/* * Copyright (c) 2000-2001 Christoph Hellwig. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions, and the following disclaimer, * without modification. * 2. The name of the author may not be used to endorse or promote products * derived from this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL"). * * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ /* * Veritas filesystem driver - filesystem to disk block mapping. */ #include #include #include #include "vxfs.h" #include "vxfs_inode.h" #include "vxfs_extern.h" #ifdef DIAGNOSTIC static void vxfs_typdump(struct vxfs_typed *typ) { printk(KERN_DEBUG "type=%Lu ", typ->vt_hdr >> VXFS_TYPED_TYPESHIFT); printk("offset=%Lx ", typ->vt_hdr & VXFS_TYPED_OFFSETMASK); printk("block=%x ", typ->vt_block); printk("size=%x\n", typ->vt_size); } #endif /** * vxfs_bmap_ext4 - do bmap for ext4 extents * @ip: pointer to the inode we do bmap for * @iblock: logical block. * * Description: * vxfs_bmap_ext4 performs the bmap operation for inodes with * ext4-style extents (which are much like the traditional UNIX * inode organisation). * * Returns: * The physical block number on success, else Zero. */ static daddr_t vxfs_bmap_ext4(struct inode *ip, long bn) { struct super_block *sb = ip->i_sb; struct vxfs_inode_info *vip = VXFS_INO(ip); struct vxfs_sb_info *sbi = VXFS_SBI(sb); unsigned long bsize = sb->s_blocksize; u32 indsize = fs32_to_cpu(sbi, vip->vii_ext4.ve4_indsize); int i; if (indsize > sb->s_blocksize) goto fail_size; for (i = 0; i < VXFS_NDADDR; i++) { struct direct *d = vip->vii_ext4.ve4_direct + i; if (bn >= 0 && bn < fs32_to_cpu(sbi, d->size)) return (bn + fs32_to_cpu(sbi, d->extent)); bn -= fs32_to_cpu(sbi, d->size); } if ((bn / (indsize * indsize * bsize / 4)) == 0) { struct buffer_head *buf; daddr_t bno; __fs32 *indir; buf = sb_bread(sb, fs32_to_cpu(sbi, vip->vii_ext4.ve4_indir[0])); if (!buf || !buffer_mapped(buf)) goto fail_buf; indir = (__fs32 *)buf->b_data; bno = fs32_to_cpu(sbi, indir[(bn / indsize) % (indsize * bn)]) + (bn % indsize); brelse(buf); return bno; } else printk(KERN_WARNING "no matching indir?"); return 0; fail_size: printk("vxfs: indirect extent too big!\n"); fail_buf: return 0; } /** * vxfs_bmap_indir - recursion for vxfs_bmap_typed * @ip: pointer to the inode we do bmap for * @indir: indirect block we start reading at * @size: size of the typed area to search * @block: partially result from further searches * * Description: * vxfs_bmap_indir reads a &struct vxfs_typed at @indir * and performs the type-defined action. * * Return Value: * The physical block number on success, else Zero. * * Note: * Kernelstack is rare. Unrecurse? */ static daddr_t vxfs_bmap_indir(struct inode *ip, long indir, int size, long block) { struct vxfs_sb_info *sbi = VXFS_SBI(ip->i_sb); struct buffer_head *bp = NULL; daddr_t pblock = 0; int i; for (i = 0; i < size * VXFS_TYPED_PER_BLOCK(ip->i_sb); i++) { struct vxfs_typed *typ; int64_t off; bp = sb_bread(ip->i_sb, indir + (i / VXFS_TYPED_PER_BLOCK(ip->i_sb))); if (!bp || !buffer_mapped(bp)) return 0; typ = ((struct vxfs_typed *)bp->b_data) + (i % VXFS_TYPED_PER_BLOCK(ip->i_sb)); off = fs64_to_cpu(sbi, typ->vt_hdr) & VXFS_TYPED_OFFSETMASK; if (block < off) { brelse(bp); continue; } switch ((u_int32_t)(fs64_to_cpu(sbi, typ->vt_hdr) >> VXFS_TYPED_TYPESHIFT)) { case VXFS_TYPED_INDIRECT: pblock = vxfs_bmap_indir(ip, fs32_to_cpu(sbi, typ->vt_block), fs32_to_cpu(sbi, typ->vt_size), block - off); if (pblock == -2) break; goto out; case VXFS_TYPED_DATA: if ((block - off) >= fs32_to_cpu(sbi, typ->vt_size)) break; pblock = fs32_to_cpu(sbi, typ->vt_block) + block - off; goto out; case VXFS_TYPED_INDIRECT_DEV4: case VXFS_TYPED_DATA_DEV4: { struct vxfs_typed_dev4 *typ4 = (struct vxfs_typed_dev4 *)typ; printk(KERN_INFO "\n\nTYPED_DEV4 detected!\n"); printk(KERN_INFO "block: %llu\tsize: %lld\tdev: %d\n", fs64_to_cpu(sbi, typ4->vd4_block), fs64_to_cpu(sbi, typ4->vd4_size), fs32_to_cpu(sbi, typ4->vd4_dev)); goto fail; } default: printk(KERN_ERR "%s:%d vt_hdr %llu\n", __func__, __LINE__, fs64_to_cpu(sbi, typ->vt_hdr)); BUG(); } brelse(bp); } fail: pblock = 0; out: brelse(bp); return (pblock); } /** * vxfs_bmap_typed - bmap for typed extents * @ip: pointer to the inode we do bmap for * @iblock: logical block * * Description: * Performs the bmap operation for typed extents. * * Return Value: * The physical block number on success, else Zero. */ static daddr_t vxfs_bmap_typed(struct inode *ip, long iblock) { struct vxfs_inode_info *vip = VXFS_INO(ip); struct vxfs_sb_info *sbi = VXFS_SBI(ip->i_sb); daddr_t pblock = 0; int i; for (i = 0; i < VXFS_NTYPED; i++) { struct vxfs_typed *typ = vip->vii_org.typed + i; u64 hdr = fs64_to_cpu(sbi, typ->vt_hdr); int64_t off = (hdr & VXFS_TYPED_OFFSETMASK); #ifdef DIAGNOSTIC vxfs_typdump(typ); #endif if (iblock < off) continue; switch ((u32)(hdr >> VXFS_TYPED_TYPESHIFT)) { case VXFS_TYPED_INDIRECT: pblock = vxfs_bmap_indir(ip, fs32_to_cpu(sbi, typ->vt_block), fs32_to_cpu(sbi, typ->vt_size), iblock - off); if (pblock == -2) break; return (pblock); case VXFS_TYPED_DATA: if ((iblock - off) < fs32_to_cpu(sbi, typ->vt_size)) return (fs32_to_cpu(sbi, typ->vt_block) + iblock - off); break; case VXFS_TYPED_INDIRECT_DEV4: case VXFS_TYPED_DATA_DEV4: { struct vxfs_typed_dev4 *typ4 = (struct vxfs_typed_dev4 *)typ; printk(KERN_INFO "\n\nTYPED_DEV4 detected!\n"); printk(KERN_INFO "block: %llu\tsize: %lld\tdev: %d\n", fs64_to_cpu(sbi, typ4->vd4_block), fs64_to_cpu(sbi, typ4->vd4_size), fs32_to_cpu(sbi, typ4->vd4_dev)); return 0; } default: BUG(); } } return 0; } /** * vxfs_bmap1 - vxfs-internal bmap operation * @ip: pointer to the inode we do bmap for * @iblock: logical block * * Description: * vxfs_bmap1 perfoms a logical to physical block mapping * for vxfs-internal purposes. * * Return Value: * The physical block number on success, else Zero. */ daddr_t vxfs_bmap1(struct inode *ip, long iblock) { struct vxfs_inode_info *vip = VXFS_INO(ip); if (VXFS_ISEXT4(vip)) return vxfs_bmap_ext4(ip, iblock); if (VXFS_ISTYPED(vip)) return vxfs_bmap_typed(ip, iblock); if (VXFS_ISNONE(vip)) goto unsupp; if (VXFS_ISIMMED(vip)) goto unsupp; printk(KERN_WARNING "vxfs: inode %ld has no valid orgtype (%x)\n", ip->i_ino, vip->vii_orgtype); BUG(); unsupp: printk(KERN_WARNING "vxfs: inode %ld has an unsupported orgtype (%x)\n", ip->i_ino, vip->vii_orgtype); return 0; } k for fw_state protection") and subsequent fix commit 5d47ec02c37ea6 ("firmware: Correct handling of fw_state_wait() return value") a race can happen between this cancelation and the firmware fw_state_wait_timeout() being woken up after a state change with which fw_load_abort() as that calls swake_up(). Upon error fw_state_wait_timeout() will also again call fw_load_abort() and trigger a null reference. At first glance we could just fix this with a !buf check on fw_load_abort() before accessing buf->fw_st, however there is a logical issue in having a state machine used for the fallback mechanism and preventing access from it once we abort as its inside the buf (buf->fw_st). The firmware_class.c code is setting the buf to NULL to annotate an abort has occurred. Replace this mechanism by simply using the state check instead. All the other code in place already uses similar checks for aborting as well so no further changes are needed. An oops can be reproduced with the new fw_fallback.sh fallback mechanism cancellation test. Either cancelling the fallback mechanism or the custom fallback mechanism triggers a crash. mcgrof@piggy ~/linux-next/tools/testing/selftests/firmware (git::20170111-fw-fixes)$ sudo ./fw_fallback.sh ./fw_fallback.sh: timeout works ./fw_fallback.sh: firmware comparison works ./fw_fallback.sh: fallback mechanism works [ this then sits here when it is trying the cancellation test ] Kernel log: test_firmware: loading 'nope-test-firmware.bin' misc test_firmware: Direct firmware load for nope-test-firmware.bin failed with error -2 misc test_firmware: Falling back to user helper BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: _request_firmware+0xa27/0xad0 PGD 0 Oops: 0000 [#1] SMP Modules linked in: test_firmware(E) ... etc ... CPU: 1 PID: 1396 Comm: fw_fallback.sh Tainted: G W E 4.10.0-rc3-next-20170111+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 task: ffff9740b27f4340 task.stack: ffffbb15c0bc8000 RIP: 0010:_request_firmware+0xa27/0xad0 RSP: 0018:ffffbb15c0bcbd10 EFLAGS: 00010246 RAX: 00000000fffffffe RBX: ffff9740afe5aa80 RCX: 0000000000000000 RDX: ffff9740b27f4340 RSI: 0000000000000283 RDI: 0000000000000000 RBP: ffffbb15c0bcbd90 R08: ffffbb15c0bcbcd8 R09: 0000000000000000 R10: 0000000894a0d4b1 R11: 000000000000008c R12: ffffffffc0312480 R13: 0000000000000005 R14: ffff9740b1c32400 R15: 00000000000003e8 FS: 00007f8604422700(0000) GS:ffff9740bfc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 000000012164c000 CR4: 00000000000006e0 Call Trace: request_firmware+0x37/0x50 trigger_request_store+0x79/0xd0 [test_firmware] dev_attr_store+0x18/0x30 sysfs_kf_write+0x37/0x40 kernfs_fop_write+0x110/0x1a0 __vfs_write+0x37/0x160 ? _cond_resched+0x1a/0x50 vfs_write+0xb5/0x1a0 SyS_write+0x55/0xc0 ? trace_do_page_fault+0x37/0xd0 entry_SYSCALL_64_fastpath+0x1e/0xad RIP: 0033:0x7f8603f49620 RSP: 002b:00007fff6287b788 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000055c307b110a0 RCX: 00007f8603f49620 RDX: 0000000000000016 RSI: 000055c3084d8a90 RDI: 0000000000000001 RBP: 0000000000000016 R08: 000000000000c0ff R09: 000055c3084d6336 R10: 000055c307b108b0 R11: 0000000000000246 R12: 000055c307b13c80 R13: 000055c3084d6320 R14: 0000000000000000 R15: 00007fff6287b950 Code: 9f 64 84 e8 9c 61 fe ff b8 f4 ff ff ff e9 6b f9 ff ff 48 c7 c7 40 6b 8d 84 89 45 a8 e8 43 84 18 00 49 8b be 00 03 00 00 8b 45 a8 <83> 7f 38 02 74 08 e8 6e ec ff ff 8b 45 a8 49 c7 86 00 03 00 00 RIP: _request_firmware+0xa27/0xad0 RSP: ffffbb15c0bcbd10 CR2: 0000000000000038 ---[ end trace 6d94ac339c133e6f ]--- Fixes: 5d47ec02c37e ("firmware: Correct handling of fw_state_wait() return value") Reported-and-Tested-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reported-and-Tested-by: Patrick Bruenn <p.bruenn@beckhoff.com> Reported-by: Chris Wilson <chris@chris-wilson.co.uk> CC: <stable@vger.kernel.org> [3.10+] Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel/time/Makefile')