linux/fs/efivarfs/super.c

428 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 Red Hat, Inc.
* Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
*/
#include <linux/ctype.h>
#include <linux/efi.h>
#include <linux/fs.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/ucs2_string.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/statfs.h>
#include <linux/notifier.h>
efivarfs: force RO when remounting if SetVariable is not supported If SetVariable at runtime is not supported by the firmware we never assign a callback for that function. At the same time mount the efivarfs as RO so no one can call that. However, we never check the permission flags when someone remounts the filesystem as RW. As a result this leads to a crash looking like this: $ mount -o remount,rw /sys/firmware/efi/efivars $ efi-updatevar -f PK.auth PK [ 303.279166] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 303.280482] Mem abort info: [ 303.280854] ESR = 0x0000000086000004 [ 303.281338] EC = 0x21: IABT (current EL), IL = 32 bits [ 303.282016] SET = 0, FnV = 0 [ 303.282414] EA = 0, S1PTW = 0 [ 303.282821] FSC = 0x04: level 0 translation fault [ 303.283771] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004258c000 [ 303.284913] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 303.286076] Internal error: Oops: 0000000086000004 [#1] PREEMPT SMP [ 303.286936] Modules linked in: qrtr tpm_tis tpm_tis_core crct10dif_ce arm_smccc_trng rng_core drm fuse ip_tables x_tables ipv6 [ 303.288586] CPU: 1 PID: 755 Comm: efi-updatevar Not tainted 6.3.0-rc1-00108-gc7d0c4695c68 #1 [ 303.289748] Hardware name: Unknown Unknown Product/Unknown Product, BIOS 2023.04-00627-g88336918701d 04/01/2023 [ 303.291150] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 303.292123] pc : 0x0 [ 303.292443] lr : efivar_set_variable_locked+0x74/0xec [ 303.293156] sp : ffff800008673c10 [ 303.293619] x29: ffff800008673c10 x28: ffff0000037e8000 x27: 0000000000000000 [ 303.294592] x26: 0000000000000800 x25: ffff000002467400 x24: 0000000000000027 [ 303.295572] x23: ffffd49ea9832000 x22: ffff0000020c9800 x21: ffff000002467000 [ 303.296566] x20: 0000000000000001 x19: 00000000000007fc x18: 0000000000000000 [ 303.297531] x17: 0000000000000000 x16: 0000000000000000 x15: 0000aaaac807ab54 [ 303.298495] x14: ed37489f673633c0 x13: 71c45c606de13f80 x12: 47464259e219acf4 [ 303.299453] x11: ffff000002af7b01 x10: 0000000000000003 x9 : 0000000000000002 [ 303.300431] x8 : 0000000000000010 x7 : ffffd49ea8973230 x6 : 0000000000a85201 [ 303.301412] x5 : 0000000000000000 x4 : ffff0000020c9800 x3 : 00000000000007fc [ 303.302370] x2 : 0000000000000027 x1 : ffff000002467400 x0 : ffff000002467000 [ 303.303341] Call trace: [ 303.303679] 0x0 [ 303.303938] efivar_entry_set_get_size+0x98/0x16c [ 303.304585] efivarfs_file_write+0xd0/0x1a4 [ 303.305148] vfs_write+0xc4/0x2e4 [ 303.305601] ksys_write+0x70/0x104 [ 303.306073] __arm64_sys_write+0x1c/0x28 [ 303.306622] invoke_syscall+0x48/0x114 [ 303.307156] el0_svc_common.constprop.0+0x44/0xec [ 303.307803] do_el0_svc+0x38/0x98 [ 303.308268] el0_svc+0x2c/0x84 [ 303.308702] el0t_64_sync_handler+0xf4/0x120 [ 303.309293] el0t_64_sync+0x190/0x194 [ 303.309794] Code: ???????? ???????? ???????? ???????? (????????) [ 303.310612] ---[ end trace 0000000000000000 ]--- Fix this by adding a .reconfigure() function to the fs operations which we can use to check the requested flags and deny anything that's not RO if the firmware doesn't implement SetVariable at runtime. Fixes: f88814cc2578 ("efi/efivars: Expose RT service availability via efivars abstraction") Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-11-07 05:40:56 +00:00
#include <linux/printk.h>
#include "internal.h"
static int efivarfs_ops_notifier(struct notifier_block *nb, unsigned long event,
void *data)
{
struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info, nb);
switch (event) {
case EFIVAR_OPS_RDONLY:
sfi->sb->s_flags |= SB_RDONLY;
break;
case EFIVAR_OPS_RDWR:
sfi->sb->s_flags &= ~SB_RDONLY;
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
static void efivarfs_evict_inode(struct inode *inode)
{
clear_inode(inode);
}
static int efivarfs_show_options(struct seq_file *m, struct dentry *root)
{
struct super_block *sb = root->d_sb;
struct efivarfs_fs_info *sbi = sb->s_fs_info;
struct efivarfs_mount_opts *opts = &sbi->mount_opts;
if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
from_kuid_munged(&init_user_ns, opts->uid));
if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, opts->gid));
return 0;
}
static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
const u32 attr = EFI_VARIABLE_NON_VOLATILE |
EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS;
u64 storage_space, remaining_space, max_variable_size;
fs: report f_fsid from s_dev for "simple" filesystems There are many "simple" filesystems (*) that report null f_fsid in statfs(2). Those "simple" filesystems report sb->s_dev as the st_dev field of the stat syscalls for all inodes of the filesystem (**). In order to enable fanotify reporting of events with fsid on those "simple" filesystems, report the sb->s_dev number in f_fsid field of statfs(2). (*) For most of the "simple" filesystem refered to in this commit, the ->statfs() operation is simple_statfs(). Some of those fs assign the simple_statfs() method directly in their ->s_op struct and some assign it indirectly via a call to simple_fill_super() or to pseudo_fs_fill_super() with either custom or "simple" s_op. We also make the same change to efivarfs and hugetlbfs, although they do not use simple_statfs(), because they use the simple_* inode opreations (e.g. simple_lookup()). (**) For most of the "simple" filesystems, the ->getattr() method is not assigned, so stat() is implemented by generic_fillattr(). A few "simple" filesystem use the simple_getattr() method which also calls generic_fillattr() to fill most of the stat struct. The two exceptions are procfs and 9p. procfs implements several different ->getattr() methods, but they all end up calling generic_fillattr() to fill the st_dev field from sb->s_dev. 9p has more complicated ->getattr() methods, but they too, end up calling generic_fillattr() to fill the st_dev field from sb->s_dev. Note that 9p and kernfs also call simple_statfs() from custom ->statfs() methods which already fill the f_fsid field, but v9fs_statfs() calls simple_statfs() only in case f_fsid was not filled and kenrfs_statfs() overwrites f_fsid after calling simple_statfs(). Link: https://lore.kernel.org/r/20230919094820.g5bwharbmy2dq46w@quack3/ Signed-off-by: Amir Goldstein <amir73il@gmail.com> Link: https://lore.kernel.org/r/20231023143049.2944970-1-amir73il@gmail.com Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-10-23 14:30:49 +00:00
u64 id = huge_encode_dev(dentry->d_sb->s_dev);
efi_status_t status;
/* Some UEFI firmware does not implement QueryVariableInfo() */
storage_space = remaining_space = 0;
if (efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) {
status = efivar_query_variable_info(attr, &storage_space,
&remaining_space,
&max_variable_size);
if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED)
pr_warn_ratelimited("query_variable_info() failed: 0x%lx\n",
status);
}
/*
* This is not a normal filesystem, so no point in pretending it has a block
* size; we declare f_bsize to 1, so that we can then report the exact value
* sent by EFI QueryVariableInfo in f_blocks and f_bfree
*/
buf->f_bsize = 1;
buf->f_namelen = NAME_MAX;
buf->f_blocks = storage_space;
buf->f_bfree = remaining_space;
buf->f_type = dentry->d_sb->s_magic;
fs: report f_fsid from s_dev for "simple" filesystems There are many "simple" filesystems (*) that report null f_fsid in statfs(2). Those "simple" filesystems report sb->s_dev as the st_dev field of the stat syscalls for all inodes of the filesystem (**). In order to enable fanotify reporting of events with fsid on those "simple" filesystems, report the sb->s_dev number in f_fsid field of statfs(2). (*) For most of the "simple" filesystem refered to in this commit, the ->statfs() operation is simple_statfs(). Some of those fs assign the simple_statfs() method directly in their ->s_op struct and some assign it indirectly via a call to simple_fill_super() or to pseudo_fs_fill_super() with either custom or "simple" s_op. We also make the same change to efivarfs and hugetlbfs, although they do not use simple_statfs(), because they use the simple_* inode opreations (e.g. simple_lookup()). (**) For most of the "simple" filesystems, the ->getattr() method is not assigned, so stat() is implemented by generic_fillattr(). A few "simple" filesystem use the simple_getattr() method which also calls generic_fillattr() to fill most of the stat struct. The two exceptions are procfs and 9p. procfs implements several different ->getattr() methods, but they all end up calling generic_fillattr() to fill the st_dev field from sb->s_dev. 9p has more complicated ->getattr() methods, but they too, end up calling generic_fillattr() to fill the st_dev field from sb->s_dev. Note that 9p and kernfs also call simple_statfs() from custom ->statfs() methods which already fill the f_fsid field, but v9fs_statfs() calls simple_statfs() only in case f_fsid was not filled and kenrfs_statfs() overwrites f_fsid after calling simple_statfs(). Link: https://lore.kernel.org/r/20230919094820.g5bwharbmy2dq46w@quack3/ Signed-off-by: Amir Goldstein <amir73il@gmail.com> Link: https://lore.kernel.org/r/20231023143049.2944970-1-amir73il@gmail.com Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-10-23 14:30:49 +00:00
buf->f_fsid = u64_to_fsid(id);
/*
* In f_bavail we declare the free space that the kernel will allow writing
* when the storage_paranoia x86 quirk is active. To use more, users
* should boot the kernel with efi_no_storage_paranoia.
*/
if (remaining_space > efivar_reserved_space())
buf->f_bavail = remaining_space - efivar_reserved_space();
else
buf->f_bavail = 0;
return 0;
}
static const struct super_operations efivarfs_ops = {
.statfs = efivarfs_statfs,
.drop_inode = generic_delete_inode,
.evict_inode = efivarfs_evict_inode,
.show_options = efivarfs_show_options,
};
/*
* Compare two efivarfs file names.
*
* An efivarfs filename is composed of two parts,
*
* 1. A case-sensitive variable name
* 2. A case-insensitive GUID
*
* So we need to perform a case-sensitive match on part 1 and a
* case-insensitive match on part 2.
*/
static int efivarfs_d_compare(const struct dentry *dentry,
unsigned int len, const char *str,
const struct qstr *name)
{
int guid = len - EFI_VARIABLE_GUID_LEN;
if (name->len != len)
return 1;
/* Case-sensitive compare for the variable name */
if (memcmp(str, name->name, guid))
return 1;
/* Case-insensitive compare for the GUID */
return strncasecmp(name->name + guid, str + guid, EFI_VARIABLE_GUID_LEN);
}
static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr)
{
unsigned long hash = init_name_hash(dentry);
const unsigned char *s = qstr->name;
unsigned int len = qstr->len;
if (!efivarfs_valid_name(s, len))
return -EINVAL;
while (len-- > EFI_VARIABLE_GUID_LEN)
hash = partial_name_hash(*s++, hash);
/* GUID is case-insensitive. */
while (len--)
hash = partial_name_hash(tolower(*s++), hash);
qstr->hash = end_name_hash(hash);
return 0;
}
static const struct dentry_operations efivarfs_d_ops = {
.d_compare = efivarfs_d_compare,
.d_hash = efivarfs_d_hash,
.d_delete = always_delete_dentry,
};
static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name)
{
struct dentry *d;
struct qstr q;
int err;
q.name = name;
q.len = strlen(name);
err = efivarfs_d_hash(parent, &q);
if (err)
return ERR_PTR(err);
d = d_alloc(parent, &q);
if (d)
return d;
return ERR_PTR(-ENOMEM);
}
static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
unsigned long name_size, void *data,
struct list_head *list)
{
struct super_block *sb = (struct super_block *)data;
struct efivar_entry *entry;
struct inode *inode = NULL;
struct dentry *dentry, *root = sb->s_root;
unsigned long size = 0;
char *name;
int len;
int err = -ENOMEM;
bool is_removable = false;
if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID))
return 0;
entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return err;
memcpy(entry->var.VariableName, name16, name_size);
memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
len = ucs2_utf8size(entry->var.VariableName);
/* name, plus '-', plus GUID, plus NUL*/
name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
if (!name)
goto fail;
ucs2_as_utf8(name, entry->var.VariableName, len);
if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
is_removable = true;
name[len] = '-';
efi_guid_to_str(&entry->var.VendorGuid, name + len + 1);
name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
/* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */
strreplace(name, '/', '!');
inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
is_removable);
if (!inode)
goto fail_name;
dentry = efivarfs_alloc_dentry(root, name);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto fail_inode;
}
__efivar_entry_get(entry, NULL, &size, NULL);
__efivar_entry_add(entry, list);
/* copied by the above to local storage in the dentry. */
kfree(name);
inode_lock(inode);
inode->i_private = entry;
i_size_write(inode, size + sizeof(entry->var.Attributes));
inode_unlock(inode);
d_add(dentry, inode);
return 0;
fail_inode:
iput(inode);
fail_name:
kfree(name);
fail:
kfree(entry);
return err;
}
static int efivarfs_destroy(struct efivar_entry *entry, void *data)
{
efivar_entry_remove(entry);
kfree(entry);
return 0;
}
enum {
Opt_uid, Opt_gid,
};
static const struct fs_parameter_spec efivarfs_parameters[] = {
fsparam_u32("uid", Opt_uid),
fsparam_u32("gid", Opt_gid),
{},
};
static int efivarfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct efivarfs_fs_info *sbi = fc->s_fs_info;
struct efivarfs_mount_opts *opts = &sbi->mount_opts;
struct fs_parse_result result;
int opt;
opt = fs_parse(fc, efivarfs_parameters, param, &result);
if (opt < 0)
return opt;
switch (opt) {
case Opt_uid:
opts->uid = make_kuid(current_user_ns(), result.uint_32);
if (!uid_valid(opts->uid))
return -EINVAL;
break;
case Opt_gid:
opts->gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(opts->gid))
return -EINVAL;
break;
default:
return -EINVAL;
}
return 0;
}
static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct efivarfs_fs_info *sfi = sb->s_fs_info;
struct inode *inode = NULL;
struct dentry *root;
int err;
sb->s_maxbytes = MAX_LFS_FILESIZE;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = EFIVARFS_MAGIC;
sb->s_op = &efivarfs_ops;
sb->s_d_op = &efivarfs_d_ops;
sb->s_time_gran = 1;
efi/efivars: Expose RT service availability via efivars abstraction Commit bf67fad19e493b ("efi: Use more granular check for availability for variable services") introduced a check into the efivarfs, efi-pstore and other drivers that aborts loading of the module if not all three variable runtime services (GetVariable, SetVariable and GetNextVariable) are supported. However, this results in efivarfs being unavailable entirely if only SetVariable support is missing, which is only needed if you want to make any modifications. Also, efi-pstore and the sysfs EFI variable interface could be backed by another implementation of the 'efivars' abstraction, in which case it is completely irrelevant which services are supported by the EFI firmware. So make the generic 'efivars' abstraction dependent on the availibility of the GetVariable and GetNextVariable EFI runtime services, and add a helper 'efivar_supports_writes()' to find out whether the currently active efivars abstraction supports writes (and wire it up to the availability of SetVariable for the generic one). Then, use the efivar_supports_writes() helper to decide whether to permit efivarfs to be mounted read-write, and whether to enable efi-pstore or the sysfs EFI variable interface altogether. Fixes: bf67fad19e493b ("efi: Use more granular check for availability for variable services") Reported-by: Heinrich Schuchardt <xypron.glpk@gmx.de> Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Tested-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2020-07-08 10:01:57 +00:00
if (!efivar_supports_writes())
sb->s_flags |= SB_RDONLY;
inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
if (!inode)
return -ENOMEM;
inode->i_op = &efivarfs_dir_inode_operations;
root = d_make_root(inode);
sb->s_root = root;
if (!root)
return -ENOMEM;
sfi->sb = sb;
sfi->nb.notifier_call = efivarfs_ops_notifier;
err = blocking_notifier_chain_register(&efivar_ops_nh, &sfi->nb);
if (err)
return err;
return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list);
}
static int efivarfs_get_tree(struct fs_context *fc)
{
return get_tree_single(fc, efivarfs_fill_super);
}
efivarfs: force RO when remounting if SetVariable is not supported If SetVariable at runtime is not supported by the firmware we never assign a callback for that function. At the same time mount the efivarfs as RO so no one can call that. However, we never check the permission flags when someone remounts the filesystem as RW. As a result this leads to a crash looking like this: $ mount -o remount,rw /sys/firmware/efi/efivars $ efi-updatevar -f PK.auth PK [ 303.279166] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 303.280482] Mem abort info: [ 303.280854] ESR = 0x0000000086000004 [ 303.281338] EC = 0x21: IABT (current EL), IL = 32 bits [ 303.282016] SET = 0, FnV = 0 [ 303.282414] EA = 0, S1PTW = 0 [ 303.282821] FSC = 0x04: level 0 translation fault [ 303.283771] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004258c000 [ 303.284913] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 303.286076] Internal error: Oops: 0000000086000004 [#1] PREEMPT SMP [ 303.286936] Modules linked in: qrtr tpm_tis tpm_tis_core crct10dif_ce arm_smccc_trng rng_core drm fuse ip_tables x_tables ipv6 [ 303.288586] CPU: 1 PID: 755 Comm: efi-updatevar Not tainted 6.3.0-rc1-00108-gc7d0c4695c68 #1 [ 303.289748] Hardware name: Unknown Unknown Product/Unknown Product, BIOS 2023.04-00627-g88336918701d 04/01/2023 [ 303.291150] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 303.292123] pc : 0x0 [ 303.292443] lr : efivar_set_variable_locked+0x74/0xec [ 303.293156] sp : ffff800008673c10 [ 303.293619] x29: ffff800008673c10 x28: ffff0000037e8000 x27: 0000000000000000 [ 303.294592] x26: 0000000000000800 x25: ffff000002467400 x24: 0000000000000027 [ 303.295572] x23: ffffd49ea9832000 x22: ffff0000020c9800 x21: ffff000002467000 [ 303.296566] x20: 0000000000000001 x19: 00000000000007fc x18: 0000000000000000 [ 303.297531] x17: 0000000000000000 x16: 0000000000000000 x15: 0000aaaac807ab54 [ 303.298495] x14: ed37489f673633c0 x13: 71c45c606de13f80 x12: 47464259e219acf4 [ 303.299453] x11: ffff000002af7b01 x10: 0000000000000003 x9 : 0000000000000002 [ 303.300431] x8 : 0000000000000010 x7 : ffffd49ea8973230 x6 : 0000000000a85201 [ 303.301412] x5 : 0000000000000000 x4 : ffff0000020c9800 x3 : 00000000000007fc [ 303.302370] x2 : 0000000000000027 x1 : ffff000002467400 x0 : ffff000002467000 [ 303.303341] Call trace: [ 303.303679] 0x0 [ 303.303938] efivar_entry_set_get_size+0x98/0x16c [ 303.304585] efivarfs_file_write+0xd0/0x1a4 [ 303.305148] vfs_write+0xc4/0x2e4 [ 303.305601] ksys_write+0x70/0x104 [ 303.306073] __arm64_sys_write+0x1c/0x28 [ 303.306622] invoke_syscall+0x48/0x114 [ 303.307156] el0_svc_common.constprop.0+0x44/0xec [ 303.307803] do_el0_svc+0x38/0x98 [ 303.308268] el0_svc+0x2c/0x84 [ 303.308702] el0t_64_sync_handler+0xf4/0x120 [ 303.309293] el0t_64_sync+0x190/0x194 [ 303.309794] Code: ???????? ???????? ???????? ???????? (????????) [ 303.310612] ---[ end trace 0000000000000000 ]--- Fix this by adding a .reconfigure() function to the fs operations which we can use to check the requested flags and deny anything that's not RO if the firmware doesn't implement SetVariable at runtime. Fixes: f88814cc2578 ("efi/efivars: Expose RT service availability via efivars abstraction") Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-11-07 05:40:56 +00:00
static int efivarfs_reconfigure(struct fs_context *fc)
{
if (!efivar_supports_writes() && !(fc->sb_flags & SB_RDONLY)) {
pr_err("Firmware does not support SetVariableRT. Can not remount with rw\n");
return -EINVAL;
}
return 0;
}
static const struct fs_context_operations efivarfs_context_ops = {
.get_tree = efivarfs_get_tree,
.parse_param = efivarfs_parse_param,
efivarfs: force RO when remounting if SetVariable is not supported If SetVariable at runtime is not supported by the firmware we never assign a callback for that function. At the same time mount the efivarfs as RO so no one can call that. However, we never check the permission flags when someone remounts the filesystem as RW. As a result this leads to a crash looking like this: $ mount -o remount,rw /sys/firmware/efi/efivars $ efi-updatevar -f PK.auth PK [ 303.279166] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 303.280482] Mem abort info: [ 303.280854] ESR = 0x0000000086000004 [ 303.281338] EC = 0x21: IABT (current EL), IL = 32 bits [ 303.282016] SET = 0, FnV = 0 [ 303.282414] EA = 0, S1PTW = 0 [ 303.282821] FSC = 0x04: level 0 translation fault [ 303.283771] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004258c000 [ 303.284913] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 303.286076] Internal error: Oops: 0000000086000004 [#1] PREEMPT SMP [ 303.286936] Modules linked in: qrtr tpm_tis tpm_tis_core crct10dif_ce arm_smccc_trng rng_core drm fuse ip_tables x_tables ipv6 [ 303.288586] CPU: 1 PID: 755 Comm: efi-updatevar Not tainted 6.3.0-rc1-00108-gc7d0c4695c68 #1 [ 303.289748] Hardware name: Unknown Unknown Product/Unknown Product, BIOS 2023.04-00627-g88336918701d 04/01/2023 [ 303.291150] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 303.292123] pc : 0x0 [ 303.292443] lr : efivar_set_variable_locked+0x74/0xec [ 303.293156] sp : ffff800008673c10 [ 303.293619] x29: ffff800008673c10 x28: ffff0000037e8000 x27: 0000000000000000 [ 303.294592] x26: 0000000000000800 x25: ffff000002467400 x24: 0000000000000027 [ 303.295572] x23: ffffd49ea9832000 x22: ffff0000020c9800 x21: ffff000002467000 [ 303.296566] x20: 0000000000000001 x19: 00000000000007fc x18: 0000000000000000 [ 303.297531] x17: 0000000000000000 x16: 0000000000000000 x15: 0000aaaac807ab54 [ 303.298495] x14: ed37489f673633c0 x13: 71c45c606de13f80 x12: 47464259e219acf4 [ 303.299453] x11: ffff000002af7b01 x10: 0000000000000003 x9 : 0000000000000002 [ 303.300431] x8 : 0000000000000010 x7 : ffffd49ea8973230 x6 : 0000000000a85201 [ 303.301412] x5 : 0000000000000000 x4 : ffff0000020c9800 x3 : 00000000000007fc [ 303.302370] x2 : 0000000000000027 x1 : ffff000002467400 x0 : ffff000002467000 [ 303.303341] Call trace: [ 303.303679] 0x0 [ 303.303938] efivar_entry_set_get_size+0x98/0x16c [ 303.304585] efivarfs_file_write+0xd0/0x1a4 [ 303.305148] vfs_write+0xc4/0x2e4 [ 303.305601] ksys_write+0x70/0x104 [ 303.306073] __arm64_sys_write+0x1c/0x28 [ 303.306622] invoke_syscall+0x48/0x114 [ 303.307156] el0_svc_common.constprop.0+0x44/0xec [ 303.307803] do_el0_svc+0x38/0x98 [ 303.308268] el0_svc+0x2c/0x84 [ 303.308702] el0t_64_sync_handler+0xf4/0x120 [ 303.309293] el0t_64_sync+0x190/0x194 [ 303.309794] Code: ???????? ???????? ???????? ???????? (????????) [ 303.310612] ---[ end trace 0000000000000000 ]--- Fix this by adding a .reconfigure() function to the fs operations which we can use to check the requested flags and deny anything that's not RO if the firmware doesn't implement SetVariable at runtime. Fixes: f88814cc2578 ("efi/efivars: Expose RT service availability via efivars abstraction") Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-11-07 05:40:56 +00:00
.reconfigure = efivarfs_reconfigure,
};
static int efivarfs_init_fs_context(struct fs_context *fc)
{
struct efivarfs_fs_info *sfi;
if (!efivar_is_available())
return -EOPNOTSUPP;
sfi = kzalloc(sizeof(*sfi), GFP_KERNEL);
if (!sfi)
return -ENOMEM;
INIT_LIST_HEAD(&sfi->efivarfs_list);
sfi->mount_opts.uid = GLOBAL_ROOT_UID;
sfi->mount_opts.gid = GLOBAL_ROOT_GID;
fc->s_fs_info = sfi;
fc->ops = &efivarfs_context_ops;
return 0;
}
static void efivarfs_kill_sb(struct super_block *sb)
{
struct efivarfs_fs_info *sfi = sb->s_fs_info;
blocking_notifier_chain_unregister(&efivar_ops_nh, &sfi->nb);
kill_litter_super(sb);
/* Remove all entries and destroy */
efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL);
kfree(sfi);
}
static struct file_system_type efivarfs_type = {
.owner = THIS_MODULE,
.name = "efivarfs",
.init_fs_context = efivarfs_init_fs_context,
.kill_sb = efivarfs_kill_sb,
.parameters = efivarfs_parameters,
};
static __init int efivarfs_init(void)
{
return register_filesystem(&efivarfs_type);
}
static __exit void efivarfs_exit(void)
{
unregister_filesystem(&efivarfs_type);
}
MODULE_AUTHOR("Matthew Garrett, Jeremy Kerr");
MODULE_DESCRIPTION("EFI Variable Filesystem");
MODULE_LICENSE("GPL");
MODULE_ALIAS_FS("efivarfs");
module_init(efivarfs_init);
module_exit(efivarfs_exit);