From: Greg Kroah-Hartman gregkh@linuxfoundation.org

ixp4xx_timer_setup is exported, and so can not be an __init function. Remove the __init marking as the build system is rightfully claiming this is an error in older kernels.

This is fixed "properly" in commit 41929c9f628b ("clocksource/drivers/ixp4xx: Drop boardfile probe path") but that can not be backported to older kernels as the reworking of the IXP4xx codebase is not suitable for stable releases.

Cc: Linus Walleij linus.walleij@linaro.org Cc: Daniel Lezcano daniel.lezcano@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/clocksource/mmio.c | 2 +- drivers/clocksource/timer-ixp4xx.c | 10 ++++------ include/linux/platform_data/timer-ixp4xx.h | 5 ++--- 3 files changed, 7 insertions(+), 10 deletions(-)

--- a/drivers/clocksource/mmio.c +++ b/drivers/clocksource/mmio.c @@ -46,7 +46,7 @@ u64 clocksource_mmio_readw_down(struct c * @bits: Number of valid bits * @read: One of clocksource_mmio_read*() above */ -int __init clocksource_mmio_init(void __iomem *base, const char *name, +int clocksource_mmio_init(void __iomem *base, const char *name, unsigned long hz, int rating, unsigned bits, u64 (*read)(struct clocksource *)) { --- a/drivers/clocksource/timer-ixp4xx.c +++ b/drivers/clocksource/timer-ixp4xx.c @@ -161,9 +161,8 @@ static int ixp4xx_resume(struct clock_ev * We use OS timer1 on the CPU for the timer tick and the timestamp * counter as a source of real clock ticks to account for missed jiffies. */ -static __init int ixp4xx_timer_register(void __iomem *base, - int timer_irq, - unsigned int timer_freq) +static int ixp4xx_timer_register(void __iomem *base, int timer_irq, + unsigned int timer_freq) { struct ixp4xx_timer *tmr; int ret; @@ -269,9 +268,8 @@ builtin_platform_driver(ixp4xx_timer_dri * @timer_irq: Linux IRQ number for the timer * @timer_freq: Fixed frequency of the timer */ -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq) +void ixp4xx_timer_setup(resource_size_t timerbase, int timer_irq, + unsigned int timer_freq) { void __iomem *base;

--- a/include/linux/platform_data/timer-ixp4xx.h +++ b/include/linux/platform_data/timer-ixp4xx.h @@ -4,8 +4,7 @@

#include <linux/ioport.h>

-void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq); +void ixp4xx_timer_setup(resource_size_t timerbase, int timer_irq, + unsigned int timer_freq);

#endif

From: Coly Li colyli@suse.de

commit 7d6b902ea0e02b2a25c480edf471cbaa4ebe6b3c upstream.

The local variables check_state (in bch_btree_check()) and state (in bch_sectors_dirty_init()) should be fully filled by 0, because before allocating them on stack, they were dynamically allocated by kzalloc().

Signed-off-by: Coly Li colyli@suse.de Link: https://lore.kernel.org/r/20220527152818.27545-2-colyli@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/bcache/btree.c | 1 + drivers/md/bcache/writeback.c | 1 + 2 files changed, 2 insertions(+)

--- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -2017,6 +2017,7 @@ int bch_btree_check(struct cache_set *c) if (c->root->level == 0) return 0;

+ memset(&check_state, 0, sizeof(struct btree_check_state)); check_state.c = c; check_state.total_threads = bch_btree_chkthread_nr(); check_state.key_idx = 0; --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -947,6 +947,7 @@ void bch_sectors_dirty_init(struct bcach return; }

+ memset(&state, 0, sizeof(struct bch_dirty_init_state)); state.c = c; state.d = d; state.total_threads = bch_btre_dirty_init_thread_nr();

From: Brian Foster bfoster@redhat.com

[ Upstream commit 5ca5916b6bc93577c360c06cb7cdf71adb9b5faf ]

If writeback I/O to a COW extent fails, the COW fork blocks are punched out and the data fork blocks left alone. It is possible for COW fork blocks to overlap non-shared data fork blocks (due to cowextsz hint prealloc), however, and writeback unconditionally maps to the COW fork whenever blocks exist at the corresponding offset of the page undergoing writeback. This means it's quite possible for a COW fork extent to overlap delalloc data fork blocks, writeback to convert and map to the COW fork blocks, writeback to fail, and finally for ioend completion to cancel the COW fork blocks and leave stale data fork delalloc blocks around in the inode. The blocks are effectively stale because writeback failure also discards dirty page state.

If this occurs, it is likely to trigger assert failures, free space accounting corruption and failures in unrelated file operations. For example, a subsequent reflink attempt of the affected file to a new target file will trip over the stale delalloc in the source file and fail. Several of these issues are occasionally reproduced by generic/648, but are reproducible on demand with the right sequence of operations and timely I/O error injection.

To fix this problem, update the ioend failure path to also punch out underlying data fork delalloc blocks on I/O error. This is analogous to the writeback submission failure path in xfs_discard_page() where we might fail to map data fork delalloc blocks and consistent with the successful COW writeback completion path, which is responsible for unmapping from the data fork and remapping in COW fork blocks.

Fixes: 787eb485509f ("xfs: fix and streamline error handling in xfs_end_io") Signed-off-by: Brian Foster bfoster@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_aops.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -82,6 +82,7 @@ xfs_end_ioend( struct iomap_ioend *ioend) { struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_mount *mp = ip->i_mount; xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; unsigned int nofs_flag; @@ -97,18 +98,26 @@ xfs_end_ioend( /* * Just clean up the in-memory structures if the fs has been shut down. */ - if (xfs_is_shutdown(ip->i_mount)) { + if (xfs_is_shutdown(mp)) { error = -EIO; goto done; }

/* - * Clean up any COW blocks on an I/O error. + * Clean up all COW blocks and underlying data fork delalloc blocks on + * I/O error. The delalloc punch is required because this ioend was + * mapped to blocks in the COW fork and the associated pages are no + * longer dirty. If we don't remove delalloc blocks here, they become + * stale and can corrupt free space accounting on unmount. */ error = blk_status_to_errno(ioend->io_bio->bi_status); if (unlikely(error)) { - if (ioend->io_flags & IOMAP_F_SHARED) + if (ioend->io_flags & IOMAP_F_SHARED) { xfs_reflink_cancel_cow_range(ip, offset, size, true); + xfs_bmap_punch_delalloc_range(ip, + XFS_B_TO_FSBT(mp, offset), + XFS_B_TO_FSB(mp, size)); + } goto done; }

From: "Darrick J. Wong" djwong@kernel.org

[ Upstream commit 089558bc7ba785c03815a49c89e28ad9b8de51f9 ]

As part of multiple customer escalations due to file data corruption after copy on write operations, I wrote some fstests that use fsstress to hammer on COW to shake things loose. Regrettably, I caught some filesystem shutdowns due to incorrect rmap operations with the following loop:

mount <filesystem> # (0) fsstress <run only readonly ops> & # (1) while true; do fsstress <run all ops> mount -o remount,ro # (2) fsstress <run only readonly ops> mount -o remount,rw # (3) done

When (2) happens, notice that (1) is still running. xfs_remount_ro will call xfs_blockgc_stop to walk the inode cache to free all the COW extents, but the blockgc mechanism races with (1)'s reader threads to take IOLOCKs and loses, which means that it doesn't clean them all out. Call such a file (A).

When (3) happens, xfs_remount_rw calls xfs_reflink_recover_cow, which walks the ondisk refcount btree and frees any COW extent that it finds. This function does not check the inode cache, which means that incore COW forks of inode (A) is now inconsistent with the ondisk metadata. If one of those former COW extents are allocated and mapped into another file (B) and someone triggers a COW to the stale reservation in (A), A's dirty data will be written into (B) and once that's done, those blocks will be transferred to (A)'s data fork without bumping the refcount.

The results are catastrophic -- file (B) and the refcount btree are now corrupt. Solve this race by forcing the xfs_blockgc_free_space to run synchronously, which causes xfs_icwalk to return to inodes that were skipped because the blockgc code couldn't take the IOLOCK. This is safe to do here because the VFS has already prohibited new writer threads.

Fixes: 10ddf64e420f ("xfs: remove leftover CoW reservations when remounting ro") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Dave Chinner dchinner@redhat.com Reviewed-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_super.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

--- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1768,7 +1768,10 @@ static int xfs_remount_ro( struct xfs_mount *mp) { - int error; + struct xfs_icwalk icw = { + .icw_flags = XFS_ICWALK_FLAG_SYNC, + }; + int error;

/* * Cancel background eofb scanning so it cannot race with the final @@ -1776,8 +1779,13 @@ xfs_remount_ro( */ xfs_blockgc_stop(mp);

- /* Get rid of any leftover CoW reservations... */ - error = xfs_blockgc_free_space(mp, NULL); + /* + * Clear out all remaining COW staging extents and speculative post-EOF + * preallocations so that we don't leave inodes requiring inactivation + * cleanups during reclaim on a read-only mount. We must process every + * cached inode, so this requires a synchronous cache scan. + */ + error = xfs_blockgc_free_space(mp, &icw); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error;

From: "Darrick J. Wong" djwong@kernel.org

[ Upstream commit f8d92a66e810acbef6ddbc0bd0cbd9b117ce8acd ]

While I was running with KASAN and lockdep enabled, I stumbled upon an KASAN report about a UAF to a freed CIL checkpoint. Looking at the comment for xfs_log_item_in_current_chkpt, it seems pretty obvious to me that the original patch to xfs_defer_finish_noroll should have done something to lock the CIL to prevent it from switching the CIL contexts while the predicate runs.

For upper level code that needs to know if a given log item is new enough not to need relogging, add a new wrapper that takes the CIL context lock long enough to sample the current CIL context. This is kind of racy in that the CIL can switch the contexts immediately after sampling, but that's ok because the consequence is that the defer ops code is a little slow to relog items.

================================================================== BUG: KASAN: use-after-free in xfs_log_item_in_current_chkpt+0x139/0x160 [xfs] Read of size 8 at addr ffff88804ea5f608 by task fsstress/527999

CPU: 1 PID: 527999 Comm: fsstress Tainted: G D 5.16.0-rc4-xfsx #rc4 Call Trace: <TASK> dump_stack_lvl+0x45/0x59 print_address_description.constprop.0+0x1f/0x140 kasan_report.cold+0x83/0xdf xfs_log_item_in_current_chkpt+0x139/0x160 xfs_defer_finish_noroll+0x3bb/0x1e30 __xfs_trans_commit+0x6c8/0xcf0 xfs_reflink_remap_extent+0x66f/0x10e0 xfs_reflink_remap_blocks+0x2dd/0xa90 xfs_file_remap_range+0x27b/0xc30 vfs_dedupe_file_range_one+0x368/0x420 vfs_dedupe_file_range+0x37c/0x5d0 do_vfs_ioctl+0x308/0x1260 __x64_sys_ioctl+0xa1/0x170 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f2c71a2950b Code: 0f 1e fa 48 8b 05 85 39 0d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 55 39 0d 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe8c0e03c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00005600862a8740 RCX: 00007f2c71a2950b RDX: 00005600862a7be0 RSI: 00000000c0189436 RDI: 0000000000000004 RBP: 000000000000000b R08: 0000000000000027 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000005a R13: 00005600862804a8 R14: 0000000000016000 R15: 00005600862a8a20 </TASK>

Allocated by task 464064: kasan_save_stack+0x1e/0x50 __kasan_kmalloc+0x81/0xa0 kmem_alloc+0xcd/0x2c0 [xfs] xlog_cil_ctx_alloc+0x17/0x1e0 [xfs] xlog_cil_push_work+0x141/0x13d0 [xfs] process_one_work+0x7f6/0x1380 worker_thread+0x59d/0x1040 kthread+0x3b0/0x490 ret_from_fork+0x1f/0x30

Freed by task 51: kasan_save_stack+0x1e/0x50 kasan_set_track+0x21/0x30 kasan_set_free_info+0x20/0x30 __kasan_slab_free+0xed/0x130 slab_free_freelist_hook+0x7f/0x160 kfree+0xde/0x340 xlog_cil_committed+0xbfd/0xfe0 [xfs] xlog_cil_process_committed+0x103/0x1c0 [xfs] xlog_state_do_callback+0x45d/0xbd0 [xfs] xlog_ioend_work+0x116/0x1c0 [xfs] process_one_work+0x7f6/0x1380 worker_thread+0x59d/0x1040 kthread+0x3b0/0x490 ret_from_fork+0x1f/0x30

Last potentially related work creation: kasan_save_stack+0x1e/0x50 __kasan_record_aux_stack+0xb7/0xc0 insert_work+0x48/0x2e0 __queue_work+0x4e7/0xda0 queue_work_on+0x69/0x80 xlog_cil_push_now.isra.0+0x16b/0x210 [xfs] xlog_cil_force_seq+0x1b7/0x850 [xfs] xfs_log_force_seq+0x1c7/0x670 [xfs] xfs_file_fsync+0x7c1/0xa60 [xfs] __x64_sys_fsync+0x52/0x80 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae

The buggy address belongs to the object at ffff88804ea5f600 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 8 bytes inside of 256-byte region [ffff88804ea5f600, ffff88804ea5f700) The buggy address belongs to the page: page:ffffea00013a9780 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88804ea5ea00 pfn:0x4ea5e head:ffffea00013a9780 order:1 compound_mapcount:0 flags: 0x4fff80000010200(slab|head|node=1|zone=1|lastcpupid=0xfff) raw: 04fff80000010200 ffffea0001245908 ffffea00011bd388 ffff888004c42b40 raw: ffff88804ea5ea00 0000000000100009 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff88804ea5f500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88804ea5f580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

ffff88804ea5f600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

^ ffff88804ea5f680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88804ea5f700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ==================================================================

Fixes: 4e919af7827a ("xfs: periodically relog deferred intent items") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_log_cil.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1442,9 +1442,9 @@ out_shutdown: */ bool xfs_log_item_in_current_chkpt( - struct xfs_log_item *lip) + struct xfs_log_item *lip) { - struct xfs_cil_ctx *ctx = lip->li_mountp->m_log->l_cilp->xc_ctx; + struct xfs_cil *cil = lip->li_mountp->m_log->l_cilp;

if (list_empty(&lip->li_cil)) return false; @@ -1454,7 +1454,7 @@ xfs_log_item_in_current_chkpt( * first checkpoint it is written to. Hence if it is different to the * current sequence, we're in a new checkpoint. */ - return lip->li_seq == ctx->sequence; + return lip->li_seq == READ_ONCE(cil->xc_current_sequence); }

/*

From: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com

commit 84ade0a6655bee803d176525ef457175cbf4df22 upstream.

Stop using the ftrace trampoline for init section once kernel init is complete.

Fixes: 67361cf8071286 ("powerpc/ftrace: Handle large kernel configs") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220516071422.463738-1-naveen.n.rao@linux.vnet.ib... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/ftrace.h | 4 +++- arch/powerpc/kernel/trace/ftrace.c | 15 ++++++++++++--- arch/powerpc/mm/mem.c | 2 ++ 3 files changed, 17 insertions(+), 4 deletions(-)

--- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -96,7 +96,7 @@ static inline bool arch_syscall_match_sy #endif /* PPC64_ELF_ABI_v1 */ #endif /* CONFIG_FTRACE_SYSCALLS */

-#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) && defined(CONFIG_FUNCTION_TRACER) #include <asm/paca.h>

static inline void this_cpu_disable_ftrace(void) @@ -120,11 +120,13 @@ static inline u8 this_cpu_get_ftrace_ena return get_paca()->ftrace_enabled; }

+void ftrace_free_init_tramp(void); #else /* CONFIG_PPC64 */ static inline void this_cpu_disable_ftrace(void) { } static inline void this_cpu_enable_ftrace(void) { } static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) { } static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } +static inline void ftrace_free_init_tramp(void) { } #endif /* CONFIG_PPC64 */ #endif /* !__ASSEMBLY__ */

--- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -336,9 +336,7 @@ static int setup_mcount_compiler_tramp(u

/* Is this a known long jump tramp? */ for (i = 0; i < NUM_FTRACE_TRAMPS; i++) - if (!ftrace_tramps[i]) - break; - else if (ftrace_tramps[i] == tramp) + if (ftrace_tramps[i] == tramp) return 0;

/* Is this a known plt tramp? */ @@ -881,6 +879,17 @@ void arch_ftrace_update_code(int command

extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];

+void ftrace_free_init_tramp(void) +{ + int i; + + for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++) + if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) { + ftrace_tramps[i] = 0; + return; + } +} + int __init ftrace_dyn_arch_init(void) { int i; --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -22,6 +22,7 @@ #include <asm/kasan.h> #include <asm/svm.h> #include <asm/mmzone.h> +#include <asm/ftrace.h>

#include <mm/mmu_decl.h>

@@ -314,6 +315,7 @@ void free_initmem(void) mark_initmem_nx(); init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); + ftrace_free_init_tramp(); }

/*

From: Christian Brauner christian.brauner@ubuntu.com

commit a793d79ea3e041081cd7cbd8ee43d0b5e4914a2b upstream.

The low-level mapping helpers were so far crammed into fs.h. They are out of place there. The fs.h header should just contain the higher-level mapping helpers that interact directly with vfs objects such as struct super_block or struct inode and not the bare mapping helpers. Similarly, only vfs and specific fs code shall interact with low-level mapping helpers. And so they won't be made accessible automatically through regular {g,u}id helpers.

Link: https://lore.kernel.org/r/20211123114227.3124056-3-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-3-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-3-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein amir73il@gmail.com Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/smbacl.c | 1 fs/ksmbd/smbacl.h | 1 fs/open.c | 1 fs/posix_acl.c | 1 fs/xfs/xfs_linux.h | 1 include/linux/fs.h | 91 ------------------------------------- include/linux/mnt_idmapping.h | 101 ++++++++++++++++++++++++++++++++++++++++++ security/commoncap.c | 1 8 files changed, 108 insertions(+), 90 deletions(-) create mode 100644 include/linux/mnt_idmapping.h

--- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -9,6 +9,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/mnt_idmapping.h>

#include "smbacl.h" #include "smb_common.h" --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/namei.h> #include <linux/posix_acl.h> +#include <linux/mnt_idmapping.h>

#include "mgmt/tree_connect.h"

--- a/fs/open.c +++ b/fs/open.c @@ -32,6 +32,7 @@ #include <linux/ima.h> #include <linux/dnotify.h> #include <linux/compat.h> +#include <linux/mnt_idmapping.h>

#include "internal.h"

--- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -23,6 +23,7 @@ #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> +#include <linux/mnt_idmapping.h>

static struct posix_acl **acl_by_type(struct inode *inode, int type) { --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -61,6 +61,7 @@ typedef __u32 xfs_nlink_t; #include <linux/ratelimit.h> #include <linux/rhashtable.h> #include <linux/xattr.h> +#include <linux/mnt_idmapping.h>

#include <asm/page.h> #include <asm/div64.h> --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -41,6 +41,7 @@ #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> +#include <linux/mnt_idmapping.h>

#include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -1627,34 +1628,6 @@ static inline void i_gid_write(struct in }

/** - * kuid_into_mnt - map a kuid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return make_kuid(mnt_userns, __kuid_val(kuid)); -} - -/** - * kgid_into_mnt - map a kgid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return make_kgid(mnt_userns, __kgid_val(kgid)); -} - -/** * i_uid_into_mnt - map an inode's i_uid down into a mnt_userns * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode to map @@ -1683,68 +1656,6 @@ static inline kgid_t i_gid_into_mnt(stru }

/** - * kuid_from_mnt - map a kuid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped up according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return KUIDT_INIT(from_kuid(mnt_userns, kuid)); -} - -/** - * kgid_from_mnt - map a kgid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped up according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return KGIDT_INIT(from_kgid(mnt_userns, kgid)); -} - -/** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsuid. A common example is initializing the i_uid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsuid mapped up according to @mnt_userns. - */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) -{ - return kuid_from_mnt(mnt_userns, current_fsuid()); -} - -/** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsgid. A common example is initializing the i_gid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsgid mapped up according to @mnt_userns. - */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) -{ - return kgid_from_mnt(mnt_userns, current_fsgid()); -} - -/** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @mnt_userns: user namespace of the mount the inode was found from --- /dev/null +++ b/include/linux/mnt_idmapping.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MNT_IDMAPPING_H +#define _LINUX_MNT_IDMAPPING_H + +#include <linux/types.h> +#include <linux/uidgid.h> + +struct user_namespace; +extern struct user_namespace init_user_ns; + +/** + * kuid_into_mnt - map a kuid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return make_kuid(mnt_userns, __kuid_val(kuid)); +} + +/** + * kgid_into_mnt - map a kgid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return make_kgid(mnt_userns, __kgid_val(kgid)); +} + +/** + * kuid_from_mnt - map a kuid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped up according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return KUIDT_INIT(from_kuid(mnt_userns, kuid)); +} + +/** + * kgid_from_mnt - map a kgid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped up according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return KGIDT_INIT(from_kgid(mnt_userns, kgid)); +} + +/** + * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsuid. A common example is initializing the i_uid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsuid mapped up according to @mnt_userns. + */ +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +{ + return kuid_from_mnt(mnt_userns, current_fsuid()); +} + +/** + * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsgid. A common example is initializing the i_gid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsgid mapped up according to @mnt_userns. + */ +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +{ + return kgid_from_mnt(mnt_userns, current_fsgid()); +} + +#endif /* _LINUX_MNT_IDMAPPING_H */ --- a/security/commoncap.c +++ b/security/commoncap.c @@ -24,6 +24,7 @@ #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> +#include <linux/mnt_idmapping.h>

/* * If a non-root user executes a setuid-root binary in

From: Christian Brauner christian.brauner@ubuntu.com

commit 1ac2a4104968e0a60b4b3572216a92aab5c1b025 upstream.

Currently we only support idmapped mounts for filesystems mounted without an idmapping. This was a conscious decision mentioned in multiple places (cf. e.g. [1]).

As explained at length in [3] it is perfectly fine to extend support for idmapped mounts to filesystem's mounted with an idmapping should the need arise. The need has been there for some time now. Various container projects in userspace need this to run unprivileged and nested unprivileged containers (cf. [2]).

Before we can port any filesystem that is mountable with an idmapping to support idmapped mounts we need to first extend the mapping helpers to account for the filesystem's idmapping. This again, is explained at length in our documentation at [3] but I'll give an overview here again.

Currently, the low-level mapping helpers implement the remapping algorithms described in [3] in a simplified manner. Because we could rely on the fact that all filesystems supporting idmapped mounts are mounted without an idmapping the translation step from or into the filesystem idmapping could be skipped.

In order to support idmapped mounts of filesystem's mountable with an idmapping the translation step we were able to skip before cannot be skipped anymore. A filesystem mounted with an idmapping is very likely to not use an identity mapping and will instead use a non-identity mapping. So the translation step from or into the filesystem's idmapping in the remapping algorithm cannot be skipped for such filesystems. More details with examples can be found in [3].

This patch adds a few new and prepares some already existing low-level mapping helpers to perform the full translation algorithm explained in [3]. The low-level helpers can be written in a way that they only perform the additional translation step when the filesystem is indeed mounted with an idmapping.

If the low-level helpers detect that they are not dealing with an idmapped mount they can simply return the relevant k{g,u}id unchanged; no remapping needs to be performed at all. The no_idmapping() helper detects whether the shortcut can be used.

If the low-level helpers detected that they are dealing with an idmapped mount but the underlying filesystem is mounted without an idmapping we can rely on the previous shorcut and can continue to skip the translation step from or into the filesystem's idmapping.

These checks guarantee that only the minimal amount of work is performed. As before, if idmapped mounts aren't used the low-level helpers are idempotent and no work is performed at all.

This patch adds the helpers mapped_k{g,u}id_fs() and mapped_k{g,u}id_user(). Following patches will port all places to replace the old k{g,u}id_into_mnt() and k{g,u}id_from_mnt() with these two new helpers. After the conversion is done k{g,u}id_into_mnt() and k{g,u}id_from_mnt() will be removed. This also concludes the renaming of the mapping helpers we started in [4]. Now, all mapping helpers will started with the "mapped_" prefix making everything nice and consistent.

The mapped_k{g,u}id_fs() helpers replace the k{g,u}id_into_mnt() helpers. They are to be used when k{g,u}ids are to be mapped from the vfs, e.g. from from struct inode's i_{g,u}id. Conversely, the mapped_k{g,u}id_user() helpers replace the k{g,u}id_from_mnt() helpers. They are to be used when k{g,u}ids are to be written to disk, e.g. when entering from a system call to change ownership of a file.

This patch only introduces the helpers. It doesn't yet convert the relevant places to account for filesystem mounted with an idmapping.

[1]: commit 2ca4dcc4909d ("fs/mount_setattr: tighten permission checks") [2]: https://github.com/containers/podman/issues/10374 [3]: Documentations/filesystems/idmappings.rst [4]: commit a65e58e791a1 ("fs: document and rename fsid helpers")

Link: https://lore.kernel.org/r/20211123114227.3124056-5-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-5-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-5-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/fs.h | 4 include/linux/mnt_idmapping.h | 193 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 191 insertions(+), 6 deletions(-)

--- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1638,7 +1638,7 @@ static inline void i_gid_write(struct in static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kuid_into_mnt(mnt_userns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); }

/** @@ -1652,7 +1652,7 @@ static inline kuid_t i_uid_into_mnt(stru static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kgid_into_mnt(mnt_userns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); }

/** --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -6,6 +6,11 @@ #include <linux/uidgid.h>

struct user_namespace; +/* + * Carries the initial idmapping of 0:0:4294967295 which is an identity + * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is + * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. + */ extern struct user_namespace init_user_ns;

/** @@ -65,8 +70,188 @@ static inline kgid_t kgid_from_mnt(struc }

/** + * initial_idmapping - check whether this is the initial mapping + * @ns: idmapping to check + * + * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, + * [...], 1000 to 1000 [...]. + * + * Return: true if this is the initial mapping, false if not. + */ +static inline bool initial_idmapping(const struct user_namespace *ns) +{ + return ns == &init_user_ns; +} + +/** + * no_idmapping - check whether we can skip remapping a kuid/gid + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * This function can be used to check whether a remapping between two + * idmappings is required. + * An idmapped mount is a mount that has an idmapping attached to it that + * is different from the filsystem's idmapping and the initial idmapping. + * If the initial mapping is used or the idmapping of the mount and the + * filesystem are identical no remapping is required. + * + * Return: true if remapping can be skipped, false if not. + */ +static inline bool no_idmapping(const struct user_namespace *mnt_userns, + const struct user_namespace *fs_userns) +{ + return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; +} + +/** + * mapped_kuid_fs - map a filesystem kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kuid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * from_kuid() so we can simply retrieve the value via __kuid_val() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + if (initial_idmapping(fs_userns)) + uid = __kuid_val(kuid); + else + uid = from_kuid(fs_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + return make_kuid(mnt_userns, uid); +} + +/** + * mapped_kgid_fs - map a filesystem kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kgid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * from_kgid() so we can simply retrieve the value via __kgid_val() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + if (initial_idmapping(fs_userns)) + gid = __kgid_val(kgid); + else + gid = from_kgid(fs_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + return make_kgid(mnt_userns, gid); +} + +/** + * mapped_kuid_user - map a user kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kuid into @fs_userns. Use this + * function when preparing a @kuid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * make_kuid() so we can simply retrieve the value via KUIDT_INIT() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + uid = from_kuid(mnt_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); +} + +/** + * mapped_kgid_user - map a user kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kgid into @fs_userns. Use this + * function when preparing a @kgid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * make_kgid() so we can simply retrieve the value via KGIDT_INIT() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + gid = from_kgid(mnt_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + if (initial_idmapping(fs_userns)) + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); +} + +/** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -78,12 +263,12 @@ static inline kgid_t kgid_from_mnt(struc */ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) { - return kuid_from_mnt(mnt_userns, current_fsuid()); + return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); }

/** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -95,7 +280,7 @@ static inline kuid_t mapped_fsuid(struct */ static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) { - return kgid_from_mnt(mnt_userns, current_fsgid()); + return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); }

#endif /* _LINUX_MNT_IDMAPPING_H */

From: Christian Brauner christian.brauner@ubuntu.com

commit 4472071331549e911a5abad41aea6e3be855a1a4 upstream.

In a few places the vfs needs to interact with bare k{g,u}ids directly instead of struct inode. These are just a few. In previous patches we introduced low-level mapping helpers that are able to support filesystems mounted an idmapping. This patch simply converts the places to use these new helpers.

Link: https://lore.kernel.org/r/20211123114227.3124056-7-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-7-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-7-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/smbacl.c | 18 ++---------------- fs/ksmbd/smbacl.h | 4 ++-- fs/open.c | 4 ++-- fs/posix_acl.c | 16 ++++++++++------ security/commoncap.c | 13 ++++++++----- 5 files changed, 24 insertions(+), 31 deletions(-)

--- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -275,14 +275,7 @@ static int sid_to_id(struct user_namespa uid_t id;

id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); - /* - * Translate raw sid into kuid in the server's user - * namespace. - */ - uid = make_kuid(&init_user_ns, id); - - /* If this is an idmapped mount, apply the idmapping. */ - uid = kuid_from_mnt(user_ns, uid); + uid = mapped_kuid_user(user_ns, &init_user_ns, KUIDT_INIT(id)); if (uid_valid(uid)) { fattr->cf_uid = uid; rc = 0; @@ -292,14 +285,7 @@ static int sid_to_id(struct user_namespa gid_t id;

id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); - /* - * Translate raw sid into kgid in the server's user - * namespace. - */ - gid = make_kgid(&init_user_ns, id); - - /* If this is an idmapped mount, apply the idmapping. */ - gid = kgid_from_mnt(user_ns, gid); + gid = mapped_kgid_user(user_ns, &init_user_ns, KGIDT_INIT(id)); if (gid_valid(gid)) { fattr->cf_gid = gid; rc = 0; --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -217,7 +217,7 @@ static inline uid_t posix_acl_uid_transl kuid_t kuid;

/* If this is an idmapped mount, apply the idmapping. */ - kuid = kuid_into_mnt(mnt_userns, pace->e_uid); + kuid = mapped_kuid_fs(mnt_userns, &init_user_ns, pace->e_uid);

/* Translate the kuid into a userspace id ksmbd would see. */ return from_kuid(&init_user_ns, kuid); @@ -229,7 +229,7 @@ static inline gid_t posix_acl_gid_transl kgid_t kgid;

/* If this is an idmapped mount, apply the idmapping. */ - kgid = kgid_into_mnt(mnt_userns, pace->e_gid); + kgid = mapped_kgid_fs(mnt_userns, &init_user_ns, pace->e_gid);

/* Translate the kgid into a userspace id ksmbd would see. */ return from_kgid(&init_user_ns, kgid); --- a/fs/open.c +++ b/fs/open.c @@ -653,8 +653,8 @@ int chown_common(const struct path *path gid = make_kgid(current_user_ns(), group);

mnt_userns = mnt_user_ns(path->mnt); - uid = kuid_from_mnt(mnt_userns, uid); - gid = kgid_from_mnt(mnt_userns, gid); + uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); + gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid);

retry_deleg: newattrs.ia_valid = ATTR_CTIME; --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -376,7 +376,9 @@ posix_acl_permission(struct user_namespa goto check_perm; break; case ACL_USER: - uid = kuid_into_mnt(mnt_userns, pa->e_uid); + uid = mapped_kuid_fs(mnt_userns, + &init_user_ns, + pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; @@ -389,7 +391,9 @@ posix_acl_permission(struct user_namespa } break; case ACL_GROUP: - gid = kgid_into_mnt(mnt_userns, pa->e_gid); + gid = mapped_kgid_fs(mnt_userns, + &init_user_ns, + pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) @@ -736,17 +740,17 @@ static void posix_acl_fix_xattr_userns( case ACL_USER: uid = make_kuid(from, le32_to_cpu(entry->e_id)); if (from_user) - uid = kuid_from_mnt(mnt_userns, uid); + uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); else - uid = kuid_into_mnt(mnt_userns, uid); + uid = mapped_kuid_fs(mnt_userns, &init_user_ns, uid); entry->e_id = cpu_to_le32(from_kuid(to, uid)); break; case ACL_GROUP: gid = make_kgid(from, le32_to_cpu(entry->e_id)); if (from_user) - gid = kgid_from_mnt(mnt_userns, gid); + gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); else - gid = kgid_into_mnt(mnt_userns, gid); + gid = mapped_kgid_fs(mnt_userns, &init_user_ns, gid); entry->e_id = cpu_to_le32(from_kgid(to, gid)); break; default: --- a/security/commoncap.c +++ b/security/commoncap.c @@ -419,7 +419,7 @@ int cap_inode_getsecurity(struct user_na kroot = make_kuid(fs_ns, root);

/* If this is an idmapped mount shift the kuid. */ - kroot = kuid_into_mnt(mnt_userns, kroot); + kroot = mapped_kuid_fs(mnt_userns, &init_user_ns, kroot);

/* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -489,6 +489,7 @@ out_free: * @size: size of @ivalue * @task_ns: user namespace of the caller * @mnt_userns: user namespace of the mount the inode was found from + * @fs_userns: user namespace of the filesystem * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then @@ -498,7 +499,8 @@ out_free: */ static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns, - struct user_namespace *mnt_userns) + struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { const struct vfs_ns_cap_data *nscap = value; kuid_t rootkid; @@ -508,7 +510,7 @@ static kuid_t rootid_from_xattr(const vo rootid = le32_to_cpu(nscap->rootid);

rootkid = make_kuid(task_ns, rootid); - return kuid_from_mnt(mnt_userns, rootkid); + return mapped_kuid_user(mnt_userns, fs_userns, rootkid); }

static bool validheader(size_t size, const struct vfs_cap_data *cap) @@ -559,7 +561,8 @@ int cap_convert_nscap(struct user_namesp /* user is privileged, just write the v2 */ return size;

- rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, + &init_user_ns); if (!uid_valid(rootid)) return -EINVAL;

@@ -700,7 +703,7 @@ int get_vfs_caps_from_disk(struct user_n /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ - rootkuid = kuid_into_mnt(mnt_userns, rootkuid); + rootkuid = mapped_kuid_fs(mnt_userns, &init_user_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA;

From: Christian Brauner christian.brauner@ubuntu.com

commit 209188ce75d0d357c292f6bb81d712acdd4e7db7 upstream.

Enable the mapped_fs{g,u}id() helpers to support filesystems mounted with an idmapping. Apart from core mapping helpers that use mapped_fs{g,u}id() to initialize struct inode's i_{g,u}id fields xfs is the only place that uses these low-level helpers directly.

The patch only extends the helpers to be able to take the filesystem idmapping into account. Since we don't actually yet pass the filesystem's idmapping in no functional changes happen. This will happen in a final patch.

Link: https://lore.kernel.org/r/20211123114227.3124056-9-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-9-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-9-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein amir73il@gmail.com Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_inode.c | 8 ++++---- fs/xfs/xfs_symlink.c | 4 ++-- include/linux/fs.h | 8 ++++---- include/linux/mnt_idmapping.h | 12 ++++++++---- 4 files changed, 18 insertions(+), 14 deletions(-)

--- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -994,8 +994,8 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1148,8 +1148,8 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -184,8 +184,8 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1666,7 +1666,7 @@ static inline kgid_t i_gid_into_mnt(stru static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns); + inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); }

/** @@ -1680,7 +1680,7 @@ static inline void inode_fsuid_set(struc static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns); + inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); }

/** @@ -1701,10 +1701,10 @@ static inline bool fsuidgid_has_mapping( kuid_t kuid; kgid_t kgid;

- kuid = mapped_fsuid(mnt_userns); + kuid = mapped_fsuid(mnt_userns, &init_user_ns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns); + kgid = mapped_fsgid(mnt_userns, &init_user_ns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -196,6 +196,7 @@ static inline kgid_t mapped_kgid_user(st /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -205,14 +206,16 @@ static inline kgid_t mapped_kgid_user(st * * Return: the caller's current fsuid mapped up according to @mnt_userns. */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); + return mapped_kuid_user(mnt_userns, fs_userns, current_fsuid()); }

/** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -222,9 +225,10 @@ static inline kuid_t mapped_fsuid(struct * * Return: the caller's current fsgid mapped up according to @mnt_userns. */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); + return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid()); }

#endif /* _LINUX_MNT_IDMAPPING_H */

From: Christian Brauner christian.brauner@ubuntu.com

commit bd303368b776eead1c29e6cdda82bde7128b82a7 upstream.

In previous patches we added new and modified existing helpers to handle idmapped mounts of filesystems mounted with an idmapping. In this final patch we convert all relevant places in the vfs to actually pass the filesystem's idmapping into these helpers.

With this the vfs is in shape to handle idmapped mounts of filesystems mounted with an idmapping. Note that this is just the generic infrastructure. Actually adding support for idmapped mounts to a filesystem mountable with an idmapping is follow-up work.

In this patch we extend the definition of an idmapped mount from a mount that that has the initial idmapping attached to it to a mount that has an idmapping attached to it which is not the same as the idmapping the filesystem was mounted with.

As before we do not allow the initial idmapping to be attached to a mount. In addition this patch prevents that the idmapping the filesystem was mounted with can be attached to a mount created based on this filesystem.

This has multiple reasons and advantages. First, attaching the initial idmapping or the filesystem's idmapping doesn't make much sense as in both cases the values of the i_{g,u}id and other places where k{g,u}ids are used do not change. Second, a user that really wants to do this for whatever reason can just create a separate dedicated identical idmapping to attach to the mount. Third, we can continue to use the initial idmapping as an indicator that a mount is not idmapped allowing us to continue to keep passing the initial idmapping into the mapping helpers to tell them that something isn't an idmapped mount even if the filesystem is mounted with an idmapping.

Link: https://lore.kernel.org/r/20211123114227.3124056-11-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-11-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-11-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/namespace.c | 51 ++++++++++++++++++++++++++++++++++++++------------- fs/open.c | 7 ++++--- fs/posix_acl.c | 8 ++++---- include/linux/fs.h | 17 +++++++++-------- security/commoncap.c | 9 ++++----- 5 files changed, 59 insertions(+), 33 deletions(-)

--- a/fs/namespace.c +++ b/fs/namespace.c @@ -31,6 +31,7 @@ #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> +#include <linux/mnt_idmapping.h>

#include "pnode.h" #include "internal.h" @@ -561,7 +562,7 @@ static void free_vfsmnt(struct mount *mn struct user_namespace *mnt_userns;

mnt_userns = mnt_user_ns(&mnt->mnt); - if (mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt_userns)) put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP @@ -965,6 +966,7 @@ static struct mount *skip_mnt_tree(struc struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; + struct user_namespace *fs_userns;

if (!fc->root) return ERR_PTR(-EINVAL); @@ -982,6 +984,10 @@ struct vfsmount *vfs_create_mount(struct mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt;

+ fs_userns = mnt->mnt.mnt_sb->s_user_ns; + if (!initial_idmapping(fs_userns)) + mnt->mnt.mnt_userns = get_user_ns(fs_userns); + lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); @@ -1072,7 +1078,7 @@ static struct mount *clone_mnt(struct mo

atomic_inc(&sb->s_active); mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); - if (mnt->mnt.mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt->mnt.mnt_userns)) mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); @@ -3927,11 +3933,19 @@ static unsigned int recalc_flags(struct static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; + struct user_namespace *fs_userns = m->mnt_sb->s_user_ns;

if (!kattr->mnt_userns) return 0;

/* + * Creating an idmapped mount with the filesystem wide idmapping + * doesn't make sense so block that. We don't allow mushy semantics. + */ + if (kattr->mnt_userns == fs_userns) + return -EINVAL; + + /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. @@ -3943,12 +3957,8 @@ static int can_idmap_mount(const struct if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL;

- /* Don't yet support filesystem mountable in user namespaces. */ - if (m->mnt_sb->s_user_ns != &init_user_ns) - return -EINVAL; - /* We're not controlling the superblock. */ - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM;

/* Mount has already been visible in the filesystem hierarchy. */ @@ -4002,14 +4012,27 @@ out:

static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *old_mnt_userns;

if (!kattr->mnt_userns) return;

+ /* + * We're the only ones able to change the mount's idmapping. So + * mnt->mnt.mnt_userns is stable and we can retrieve it directly. + */ + old_mnt_userns = mnt->mnt.mnt_userns; + mnt_userns = get_user_ns(kattr->mnt_userns); /* Pairs with smp_load_acquire() in mnt_user_ns(). */ smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); + + /* + * If this is an idmapped filesystem drop the reference we've taken + * in vfs_create_mount() before. + */ + if (!initial_idmapping(old_mnt_userns)) + put_user_ns(old_mnt_userns); }

static void mount_setattr_commit(struct mount_kattr *kattr, @@ -4133,13 +4156,15 @@ static int build_mount_idmapped(const st }

/* - * The init_user_ns is used to indicate that a vfsmount is not idmapped. - * This is simpler than just having to treat NULL as unmapped. Users - * wanting to idmap a mount to init_user_ns can just use a namespace - * with an identity mapping. + * The initial idmapping cannot be used to create an idmapped + * mount. We use the initial idmapping as an indicator of a mount + * that is not idmapped. It can simply be passed into helpers that + * are aware of idmapped mounts as a convenient shortcut. A user + * can just create a dedicated identity mapping to achieve the same + * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); - if (mnt_userns == &init_user_ns) { + if (initial_idmapping(mnt_userns)) { err = -EPERM; goto out_fput; } --- a/fs/open.c +++ b/fs/open.c @@ -641,7 +641,7 @@ SYSCALL_DEFINE2(chmod, const char __user

int chown_common(const struct path *path, uid_t user, gid_t group) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; @@ -653,8 +653,9 @@ int chown_common(const struct path *path gid = make_kgid(current_user_ns(), group);

mnt_userns = mnt_user_ns(path->mnt); - uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); - gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); + fs_userns = i_user_ns(inode); + uid = mapped_kuid_user(mnt_userns, fs_userns, uid); + gid = mapped_kgid_user(mnt_userns, fs_userns, gid);

retry_deleg: newattrs.ia_valid = ATTR_CTIME; --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -377,8 +377,8 @@ posix_acl_permission(struct user_namespa break; case ACL_USER: uid = mapped_kuid_fs(mnt_userns, - &init_user_ns, - pa->e_uid); + i_user_ns(inode), + pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; @@ -392,8 +392,8 @@ posix_acl_permission(struct user_namespa break; case ACL_GROUP: gid = mapped_kgid_fs(mnt_userns, - &init_user_ns, - pa->e_gid); + i_user_ns(inode), + pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1643,7 +1643,7 @@ static inline void i_gid_write(struct in static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid); }

/** @@ -1657,7 +1657,7 @@ static inline kuid_t i_uid_into_mnt(stru static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid); }

/** @@ -1671,7 +1671,7 @@ static inline kgid_t i_gid_into_mnt(stru static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); + inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); }

/** @@ -1685,7 +1685,7 @@ static inline void inode_fsuid_set(struc static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); + inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); }

/** @@ -1706,10 +1706,10 @@ static inline bool fsuidgid_has_mapping( kuid_t kuid; kgid_t kgid;

- kuid = mapped_fsuid(mnt_userns, &init_user_ns); + kuid = mapped_fsuid(mnt_userns, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, &init_user_ns); + kgid = mapped_fsgid(mnt_userns, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && @@ -2655,13 +2655,14 @@ static inline struct user_namespace *fil * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * - * If @mnt has an idmapping attached to it @mnt is mapped. + * If @mnt has an idmapping attached different from the + * filesystem's idmapping then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { - return mnt_user_ns(mnt) != &init_user_ns; + return mnt_user_ns(mnt) != mnt->mnt_sb->s_user_ns; }

extern long vfs_truncate(const struct path *, loff_t); --- a/security/commoncap.c +++ b/security/commoncap.c @@ -419,7 +419,7 @@ int cap_inode_getsecurity(struct user_na kroot = make_kuid(fs_ns, root);

/* If this is an idmapped mount shift the kuid. */ - kroot = mapped_kuid_fs(mnt_userns, &init_user_ns, kroot); + kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot);

/* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -556,13 +556,12 @@ int cap_convert_nscap(struct user_namesp return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; - if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns)) + if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size;

- rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, - &init_user_ns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL;

@@ -703,7 +702,7 @@ int get_vfs_caps_from_disk(struct user_n /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ - rootkuid = mapped_kuid_fs(mnt_userns, &init_user_ns, rootkuid); + rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA;

From: Christian Brauner brauner@kernel.org

commit 168f912893407a5acb798a4a58613b5f1f98c717 upstream.

When calling setattr_prepare() to determine the validity of the attributes the ia_{g,u}id fields contain the value that will be written to inode->i_{g,u}id. This is exactly the same for idmapped and non-idmapped mounts and allows callers to pass in the values they want to see written to inode->i_{g,u}id.

When group ownership is changed a caller whose fsuid owns the inode can change the group of the inode to any group they are a member of. When searching through the caller's groups we need to use the gid mapped according to the idmapped mount otherwise we will fail to change ownership for unprivileged users.

Consider a caller running with fsuid and fsgid 1000 using an idmapped mount that maps id 65534 to 1000 and 65535 to 1001. Consequently, a file owned by 65534:65535 in the filesystem will be owned by 1000:1001 in the idmapped mount.

The caller now requests the gid of the file to be changed to 1000 going through the idmapped mount. In the vfs we will immediately map the requested gid to the value that will need to be written to inode->i_gid and place it in attr->ia_gid. Since this idmapped mount maps 65534 to 1000 we place 65534 in attr->ia_gid.

When we check whether the caller is allowed to change group ownership we first validate that their fsuid matches the inode's uid. The inode->i_uid is 65534 which is mapped to uid 1000 in the idmapped mount. Since the caller's fsuid is 1000 we pass the check.

We now check whether the caller is allowed to change inode->i_gid to the requested gid by calling in_group_p(). This will compare the passed in gid to the caller's fsgid and search the caller's additional groups.

Since we're dealing with an idmapped mount we need to pass in the gid mapped according to the idmapped mount. This is akin to checking whether a caller is privileged over the future group the inode is owned by. And that needs to take the idmapped mount into account. Note, all helpers are nops without idmapped mounts.

New regression test sent to xfstests.

Link: https://github.com/lxc/lxd/issues/10537 Link: https://lore.kernel.org/r/20220613111517.2186646-1-brauner@kernel.org Fixes: 2f221d6f7b88 ("attr: handle idmapped mounts") Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Aleksa Sarai cyphar@cyphar.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: stable@vger.kernel.org # 5.15+ CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/attr.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-)

--- a/fs/attr.c +++ b/fs/attr.c @@ -61,9 +61,15 @@ static bool chgrp_ok(struct user_namespa const struct inode *inode, kgid_t gid) { kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); - if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) && - (in_group_p(gid) || gid_eq(gid, inode->i_gid))) - return true; + if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) { + kgid_t mapped_gid; + + if (gid_eq(gid, inode->i_gid)) + return true; + mapped_gid = mapped_kgid_fs(mnt_userns, i_user_ns(inode), gid); + if (in_group_p(mapped_gid)) + return true; + } if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; if (gid_eq(kgid, INVALID_GID) && @@ -123,12 +129,20 @@ int setattr_prepare(struct user_namespac

/* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { + kgid_t mapped_gid; + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; + + if (ia_valid & ATTR_GID) + mapped_gid = mapped_kgid_fs(mnt_userns, + i_user_ns(inode), attr->ia_gid); + else + mapped_gid = i_gid_into_mnt(mnt_userns, inode); + /* Also check the setgid bit! */ - if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : - i_gid_into_mnt(mnt_userns, inode)) && - !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + if (!in_group_p(mapped_gid) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; }

From: Ping-Ke Shih pkshih@realtek.com

commit e109e3617e5d563b431a52e6e2f07f0fc65a93ae upstream.

Ping-Ke Shih answered[1] a question for a user about an rtl8821ce device that reported RFE 6, which the driver did not support. Ping-Ke suggested a possible fix, but the user never reported back.

A second user discovered the above thread and tested the proposed fix. Accordingly, I am pushing this change, even though I am not the author.

[1] https://lore.kernel.org/linux-wireless/3f5e2f6eac344316b5dd518ebfea2f95@real...

Signed-off-by: Ping-Ke Shih pkshih@realtek.com Reported-and-tested-by: masterzorag masterzorag@gmail.com Signed-off-by: Larry Finger Larry.Finger@lwfinger.net Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220107024739.20967-1-Larry.Finger@lwfinger.net Signed-off-by: Meng Tang tangmeng@uniontech.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/realtek/rtw88/rtw8821c.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -1513,6 +1513,7 @@ static const struct rtw_rfe_def rtw8821c [0] = RTW_DEF_RFE(8821c, 0, 0), [2] = RTW_DEF_RFE_EXT(8821c, 0, 0, 2), [4] = RTW_DEF_RFE_EXT(8821c, 0, 0, 2), + [6] = RTW_DEF_RFE(8821c, 0, 0), };

static struct rtw_hw_reg rtw8821c_dig[] = {

From: Pavel Begunkov asml.silence@gmail.com

commit 05b538c1765f8d14a71ccf5f85258dcbeaf189f7 upstream.

We can look inside the fixed buffer table only while holding ->uring_lock, however in some cases we don't do the right async prep for IORING_OP_{WRITE,READ}_FIXED ending up with NULL req->imu forcing making an io-wq worker to try to resolve the fixed buffer without proper locking.

Move req->imu setup into early req init paths, i.e. io_prep_rw(), which is called unconditionally for rw requests and under uring_lock.

Fixes: 634d00df5e1cf ("io_uring: add full-fledged dynamic buffers support") Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2932,15 +2932,24 @@ static int io_prep_rw(struct io_kiocb *r kiocb->ki_complete = io_complete_rw; }

+ /* used for fixed read/write too - just read unconditionally */ + req->buf_index = READ_ONCE(sqe->buf_index); + req->imu = NULL; + if (req->opcode == IORING_OP_READ_FIXED || req->opcode == IORING_OP_WRITE_FIXED) { - req->imu = NULL; + struct io_ring_ctx *ctx = req->ctx; + u16 index; + + if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); + req->imu = ctx->user_bufs[index]; io_req_set_rsrc_node(req); }

req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); - req->buf_index = READ_ONCE(sqe->buf_index); return 0; }

@@ -3066,18 +3075,9 @@ static int __io_import_fixed(struct io_k

static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { - struct io_ring_ctx *ctx = req->ctx; - struct io_mapped_ubuf *imu = req->imu; - u16 index, buf_index = req->buf_index; - - if (likely(!imu)) { - if (unlikely(buf_index >= ctx->nr_user_bufs)) - return -EFAULT; - index = array_index_nospec(buf_index, ctx->nr_user_bufs); - imu = READ_ONCE(ctx->user_bufs[index]); - req->imu = imu; - } - return __io_import_fixed(req, rw, iter, imu); + if (WARN_ON_ONCE(!req->imu)) + return -EFAULT; + return __io_import_fixed(req, rw, iter, req->imu); }

static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)