diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 587a93973929..78240e29b0bb 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -586,6 +586,14 @@ without significant effort. The advantage of mounting with the "volatile" option is that all forms of sync calls to the upper filesystem are omitted. +In order to avoid a giving a false sense of safety, the syncfs (and fsync) +semantics of volatile mounts are slightly different than that of the rest of +VFS. If any writeback error occurs on the upperdir's filesystem after a +volatile mount takes place, all sync functions will return an error. Once this +condition is reached, the filesystem will not recover, and every subsequent sync +call will return an error, even if the upperdir has not experience a new error +since the last sync call. + When overlay is mounted with "volatile" option, the directory "$workdir/work/incompat/volatile" is created. During next mount, overlay checks for this directory and refuses to mount if present. This is a strong diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3412c4595efd..740f3bdb3f61 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -660,6 +660,17 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ + e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. @@ -717,15 +728,6 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { - /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 1db063b02f63..22566b4b3150 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2123,12 +2123,12 @@ void acpi_walk_dep_device_list(acpi_handle handle) list_for_each_entry_safe(dep, tmp, &acpi_dep_list, node) { if (dep->supplier == handle) { acpi_bus_get_device(dep->consumer, &adev); - if (!adev) - continue; - adev->dep_unmet--; - if (!adev->dep_unmet) - acpi_bus_attach(adev, true); + if (adev) { + adev->dep_unmet--; + if (!adev->dep_unmet) + acpi_bus_attach(adev, true); + } list_del(&dep->node); kfree(dep); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b9fecc25d213..790393d1e318 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1558,7 +1558,6 @@ int pci_save_state(struct pci_dev *dev) return i; pci_save_ltr_state(dev); - pci_save_aspm_l1ss_state(dev); pci_save_dpc_state(dev); pci_save_aer_state(dev); pci_save_ptm_state(dev); @@ -1665,7 +1664,6 @@ void pci_restore_state(struct pci_dev *dev) * LTR itself (in the PCIe capability). */ pci_restore_ltr_state(dev); - pci_restore_aspm_l1ss_state(dev); pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); @@ -3353,11 +3351,6 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev) if (error) pci_err(dev, "unable to allocate suspend buffer for LTR\n"); - error = pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_L1SS, - 2 * sizeof(u32)); - if (error) - pci_err(dev, "unable to allocate suspend buffer for ASPM-L1SS\n"); - pci_allocate_vc_save_buffers(dev); } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5c59365092fa..a7bdf0b1d45d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -582,15 +582,11 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); -void pci_save_aspm_l1ss_state(struct pci_dev *dev); -void pci_restore_aspm_l1ss_state(struct pci_dev *dev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } -static inline void pci_save_aspm_l1ss_state(struct pci_dev *dev) { } -static inline void pci_restore_aspm_l1ss_state(struct pci_dev *dev) { } #endif #ifdef CONFIG_PCIE_ECRC diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index a08e7d6dc248..ac0557a305af 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -734,50 +734,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) PCI_L1SS_CTL1_L1SS_MASK, val); } -void pci_save_aspm_l1ss_state(struct pci_dev *dev) -{ - int aspm_l1ss; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - aspm_l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS); - if (!aspm_l1ss) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS); - if (!save_state) - return; - - cap = (u32 *)&save_state->cap.data[0]; - pci_read_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL1, cap++); - pci_read_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL2, cap++); -} - -void pci_restore_aspm_l1ss_state(struct pci_dev *dev) -{ - int aspm_l1ss; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - aspm_l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS); - if (!aspm_l1ss) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS); - if (!save_state) - return; - - cap = (u32 *)&save_state->cap.data[0]; - pci_write_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL1, *cap++); - pci_write_config_dword(dev, aspm_l1ss + PCI_L1SS_CTL2, *cap++); -} - static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val) { pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL, diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index e5b616c93e11..0fed532efa68 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old, if (ovl_is_private_xattr(sb, name)) continue; + + error = security_inode_copy_up_xattr(name); + if (error < 0 && error != -EOPNOTSUPP) + break; + if (error == 1) { + error = 0; + continue; /* Discard */ + } retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) @@ -107,13 +115,6 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old, goto retry; } - error = security_inode_copy_up_xattr(name); - if (error < 0 && error != -EOPNOTSUPP) - break; - if (error == 1) { - error = 0; - continue; /* Discard */ - } error = vfs_setxattr(new, name, value, size, 0); if (error) { if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 28a075b5f5b2..d1efa3a5a503 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect) buflen -= thislen; memcpy(&buf[buflen], name, thislen); - tmp = dget_dlock(d->d_parent); spin_unlock(&d->d_lock); + tmp = dget_parent(d); dput(d); d = tmp; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 56be2ffc5a14..3d921e587a65 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -385,8 +385,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) const struct cred *old_cred; int ret; - if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb))) - return 0; + ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); + if (ret <= 0) + return ret; ret = ovl_real_fdget_meta(file, &real, !datasync); if (ret) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b22b9fb95c30..ea28c956fe73 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, goto out; if (!value && !upperdentry) { + old_cred = ovl_override_creds(dentry->d_sb); err = vfs_getxattr(realdentry, name, NULL, 0); + revert_creds(old_cred); if (err < 0) goto out_drop_write; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 4b8b2c53b672..95e005a617c3 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -326,6 +326,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry); bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry, int padding); +int ovl_sync_status(struct ovl_fs *ofs); static inline bool ovl_is_impuredir(struct super_block *sb, struct dentry *dentry) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index fbd5e27ce66b..63efee554f69 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -81,6 +81,8 @@ struct ovl_fs { atomic_long_t last_ino; /* Whiteout dentry cache */ struct dentry *whiteout; + /* r/o snapshot of upperdir sb's only taken on volatile mounts */ + errseq_t errseq; }; static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 01620ebae1bd..f404a78e6b60 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; - struct file *realfile = od->realfile; + struct file *old, *realfile = od->realfile; if (!OVL_TYPE_UPPER(ovl_path_type(dentry))) return want_upper ? NULL : realfile; @@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) * Need to check if we started out being a lower dir, but got copied up */ if (!od->is_upper) { - struct inode *inode = file_inode(file); - realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; ovl_path_upper(dentry, &upperpath); realfile = ovl_dir_open_realfile(file, &upperpath); + if (IS_ERR(realfile)) + return realfile; - inode_lock(inode); - if (!od->upperfile) { - if (IS_ERR(realfile)) { - inode_unlock(inode); - return realfile; - } - smp_store_release(&od->upperfile, realfile); - } else { - /* somebody has beaten us to it */ - if (!IS_ERR(realfile)) - fput(realfile); - realfile = od->upperfile; + old = cmpxchg_release(&od->upperfile, NULL, realfile); + if (old) { + fput(realfile); + realfile = old; } - inode_unlock(inode); } } @@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, struct file *realfile; int err; - if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb))) - return 0; + err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb)); + if (err <= 0) + return err; realfile = ovl_dir_real_file(file, true); err = PTR_ERR_OR_ZERO(realfile); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fdaa4487642a..944bdb06da7e 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait) struct super_block *upper_sb; int ret; - if (!ovl_upper_mnt(ofs)) - return 0; + ret = ovl_sync_status(ofs); + /* + * We have to always set the err, because the return value isn't + * checked in syncfs, and instead indirectly return an error via + * the sb's writeback errseq, which VFS inspects after this call. + */ + if (ret < 0) { + errseq_set(&sb->s_wb_err, -EIO); + return -EIO; + } + + if (!ret) + return ret; - if (!ovl_should_sync(ofs)) - return 0; /* * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC). * All the super blocks will be iterated, including upper_sb. @@ -1925,6 +1934,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) unsigned int numlower; int err; + err = -EIO; + if (WARN_ON(sb->s_user_ns != current_user_ns())) + goto out; + sb->s_d_op = &ovl_dentry_operations; err = -ENOMEM; @@ -1991,6 +2004,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ovl_super_operations; if (ofs->config.upperdir) { + struct super_block *upper_sb; + if (!ofs->config.workdir) { pr_err("missing 'workdir'\n"); goto out_err; @@ -2000,6 +2015,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_err; + upper_sb = ovl_upper_mnt(ofs)->mnt_sb; + if (!ovl_should_sync(ofs)) { + ofs->errseq = errseq_sample(&upper_sb->s_wb_err); + if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) { + err = -EIO; + pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n"); + goto out_err; + } + } + err = ovl_get_workdir(sb, ofs, &upperpath); if (err) goto out_err; @@ -2007,9 +2032,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!ofs->workdir) sb->s_flags |= SB_RDONLY; - sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth; - sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran; - + sb->s_stack_depth = upper_sb->s_stack_depth; + sb->s_time_gran = upper_sb->s_time_gran; } oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers); err = PTR_ERR(oe); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index c258e97d52a1..c469356f2522 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -962,3 +962,30 @@ char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry, kfree(buf); return ERR_PTR(res); } + +/* + * ovl_sync_status() - Check fs sync status for volatile mounts + * + * Returns 1 if this is not a volatile mount and a real sync is required. + * + * Returns 0 if syncing can be skipped because mount is volatile, and no errors + * have occurred on the upperdir since the mount. + * + * Returns -errno if it is a volatile mount, and the error that occurred since + * the last mount. If the error code changes, it'll return the latest error + * code. + */ + +int ovl_sync_status(struct ovl_fs *ofs) +{ + struct vfsmount *mnt; + + if (ovl_should_sync(ofs)) + return 1; + + mnt = ovl_upper_mnt(ofs); + if (!mnt) + return 0; + + return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq); +} diff --git a/security/commoncap.c b/security/commoncap.c index 0266980ce490..53d0b19b61a6 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -372,10 +372,11 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, { int size, ret; kuid_t kroot; + u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; - struct vfs_ns_cap_data *nscap; + struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; @@ -397,46 +398,61 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { - /* If this is sizeof(vfs_cap_data) then we're ok with the - * on-disk value, so return that. */ - if (alloc) - *buffer = tmpbuf; - else - kfree(tmpbuf); - return ret; - } else if (!is_v3header((size_t) ret, cap)) { - kfree(tmpbuf); - return -EINVAL; + root = 0; + } else if (is_v3header((size_t) ret, cap)) { + nscap = (struct vfs_ns_cap_data *) tmpbuf; + root = le32_to_cpu(nscap->rootid); + } else { + size = -EINVAL; + goto out_free; } - nscap = (struct vfs_ns_cap_data *) tmpbuf; - root = le32_to_cpu(nscap->rootid); kroot = make_kuid(fs_ns, root); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { + size = sizeof(struct vfs_ns_cap_data); if (alloc) { - *buffer = tmpbuf; + if (!nscap) { + /* v2 -> v3 conversion */ + nscap = kzalloc(size, GFP_ATOMIC); + if (!nscap) { + size = -ENOMEM; + goto out_free; + } + nsmagic = VFS_CAP_REVISION_3; + magic = le32_to_cpu(cap->magic_etc); + if (magic & VFS_CAP_FLAGS_EFFECTIVE) + nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; + memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); + nscap->magic_etc = cpu_to_le32(nsmagic); + } else { + /* use allocated v3 buffer */ + tmpbuf = NULL; + } nscap->rootid = cpu_to_le32(mappedroot); - } else - kfree(tmpbuf); - return size; + *buffer = nscap; + } + goto out_free; } if (!rootid_owns_currentns(kroot)) { - kfree(tmpbuf); - return -EOPNOTSUPP; + size = -EOVERFLOW; + goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { - *buffer = kmalloc(size, GFP_ATOMIC); - if (*buffer) { - struct vfs_cap_data *cap = *buffer; - __le32 nsmagic, magic; + if (nscap) { + /* v3 -> v2 conversion */ + cap = kzalloc(size, GFP_ATOMIC); + if (!cap) { + size = -ENOMEM; + goto out_free; + } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) @@ -444,9 +460,12 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { - size = -ENOMEM; + /* use unconverted v2 */ + tmpbuf = NULL; } + *buffer = cap; } +out_free: kfree(tmpbuf); return size; }