr, ptr, 16); - } else { - /* each FPR value is byte-swapped separately */ - ret = 0; - for (i = 0; i < 16; ++i) { - if (!(flags & ST)) - ret |= __get_user(ptr[i^7], addr + i); - else - ret |= __put_user(ptr[i^7], addr + i); + if (flags & SW) + sw = 7; + ret = 0; + for (i = 0; i < 8; ++i) { + if (!(flags & ST)) { + ret |= __get_user(ptr0[i^sw], addr + i); + ret |= __get_user(ptr1[i^sw], addr + i + 8); + } else { + ret |= __put_user(ptr0[i^sw], addr + i); + ret |= __put_user(ptr1[i^sw], addr + i + 8); } } if (ret) diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 70693a5c12a1..693b14a778fa 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -62,18 +62,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 72: std r8,8(r3) beq+ 3f addi r3,r3,16 -23: ld r9,8(r4) .Ldo_tail: bf cr7*4+1,1f - rotldi r9,r9,32 +23: lwz r9,8(r4) + addi r4,r4,4 73: stw r9,0(r3) addi r3,r3,4 1: bf cr7*4+2,2f - rotldi r9,r9,16 +44: lhz r9,8(r4) + addi r4,r4,2 74: sth r9,0(r3) addi r3,r3,2 2: bf cr7*4+3,3f - rotldi r9,r9,8 +45: lbz r9,8(r4) 75: stb r9,0(r3) 3: li r3,0 blr @@ -141,11 +142,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 6: cmpwi cr1,r5,8 addi r3,r3,32 sld r9,r9,r10 - ble cr1,.Ldo_tail + ble cr1,7f 34: ld r0,8(r4) srd r7,r0,r11 or r9,r7,r9 - b .Ldo_tail +7: + bf cr7*4+1,1f + rotldi r9,r9,32 +94: stw r9,0(r3) + addi r3,r3,4 +1: bf cr7*4+2,2f + rotldi r9,r9,16 +95: sth r9,0(r3) + addi r3,r3,2 +2: bf cr7*4+3,3f + rotldi r9,r9,8 +96: stb r9,0(r3) +3: li r3,0 + blr .Ldst_unaligned: PPC_MTOCRF 0x01,r6 /* put #bytes to 8B bdry into cr7 */ @@ -218,7 +232,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 121: 132: addi r3,r3,8 -123: 134: 135: 138: @@ -226,6 +239,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 140: 141: 142: +123: +144: +145: /* * here we have had a fault on a load and r3 points to the first @@ -309,6 +325,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 187: 188: 189: +194: +195: +196: 1: ld r6,-24(r1) ld r5,-8(r1) @@ -329,7 +348,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) .llong 72b,172b .llong 23b,123b .llong 73b,173b + .llong 44b,144b .llong 74b,174b + .llong 45b,145b .llong 75b,175b .llong 24b,124b .llong 25b,125b @@ -347,6 +368,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) .llong 79b,179b .llong 80b,180b .llong 34b,134b + .llong 94b,194b + .llong 95b,195b + .llong 96b,196b .llong 35b,135b .llong 81b,181b .llong 36b,136b diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index fe2d34e5332d..e178922b2c21 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -53,18 +53,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 3: std r8,8(r3) beq 3f addi r3,r3,16 - ld r9,8(r4) .Ldo_tail: bf cr7*4+1,1f - rotldi r9,r9,32 + lwz r9,8(r4) + addi r4,r4,4 stw r9,0(r3) addi r3,r3,4 1: bf cr7*4+2,2f - rotldi r9,r9,16 + lhz r9,8(r4) + addi r4,r4,2 sth r9,0(r3) addi r3,r3,2 2: bf cr7*4+3,3f - rotldi r9,r9,8 + lbz r9,8(r4) stb r9,0(r3) 3: ld r3,48(r1) /* return dest pointer */ blr @@ -133,11 +134,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) cmpwi cr1,r5,8 addi r3,r3,32 sld r9,r9,r10 - ble cr1,.Ldo_tail + ble cr1,6f ld r0,8(r4) srd r7,r0,r11 or r9,r7,r9 - b .Ldo_tail +6: + bf cr7*4+1,1f + rotldi r9,r9,32 + stw r9,0(r3) + addi r3,r3,4 +1: bf cr7*4+2,2f + rotldi r9,r9,16 + sth r9,0(r3) + addi r3,r3,2 +2: bf cr7*4+3,3f + rotldi r9,r9,8 + stb r9,0(r3) +3: ld r3,48(r1) /* return dest pointer */ + blr .Ldst_unaligned: PPC_MTOCRF 0x01,r6 # put #bytes to 8B bdry into cr7 diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index 77fae5f64f2e..5558d932b4d5 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -204,6 +204,23 @@ static int __init ppc4xx_setup_one_pci_PMM(struct pci_controller *hose, { u32 ma, pcila, pciha; + /* Hack warning ! The "old" PCI 2.x cell only let us configure the low + * 32-bit of incoming PLB addresses. The top 4 bits of the 36-bit + * address are actually hard wired to a value that appears to depend + * on the specific SoC. For example, it's 0 on 440EP and 1 on 440EPx. + * + * The trick here is we just crop those top bits and ignore them when + * programming the chip. That means the device-tree has to be right + * for the specific part used (we don't print a warning if it's wrong + * but on the other hand, you'll crash quickly enough), but at least + * this code should work whatever the hard coded value is + */ + plb_addr &= 0xffffffffull; + + /* Note: Due to the above hack, the test below doesn't actually test + * if you address is above 4G, but it tests that address and + * (address + size) are both contained in the same 4G + */ if ((plb_addr + size) > 0xffffffffull || !is_power_of_2(size) || size < 0x1000 || (plb_addr & (size - 1)) != 0) { printk(KERN_WARNING "%s: Resource out of range\n", diff --git a/block/blk-merge.c b/block/blk-merge.c index b92f5b0866b0..a104593e70c3 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -38,72 +38,84 @@ void blk_recalc_rq_sectors(struct request *rq, int nsect) } } -void blk_recalc_rq_segments(struct request *rq) +static unsigned int __blk_recalc_rq_segments(struct request_queue *q, + struct bio *bio, + unsigned int *seg_size_ptr) { - int nr_phys_segs; unsigned int phys_size; struct bio_vec *bv, *bvprv = NULL; - int seg_size; - int cluster; - struct req_iterator iter; - int high, highprv = 1; - struct request_queue *q = rq->q; + int cluster, i, high, highprv = 1; + unsigned int seg_size, nr_phys_segs; + struct bio *fbio; - if (!rq->bio) - return; + if (!bio) + return 0; + fbio = bio; cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); seg_size = 0; phys_size = nr_phys_segs = 0; - rq_for_each_segment(bv, rq, iter) { - /* - * the trick here is making sure that a high page is never - * considered part of another segment, since that might - * change with the bounce page. - */ - high = page_to_pfn(bv->bv_page) > q->bounce_pfn; - if (high || highprv) - goto new_segment; - if (cluster) { - if (seg_size + bv->bv_len > q->max_segment_size) - goto new_segment; - if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv)) - goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv)) + for_each_bio(bio) { + bio_for_each_segment(bv, bio, i) { + /* + * the trick here is making sure that a high page is + * never considered part of another segment, since that + * might change with the bounce page. + */ + high = page_to_pfn(bv->bv_page) > q->bounce_pfn; + if (high || highprv) goto new_segment; + if (cluster) { + if (seg_size + bv->bv_len > q->max_segment_size) + goto new_segment; + if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv)) + goto new_segment; + if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv)) + goto new_segment; + + seg_size += bv->bv_len; + bvprv = bv; + continue; + } +new_segment: + if (nr_phys_segs == 1 && seg_size > + fbio->bi_seg_front_size) + fbio->bi_seg_front_size = seg_size; - seg_size += bv->bv_len; + nr_phys_segs++; bvprv = bv; - continue; + seg_size = bv->bv_len; + highprv = high; } -new_segment: - if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size) - rq->bio->bi_seg_front_size = seg_size; - - nr_phys_segs++; - bvprv = bv; - seg_size = bv->bv_len; - highprv = high; } - if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size) + if (seg_size_ptr) + *seg_size_ptr = seg_size; + + return nr_phys_segs; +} + +void blk_recalc_rq_segments(struct request *rq) +{ + unsigned int seg_size = 0, phys_segs; + + phys_segs = __blk_recalc_rq_segments(rq->q, rq->bio, &seg_size); + + if (phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size) rq->bio->bi_seg_front_size = seg_size; if (seg_size > rq->biotail->bi_seg_back_size) rq->biotail->bi_seg_back_size = seg_size; - rq->nr_phys_segments = nr_phys_segs; + rq->nr_phys_segments = phys_segs; } void blk_recount_segments(struct request_queue *q, struct bio *bio) { - struct request rq; struct bio *nxt = bio->bi_next; - rq.q = q; - rq.bio = rq.biotail = bio; + bio->bi_next = NULL; - blk_recalc_rq_segments(&rq); + bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, NULL); bio->bi_next = nxt; - bio->bi_phys_segments = rq.nr_phys_segments; bio->bi_flags |= (1 << BIO_SEG_VALID); } EXPORT_SYMBOL(blk_recount_segments); diff --git a/block/genhd.c b/block/genhd.c index e1eadcc9546a..a9ec910974c1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -256,6 +256,22 @@ void blkdev_show(struct seq_file *seqf, off_t offset) } #endif /* CONFIG_PROC_FS */ +/** + * register_blkdev - register a new block device + * + * @major: the requested major device number [1..255]. If @major=0, try to + * allocate any unused major number. + * @name: the name of the new block device as a zero terminated string + * + * The @name must be unique within the system. + * + * The return value depends on the @major input parameter. + * - if a major device number was requested in range [1..255] then the + * function returns zero on success, or a negative error code + * - if any unused major number was requested with @major=0 parameter + * then the return value is the allocated major number in range + * [1..255] or a negative error code otherwise + */ int register_blkdev(unsigned int major, const char *name) { struct blk_major_name **n, *p; diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index d2cb67b61176..b5a061114630 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -3611,11 +3611,15 @@ static int __devinit cciss_init_one(struct pci_dev *pdev, schedule_timeout_uninterruptible(30*HZ); /* Now try to get the controller to respond to a no-op */ - for (i=0; i<12; i++) { + for (i=0; i<30; i++) { if (cciss_noop(pdev) == 0) break; - else - printk("cciss: no-op failed%s\n", (i < 11 ? "; re-trying" : "")); + + schedule_timeout_uninterruptible(HZ); + } + if (i == 30) { + printk(KERN_ERR "cciss: controller seems dead\n"); + return -EBUSY; } } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 918ef725de41..b6c8ce254359 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -40,6 +40,7 @@ #include <linux/hdreg.h> #include <linux/cdrom.h> #include <linux/module.h> +#include <linux/scatterlist.h> #include <xen/xenbus.h> #include <xen/grant_table.h> @@ -82,6 +83,7 @@ struct blkfront_info enum blkif_state connected; int ring_ref; struct blkif_front_ring ring; + struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; unsigned int evtchn, irq; struct request_queue *rq; struct work_struct work; @@ -204,12 +206,11 @@ static int blkif_queue_request(struct request *req) struct blkfront_info *info = req->rq_disk->private_data; unsigned long buffer_mfn; struct blkif_request *ring_req; - struct req_iterator iter; - struct bio_vec *bvec; unsigned long id; unsigned int fsect, lsect; - int ref; + int i, ref; grant_ref_t gref_head; + struct scatterlist *sg; if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) return 1; @@ -238,12 +239,13 @@ static int blkif_queue_request(struct request *req) if (blk_barrier_rq(req)) ring_req->operation = BLKIF_OP_WRITE_BARRIER; - ring_req->nr_segments = 0; - rq_for_each_segment(bvec, req, iter) { - BUG_ON(ring_req->nr_segments == BLKIF_MAX_SEGMENTS_PER_REQUEST); - buffer_mfn = pfn_to_mfn(page_to_pfn(bvec->bv_page)); - fsect = bvec->bv_offset >> 9; - lsect = fsect + (bvec->bv_len >> 9) - 1; + ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); + BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST); + + for_each_sg(info->sg, sg, ring_req->nr_segments, i) { + buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg))); + fsect = sg->offset >> 9; + lsect = fsect + (sg->length >> 9) - 1; /* install a grant reference. */ ref = gnttab_claim_grant_reference(&gref_head); BUG_ON(ref == -ENOSPC); @@ -254,16 +256,12 @@ static int blkif_queue_request(struct request *req) buffer_mfn, rq_data_dir(req) ); - info->shadow[id].frame[ring_req->nr_segments] = - mfn_to_pfn(buffer_mfn); - - ring_req->seg[ring_req->nr_segments] = + info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn); + ring_req->seg[i] = (struct blkif_request_segment) { .gref = ref, .first_sect = fsect, .last_sect = lsect }; - - ring_req->nr_segments++; } info->ring.req_prod_pvt++; @@ -622,6 +620,8 @@ static int setup_blkring(struct xenbus_device *dev, SHARED_RING_INIT(sring); FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE); + sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST); + err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring)); if (err < 0) { free_page((unsigned long)sring); diff --git a/drivers/ieee1394/ieee1394_core.c b/drivers/ieee1394/ieee1394_core.c index 1028e725a27e..872338003721 100644 --- a/drivers/ieee1394/ieee1394_core.c +++ b/drivers/ieee1394/ieee1394_core.c @@ -1275,7 +1275,7 @@ static void __exit ieee1394_cleanup(void) unregister_chrdev_region(IEEE1394_CORE_DEV, 256); } -module_init(ieee1394_init); +fs_initcall(ieee1394_init); module_exit(ieee1394_cleanup); /* Exported symbols */ diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index f26667a7abf7..cf991850f01b 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -710,6 +710,7 @@ out: static struct pci_device_id ilo_devices[] = { { PCI_DEVICE(PCI_VENDOR_ID_COMPAQ, 0xB204) }, + { PCI_DEVICE(PCI_VENDOR_ID_HP, 0x3307) }, { } }; MODULE_DEVICE_TABLE(pci, ilo_devices); @@ -758,7 +759,7 @@ static void __exit ilo_exit(void) class_destroy(ilo_class); } -MODULE_VERSION("0.06"); +MODULE_VERSION("1.0"); MODULE_ALIAS(ILO_NAME); MODULE_DESCRIPTION(ILO_NAME); MODULE_AUTHOR("David Altobelli <david.altobelli@hp.com>"); diff --git a/drivers/mtd/chips/map_rom.c b/drivers/mtd/chips/map_rom.c index 821d0ed6bae3..c76d6e5f47ee 100644 --- a/drivers/mtd/chips/map_rom.c +++ b/drivers/mtd/chips/map_rom.c @@ -19,6 +19,7 @@ static int maprom_read (struct mtd_info *, loff_t, size_t, size_t *, u_char *); static int maprom_write (struct mtd_info *, loff_t, size_t, size_t *, const u_char *); static void maprom_nop (struct mtd_info *); static struct mtd_info *map_rom_probe(struct map_info *map); +static int maprom_erase (struct mtd_info *mtd, struct erase_info *info); static struct mtd_chip_driver maprom_chipdrv = { .probe = map_rom_probe, @@ -42,6 +43,7 @@ static struct mtd_info *map_rom_probe(struct map_info *map) mtd->read = maprom_read; mtd->write = maprom_write; mtd->sync = maprom_nop; + mtd->erase = maprom_erase; mtd->flags = MTD_CAP_ROM; mtd->erasesize = map->size; mtd->writesize = 1; @@ -71,6 +73,12 @@ static int maprom_write (struct mtd_info *mtd, loff_t to, size_t len, size_t *re return -EIO; } +static int maprom_erase (struct mtd_info *mtd, struct erase_info *info) +{ + /* We do our best 8) */ + return -EROFS; +} + static int __init map_rom_init(void) { register_mtd_chip_driver(&maprom_chipdrv); diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c index a425d09f35a0..00248e81ecd5 100644 --- a/drivers/mtd/devices/slram.c +++ b/drivers/mtd/devices/slram.c @@ -267,22 +267,28 @@ static int parse_cmdline(char *devname, char *szstart, char *szlength) if (*(szlength) != '+') { devlength = simple_strtoul(szlength, &buffer, 0); devlength = handle_unit(devlength, buffer) - devstart; + if (devlength < devstart) + goto err_out; + + devlength -= devstart; } else { devlength = simple_strtoul(szlength + 1, &buffer, 0); devlength = handle_unit(devlength, buffer); } T("slram: devname=%s, devstart=0x%lx, devlength=0x%lx\n", devname, devstart, devlength); - if ((devstart < 0) || (devlength < 0) || (devlength % SLRAM_BLK_SZ != 0)) { - E("slram: Illegal start / length parameter.\n"); - return(-EINVAL); - } + if (devlength % SLRAM_BLK_SZ != 0) + goto err_out; if ((devstart = register_device(devname, devstart, devlength))){ unregister_devices(); return((int)devstart); } return(0); + +err_out: + E("slram: Illegal length parameter.\n"); + return(-EINVAL); } #ifndef MODULE diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig index acd4ea9b2278..5a401d8047ab 100644 --- a/drivers/mtd/lpddr/Kconfig +++ b/drivers/mtd/lpddr/Kconfig @@ -12,6 +12,7 @@ config MTD_LPDDR DDR memories, intended for battery-operated systems. config MTD_QINFO_PROBE + depends on MTD_LPDDR tristate "Detect flash chips by QINFO probe" help Device Information for LPDDR chips is offered through the Overlay diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index 0225cbbf22de..043d50fb6ef6 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -491,7 +491,7 @@ config MTD_PCMCIA_ANONYMOUS config MTD_BFIN_ASYNC tristate "Blackfin BF533-STAMP Flash Chip Support" - depends on BFIN533_STAMP && MTD_CFI + depends on BFIN533_STAMP && MTD_CFI && MTD_COMPLEX_MAPPINGS select MTD_PARTITIONS default y help diff --git a/drivers/mtd/maps/bfin-async-flash.c b/drivers/mtd/maps/bfin-async-flash.c index 6fec86aaed7e..576611f605db 100644 --- a/drivers/mtd/maps/bfin-async-flash.c +++ b/drivers/mtd/maps/bfin-async-flash.c @@ -152,14 +152,18 @@ static int __devinit bfin_flash_probe(struct platform_device *pdev) if (gpio_request(state->enet_flash_pin, DRIVER_NAME)) { pr_devinit(KERN_ERR DRIVER_NAME ": Failed to request gpio %d\n", state->enet_flash_pin); + kfree(state); return -EBUSY; } gpio_direction_output(state->enet_flash_pin, 1); pr_devinit(KERN_NOTICE DRIVER_NAME ": probing %d-bit flash bus\n", state->map.bankwidth * 8); state->mtd = do_map_probe(memory->name, &state->map); - if (!state->mtd) + if (!state->mtd) { + gpio_free(state->enet_flash_pin); + kfree(state); return -ENXIO; + } #ifdef CONFIG_MTD_PARTITIONS ret = parse_mtd_partitions(state->mtd, part_probe_types, &pdata->parts, 0); diff --git a/drivers/mtd/maps/ck804xrom.c b/drivers/mtd/maps/ck804xrom.c index 5f7a245ed132..424f17d6ffd1 100644 --- a/drivers/mtd/maps/ck804xrom.c +++ b/drivers/mtd/maps/ck804xrom.c @@ -342,9 +342,9 @@ static struct pci_device_id ck804xrom_pci_tbl[] = { { 0, } }; +#if 0 MODULE_DEVICE_TABLE(pci, ck804xrom_pci_tbl); -#if 0 static struct pci_driver ck804xrom_driver = { .name = MOD_NAME, .id_table = ck804xrom_pci_tbl, diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c index 87743661d48e..4b122e7ab4b3 100644 --- a/drivers/mtd/maps/physmap.c +++ b/drivers/mtd/maps/physmap.c @@ -29,6 +29,7 @@ struct physmap_flash_info { struct map_info map[MAX_RESOURCES]; #ifdef CONFIG_MTD_PARTITIONS int nr_parts; + struct mtd_partition *parts; #endif }; @@ -45,25 +46,26 @@ static int physmap_flash_remove(struct platform_device *dev) physmap_data = dev->dev.platform_data; -#ifdef CONFIG_MTD_CONCAT - if (info->cmtd != info->mtd[0]) { +#ifdef CONFIG_MTD_PARTITIONS + if (info->nr_parts) { + del_mtd_partitions(info->cmtd); + kfree(info->parts); + } else if (physmap_data->nr_parts) + del_mtd_partitions(info->cmtd); + else del_mtd_device(info->cmtd); +#else + del_mtd_device(info->cmtd); +#endif + +#ifdef CONFIG_MTD_CONCAT + if (info->cmtd != info->mtd[0]) mtd_concat_destroy(info->cmtd); - } #endif for (i = 0; i < MAX_RESOURCES; i++) { - if (info->mtd[i] != NULL) { -#ifdef CONFIG_MTD_PARTITIONS - if (info->nr_parts || physmap_data->nr_parts) - del_mtd_partitions(info->mtd[i]); - else - del_mtd_device(info->mtd[i]); -#else - del_mtd_device(info->mtd[i]); -#endif + if (info->mtd[i] != NULL) map_destroy(info->mtd[i]); - } } return 0; } @@ -86,9 +88,6 @@ static int physmap_flash_probe(struct platform_device *dev) int err = 0; int i; int devices_found = 0; -#ifdef CONFIG_MTD_PARTITIONS - struct mtd_partition *parts; -#endif physmap_data = dev->dev.platform_data; if (physmap_data == NULL) @@ -167,10 +166,11 @@ static int physmap_flash_probe(struct platform_device *dev) goto err_out; #ifdef CONFIG_MTD_PARTITIONS - err = parse_mtd_partitions(info->cmtd, part_probe_types, &parts, 0); + err = parse_mtd_partitions(info->cmtd, part_probe_types, + &info->parts, 0); if (err > 0) { - add_mtd_partitions(info->cmtd, parts, err); - kfree(parts); + add_mtd_partitions(info->cmtd, info->parts, err); + info->nr_parts = err; return 0; } diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index db85284ffb62..39ae37589fda 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -111,6 +111,7 @@ struct controller { int cmd_busy; unsigned int no_cmd_complete:1; unsigned int link_active_reporting:1; + unsigned int notification_enabled:1; }; #define INT_BUTTON_IGNORE 0 @@ -170,6 +171,7 @@ extern int pciehp_configure_device(struct slot *p_slot); extern int pciehp_unconfigure_device(struct slot *p_slot); extern void pciehp_queue_pushbutton_work(struct work_struct *work); struct controller *pcie_init(struct pcie_device *dev); +int pcie_init_notification(struct controller *ctrl); int pciehp_enable_slot(struct slot *p_slot); int pciehp_disable_slot(struct slot *p_slot); int pcie_enable_notification(struct controller *ctrl); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index c2485542f543..681e3912b821 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -434,6 +434,13 @@ static int pciehp_probe(struct pcie_device *dev, const struct pcie_port_service_ goto err_out_release_ctlr; } + /* Enable events after we have setup the data structures */ + rc = pcie_init_notification(ctrl); + if (rc) { + ctrl_err(ctrl, "Notification initialization failed\n"); + goto err_out_release_ctlr; + } + /* Check if slot is occupied */ t_slot = pciehp_find_slot(ctrl, ctrl->slot_device_offset); t_slot->hpc_ops->get_adapter_status(t_slot, &value); diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 71a8012886b0..7a16c6897bb9 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -934,7 +934,7 @@ static void pcie_disable_notification(struct controller *ctrl) ctrl_warn(ctrl, "Cannot disable software notification\n"); } -static int pcie_init_notification(struct controller *ctrl) +int pcie_init_notification(struct controller *ctrl) { if (pciehp_request_irq(ctrl)) return -1; @@ -942,13 +942,17 @@ static int pcie_init_notification(struct controller *ctrl) pciehp_free_irq(ctrl); return -1; } + ctrl->notification_enabled = 1; return 0; } static void pcie_shutdown_notification(struct controller *ctrl) { - pcie_disable_notification(ctrl); - pciehp_free_irq(ctrl); + if (ctrl->notification_enabled) { + pcie_disable_notification(ctrl); + pciehp_free_irq(ctrl); + ctrl->notification_enabled = 0; + } } static int pcie_init_slot(struct controller *ctrl) @@ -1110,13 +1114,8 @@ struct controller *pcie_init(struct pcie_device *dev) if (pcie_init_slot(ctrl)) goto abort_ctrl; - if (pcie_init_notification(ctrl)) - goto abort_slot; - return ctrl; -abort_slot: - pcie_cleanup_slot(ctrl); abort_ctrl: kfree(ctrl); abort: diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index aac7006949f1..d0c973685868 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -108,6 +108,34 @@ int pci_cleanup_aer_correct_error_status(struct pci_dev *dev) } #endif /* 0 */ + +static void set_device_error_reporting(struct pci_dev *dev, void *data) +{ + bool enable = *((bool *)data); + + if (dev->pcie_type != PCIE_RC_PORT && + dev->pcie_type != PCIE_SW_UPSTREAM_PORT && + dev->pcie_type != PCIE_SW_DOWNSTREAM_PORT) + return; + + if (enable) + pci_enable_pcie_error_reporting(dev); + else + pci_disable_pcie_error_reporting(dev); +} + +/** + * set_downstream_devices_error_reporting - enable/disable the error reporting bits on the root port and its downstream ports. + * @dev: pointer to root port's pci_dev data structure + * @enable: true = enable error reporting, false = disable error reporting. + */ +static void set_downstream_devices_error_reporting(struct pci_dev *dev, + bool enable) +{ + set_device_error_reporting(dev, &enable); + pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable); +} + static int find_device_iter(struct device *device, void *data) { struct pci_dev *dev; @@ -525,15 +553,11 @@ void aer_enable_rootport(struct aer_rpc *rpc) pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, ®32); pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32); - /* Enable Root Port device reporting error itself */ - pci_read_config_word(pdev, pos+PCI_EXP_DEVCTL, ®16); - reg16 = reg16 | - PCI_EXP_DEVCTL_CERE | - PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE; - pci_write_config_word(pdev, pos+PCI_EXP_DEVCTL, - reg16); + /* + * Enable error reporting for the root port device and downstream port + * devices. + */ + set_downstream_devices_error_reporting(pdev, true); /* Enable Root Port's interrupt in response to error messages */ pci_write_config_dword(pdev, @@ -553,6 +577,12 @@ static void disable_root_aer(struct aer_rpc *rpc) u32 reg32; int pos; + /* + * Disable error reporting for the root port device and downstream port + * devices. + */ + set_downstream_devices_error_reporting(pdev, false); + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); /* Disable Root's interrupt in response to error messages */ pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, 0); diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index f9b874eaeb9f..248b4db91552 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -97,8 +97,6 @@ static int __devinit pcie_portdrv_probe (struct pci_dev *dev, pcie_portdrv_save_config(dev); - pci_enable_pcie_error_reporting(dev); - return 0; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index baad093aafe3..f20d55368edb 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1584,6 +1584,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_ */ #define AMD_813X_MISC 0x40 #define AMD_813X_NOIOAMODE (1<<0) +#define AMD_813X_REV_B2 0x13 static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev) { @@ -1591,6 +1592,8 @@ static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev) if (noioapicquirk) return; + if (dev->revision == AMD_813X_REV_B2) + return; pci_read_config_dword(dev, AMD_813X_MISC, &pci_config_dword); pci_config_dword &= ~AMD_813X_NOIOAMODE; @@ -1981,7 +1984,6 @@ static void __devinit quirk_msi_ht_cap(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE, quirk_msi_ht_cap); - /* The nVidia CK804 chipset may have 2 HT MSI mappings. * MSI are supported if the MSI capability set in any of these mappings. */ @@ -2032,6 +2034,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000_PXB, ht_enable_msi_mapping); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE, + ht_enable_msi_mapping); + /* The P5N32-SLI Premium motherboard from Asus has a problem with msi * for the MCP55 NIC. It is not yet determined whether the msi problem * also affects other devices. As for now, turn off msi for this device. @@ -2048,10 +2053,100 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_15, nvenet_msi_disable); -static void __devinit nv_msi_ht_cap_quirk(struct pci_dev *dev) +static void __devinit nv_ht_enable_msi_mapping(struct pci_dev *dev) { struct pci_dev *host_bridge; + int pos; + int i, dev_no; + int found = 0; + + dev_no = dev->devfn >> 3; + for (i = dev_no; i >= 0; i--) { + host_bridge = pci_get_slot(dev->bus, PCI_DEVFN(i, 0)); + if (!host_bridge) + continue; + + pos = pci_find_ht_capability(host_bridge, HT_CAPTYPE_SLAVE); + if (pos != 0) { + found = 1; + break; + } + pci_dev_put(host_bridge); + } + + if (!found) + return; + + /* root did that ! */ + if (msi_ht_cap_enabled(host_bridge)) + goto out; + + ht_enable_msi_mapping(dev); + +out: + pci_dev_put(host_bridge); +} + +static void __devinit ht_disable_msi_mapping(struct pci_dev *dev) +{ + int pos, ttl = 48; + + pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING); + while (pos && ttl--) { + u8 flags; + + if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS, + &flags) == 0) { + dev_info(&dev->dev, "Enabling HT MSI Mapping\n"); + + pci_write_config_byte(dev, pos + HT_MSI_FLAGS, + flags & ~HT_MSI_FLAGS_ENABLE); + } + pos = pci_find_next_ht_capability(dev, pos, + HT_CAPTYPE_MSI_MAPPING); + } +} + +static int __devinit ht_check_msi_mapping(struct pci_dev *dev) +{ int pos, ttl = 48; + int found = 0; + + /* check if there is HT MSI cap or enabled on this device */ + pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING); + while (pos && ttl--) { + u8 flags; + + if (found < 1) + found = 1; + if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS, + &flags) == 0) { + if (flags & HT_MSI_FLAGS_ENABLE) { + if (found < 2) { + found = 2; + break; + } + } + } + pos = pci_find_next_ht_capability(dev, pos, + HT_CAPTYPE_MSI_MAPPING); + } + + return found; +} + +static void __devinit nv_msi_ht_cap_quirk(struct pci_dev *dev) +{ + struct pci_dev *host_bridge; + int pos; + int found; + + /* check if there is HT MSI cap or enabled on this device */ + found = ht_check_msi_mapping(dev); + + /* no HT MSI CAP */ + if (found == 0) + return; /* * HT MSI mapping should be disabled on devices that are below @@ -2067,24 +2162,19 @@ static void __devinit nv_msi_ht_cap_quirk(struct pci_dev *dev) pos = pci_find_ht_capability(host_bridge, HT_CAPTYPE_SLAVE); if (pos != 0) { /* Host bridge is to HT */ - ht_enable_msi_mapping(dev); + if (found == 1) { + /* it is not enabled, try to enable it */ + nv_ht_enable_msi_mapping(dev); + } return; } - /* Host bridge is not to HT, disable HT MSI mapping on this device */ - pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING); - while (pos && ttl--) { - u8 flags; + /* HT MSI is not enabled */ + if (found == 1) + return; - if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS, - &flags) == 0) { - dev_info(&dev->dev, "Disabling HT MSI mapping"); - pci_write_config_byte(dev, pos + HT_MSI_FLAGS, - flags & ~HT_MSI_FLAGS_ENABLE); - } - pos = pci_find_next_ht_capability(dev, pos, - HT_CAPTYPE_MSI_MAPPING); - } + /* Host bridge is not to HT, disable HT MSI mapping on this device */ + ht_disable_msi_mapping(dev); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk); diff --git a/drivers/w1/slaves/Kconfig b/drivers/w1/slaves/Kconfig index 8d0b1fb1e52e..1f51366417b9 100644 --- a/drivers/w1/slaves/Kconfig +++ b/drivers/w1/slaves/Kconfig @@ -16,6 +16,12 @@ config W1_SLAVE_SMEM Say Y here if you want to connect 1-wire simple 64bit memory rom(ds2401/ds2411/ds1990*) to your wire. +config W1_SLAVE_DS2431 + tristate "1kb EEPROM family support (DS2431)" + help + Say Y here if you want to use a 1-wire + 1kb EEPROM family device (DS2431) + config W1_SLAVE_DS2433 tristate "4kb EEPROM family support (DS2433)" help diff --git a/drivers/w1/slaves/Makefile b/drivers/w1/slaves/Makefile index 990f400b6d22..f1f51f19b129 100644 --- a/drivers/w1/slaves/Makefile +++ b/drivers/w1/slaves/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_W1_SLAVE_THERM) += w1_therm.o obj-$(CONFIG_W1_SLAVE_SMEM) += w1_smem.o +obj-$(CONFIG_W1_SLAVE_DS2431) += w1_ds2431.o obj-$(CONFIG_W1_SLAVE_DS2433) += w1_ds2433.o obj-$(CONFIG_W1_SLAVE_DS2760) += w1_ds2760.o obj-$(CONFIG_W1_SLAVE_BQ27000) += w1_bq27000.o diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index 858c16a544c2..139447148822 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -156,6 +156,9 @@ out_up: */ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data) { +#ifdef CONFIG_W1_SLAVE_DS2433_CRC + struct w1_f23_data *f23 = sl->family_data; +#endif u8 wrbuf[4]; u8 rdbuf[W1_PAGE_SIZE + 3]; u8 es = (addr + len - 1) & 0x1f; @@ -196,7 +199,9 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data) /* Reset the bus to wake up the EEPROM (this may not be needed) */ w1_reset_bus(sl->master); - +#ifdef CONFIG_W1_SLAVE_DS2433_CRC + f23->validcrc &= ~(1 << (addr >> W1_PAGE_BITS)); +#endif return 0; } @@ -302,7 +302,7 @@ void bio_init(struct bio *bio) struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) { struct bio *bio = NULL; - void *p; + void *uninitialized_var(p); if (bs) { p = mempool_alloc(bs->bio_pool, gfp_mask); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index a8c9693b75ac..72677ce2b74f 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -66,6 +66,9 @@ struct btrfs_inode { */ struct list_head delalloc_inodes; + /* the space_info for where this inode's data allocations are done */ + struct btrfs_space_info *space_info; + /* full 64 bit generation number, struct vfs_inode doesn't have a big * enough field for this. */ @@ -94,6 +97,11 @@ struct btrfs_inode { */ u64 delalloc_bytes; + /* total number of bytes that may be used for this inode for + * delalloc + */ + u64 reserved_bytes; + /* * the size of the file stored in the metadata on disk. data=ordered * means the in-memory i_size might be larger than the size on disk diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 766b31ae3186..82491ba8fa40 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -596,13 +596,27 @@ struct btrfs_block_group_item { struct btrfs_space_info { u64 flags; - u64 total_bytes; - u64 bytes_used; - u64 bytes_pinned; - u64 bytes_reserved; - u64 bytes_readonly; - int full; - int force_alloc; + + u64 total_bytes; /* total bytes in the space */ + u64 bytes_used; /* total bytes used on disk */ + u64 bytes_pinned; /* total bytes pinned, will be freed when the + transaction finishes */ + u64 bytes_reserved; /* total bytes the allocator has reserved for + current allocations */ + u64 bytes_readonly; /* total bytes that are read only */ + + /* delalloc accounting */ + u64 bytes_delalloc; /* number of bytes reserved for allocation, + this space is not necessarily reserved yet + by the allocator */ + u64 bytes_may_use; /* number of bytes that may be used for + delalloc */ + + int full; /* indicates that we cannot allocate any more + chunks for this space */ + int force_alloc; /* set if we need to force a chunk alloc for + this space */ + struct list_head list; /* for block groups in our same type */ @@ -1782,6 +1796,16 @@ int btrfs_add_dead_reloc_root(struct btrfs_root *root); int btrfs_cleanup_reloc_trees(struct btrfs_root *root); int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags); +void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde); +int btrfs_check_metadata_free_space(struct btrfs_root *root); +int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode, + u64 bytes); +void btrfs_free_reserved_data_space(struct btrfs_root *root, + struct inode *inode, u64 bytes); +void btrfs_delalloc_reserve_space(struct btrfs_root *root, struct inode *inode, + u64 bytes); +void btrfs_delalloc_free_space(struct btrfs_root *root, struct inode *inode, + u64 bytes); /* ctree.c */ int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, @@ -2027,8 +2051,6 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, unsigned long btrfs_force_ra(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t offset, pgoff_t last_index); -int btrfs_check_free_space(struct btrfs_root *root, u64 num_required, - int for_del); int btrfs_page_mkwrite(struct vm_area_struct *vma, struct page *page); int btrfs_readpage(struct file *file, struct page *page); void btrfs_delete_inode(struct inode *inode); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0a5d796c9f7e..6b5966aacf44 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -60,6 +60,10 @@ static int update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, int alloc, int mark_free); +static int do_chunk_alloc(struct btrfs_trans_handle *trans, + struct btrfs_root *extent_root, u64 alloc_bytes, + u64 flags, int force); + static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits) { return (cache->flags & bits) == bits; @@ -1909,6 +1913,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_pinned = 0; found->bytes_reserved = 0; found->bytes_readonly = 0; + found->bytes_delalloc = 0; found->full = 0; found->force_alloc = 0; *space_info = found; @@ -1972,6 +1977,233 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags) return flags; } +static u64 btrfs_get_alloc_profile(struct btrfs_root *root, u64 data) +{ + struct btrfs_fs_info *info = root->fs_info; + u64 alloc_profile; + + if (data) { + alloc_profile = info->avail_data_alloc_bits & + info->data_alloc_profile; + data = BTRFS_BLOCK_GROUP_DATA | alloc_profile; + } else if (root == root->fs_info->chunk_root) { + alloc_profile = info->avail_system_alloc_bits & + info->system_alloc_profile; + data = BTRFS_BLOCK_GROUP_SYSTEM | alloc_profile; + } else { + alloc_profile = info->avail_metadata_alloc_bits & + info->metadata_alloc_profile; + data = BTRFS_BLOCK_GROUP_METADATA | alloc_profile; + } + + return btrfs_reduce_alloc_profile(root, data); +} + +void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *inode) +{ + u64 alloc_target; + + alloc_target = btrfs_get_alloc_profile(root, 1); + BTRFS_I(inode)->space_info = __find_space_info(root->fs_info, + alloc_target); +} + +/* + * for now this just makes sure we have at least 5% of our metadata space free + * for use. + */ +int btrfs_check_metadata_free_space(struct btrfs_root *root) +{ + struct btrfs_fs_info *info = root->fs_info; + struct btrfs_space_info *meta_sinfo; + u64 alloc_target, thresh; + int committed = 0, ret; + + /* get the space info for where the metadata will live */ + alloc_target = btrfs_get_alloc_profile(root, 0); + meta_sinfo = __find_space_info(info, alloc_target); + +again: + spin_lock(&meta_sinfo->lock); + if (!meta_sinfo->full) + thresh = meta_sinfo->total_bytes * 80; + else + thresh = meta_sinfo->total_bytes * 95; + + do_div(thresh, 100); + + if (meta_sinfo->bytes_used + meta_sinfo->bytes_reserved + + meta_sinfo->bytes_pinned + meta_sinfo->bytes_readonly > thresh) { + struct btrfs_trans_handle *trans; + if (!meta_sinfo->full) { + meta_sinfo->force_alloc = 1; + spin_unlock(&meta_sinfo->lock); + + trans = btrfs_start_transaction(root, 1); + if (!trans) + return -ENOMEM; + + ret = do_chunk_alloc(trans, root->fs_info->extent_root, + 2 * 1024 * 1024, alloc_target, 0); + btrfs_end_transaction(trans, root); + goto again; + } + spin_unlock(&meta_sinfo->lock); + + if (!committed) { + committed = 1; + trans = btrfs_join_transaction(root, 1); + if (!trans) + return -ENOMEM; + ret = btrfs_commit_transaction(trans, root); + if (ret) + return ret; + goto again; + } + return -ENOSPC; + } + spin_unlock(&meta_sinfo->lock); + + return 0; +} + +/* + * This will check the space that the inode allocates from to make sure we have + * enough space for bytes. + */ +int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode, + u64 bytes) +{ + struct btrfs_space_info *data_sinfo; + int ret = 0, committed = 0; + + /* make sure bytes are sectorsize aligned */ + bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1); + + data_sinfo = BTRFS_I(inode)->space_info; +again: + /* make sure we have enough space to handle the data first */ + spin_lock(&data_sinfo->lock); + if (data_sinfo->total_bytes - data_sinfo->bytes_used - + data_sinfo->bytes_delalloc - data_sinfo->bytes_reserved - + data_sinfo->bytes_pinned - data_sinfo->bytes_readonly - + data_sinfo->bytes_may_use < bytes) { + struct btrfs_trans_handle *trans; + + /* + * if we don't have enough free bytes in this space then we need + * to alloc a new chunk. + */ + if (!data_sinfo->full) { + u64 alloc_target; + + data_sinfo->force_alloc = 1; + spin_unlock(&data_sinfo->lock); + + alloc_target = btrfs_get_alloc_profile(root, 1); + trans = btrfs_start_transaction(root, 1); + if (!trans) + return -ENOMEM; + + ret = do_chunk_alloc(trans, root->fs_info->extent_root, + bytes + 2 * 1024 * 1024, + alloc_target, 0); + btrfs_end_transaction(trans, root); + if (ret) + return ret; + goto again; + } + spin_unlock(&data_sinfo->lock); + + /* commit the current transaction and try again */ + if (!committed) { + committed = 1; + trans = btrfs_join_transaction(root, 1); + if (!trans) + return -ENOMEM; + ret = btrfs_commit_transaction(trans, root); + if (ret) + return ret; + goto again; + } + + printk(KERN_ERR "no space left, need %llu, %llu delalloc bytes" + ", %llu bytes_used, %llu bytes_reserved, " + "%llu bytes_pinned, %llu bytes_readonly, %llu may use" + "%llu total\n", bytes, data_sinfo->bytes_delalloc, + data_sinfo->bytes_used, data_sinfo->bytes_reserved, + data_sinfo->bytes_pinned, data_sinfo->bytes_readonly, + data_sinfo->bytes_may_use, data_sinfo->total_bytes); + return -ENOSPC; + } + data_sinfo->bytes_may_use += bytes; + BTRFS_I(inode)->reserved_bytes += bytes; + spin_unlock(&data_sinfo->lock); + + return btrfs_check_metadata_free_space(root); +} + +/* + * if there was an error for whatever reason after calling + * btrfs_check_data_free_space, call this so we can cleanup the counters. + */ +void btrfs_free_reserved_data_space(struct btrfs_root *root, + struct inode *inode, u64 bytes) +{ + struct btrfs_space_info *data_sinfo; + + /* make sure bytes are sectorsize aligned */ + bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1); + + data_sinfo = BTRFS_I(inode)->space_info; + spin_lock(&data_sinfo->lock); + data_sinfo->bytes_may_use -= bytes; + BTRFS_I(inode)->reserved_bytes -= bytes; + spin_unlock(&data_sinfo->lock); +} + +/* called when we are adding a delalloc extent to the inode's io_tree */ +void btrfs_delalloc_reserve_space(struct btrfs_root *root, struct inode *inode, + u64 bytes) +{ + struct btrfs_space_info *data_sinfo; + + /* get the space info for where this inode will be storing its data */ + data_sinfo = BTRFS_I(inode)->space_info; + + /* make sure we have enough space to handle the data first */ + spin_lock(&data_sinfo->lock); + data_sinfo->bytes_delalloc += bytes; + + /* + * we are adding a delalloc extent without calling + * btrfs_check_data_free_space first. This happens on a weird + * writepage condition, but shouldn't hurt our accounting + */ + if (unlikely(bytes > BTRFS_I(inode)->reserved_bytes)) { + data_sinfo->bytes_may_use -= BTRFS_I(inode)->reserved_bytes; + BTRFS_I(inode)->reserved_bytes = 0; + } else { + data_sinfo->bytes_may_use -= bytes; + BTRFS_I(inode)->reserved_bytes -= bytes; + } + + spin_unlock(&data_sinfo->lock); +} + +/* called when we are clearing an delalloc extent from the inode's io_tree */ +void btrfs_delalloc_free_space(struct btrfs_root *root, struct inode *inode, + u64 bytes) +{ + struct btrfs_space_info *info; + + info = BTRFS_I(inode)->space_info; + + spin_lock(&info->lock); + info->bytes_delalloc -= bytes; + spin_unlock(&info->lock); +} + static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 alloc_bytes, u64 flags, int force) @@ -3105,6 +3337,10 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes) (unsigned long long)(info->total_bytes - info->bytes_used - info->bytes_pinned - info->bytes_reserved), (info->full) ? "" : "not "); + printk(KERN_INFO "space_info total=%llu, pinned=%llu, delalloc=%llu," + " may_use=%llu, used=%llu\n", info->total_bytes, + info->bytes_pinned, info->bytes_delalloc, info->bytes_may_use, + info->bytes_used); down_read(&info->groups_sem); list_for_each_entry(cache, &info->block_groups, list) { @@ -3131,24 +3367,10 @@ static int __btrfs_reserve_extent(struct btrfs_trans_handle *trans, { int ret; u64 search_start = 0; - u64 alloc_profile; struct btrfs_fs_info *info = root->fs_info; - if (data) { - alloc_profile = info->avail_data_alloc_bits & - info->data_alloc_profile; - data = BTRFS_BLOCK_GROUP_DATA | alloc_profile; - } else if (root == root->fs_info->chunk_root) { - alloc_profile = info->avail_system_alloc_bits & - info->system_alloc_profile; - data = BTRFS_BLOCK_GROUP_SYSTEM | alloc_profile; - } else { - alloc_profile = info->avail_metadata_alloc_bits & - info->metadata_alloc_profile; - data = BTRFS_BLOCK_GROUP_METADATA | alloc_profile; - } + data = btrfs_get_alloc_profile(root, data); again: - data = btrfs_reduce_alloc_profile(root, data); /* * the only place that sets empty_size is btrfs_realloc_node, which * is not called recursively on allocations diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 872f104576e5..dc78954861b3 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1091,19 +1091,24 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, WARN_ON(num_pages > nrptrs); memset(pages, 0, sizeof(struct page *) * nrptrs); - ret = btrfs_check_free_space(root, write_bytes, 0); + ret = btrfs_check_data_free_space(root, inode, write_bytes); if (ret) goto out; ret = prepare_pages(root, file, pages, num_pages, pos, first_index, last_index, write_bytes); - if (ret) + if (ret) { + btrfs_free_reserved_data_space(root, inode, + write_bytes); goto out; + } ret = btrfs_copy_from_user(pos, num_pages, write_bytes, pages, buf); if (ret) { + btrfs_free_reserved_data_space(root, inode, + write_bytes); btrfs_drop_pages(pages, num_pages); goto out; } @@ -1111,8 +1116,11 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, ret = dirty_and_release_pages(NULL, root, file, pages, num_pages, pos, write_bytes); btrfs_drop_pages(pages, num_pages); - if (ret) + if (ret) { + btrfs_free_reserved_data_space(root, inode, + write_bytes); goto out; + } if (will_write) { btrfs_fdatawrite_range(inode->i_mapping, pos, @@ -1136,6 +1144,8 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, } out: mutex_unlock(&inode->i_mutex); + if (ret) + err = ret; out_nolock: kfree(pages); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3cee77ae03c8..7d4f948bc22a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -102,34 +102,6 @@ static int btrfs_init_inode_security(struct inode *inode, struct inode *dir) } /* - * a very lame attempt at stopping writes when the FS is 85% full. There - * are countless ways this is incorrect, but it is better than nothing. - */ -int btrfs_check_free_space(struct btrfs_root *root, u64 num_required, - int for_del) -{ - u64 total; - u64 used; - u64 thresh; - int ret = 0; - - spin_lock(&root->fs_info->delalloc_lock); - total = btrfs_super_total_bytes(&root->fs_info->super_copy); - used = btrfs_super_bytes_used(&root->fs_info->super_copy); - if (for_del) - thresh = total * 90; - else - thresh = total * 85; - - do_div(thresh, 100); - - if (used + root->fs_info->delalloc_bytes + num_required > thresh) - ret = -ENOSPC; - spin_unlock(&root->fs_info->delalloc_lock); - return ret; -} - -/* * this does all the hard work for inserting an inline extent into * the btree. The caller should have done a btrfs_drop_extents so that * no overlapping inline items exist in the btree @@ -1190,6 +1162,7 @@ static int btrfs_set_bit_hook(struct inode *inode, u64 start, u64 end, */ if (!(old & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) { struct btrfs_root *root = BTRFS_I(inode)->root; + btrfs_delalloc_reserve_space(root, inode, end - start + 1); spin_lock(&root->fs_info->delalloc_lock); BTRFS_I(inode)->delalloc_bytes += end - start + 1; root->fs_info->delalloc_bytes += end - start + 1; @@ -1223,9 +1196,12 @@ static int btrfs_clear_bit_hook(struct inode *inode, u64 start, u64 end, (unsigned long long)end - start + 1, (unsigned long long) root->fs_info->delalloc_bytes); + btrfs_delalloc_free_space(root, inode, (u64)-1); root->fs_info->delalloc_bytes = 0; BTRFS_I(inode)->delalloc_bytes = 0; } else { + btrfs_delalloc_free_space(root, inode, + end - start + 1); root->fs_info->delalloc_bytes -= end - start + 1; BTRFS_I(inode)->delalloc_bytes -= end - start + 1; } @@ -2245,10 +2221,6 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) root = BTRFS_I(dir)->root; - ret = btrfs_check_free_space(root, 1, 1); - if (ret) - goto fail; - trans = btrfs_start_transaction(root, 1); btrfs_set_trans_block_group(trans, dir); @@ -2261,7 +2233,6 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) nr = trans->blocks_used; btrfs_end_transaction_throttle(trans, root); -fail: btrfs_btree_balance_dirty(root, nr); return ret; } @@ -2284,10 +2255,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) return -ENOTEMPTY; } - ret = btrfs_check_free_space(root, 1, 1); - if (ret) - goto fail; - trans = btrfs_start_transaction(root, 1); btrfs_set_trans_block_group(trans, dir); @@ -2304,7 +2271,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) fail_trans: nr = trans->blocks_used; ret = btrfs_end_transaction_throttle(trans, root); -fail: btrfs_btree_balance_dirty(root, nr); if (ret && !err) @@ -2818,7 +2784,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t size) if (size <= hole_start) return 0; - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) return err; @@ -3014,6 +2980,7 @@ static noinline void init_btrfs_i(struct inode *inode) bi->last_trans = 0; bi->logged_trans = 0; bi->delalloc_bytes = 0; + bi->reserved_bytes = 0; bi->disk_i_size = 0; bi->flags = 0; bi->index_cnt = (u64)-1; @@ -3035,6 +3002,7 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p) inode->i_ino = args->ino; init_btrfs_i(inode); BTRFS_I(inode)->root = args->root; + btrfs_set_inode_space_info(args->root, inode); return 0; } @@ -3455,6 +3423,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, BTRFS_I(inode)->index_cnt = 2; BTRFS_I(inode)->root = root; BTRFS_I(inode)->generation = trans->transid; + btrfs_set_inode_space_info(root, inode); if (mode & S_IFDIR) owner = 0; @@ -3602,7 +3571,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (!new_valid_dev(rdev)) return -EINVAL; - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) goto fail; @@ -3665,7 +3634,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, u64 objectid; u64 index = 0; - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) goto fail; trans = btrfs_start_transaction(root, 1); @@ -3733,7 +3702,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, return -ENOENT; btrfs_inc_nlink(inode); - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) goto fail; err = btrfs_set_inode_index(dir, &index); @@ -3779,7 +3748,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) u64 index = 0; unsigned long nr = 1; - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) goto out_unlock; @@ -4336,7 +4305,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct page *page) u64 page_start; u64 page_end; - ret = btrfs_check_free_space(root, PAGE_CACHE_SIZE, 0); + ret = btrfs_check_data_free_space(root, inode, PAGE_CACHE_SIZE); if (ret) goto out; @@ -4349,6 +4318,7 @@ again: if ((page->mapping != inode->i_mapping) || (page_start >= size)) { + btrfs_free_reserved_data_space(root, inode, PAGE_CACHE_SIZE); /* page got truncated out from underneath us */ goto out_unlock; } @@ -4631,7 +4601,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) return -EXDEV; - ret = btrfs_check_free_space(root, 1, 0); + ret = btrfs_check_metadata_free_space(root); if (ret) goto out_unlock; @@ -4749,7 +4719,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(root)) return -ENAMETOOLONG; - err = btrfs_check_free_space(root, 1, 0); + err = btrfs_check_metadata_free_space(root); if (err) goto out_fail; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 988fdc8b49eb..bca729fc80c8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -70,7 +70,7 @@ static noinline int create_subvol(struct btrfs_root *root, u64 index = 0; unsigned long nr = 1; - ret = btrfs_check_free_space(root, 1, 0); + ret = btrfs_check_metadata_free_space(root); if (ret) goto fail_commit; @@ -203,7 +203,7 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, if (!root->ref_cows) return -EINVAL; - ret = btrfs_check_free_space(root, 1, 0); + ret = btrfs_check_metadata_free_space(root); if (ret) goto fail_unlock; @@ -374,7 +374,7 @@ static int btrfs_defrag_file(struct file *file) unsigned long i; int ret; - ret = btrfs_check_free_space(root, inode->i_size, 0); + ret = btrfs_check_data_free_space(root, inode, inode->i_size); if (ret) return -ENOSPC; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 39bd4d38e889..45e59d3c7f1f 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1913,6 +1913,9 @@ COMPATIBLE_IOCTL(FIONREAD) /* This is also TIOCINQ */ /* 0x00 */ COMPATIBLE_IOCTL(FIBMAP) COMPATIBLE_IOCTL(FIGETBSZ) +/* 'X' - originally XFS but some now in the VFS */ +COMPATIBLE_IOCTL(FIFREEZE) +COMPATIBLE_IOCTL(FITHAW) /* RAID */ COMPATIBLE_IOCTL(RAID_VERSION) COMPATIBLE_IOCTL(GET_ARRAY_INFO) diff --git a/fs/dcache.c b/fs/dcache.c index 937df0fb0da5..07e2d4a44bda 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1180,7 +1180,7 @@ struct dentry *d_obtain_alias(struct inode *inode) iput(inode); return res; } -EXPORT_SYMBOL_GPL(d_obtain_alias); +EXPORT_SYMBOL(d_obtain_alias); /** * d_splice_alias - splice a disconnected dentry into the tree if one exists diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 3cceef4ad2b7..e9580104b6ba 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -95,13 +95,17 @@ static int jffs2_garbage_collect_thread(void *_c) spin_unlock(&c->erase_completion_lock); - /* This thread is purely an optimisation. But if it runs when - other things could be running, it actually makes things a - lot worse. Use yield() and put it at the back of the runqueue - every time. Especially during boot, pulling an inode in - with read_inode() is much preferable to having the GC thread - get there first. */ - yield(); + /* Problem - immediately after bootup, the GCD spends a lot + * of time in places like jffs2_kill_fragtree(); so much so + * that userspace processes (like gdm and X) are starved + * despite plenty of cond_resched()s and renicing. Yield() + * doesn't help, either (presumably because userspace and GCD + * are generally competing for a higher latency resource - + * disk). + * This forces the GCD to slow the hell down. Pulling an + * inode in with read_inode() is much preferable to having + * the GC thread get there first. */ + schedule_timeout_interruptible(msecs_to_jiffies(50)); /* Put_super will send a SIGKILL and then wait on the sem. */ diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 6ca08ad887c0..1fc1e92356ee 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -220,7 +220,7 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c, struct jffs2_tmp_dnode_info *tn) { uint32_t fn_end = tn->fn->ofs + tn->fn->size; - struct jffs2_tmp_dnode_info *this; + struct jffs2_tmp_dnode_info *this, *ptn; dbg_readinode("insert fragment %#04x-%#04x, ver %u at %08x\n", tn->fn->ofs, fn_end, tn->version, ref_offset(tn->fn->raw)); @@ -251,11 +251,18 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c, if (this) { /* If the node is coincident with another at a lower address, back up until the other node is found. It may be relevant */ - while (this->overlapped) - this = tn_prev(this); - - /* First node should never be marked overlapped */ - BUG_ON(!this); + while (this->overlapped) { + ptn = tn_prev(this); + if (!ptn) { + /* + * We killed a node which set the overlapped + * flags during the scan. Fix it up. + */ + this->overlapped = 0; + break; + } + this = ptn; + } dbg_readinode("'this' found %#04x-%#04x (%s)\n", this->fn->ofs, this->fn->ofs + this->fn->size, this->fn ? "data" : "hole"); } @@ -360,7 +367,17 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c, } if (!this->overlapped) break; - this = tn_prev(this); + + ptn = tn_prev(this); + if (!ptn) { + /* + * We killed a node which set the overlapped + * flags during the scan. Fix it up. + */ + this->overlapped = 0; + break; + } + this = ptn; } } @@ -456,8 +473,15 @@ static int jffs2_build_inode_fragtree(struct jffs2_sb_info *c, eat_last(&rii->tn_root, &last->rb); ver_insert(&ver_root, last); - if (unlikely(last->overlapped)) - continue; + if (unlikely(last->overlapped)) { + if (pen) + continue; + /* + * We killed a node which set the overlapped + * flags during the scan. Fix it up. + */ + last->overlapped = 0; + } /* Now we have a bunch of nodes in reverse version order, in the tree at ver_root. Most of the time, diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 60fe74035db5..3a9e5deed74d 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -4796,6 +4796,29 @@ out: return ret; } +static int ocfs2_replace_extent_rec(struct inode *inode, + handle_t *handle, + struct ocfs2_path *path, + struct ocfs2_extent_list *el, + int split_index, + struct ocfs2_extent_rec *split_rec) +{ + int ret; + + ret = ocfs2_path_bh_journal_access(handle, inode, path, + path_num_items(path) - 1); + if (ret) { + mlog_errno(ret); + goto out; + } + + el->l_recs[split_index] = *split_rec; + + ocfs2_journal_dirty(handle, path_leaf_bh(path)); +out: + return ret; +} + /* * Mark part or all of the extent record at split_index in the leaf * pointed to by path as written. This removes the unwritten @@ -4885,7 +4908,9 @@ static int __ocfs2_mark_extent_written(struct inode *inode, if (ctxt.c_contig_type == CONTIG_NONE) { if (ctxt.c_split_covers_rec) - el->l_recs[split_index] = *split_rec; + ret = ocfs2_replace_extent_rec(inode, handle, + path, el, + split_index, split_rec); else ret = ocfs2_split_and_insert(inode, handle, path, et, &last_eb_bh, split_index, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 54e182a27caf..0a2813947853 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1849,12 +1849,12 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data, if (!mle) { if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN && res->owner != assert->node_idx) { - mlog(ML_ERROR, "assert_master from " - "%u, but current owner is " - "%u! (%.*s)\n", - assert->node_idx, res->owner, - namelen, name); - goto kill; + mlog(ML_ERROR, "DIE! Mastery assert from %u, " + "but current owner is %u! (%.*s)\n", + assert->node_idx, res->owner, namelen, + name); + __dlm_print_one_lock_resource(res); + BUG(); } } else if (mle->type != DLM_MLE_MIGRATION) { if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN) { diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index d1295203029f..4060bb328bc8 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -181,8 +181,7 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); /* This ensures that clear refmap is sent after the set */ - __dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_SETREF_INPROG | - DLM_LOCK_RES_MIGRATING)); + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); spin_unlock(&res->spinlock); /* clear our bit from the master's refmap, ignore errors */ diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 86ca085ef324..fcf879ed6930 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -117,11 +117,11 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, else BUG_ON(res->owner == dlm->node_num); - spin_lock(&dlm->spinlock); + spin_lock(&dlm->ast_lock); /* We want to be sure that we're not freeing a lock * that still has AST's pending... */ in_use = !list_empty(&lock->ast_list); - spin_unlock(&dlm->spinlock); + spin_unlock(&dlm->ast_lock); if (in_use) { mlog(ML_ERROR, "lockres %.*s: Someone is calling dlmunlock " "while waiting for an ast!", res->lockname.len, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 206a2370876a..7219a86d34cc 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -320,9 +320,14 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres); static inline void ocfs2_recover_from_dlm_error(struct ocfs2_lock_res *lockres, int convert); -#define ocfs2_log_dlm_error(_func, _err, _lockres) do { \ - mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n", \ - _err, _func, _lockres->l_name); \ +#define ocfs2_log_dlm_error(_func, _err, _lockres) do { \ + if ((_lockres)->l_type != OCFS2_LOCK_TYPE_DENTRY) \ + mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n", \ + _err, _func, _lockres->l_name); \ + else \ + mlog(ML_ERROR, "DLM error %d while calling %s on resource %.*s%08x\n", \ + _err, _func, OCFS2_DENTRY_LOCK_INO_START - 1, (_lockres)->l_name, \ + (unsigned int)ocfs2_get_dentry_lock_ino(_lockres)); \ } while (0) static int ocfs2_downconvert_thread(void *arg); static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 077384135f4e..946d3c34b90b 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -341,6 +341,9 @@ struct ocfs2_super struct ocfs2_node_map osb_recovering_orphan_dirs; unsigned int *osb_orphan_wipes; wait_queue_head_t osb_wipe_event; + + /* used to protect metaecc calculation check of xattr. */ + spinlock_t osb_xattr_lock; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index b1cb38fbe807..7ac83a81ee55 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1537,6 +1537,13 @@ static int ocfs2_get_sector(struct super_block *sb, unlock_buffer(*bh); ll_rw_block(READ, 1, bh); wait_on_buffer(*bh); + if (!buffer_uptodate(*bh)) { + mlog_errno(-EIO); + brelse(*bh); + *bh = NULL; + return -EIO; + } + return 0; } @@ -1747,6 +1754,7 @@ static int ocfs2_initialize_super(struct super_block *sb, INIT_LIST_HEAD(&osb->blocked_lock_list); osb->blocked_lock_count = 0; spin_lock_init(&osb->osb_lock); + spin_lock_init(&osb->osb_xattr_lock); ocfs2_init_inode_steal_slot(osb); atomic_set(&osb->alloc_stats.moves, 0); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 915039fffe6e..4ddd788add67 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -82,13 +82,14 @@ struct ocfs2_xattr_set_ctxt { #define OCFS2_XATTR_ROOT_SIZE (sizeof(struct ocfs2_xattr_def_value_root)) #define OCFS2_XATTR_INLINE_SIZE 80 +#define OCFS2_XATTR_HEADER_GAP 4 #define OCFS2_XATTR_FREE_IN_IBODY (OCFS2_MIN_XATTR_INLINE_SIZE \ - sizeof(struct ocfs2_xattr_header) \ - - sizeof(__u32)) + - OCFS2_XATTR_HEADER_GAP) #define OCFS2_XATTR_FREE_IN_BLOCK(ptr) ((ptr)->i_sb->s_blocksize \ - sizeof(struct ocfs2_xattr_block) \ - sizeof(struct ocfs2_xattr_header) \ - - sizeof(__u32)) + - OCFS2_XATTR_HEADER_GAP) static struct ocfs2_xattr_def_value_root def_xv = { .xv.xr_list.l_count = cpu_to_le16(1), @@ -274,10 +275,12 @@ static int ocfs2_read_xattr_bucket(struct ocfs2_xattr_bucket *bucket, bucket->bu_blocks, bucket->bu_bhs, 0, NULL); if (!rc) { + spin_lock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock); rc = ocfs2_validate_meta_ecc_bhs(bucket->bu_inode->i_sb, bucket->bu_bhs, bucket->bu_blocks, &bucket_xh(bucket)->xh_check); + spin_unlock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock); if (rc) mlog_errno(rc); } @@ -310,9 +313,11 @@ static void ocfs2_xattr_bucket_journal_dirty(handle_t *handle, { int i; + spin_lock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock); ocfs2_compute_meta_ecc_bhs(bucket->bu_inode->i_sb, bucket->bu_bhs, bucket->bu_blocks, &bucket_xh(bucket)->xh_check); + spin_unlock(&OCFS2_SB(bucket->bu_inode->i_sb)->osb_xattr_lock); for (i = 0; i < bucket->bu_blocks; i++) ocfs2_journal_dirty(handle, bucket->bu_bhs[i]); @@ -1507,7 +1512,7 @@ static int ocfs2_xattr_set_entry(struct inode *inode, last += 1; } - free = min_offs - ((void *)last - xs->base) - sizeof(__u32); + free = min_offs - ((void *)last - xs->base) - OCFS2_XATTR_HEADER_GAP; if (free < 0) return -EIO; @@ -2190,7 +2195,7 @@ static int ocfs2_xattr_can_be_in_inode(struct inode *inode, last += 1; } - free = min_offs - ((void *)last - xs->base) - sizeof(__u32); + free = min_offs - ((void *)last - xs->base) - OCFS2_XATTR_HEADER_GAP; if (free < 0) return 0; @@ -2592,8 +2597,9 @@ static int __ocfs2_xattr_set_handle(struct inode *inode, if (!ret) { /* Update inode ctime. */ - ret = ocfs2_journal_access(ctxt->handle, inode, xis->inode_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + ret = ocfs2_journal_access_di(ctxt->handle, inode, + xis->inode_bh, + OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; @@ -5060,8 +5066,8 @@ try_again: xh_free_start = le16_to_cpu(xh->xh_free_start); header_size = sizeof(struct ocfs2_xattr_header) + count * sizeof(struct ocfs2_xattr_entry); - max_free = OCFS2_XATTR_BUCKET_SIZE - - le16_to_cpu(xh->xh_name_value_len) - header_size; + max_free = OCFS2_XATTR_BUCKET_SIZE - header_size - + le16_to_cpu(xh->xh_name_value_len) - OCFS2_XATTR_HEADER_GAP; mlog_bug_on_msg(header_size > blocksize, "bucket %llu has header size " "of %u which exceed block size\n", @@ -5094,7 +5100,7 @@ try_again: need = 0; } - free = xh_free_start - header_size; + free = xh_free_start - header_size - OCFS2_XATTR_HEADER_GAP; /* * We need to make sure the new name/value pair * can exist in the same block. @@ -5127,7 +5133,8 @@ try_again: } xh_free_start = le16_to_cpu(xh->xh_free_start); - free = xh_free_start - header_size; + free = xh_free_start - header_size + - OCFS2_XATTR_HEADER_GAP; if (xh_free_start % blocksize < need) free -= xh_free_start % blocksize; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dcaa0fd84b02..465d6babc847 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -708,6 +708,8 @@ struct req_iterator { }; /* This should not be used directly - use rq_for_each_segment */ +#define for_each_bio(_bio) \ + for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 315bcd375224..cc4f45361dbb 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -13,6 +13,7 @@ struct user_namespace { struct kref kref; struct hlist_head uidhash_table[UIDHASH_SZ]; struct user_struct *creator; + struct work_struct destroyer; }; extern struct user_namespace init_user_ns; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 79084311ee57..076c7c8215b0 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -60,12 +60,25 @@ int create_user_ns(struct cred *new) return 0; } -void free_user_ns(struct kref *kref) +/* + * Deferred destructor for a user namespace. This is required because + * free_user_ns() may be called with uidhash_lock held, but we need to call + * back to free_uid() which will want to take the lock again. + */ +static void free_user_ns_work(struct work_struct *work) { - struct user_namespace *ns; - - ns = container_of(kref, struct user_namespace, kref); + struct user_namespace *ns = + container_of(work, struct user_namespace, destroyer); free_uid(ns->creator); kfree(ns); } + +void free_user_ns(struct kref *kref) +{ + struct user_namespace *ns = + container_of(kref, struct user_namespace, kref); + + INIT_WORK(&ns->destroyer, free_user_ns_work); + schedule_work(&ns->destroyer); +} EXPORT_SYMBOL(free_user_ns); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 903cad46e796..520a75980269 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -323,6 +323,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long addr; int purged = 0; + BUG_ON(!size); BUG_ON(size & ~PAGE_MASK); va = kmalloc_node(sizeof(struct vmap_area), @@ -334,6 +335,9 @@ retry: addr = ALIGN(vstart, align); spin_lock(&vmap_area_lock); + if (addr + size - 1 < addr) + goto overflow; + /* XXX: could have a last_hole cache */ n = vmap_area_root.rb_node; if (n) { @@ -365,6 +369,8 @@ retry: while (addr + size > first->va_start && addr + size <= vend) { addr = ALIGN(first->va_end + PAGE_SIZE, align); + if (addr + size - 1 < addr) + goto overflow; n = rb_next(&first->rb_node); if (n) @@ -375,6 +381,7 @@ retry: } found: if (addr + size > vend) { +overflow: spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); @@ -498,6 +505,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, static DEFINE_SPINLOCK(purge_lock); LIST_HEAD(valist); struct vmap_area *va; + struct vmap_area *n_va; int nr = 0; /* @@ -537,7 +545,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (nr) { spin_lock(&vmap_area_lock); - list_for_each_entry(va, &valist, purge_list) + list_for_each_entry_safe(va, n_va, &valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 45eb0ae98eba..2d5ece798c4c 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -10,7 +10,7 @@ use strict; my $P = $0; $P =~ s@.*/@@g; -my $V = '0.27'; +my $V = '0.28'; use Getopt::Long qw(:config no_auto_abbrev); @@ -110,7 +110,8 @@ our $Sparse = qr{ __iomem| __must_check| __init_refok| - __kprobes + __kprobes| + __ref }x; our $Attribute = qr{ const| @@ -1240,7 +1241,8 @@ sub process { $realfile =~ s@^([^/]*)/@@; $p1_prefix = $1; - if ($tree && $p1_prefix ne '' && -e "$root/$p1_prefix") { + if (!$file && $tree && $p1_prefix ne '' && + -e "$root/$p1_prefix") { WARN("patch prefix '$p1_prefix' exists, appears to be a -p0 patch\n"); } @@ -1583,9 +1585,9 @@ sub process { } # TEST: allow direct testing of the attribute matcher. if ($dbg_attr) { - if ($line =~ /^.\s*$Attribute\s*$/) { + if ($line =~ /^.\s*$Modifier\s*$/) { ERROR("TEST: is attr\n" . $herecurr); - } elsif ($dbg_attr > 1 && $line =~ /^.+($Attribute)/) { + } elsif ($dbg_attr > 1 && $line =~ /^.+($Modifier)/) { ERROR("TEST: is not attr ($1 is)\n". $herecurr); } next; @@ -1657,7 +1659,7 @@ sub process { # * goes on variable not on type # (char*[ const]) - if ($line =~ m{\($NonptrType(\s*\*[\s\*]*(?:$Modifier\s*)*)\)}) { + if ($line =~ m{\($NonptrType(\s*(?:$Modifier\b\s*|\*\s*)+)\)}) { my ($from, $to) = ($1, $1); # Should start with a space. @@ -1672,7 +1674,7 @@ sub process { if ($from ne $to) { ERROR("\"(foo$from)\" should be \"(foo$to)\"\n" . $herecurr); } - } elsif ($line =~ m{\b$NonptrType(\s*\*[\s\*]*(?:$Modifier\s*)?)($Ident)}) { + } elsif ($line =~ m{\b$NonptrType(\s*(?:$Modifier\b\s*|\*\s*)+)($Ident)}) { my ($from, $to, $ident) = ($1, $1, $2); # Should start with a space. @@ -1685,8 +1687,8 @@ sub process { # Modifiers should have spaces. $to =~ s/(\b$Modifier$)/$1 /; - #print "from<$from> to<$to>\n"; - if ($from ne $to) { + #print "from<$from> to<$to> ident<$ident>\n"; + if ($from ne $to && $ident !~ /^$Modifier$/) { ERROR("\"foo${from}bar\" should be \"foo${to}bar\"\n" . $herecurr); } } @@ -1885,11 +1887,11 @@ sub process { if ($ctx !~ /[WEBC]x./ && $ca !~ /(?:\)|!|~|\*|-|\&|\||\+\+|\-\-|\{)$/) { ERROR("space required before that '$op' $at\n" . $hereptr); } - if ($op eq '*' && $cc =~/\s*const\b/) { + if ($op eq '*' && $cc =~/\s*$Modifier\b/) { # A unary '*' may be const } elsif ($ctx =~ /.xW/) { - ERROR("space prohibited after that '$op' $at\n" . $hereptr); + ERROR("Aspace prohibited after that '$op' $at\n" . $hereptr); } # unary ++ and unary -- are allowed no space on one side. @@ -2560,7 +2562,7 @@ sub process { if ($line =~ /\bin_atomic\s*\(/) { if ($realfile =~ m@^drivers/@) { ERROR("do not use in_atomic in drivers\n" . $herecurr); - } else { + } elsif ($realfile !~ m@^kernel/@) { WARN("use of in_atomic() is incorrect outside core kernel code\n" . $herecurr); } } |