diff options
42 files changed, 476 insertions, 599 deletions
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index deac4e973ddc..4d05b9862451 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -949,3 +949,99 @@ mmap_lock held. All in-tree users have been audited and do not seem to depend on the mmap_lock being held, but out of tree users should verify for themselves. If they do need it, they can return VM_FAULT_RETRY to be called with the mmap_lock held. + +--- + +**mandatory** + +The order of opening block devices and matching or creating superblocks has +changed. + +The old logic opened block devices first and then tried to find a +suitable superblock to reuse based on the block device pointer. + +The new logic tries to find a suitable superblock first based on the device +number, and opening the block device afterwards. + +Since opening block devices cannot happen under s_umount because of lock +ordering requirements s_umount is now dropped while opening block devices and +reacquired before calling fill_super(). + +In the old logic concurrent mounters would find the superblock on the list of +superblocks for the filesystem type. Since the first opener of the block device +would hold s_umount they would wait until the superblock became either born or +was discarded due to initialization failure. + +Since the new logic drops s_umount concurrent mounters could grab s_umount and +would spin. Instead they are now made to wait using an explicit wait-wake +mechanism without having to hold s_umount. + +--- + +**mandatory** + +The holder of a block device is now the superblock. + +The holder of a block device used to be the file_system_type which wasn't +particularly useful. It wasn't possible to go from block device to owning +superblock without matching on the device pointer stored in the superblock. +This mechanism would only work for a single device so the block layer couldn't +find the owning superblock of any additional devices. + +In the old mechanism reusing or creating a superblock for a racing mount(2) and +umount(2) relied on the file_system_type as the holder. This was severly +underdocumented however: + +(1) Any concurrent mounter that managed to grab an active reference on an + existing superblock was made to wait until the superblock either became + ready or until the superblock was removed from the list of superblocks of + the filesystem type. If the superblock is ready the caller would simple + reuse it. + +(2) If the mounter came after deactivate_locked_super() but before + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would wait until the superblock was shutdown, + reuse the block device and allocate a new superblock. + +(3) If the mounter came after deactivate_locked_super() and after + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would reuse the block device and allocate a new + superblock (the bd_holder point may still be set to the filesystem type). + +Because the holder of the block device was the file_system_type any concurrent +mounter could open the block devices of any superblock of the same +file_system_type without risking seeing EBUSY because the block device was +still in use by another superblock. + +Making the superblock the owner of the block device changes this as the holder +is now a unique superblock and thus block devices associated with it cannot be +reused by concurrent mounters. So a concurrent mounter in (2) could suddenly +see EBUSY when trying to open a block device whose holder was a different +superblock. + +The new logic thus waits until the superblock and the devices are shutdown in +->kill_sb(). Removal of the superblock from the list of superblocks of the +filesystem type is now moved to a later point when the devices are closed: + +(1) Any concurrent mounter managing to grab an active reference on an existing + superblock is made to wait until the superblock is either ready or until + the superblock and all devices are shutdown in ->kill_sb(). If the + superblock is ready the caller will simply reuse it. + +(2) If the mounter comes after deactivate_locked_super() but before + the superblock has been removed from the list of superblocks of the + filesystem type the mounter is made to wait until the superblock and the + devices are shut down in ->kill_sb() and the superblock is removed from the + list of superblocks of the filesystem type. The mounter will allocate a new + superblock and grab ownership of the block device (the bd_holder pointer of + the block device will be set to the newly allocated superblock). + +(3) This case is now collapsed into (2) as the superblock is left on the list + of superblocks of the filesystem type until all devices are shutdown in + ->kill_sb(). In other words, if the superblock isn't on the list of + superblock of the filesystem type anymore then it has given up ownership of + all associated block devices (the bd_holder pointer is NULL). + +As this is a VFS level change it has no practical consequences for filesystems +other than that all of them must use one of the provided kill_litter_super(), +kill_anon_super(), or kill_block_super() helpers. diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index e4490639d383..9d2738e10c0b 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -233,7 +233,8 @@ int parent_create_sysfs_files(struct mdev_parent *parent) out_err: while (--i >= 0) mdev_type_remove(parent->types[i]); - return 0; + kset_unregister(parent->mdev_types_kset); + return ret; } static ssize_t remove_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/vfio/pci/pds/Kconfig b/drivers/vfio/pci/pds/Kconfig index 407b3fd32733..6eceef7b028a 100644 --- a/drivers/vfio/pci/pds/Kconfig +++ b/drivers/vfio/pci/pds/Kconfig @@ -3,7 +3,7 @@ config PDS_VFIO_PCI tristate "VFIO support for PDS PCI devices" - depends on PDS_CORE + depends on PDS_CORE && PCI_IOV select VFIO_PCI_CORE help This provides generic PCI support for PDS devices using the VFIO diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c index b46174f5eb09..649b18ee394b 100644 --- a/drivers/vfio/pci/pds/vfio_dev.c +++ b/drivers/vfio/pci/pds/vfio_dev.c @@ -162,7 +162,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev) pci_id = PCI_DEVID(pdev->bus->number, pdev->devfn); dev_dbg(&pdev->dev, "%s: PF %#04x VF %#04x vf_id %d domain %d pds_vfio %p\n", - __func__, pci_dev_id(pdev->physfn), pci_id, vf_id, + __func__, pci_dev_id(pci_physfn(pdev)), pci_id, vf_id, pci_domain_nr(pdev->bus), pds_vfio); return 0; @@ -80,7 +80,7 @@ struct aio_ring { struct kioctx_table { struct rcu_head rcu; unsigned nr; - struct kioctx __rcu *table[]; + struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 6a13cf00218b..9fe4ccca50a0 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -103,24 +103,17 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) * Transfer bytes to our delayed refs rsv. * * @fs_info: the filesystem - * @src: source block rsv to transfer from * @num_bytes: number of bytes to transfer * - * This transfers up to the num_bytes amount from the src rsv to the + * This transfers up to the num_bytes amount, previously reserved, to the * delayed_refs_rsv. Any extra bytes are returned to the space info. */ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes) { struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; u64 to_free = 0; - spin_lock(&src->lock); - src->reserved -= num_bytes; - src->size -= num_bytes; - spin_unlock(&src->lock); - spin_lock(&delayed_refs_rsv->lock); if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) { u64 delta = delayed_refs_rsv->size - @@ -163,6 +156,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv; u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1); u64 num_bytes = 0; + u64 refilled_bytes; + u64 to_free; int ret = -ENOSPC; spin_lock(&block_rsv->lock); @@ -178,9 +173,38 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, num_bytes, flush); if (ret) return ret; - btrfs_block_rsv_add_bytes(block_rsv, num_bytes, false); - trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", - 0, num_bytes, 1); + + /* + * We may have raced with someone else, so check again if we the block + * reserve is still not full and release any excess space. + */ + spin_lock(&block_rsv->lock); + if (block_rsv->reserved < block_rsv->size) { + u64 needed = block_rsv->size - block_rsv->reserved; + + if (num_bytes >= needed) { + block_rsv->reserved += needed; + block_rsv->full = true; + to_free = num_bytes - needed; + refilled_bytes = needed; + } else { + block_rsv->reserved += num_bytes; + to_free = 0; + refilled_bytes = num_bytes; + } + } else { + to_free = num_bytes; + refilled_bytes = 0; + } + spin_unlock(&block_rsv->lock); + + if (to_free > 0) + btrfs_space_info_free_bytes_may_use(fs_info, block_rsv->space_info, + to_free); + + if (refilled_bytes > 0) + trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, + refilled_bytes, 1); return 0; } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index b8e14b0ba5f1..fd9bf2b709c0 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -407,7 +407,6 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f356f08b55cb..fc313fce5bbd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1514,15 +1514,14 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_release_path(path); /* now insert the actual backref */ - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - BUG_ON(refs_to_add != 1); + if (owner < BTRFS_FIRST_FREE_OBJECTID) ret = insert_tree_block_ref(trans, path, bytenr, parent, root_objectid); - } else { + else ret = insert_extent_data_ref(trans, path, bytenr, parent, root_objectid, owner, offset, refs_to_add); - } + if (ret) btrfs_abort_transaction(trans, ret); out: @@ -1656,7 +1655,10 @@ again: goto again; } } else { - err = -EIO; + err = -EUCLEAN; + btrfs_err(fs_info, + "missing extent item for extent %llu num_bytes %llu level %d", + head->bytenr, head->num_bytes, extent_op->level); goto out; } } @@ -1699,12 +1701,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent = ref->parent; ref_root = ref->root; - if (node->ref_mod != 1) { + if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, - "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu", + "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); - return -EIO; + return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { BUG_ON(!extent_op || !extent_op->update_flags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6954ae763b86..caccd0376342 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3995,8 +3995,14 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, char *dst = (char *)dstv; unsigned long i = get_eb_page_index(start); - if (check_eb_range(eb, start, len)) + if (check_eb_range(eb, start, len)) { + /* + * Invalid range hit, reset the memory, so callers won't get + * some random garbage for their uninitialzed memory. + */ + memset(dstv, 0, len); return; + } offset = get_eb_offset_in_page(eb, start); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cffdd6f7f8e8..1a093ec0f7e3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2117,7 +2117,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 0bf42dccb041..c780d3729463 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -631,14 +631,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, reloc_reserved = true; } - ret = btrfs_block_rsv_add(fs_info, rsv, num_bytes, flush); + ret = btrfs_reserve_metadata_bytes(fs_info, rsv, num_bytes, flush); if (ret) goto reserve_fail; if (delayed_refs_bytes) { - btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv, - delayed_refs_bytes); + btrfs_migrate_to_delayed_refs_rsv(fs_info, delayed_refs_bytes); num_bytes -= delayed_refs_bytes; } + btrfs_block_rsv_add_bytes(rsv, num_bytes, true); if (rsv->space_info->force_alloc) do_chunk_alloc = true; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d1e46b839519..cbb17b542131 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4722,7 +4722,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int slot; int ins_nr = 0; - int start_slot; + int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9621455edebc..5a5a8d488a7b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1594,7 +1594,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 search_start; u64 hole_size; u64 max_hole_start; - u64 max_hole_size; + u64 max_hole_size = 0; u64 extent_end; u64 search_end = device->total_bytes; int ret; @@ -1602,17 +1602,16 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, struct extent_buffer *l; search_start = dev_extent_search_start(device); + max_hole_start = search_start; WARN_ON(device->zone_info && !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - max_hole_start = search_start; - max_hole_size = 0; - + if (!path) { + ret = -ENOMEM; + goto out; + } again: if (search_start >= search_end || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 969ce991b0b0..c1af01b2c42d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1535,10 +1535,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, if (wbc->pages_skipped) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * Writeback is not making progress due to locked buffers. + * Skip this inode for now. Although having skipped pages + * is odd for clean inodes, it can happen for some + * filesystems so handle that gracefully. */ - redirty_tail_locked(inode, wb); + if (inode->i_state & I_DIRTY_ALL) + redirty_tail_locked(inode, wb); + else + inode_cgwb_move_to_attached(inode, wb); return; } diff --git a/fs/libfs.c b/fs/libfs.c index a4eb12757886..37f2d34ee090 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1903,6 +1903,7 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ + iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index cfec5e0c7f66..5661a363005e 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1562,6 +1562,7 @@ load_root: put_inode_out: iput(inode); out: + ntfs3_put_sbi(sbi); kfree(boot2); return err; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index d1761ec5866a..ada3fcc9c6d5 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -337,7 +337,7 @@ static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry, { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4193633c4c7a..693971d20280 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -391,6 +391,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); + /* + * Overlayfs doesn't support deferred completions, don't copy + * this property in case it is set by the issuer. + */ + ifl &= ~IOCB_DIO_CALLER_COMP; + old_cred = ovl_override_creds(file_inode(file)->i_sb); if (is_sync_kiocb(iocb)) { file_start_write(real.file); diff --git a/fs/pipe.c b/fs/pipe.c index 6c1a9b1db907..139190165a1c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -537,7 +537,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) break; } ret += copied; - buf->offset = 0; buf->len = copied; if (!iov_iter_count(from)) diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index b81749492ef9..7d12b8c5b2fa 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -2699,7 +2699,7 @@ struct reiserfs_iget_args { #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12) #define journal_trans_half(blocksize) \ - ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32)) + ((blocksize - sizeof(struct reiserfs_journal_desc) - 12) / sizeof(__u32)) /* journal.c see journal.c for all the comments here */ @@ -2711,7 +2711,7 @@ struct reiserfs_journal_desc { __le32 j_len; __le32 j_mount_id; /* mount id of this trans */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id) @@ -2726,7 +2726,7 @@ struct reiserfs_journal_desc { struct reiserfs_journal_commit { __le32 j_trans_id; /* must match j_trans_id from the desc block */ __le32 j_len; /* ditto */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c85825e17df8..b9f053a5a5f0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6535,9 +6535,6 @@ void __init workqueue_init_early(void) BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); - wq_update_pod_attrs_buf = alloc_workqueue_attrs(); - BUG_ON(!wq_update_pod_attrs_buf); - pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; @@ -6605,13 +6602,13 @@ static void __init wq_cpu_intensive_thresh_init(void) unsigned long thresh; unsigned long bogo; + pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); + BUG_ON(IS_ERR(pwq_release_worker)); + /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; - pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); - BUG_ON(IS_ERR(pwq_release_worker)); - /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index a00a53e15ab7..1d111350197f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -57,6 +57,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -155,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -178,6 +188,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index fd6c1cb585db..abe087c53b4b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) + #undef __NR_syscalls -#define __NR_syscalls 452 +#define __NR_syscalls 453 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index a87bbbbca2d4..794c1d857677 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -673,8 +673,11 @@ struct drm_gem_open { * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT * and &DRM_PRIME_CAP_EXPORT. * - * PRIME buffers are exposed as dma-buf file descriptors. See - * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and + * &DRM_PRIME_CAP_EXPORT are always advertised. + * + * PRIME buffers are exposed as dma-buf file descriptors. + * See :ref:`prime_buffer_sharing`. */ #define DRM_CAP_PRIME 0x5 /** @@ -682,6 +685,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_IMPORT 0x1 /** @@ -689,6 +694,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_EXPORT 0x2 /** @@ -756,15 +763,14 @@ struct drm_gem_open { /** * DRM_CAP_SYNCOBJ * - * If set to 1, the driver supports sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ 0x13 /** * DRM_CAP_SYNCOBJ_TIMELINE * * If set to 1, the driver supports timeline operations on sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 @@ -909,6 +915,27 @@ struct drm_syncobj_timeline_wait { __u32 pad; }; +/** + * struct drm_syncobj_eventfd + * @handle: syncobj handle. + * @flags: Zero to wait for the point to be signalled, or + * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be + * available for the point. + * @point: syncobj timeline point (set to zero for binary syncobjs). + * @fd: Existing eventfd to sent events to. + * @pad: Must be zero. + * + * Register an eventfd to be signalled by a syncobj. The eventfd counter will + * be incremented by one. + */ +struct drm_syncobj_eventfd { + __u32 handle; + __u32 flags; + __u64 point; + __s32 fd; + __u32 pad; +}; + struct drm_syncobj_array { __u64 handles; @@ -1169,6 +1196,8 @@ extern "C" { */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) +#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. @@ -1180,25 +1209,50 @@ extern "C" { #define DRM_COMMAND_BASE 0x40 #define DRM_COMMAND_END 0xA0 -/* - * Header for events written back to userspace on the drm fd. The - * type defines the type of event, the length specifies the total - * length of the event (including the header), and user_data is - * typically a 64 bit value passed with the ioctl that triggered the - * event. A read on the drm fd will always only return complete - * events, that is, if for example the read buffer is 100 bytes, and - * there are two 64 byte events pending, only one will be returned. +/** + * struct drm_event - Header for DRM events + * @type: event type. + * @length: total number of payload bytes (including header). * - * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and - * up are chipset specific. + * This struct is a header for events written back to user-space on the DRM FD. + * A read on the DRM FD will always only return complete events: e.g. if the + * read buffer is 100 bytes large and there are two 64 byte events pending, + * only one will be returned. + * + * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and + * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK, + * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE. */ struct drm_event { __u32 type; __u32 length; }; +/** + * DRM_EVENT_VBLANK - vertical blanking event + * + * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the + * &_DRM_VBLANK_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_VBLANK 0x01 +/** + * DRM_EVENT_FLIP_COMPLETE - page-flip completion event + * + * This event is sent in response to an atomic commit or legacy page-flip with + * the &DRM_MODE_PAGE_FLIP_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_FLIP_COMPLETE 0x02 +/** + * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event + * + * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE. + * + * The event payload is a struct drm_event_crtc_sequence. + */ #define DRM_EVENT_CRTC_SEQUENCE 0x03 struct drm_event_vblank { diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h new file mode 100644 index 000000000000..dbfc9b37fcae --- /dev/null +++ b/tools/include/uapi/linux/seccomp.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SECCOMP_H +#define _UAPI_LINUX_SECCOMP_H + +#include <linux/compiler.h> +#include <linux/types.h> + + +/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */ +#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */ +#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */ +#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ + +/* Valid operations for seccomp syscall. */ +#define SECCOMP_SET_MODE_STRICT 0 +#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_GET_ACTION_AVAIL 2 +#define SECCOMP_GET_NOTIF_SIZES 3 + +/* Valid flags for SECCOMP_SET_MODE_FILTER */ +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) + +/* + * All BPF programs must return a 32-bit value. + * The bottom 16-bits are for optional return data. + * The upper 16-bits are ordered from least permissive values to most, + * as a signed value (so 0x8000000 is negative). + * + * The ordering ensures that a min_t() over composed return values always + * selects the least permissive choice. + */ +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ + +/* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION_FULL 0xffff0000U +#define SECCOMP_RET_ACTION 0x7fff0000U +#define SECCOMP_RET_DATA 0x0000ffffU + +/** + * struct seccomp_data - the format the BPF program executes over. + * @nr: the system call number + * @arch: indicates system call convention as an AUDIT_ARCH_* value + * as defined in <linux/audit.h>. + * @instruction_pointer: at the time of the system call. + * @args: up to 6 system call arguments always stored as 64-bit values + * regardless of the architecture. + */ +struct seccomp_data { + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; +}; + +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +/* + * Valid flags for struct seccomp_notif_resp + * + * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution! + * If set by the process supervising the syscalls of another process the + * syscall will continue. This is problematic because of an inherent TOCTOU. + * An attacker can exploit the time while the supervised process is waiting on + * a response from the supervising process to rewrite syscall arguments which + * are passed as pointers of the intercepted syscall. + * It should be absolutely clear that this means that the seccomp notifier + * _cannot_ be used to implement a security policy! It should only ever be used + * in scenarios where a more privileged process supervises the syscalls of a + * lesser privileged process to get around kernel-enforced security + * restrictions when the privileged process deems this safe. In other words, + * in order to continue a syscall the supervising process should be sure that + * another security mechanism or the kernel itself will sufficiently block + * syscalls if arguments are rewritten to something unsafe. + * + * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF + * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the + * same syscall, the most recently added filter takes precedence. This means + * that the new SECCOMP_RET_USER_NOTIF filter can override any + * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all + * such filtered syscalls to be executed by sending the response + * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally + * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE. + */ +#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0) + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ +#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */ + +/** + * struct seccomp_notif_addfd + * @id: The ID of the seccomp notification + * @flags: SECCOMP_ADDFD_FLAG_* + * @srcfd: The local fd number + * @newfd: Optional remote FD number if SETFD option is set, otherwise 0. + * @newfd_flags: The O_* flags the remote FD should have applied + */ +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) + +#endif /* _UAPI_LINUX_SECCOMP_H */ diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index cfda2511badf..cb5e757f6621 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -366,3 +366,4 @@ 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 n64 cachestat sys_cachestat +452 n64 fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 8c0b08b7a80e..20e50586e8a2 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -538,3 +538,4 @@ 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index a6935af2235c..0122cc156952 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 227538b0ce80..1d6eee30eceb 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -373,6 +373,8 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 64 map_shadow_stack sys_map_shadow_stack # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c index b04ebcde4036..a01c40131493 100644 --- a/tools/perf/bench/sched-seccomp-notify.c +++ b/tools/perf/bench/sched-seccomp-notify.c @@ -9,7 +9,7 @@ #include <sys/syscall.h> #include <sys/ioctl.h> #include <linux/time64.h> -#include <linux/seccomp.h> +#include <uapi/linux/seccomp.h> #include <sys/prctl.h> #include <unistd.h> diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 4314c9197850..e21caadda7c1 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -21,6 +21,7 @@ FILES=( "include/uapi/linux/perf_event.h" "include/uapi/linux/prctl.h" "include/uapi/linux/sched.h" + "include/uapi/linux/seccomp.h" "include/uapi/linux/stat.h" "include/uapi/linux/usbdevice_fs.h" "include/uapi/linux/vhost.h" diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index a7e88332276d..72ba4a9239c6 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -991,7 +991,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) } } free(cpuid); - if (!pmu) + if (!pmu || !table) return table; for (i = 0; i < table->num_pmus; i++) { diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 0e9ec65d92ae..3e673f25d5fd 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -413,10 +413,10 @@ def has_event(event: Event) -> Function: # pylint: disable=invalid-name return Function('has_event', event) -def strcmp_cpuid_str(event: str) -> Function: +def strcmp_cpuid_str(cpuid: Event) -> Function: # pylint: disable=redefined-builtin # pylint: disable=invalid-name - return Function('strcmp_cpuid_str', event) + return Function('strcmp_cpuid_str', cpuid) class Metric: """An individual metric that will specifiable on the perf command line.""" diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c deleted file mode 100644 index 9887ae09242d..000000000000 --- a/tools/perf/util/bpf-prologue.c +++ /dev/null @@ -1,508 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-prologue.c - * - * Copyright (C) 2015 He Kuang <hekuang@huawei.com> - * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015 Huawei Inc. - */ - -#include <bpf/libbpf.h> -#include "debug.h" -#include "bpf-loader.h" -#include "bpf-prologue.h" -#include "probe-finder.h" -#include <errno.h> -#include <stdlib.h> -#include <dwarf-regs.h> -#include <linux/filter.h> - -#define BPF_REG_SIZE 8 - -#define JMP_TO_ERROR_CODE -1 -#define JMP_TO_SUCCESS_CODE -2 -#define JMP_TO_USER_CODE -3 - -struct bpf_insn_pos { - struct bpf_insn *begin; - struct bpf_insn *end; - struct bpf_insn *pos; -}; - -static inline int -pos_get_cnt(struct bpf_insn_pos *pos) -{ - return pos->pos - pos->begin; -} - -static int -append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos) -{ - if (!pos->pos) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - if (pos->pos + 1 >= pos->end) { - pr_err("bpf prologue: prologue too long\n"); - pos->pos = NULL; - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - } - - *(pos->pos)++ = new_insn; - return 0; -} - -static int -check_pos(struct bpf_insn_pos *pos) -{ - if (!pos->pos || pos->pos >= pos->end) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - return 0; -} - -/* - * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see - * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM - * instruction (BPF_{B,H,W,DW}). - */ -static int -argtype_to_ldx_size(const char *type) -{ - int arg_size = type ? atoi(&type[1]) : 64; - - switch (arg_size) { - case 8: - return BPF_B; - case 16: - return BPF_H; - case 32: - return BPF_W; - case 64: - default: - return BPF_DW; - } -} - -static const char * -insn_sz_to_str(int insn_sz) -{ - switch (insn_sz) { - case BPF_B: - return "BPF_B"; - case BPF_H: - return "BPF_H"; - case BPF_W: - return "BPF_W"; - case BPF_DW: - return "BPF_DW"; - default: - return "UNKNOWN"; - } -} - -/* Give it a shorter name */ -#define ins(i, p) append_insn((i), (p)) - -/* - * Give a register name (in 'reg'), generate instruction to - * load register into an eBPF register rd: - * 'ldd target_reg, offset(ctx_reg)', where: - * ctx_reg is pre initialized to pointer of 'struct pt_regs'. - */ -static int -gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg, - const char *reg, int target_reg) -{ - int offset = regs_query_register_offset(reg); - - if (offset < 0) { - pr_err("bpf: prologue: failed to get register %s\n", - reg); - return offset; - } - ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos); - - return check_pos(pos); -} - -/* - * Generate a BPF_FUNC_probe_read function call. - * - * src_base_addr_reg is a register holding base address, - * dst_addr_reg is a register holding dest address (on stack), - * result is: - * - * *[dst_addr_reg] = *([src_base_addr_reg] + offset) - * - * Arguments of BPF_FUNC_probe_read: - * ARG1: ptr to stack (dest) - * ARG2: size (8) - * ARG3: unsafe ptr (src) - */ -static int -gen_read_mem(struct bpf_insn_pos *pos, - int src_base_addr_reg, - int dst_addr_reg, - long offset, - int probeid) -{ - /* mov arg3, src_base_addr_reg */ - if (src_base_addr_reg != BPF_REG_ARG3) - ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos); - /* add arg3, #offset */ - if (offset) - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos); - - /* mov arg2, #reg_size */ - ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos); - - /* mov arg1, dst_addr_reg */ - if (dst_addr_reg != BPF_REG_ARG1) - ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos); - - /* Call probe_read */ - ins(BPF_EMIT_CALL(probeid), pos); - /* - * Error processing: if read fail, goto error code, - * will be relocated. Target should be the start of - * error processing code. - */ - ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE), - pos); - - return check_pos(pos); -} - -/* - * Each arg should be bare register. Fetch and save them into argument - * registers (r3 - r5). - * - * BPF_REG_1 should have been initialized with pointer to - * 'struct pt_regs'. - */ -static int -gen_prologue_fastpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int i, err = 0; - - for (i = 0; i < nargs; i++) { - err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value, - BPF_PROLOGUE_START_ARG_REG + i); - if (err) - goto errout; - } - - return check_pos(pos); -errout: - return err; -} - -/* - * Slow path: - * At least one argument has the form of 'offset($rx)'. - * - * Following code first stores them into stack, then loads all of then - * to r2 - r5. - * Before final loading, the final result should be: - * - * low address - * BPF_REG_FP - 24 ARG3 - * BPF_REG_FP - 16 ARG2 - * BPF_REG_FP - 8 ARG1 - * BPF_REG_FP - * high address - * - * For each argument (described as: offn(...off2(off1(reg)))), - * generates following code: - * - * r7 <- fp - * r7 <- r7 - stack_offset // Ideal code should initialize r7 using - * // fp before generating args. However, - * // eBPF won't regard r7 as stack pointer - * // if it is generated by minus 8 from - * // another stack pointer except fp. - * // This is why we have to set r7 - * // to fp for each variable. - * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx() - * (r7) <- r3 // skip following instructions for bare reg - * r3 <- r3 + off1 . // skip if off1 == 0 - * r2 <- 8 \ - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * r3 <- (r7) - * r3 <- r3 + off2 . // skip if off2 == 0 - * r2 <- 8 \ // r2 may be broken by probe_read, so set again - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * ... - */ -static int -gen_prologue_slowpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int err, i, probeid; - - for (i = 0; i < nargs; i++) { - struct probe_trace_arg *arg = &args[i]; - const char *reg = arg->value; - struct probe_trace_arg_ref *ref = NULL; - int stack_offset = (i + 1) * -8; - - pr_debug("prologue: fetch arg %d, base reg is %s\n", - i, reg); - - /* value of base register is stored into ARG3 */ - err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg, - BPF_REG_ARG3); - if (err) { - pr_err("prologue: failed to get offset of register %s\n", - reg); - goto errout; - } - - /* Make r7 the stack pointer. */ - ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos); - /* r7 += -8 */ - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos); - /* - * Store r3 (base register) onto stack - * Ensure fp[offset] is set. - * fp is the only valid base register when storing - * into stack. We are not allowed to use r7 as base - * register here. - */ - ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3, - stack_offset), pos); - - ref = arg->ref; - probeid = BPF_FUNC_probe_read_kernel; - while (ref) { - pr_debug("prologue: arg %d: offset %ld\n", - i, ref->offset); - - if (ref->user_access) - probeid = BPF_FUNC_probe_read_user; - - err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7, - ref->offset, probeid); - if (err) { - pr_err("prologue: failed to generate probe_read function call\n"); - goto errout; - } - - ref = ref->next; - /* - * Load previous result into ARG3. Use - * BPF_REG_FP instead of r7 because verifier - * allows FP based addressing only. - */ - if (ref) - ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3, - BPF_REG_FP, stack_offset), pos); - } - } - - /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) { - int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW; - - pr_debug("prologue: load arg %d, insn_sz is %s\n", - i, insn_sz_to_str(insn_sz)); - ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, - BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); - } - - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); - - return check_pos(pos); -errout: - return err; -} - -static int -prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code, - struct bpf_insn *success_code, struct bpf_insn *user_code) -{ - struct bpf_insn *insn; - - if (check_pos(pos)) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - for (insn = pos->begin; insn < pos->pos; insn++) { - struct bpf_insn *target; - u8 class = BPF_CLASS(insn->code); - u8 opcode; - - if (class != BPF_JMP) - continue; - opcode = BPF_OP(insn->code); - if (opcode == BPF_CALL) - continue; - - switch (insn->off) { - case JMP_TO_ERROR_CODE: - target = error_code; - break; - case JMP_TO_SUCCESS_CODE: - target = success_code; - break; - case JMP_TO_USER_CODE: - target = user_code; - break; - default: - pr_err("bpf prologue: internal error: relocation failed\n"); - return -BPF_LOADER_ERRNO__PROLOGUE; - } - - insn->off = target - (insn + 1); - } - return 0; -} - -int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, - struct bpf_insn *new_prog, size_t *new_cnt, - size_t cnt_space) -{ - struct bpf_insn *success_code = NULL; - struct bpf_insn *error_code = NULL; - struct bpf_insn *user_code = NULL; - struct bpf_insn_pos pos; - bool fastpath = true; - int err = 0, i; - - if (!new_prog || !new_cnt) - return -EINVAL; - - if (cnt_space > BPF_MAXINSNS) - cnt_space = BPF_MAXINSNS; - - pos.begin = new_prog; - pos.end = new_prog + cnt_space; - pos.pos = new_prog; - - if (!nargs) { - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), - &pos); - - if (check_pos(&pos)) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; - } - - if (nargs > BPF_PROLOGUE_MAX_ARGS) { - pr_warning("bpf: prologue: %d arguments are dropped\n", - nargs - BPF_PROLOGUE_MAX_ARGS); - nargs = BPF_PROLOGUE_MAX_ARGS; - } - - /* First pass: validation */ - for (i = 0; i < nargs; i++) { - struct probe_trace_arg_ref *ref = args[i].ref; - - if (args[i].value[0] == '@') { - /* TODO: fetch global variable */ - pr_err("bpf: prologue: global %s%+ld not support\n", - args[i].value, ref ? ref->offset : 0); - return -ENOTSUP; - } - - while (ref) { - /* fastpath is true if all args has ref == NULL */ - fastpath = false; - - /* - * Instruction encodes immediate value using - * s32, ref->offset is long. On systems which - * can't fill long in s32, refuse to process if - * ref->offset too large (or small). - */ -#ifdef __LP64__ -#define OFFSET_MAX ((1LL << 31) - 1) -#define OFFSET_MIN ((1LL << 31) * -1) - if (ref->offset > OFFSET_MAX || - ref->offset < OFFSET_MIN) { - pr_err("bpf: prologue: offset out of bound: %ld\n", - ref->offset); - return -BPF_LOADER_ERRNO__PROLOGUEOOB; - } -#endif - ref = ref->next; - } - } - pr_debug("prologue: pass validation\n"); - - if (fastpath) { - /* If all variables are registers... */ - pr_debug("prologue: fast path\n"); - err = gen_prologue_fastpath(&pos, args, nargs); - if (err) - goto errout; - } else { - pr_debug("prologue: slow path\n"); - - /* Initialization: move ctx to a callee saved register. */ - ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos); - - err = gen_prologue_slowpath(&pos, args, nargs); - if (err) - goto errout; - /* - * start of ERROR_CODE (only slow pass needs error code) - * mov r2 <- 1 // r2 is error number - * mov r3 <- 0 // r3, r4... should be touched or - * // verifier would complain - * mov r4 <- 0 - * ... - * goto usercode - */ - error_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1), - &pos); - - for (i = 0; i < nargs; i++) - ins(BPF_ALU64_IMM(BPF_MOV, - BPF_PROLOGUE_START_ARG_REG + i, - 0), - &pos); - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE), - &pos); - } - - /* - * start of SUCCESS_CODE: - * mov r2 <- 0 - * goto usercode // skip - */ - success_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos); - - /* - * start of USER_CODE: - * Restore ctx to r1 - */ - user_code = pos.pos; - if (!fastpath) { - /* - * Only slow path needs restoring of ctx. In fast path, - * register are loaded directly from r1. - */ - ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos); - err = prologue_relocate(&pos, error_code, success_code, - user_code); - if (err) - goto errout; - } - - err = check_pos(&pos); - if (err) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; -errout: - return err; -} diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 90ce22f9c1a9..939ec769bf4a 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -23,7 +23,9 @@ #define MAX_CPUS 4096 // FIXME: These should come from system headers +#ifndef bool typedef char bool; +#endif typedef int pid_t; typedef long long int __s64; typedef __s64 time64_t; diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index 0a5bf1937a7c..c12f8320e668 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -80,16 +80,6 @@ struct hashmap { size_t sz; }; -#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ - .hash_fn = (hash_fn), \ - .equal_fn = (equal_fn), \ - .ctx = (ctx), \ - .buckets = NULL, \ - .cap = 0, \ - .cap_bits = 0, \ - .sz = 0, \ -} - void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, hashmap_equal_fn equal_fn, void *ctx); struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d85602aa4b9f..8de6f39abd1b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -520,7 +520,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, pmu_name = pe->pmu; } - alias = malloc(sizeof(*alias)); + alias = zalloc(sizeof(*alias)); if (!alias) return -ENOMEM; diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 22374d29ffdd..8202f1327c39 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -91,16 +91,18 @@ static int reg_disable(long *enable, int bit) FIXTURE(user) { long check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); change_event(false); self->check = 0; } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); } TEST_F(user, enablement) { diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 32c827a52d7d..a85980190bea 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -144,13 +144,16 @@ do { \ FIXTURE(user) { int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + wait_for_delete(); } diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 6a260caeeddc..dcd7509fe2e0 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -204,10 +204,11 @@ FIXTURE(user) { int data_fd; int enable_fd; int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); self->status_fd = open(status_file, O_RDONLY); ASSERT_NE(-1, self->status_fd); @@ -219,6 +220,8 @@ FIXTURE_SETUP(user) { } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + close(self->status_fd); close(self->data_fd); diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index f893398cda05..5288e768b207 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -111,16 +111,19 @@ static int clear(int *check) FIXTURE(user) { int data_fd; int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); self->data_fd = open(data_file, O_RDWR); ASSERT_NE(-1, self->data_fd); } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + close(self->data_fd); if (clear(&self->check) != 0) diff --git a/tools/testing/selftests/user_events/user_events_selftests.h b/tools/testing/selftests/user_events/user_events_selftests.h index 690378942f82..e1c3c063c031 100644 --- a/tools/testing/selftests/user_events/user_events_selftests.h +++ b/tools/testing/selftests/user_events/user_events_selftests.h @@ -11,13 +11,19 @@ #include "../kselftest.h" -static inline bool tracefs_enabled(char **message, bool *fail) +static inline void tracefs_unmount(void) +{ + umount("/sys/kernel/tracing"); +} + +static inline bool tracefs_enabled(char **message, bool *fail, bool *umount) { struct stat buf; int ret; *message = ""; *fail = false; + *umount = false; /* Ensure tracefs is installed */ ret = stat("/sys/kernel/tracing", &buf); @@ -37,6 +43,8 @@ static inline bool tracefs_enabled(char **message, bool *fail) return false; } + *umount = true; + ret = stat("/sys/kernel/tracing/README", &buf); } @@ -49,13 +57,14 @@ static inline bool tracefs_enabled(char **message, bool *fail) return true; } -static inline bool user_events_enabled(char **message, bool *fail) +static inline bool user_events_enabled(char **message, bool *fail, bool *umount) { struct stat buf; int ret; *message = ""; *fail = false; + *umount = false; if (getuid() != 0) { *message = "Must be run as root"; @@ -63,7 +72,7 @@ static inline bool user_events_enabled(char **message, bool *fail) return false; } - if (!tracefs_enabled(message, fail)) + if (!tracefs_enabled(message, fail, umount)) return false; /* Ensure user_events is installed */ @@ -85,10 +94,10 @@ static inline bool user_events_enabled(char **message, bool *fail) return true; } -#define USER_EVENT_FIXTURE_SETUP(statement) do { \ +#define USER_EVENT_FIXTURE_SETUP(statement, umount) do { \ char *message; \ bool fail; \ - if (!user_events_enabled(&message, &fail)) { \ + if (!user_events_enabled(&message, &fail, &(umount))) { \ if (fail) { \ TH_LOG("Setup failed due to: %s", message); \ ASSERT_FALSE(fail); \ @@ -97,4 +106,9 @@ static inline bool user_events_enabled(char **message, bool *fail) } \ } while (0) +#define USER_EVENT_FIXTURE_TEARDOWN(umount) do { \ + if ((umount)) \ + tracefs_unmount(); \ +} while (0) + #endif /* _USER_EVENTS_SELFTESTS_H */ |