Backport following CVE fix patches: CVE-2022-1055: 04c2a47ffb13c net: sched: fix use-after-free in tc_new_tfilter()
CVE-2022-23036: 6b1775f26a2d xen/grant-table: add gnttab_try_end_foreign_access() abf1fd5919d6 xen/blkfront: don't use gnttab_query_foreign_access() for mapped status
CVE-2022-23037: 31185df7e2b1d xen/netfront: don't use gnttab_query_foreign_access() for mapped status
CVE-2022-23038: 33172ab50a535 xen/scsifront: don't use gnttab_query_foreign_access() for mapped status
CVE-2022-23039: d3b6372c5881 xen/gntalloc: don't use gnttab_query_foreign_access()
CVE-2022-23040: 3777ea7bac31 xen/xenbus: don't let xenbus_grant_ring() remove grants in error case
CVE-2022-23041: 5cadd4bb1d7f xen/9p: use alloc/free_pages_exact() b0576cc9c6b8 xen/pvcalls: use alloc/free_pages_exact() 42baefac638f xen/gnttab: fix gnttab_end_foreign_access() without page specified
CVE-2022-23042: 66e3531b33ee5 xen/netfront: react properly to failing gnttab_end_foreign_access_ref()
Eric Dumazet (1): net: sched: fix use-after-free in tc_new_tfilter()
Juergen Gross (11): xen/xenbus: don't let xenbus_grant_ring() remove grants in error case xen/grant-table: add gnttab_try_end_foreign_access() xen/blkfront: don't use gnttab_query_foreign_access() for mapped status xen/netfront: don't use gnttab_query_foreign_access() for mapped status xen/scsifront: don't use gnttab_query_foreign_access() for mapped status xen/gntalloc: don't use gnttab_query_foreign_access() xen: remove gnttab_query_foreign_access() xen/9p: use alloc/free_pages_exact() xen/pvcalls: use alloc/free_pages_exact() xen/gnttab: fix gnttab_end_foreign_access() without page specified xen/netfront: react properly to failing gnttab_end_foreign_access_ref()
drivers/block/xen-blkfront.c | 63 +++++++++++++++----------- drivers/net/xen-netfront.c | 54 ++++++++++++++--------- drivers/scsi/xen-scsifront.c | 3 +- drivers/xen/gntalloc.c | 25 +++-------- drivers/xen/grant-table.c | 71 ++++++++++++++++-------------- drivers/xen/pvcalls-front.c | 8 ++-- drivers/xen/xenbus/xenbus_client.c | 24 +++++----- include/xen/grant_table.h | 19 +++++++- net/9p/trans_xen.c | 14 +++--- net/sched/cls_api.c | 11 +++-- 10 files changed, 162 insertions(+), 130 deletions(-)
From: Eric Dumazet edumazet@google.com
stable inclusion from stable-v5.10.97 commit e7be56926397cf9d992be8913f74a76152f8f08d bugzilla: 186375 https://gitee.com/src-openeuler/kernel/issues/I50W91 CVE: CVE-2022-1055
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 04c2a47ffb13c29778e2a14e414ad4cb5a5db4b5 upstream.
Whenever tc_new_tfilter() jumps back to replay: label, we need to make sure @q and @chain local variables are cleared again, or risk use-after-free as in [1]
For consistency, apply the same fix in tc_ctl_chain()
BUG: KASAN: use-after-free in mini_qdisc_pair_swap+0x1b9/0x1f0 net/sched/sch_generic.c:1581 Write of size 8 at addr ffff8880985c4b08 by task syz-executor.4/1945
CPU: 0 PID: 1945 Comm: syz-executor.4 Not tainted 5.17.0-rc1-syzkaller-00495-gff58831fa02d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x336 mm/kasan/report.c:255 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 mini_qdisc_pair_swap+0x1b9/0x1f0 net/sched/sch_generic.c:1581 tcf_chain_head_change_item net/sched/cls_api.c:372 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:386 tcf_chain_tp_insert net/sched/cls_api.c:1657 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1707 [inline] tc_new_tfilter+0x1e67/0x2350 net/sched/cls_api.c:2086 rtnetlink_rcv_msg+0x80d/0xb80 net/core/rtnetlink.c:5583 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f2647172059 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f2645aa5168 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00007f2647285100 RCX: 00007f2647172059 RDX: 040000000000009f RSI: 00000000200002c0 RDI: 0000000000000006 RBP: 00007f26471cc08d R08: 0000000000000000 R09: 0000000000000000 R10: 9e00000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffb3f7f02f R14: 00007f2645aa5300 R15: 0000000000022000 </TASK>
Allocated by task 1944: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:436 [inline] ____kasan_kmalloc mm/kasan/common.c:515 [inline] ____kasan_kmalloc mm/kasan/common.c:474 [inline] __kasan_kmalloc+0xa9/0xd0 mm/kasan/common.c:524 kmalloc_node include/linux/slab.h:604 [inline] kzalloc_node include/linux/slab.h:726 [inline] qdisc_alloc+0xac/0xa10 net/sched/sch_generic.c:941 qdisc_create.constprop.0+0xce/0x10f0 net/sched/sch_api.c:1211 tc_modify_qdisc+0x4c5/0x1980 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5592 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
Freed by task 3609: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:45 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free+0x130/0x160 mm/kasan/common.c:328 kasan_slab_free include/linux/kasan.h:236 [inline] slab_free_hook mm/slub.c:1728 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1754 slab_free mm/slub.c:3509 [inline] kfree+0xcb/0x280 mm/slub.c:4562 rcu_do_batch kernel/rcu/tree.c:2527 [inline] rcu_core+0x7b8/0x1540 kernel/rcu/tree.c:2778 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558
Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:3026 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3106 qdisc_put_unlocked+0x6f/0x90 net/sched/sch_generic.c:1109 tcf_block_release+0x86/0x90 net/sched/cls_api.c:1238 tc_new_tfilter+0xc0d/0x2350 net/sched/cls_api.c:2148 rtnetlink_rcv_msg+0x80d/0xb80 net/core/rtnetlink.c:5583 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
The buggy address belongs to the object at ffff8880985c4800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 776 bytes inside of 1024-byte region [ffff8880985c4800, ffff8880985c4c00) The buggy address belongs to the page: page:ffffea0002617000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x985c0 head:ffffea0002617000 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000010200 0000000000000000 dead000000000122 ffff888010c41dc0 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0x1d20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL), pid 1941, ts 1038999441284, free_ts 1033444432829 prep_new_page mm/page_alloc.c:2434 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4165 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5389 alloc_pages+0x1aa/0x310 mm/mempolicy.c:2271 alloc_slab_page mm/slub.c:1799 [inline] allocate_slab mm/slub.c:1944 [inline] new_slab+0x28a/0x3b0 mm/slub.c:2004 ___slab_alloc+0x87c/0xe90 mm/slub.c:3018 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3105 slab_alloc_node mm/slub.c:3196 [inline] slab_alloc mm/slub.c:3238 [inline] __kmalloc+0x2fb/0x340 mm/slub.c:4420 kmalloc include/linux/slab.h:586 [inline] kzalloc include/linux/slab.h:715 [inline] __register_sysctl_table+0x112/0x1090 fs/proc/proc_sysctl.c:1335 neigh_sysctl_register+0x2c8/0x5e0 net/core/neighbour.c:3787 devinet_sysctl_register+0xb1/0x230 net/ipv4/devinet.c:2618 inetdev_init+0x286/0x580 net/ipv4/devinet.c:278 inetdev_event+0xa8a/0x15d0 net/ipv4/devinet.c:1532 notifier_call_chain+0xb5/0x200 kernel/notifier.c:84 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1919 call_netdevice_notifiers_extack net/core/dev.c:1931 [inline] call_netdevice_notifiers net/core/dev.c:1945 [inline] register_netdevice+0x1073/0x1500 net/core/dev.c:9698 veth_newlink+0x59c/0xa90 drivers/net/veth.c:1722 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1352 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1404 free_unref_page_prepare mm/page_alloc.c:3325 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3404 release_pages+0x748/0x1220 mm/swap.c:956 tlb_batch_pages_flush mm/mmu_gather.c:50 [inline] tlb_flush_mmu_free mm/mmu_gather.c:243 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:250 zap_pte_range mm/memory.c:1441 [inline] zap_pmd_range mm/memory.c:1490 [inline] zap_pud_range mm/memory.c:1519 [inline] zap_p4d_range mm/memory.c:1540 [inline] unmap_page_range+0x1d1d/0x2a30 mm/memory.c:1561 unmap_single_vma+0x198/0x310 mm/memory.c:1606 unmap_vmas+0x16b/0x2f0 mm/memory.c:1638 exit_mmap+0x201/0x670 mm/mmap.c:3178 __mmput+0x122/0x4b0 kernel/fork.c:1114 mmput+0x56/0x60 kernel/fork.c:1135 exit_mm kernel/exit.c:507 [inline] do_exit+0xa3c/0x2a30 kernel/exit.c:793 do_group_exit+0xd2/0x2f0 kernel/exit.c:935 __do_sys_exit_group kernel/exit.c:946 [inline] __se_sys_exit_group kernel/exit.c:944 [inline] __x64_sys_exit_group+0x3a/0x50 kernel/exit.c:944 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
Memory state around the buggy address: ffff8880985c4a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880985c4a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8880985c4b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^ ffff8880985c4b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880985c4c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Vlad Buslov vladbu@mellanox.com Cc: Jiri Pirko jiri@mellanox.com Cc: Cong Wang xiyou.wangcong@gmail.com Reported-by: syzbot syzkaller@googlegroups.com Link: https://lore.kernel.org/r/20220131172018.3704490-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/sched/cls_api.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cb1331b35745..7993a692c7fd 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1954,9 +1954,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, bool prio_allocate; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; unsigned long cl; @@ -1984,6 +1984,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, tp = NULL; cl = 0; block = NULL; + q = NULL; + chain = NULL;
if (prio == 0) { /* If no priority is provided by the user, @@ -2804,8 +2806,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; - struct tcf_chain *chain = NULL; + struct Qdisc *q; + struct tcf_chain *chain; struct tcf_block *block; unsigned long cl; int err; @@ -2815,6 +2817,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, return -EPERM;
replay: + q = NULL; err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0)
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 5c600371b8fd02cbbb0eb83a9f664e3f0b75c28e bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WA6 CVE: CVE-2022-23040
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 3777ea7bac3113005b7180e6b9dadf16d19a5827 upstream.
Letting xenbus_grant_ring() tear down grants in the error case is problematic, as the other side could already have used these grants. Calling gnttab_end_foreign_access_ref() without checking success is resulting in an unclear situation for any caller of xenbus_grant_ring() as in the error case the memory pages of the ring page might be partially mapped. Freeing them would risk unwanted foreign access to them, while not freeing them would leak memory.
In order to remove the need to undo any gnttab_grant_foreign_access() calls, use gnttab_alloc_grant_references() to make sure no further error can occur in the loop granting access to the ring pages.
It should be noted that this way of handling removes leaking of grant entries in the error case, too.
This is CVE-2022-23040 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/xenbus/xenbus_client.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-)
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 0cd728961fce..16cfef099329 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -379,7 +379,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, unsigned int nr_pages, grant_ref_t *grefs) { int err; - int i, j; + unsigned int i; + grant_ref_t gref_head; + + err = gnttab_alloc_grant_references(nr_pages, &gref_head); + if (err) { + xenbus_dev_fatal(dev, err, "granting access to ring page"); + return err; + }
for (i = 0; i < nr_pages; i++) { unsigned long gfn; @@ -389,23 +396,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, else gfn = virt_to_gfn(vaddr);
- err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0); - if (err < 0) { - xenbus_dev_fatal(dev, err, - "granting access to ring page"); - goto fail; - } - grefs[i] = err; + grefs[i] = gnttab_claim_grant_reference(&gref_head); + gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id, + gfn, 0);
vaddr = vaddr + XEN_PAGE_SIZE; }
return 0; - -fail: - for (j = 0; j < i; j++) - gnttab_end_foreign_access_ref(grefs[j], 0); - return err; } EXPORT_SYMBOL_GPL(xenbus_grant_ring);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 3d81e85f30a8f712c3e4f2a507553d9063a20ed6 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WBV CVE: CVE-2022-23036, CVE-2022-23038
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 6b1775f26a2da2b05a6dc8ec2b5d14e9a4701a1a upstream.
Add a new grant table function gnttab_try_end_foreign_access(), which will remove and free a grant if it is not in use.
Its main use case is to either free a grant if it is no longer in use, or to take some other action if it is still in use. This other action can be an error exit, or (e.g. in the case of blkfront persistent grant feature) some special handling.
This is CVE-2022-23036, CVE-2022-23038 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/grant-table.c | 14 ++++++++++++-- include/xen/grant_table.h | 12 ++++++++++++ 2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 3729bea0c989..1b82e7a3722a 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -435,11 +435,21 @@ static void gnttab_add_deferred(grant_ref_t ref, bool readonly, what, ref, page ? page_to_pfn(page) : -1); }
+int gnttab_try_end_foreign_access(grant_ref_t ref) +{ + int ret = _gnttab_end_foreign_access_ref(ref, 0); + + if (ret) + put_free_entry(ref); + + return ret; +} +EXPORT_SYMBOL_GPL(gnttab_try_end_foreign_access); + void gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page) { - if (gnttab_end_foreign_access_ref(ref, readonly)) { - put_free_entry(ref); + if (gnttab_try_end_foreign_access(ref)) { if (page != 0) put_page(virt_to_page(page)); } else diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 0b1182a3cf41..dbbb00dd7fb0 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -97,10 +97,22 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); * access has been ended, free the given page too. Access will be ended * immediately iff the grant entry is not in use, otherwise it will happen * some time later. page may be 0, in which case no freeing will occur. + * Note that the granted page might still be accessed (read or write) by the + * other side after gnttab_end_foreign_access() returns, so even if page was + * specified as 0 it is not allowed to just reuse the page for other + * purposes immediately. */ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page);
+/* + * End access through the given grant reference, iff the grant entry is + * no longer in use. In case of success ending foreign access, the + * grant reference is deallocated. + * Return 1 if the grant entry was freed, 0 if it is still in use. + */ +int gnttab_try_end_foreign_access(grant_ref_t ref); + int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn);
unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 96219af4e504d0e96a231a0ba86062ec5b3af979 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WBV CVE: CVE-2022-23036
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit abf1fd5919d6238ee3bc5eb4a9b6c3947caa6638 upstream.
It isn't enough to check whether a grant is still being in use by calling gnttab_query_foreign_access(), as a mapping could be realized by the other side just after having called that function.
In case the call was done in preparation of revoking a grant it is better to do so via gnttab_end_foreign_access_ref() and check the success of that operation instead.
For the ring allocation use alloc_pages_exact() in order to avoid high order pages in case of a multi-page ring.
If a grant wasn't unmapped by the backend without persistent grants being used, set the device state to "error".
This is CVE-2022-23036 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Roger Pau Monné roger.pau@citrix.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/block/xen-blkfront.c | 63 +++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 26 deletions(-)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 22842d2938c2..47d4bb23d6f3 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1352,7 +1352,8 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); + free_pages_exact(rinfo->ring.sring, + info->nr_ring_pages * XEN_PAGE_SIZE); rinfo->ring.sring = NULL;
if (rinfo->irq) @@ -1436,9 +1437,15 @@ static int blkif_get_final_status(enum blk_req_status s1, return BLKIF_RSP_OKAY; }
-static bool blkif_completion(unsigned long *id, - struct blkfront_ring_info *rinfo, - struct blkif_response *bret) +/* + * Return values: + * 1 response processed. + * 0 missing further responses. + * -1 error while processing. + */ +static int blkif_completion(unsigned long *id, + struct blkfront_ring_info *rinfo, + struct blkif_response *bret) { int i = 0; struct scatterlist *sg; @@ -1461,7 +1468,7 @@ static bool blkif_completion(unsigned long *id,
/* Wait the second response if not yet here. */ if (s2->status < REQ_DONE) - return false; + return 0;
bret->status = blkif_get_final_status(s->status, s2->status); @@ -1512,42 +1519,43 @@ static bool blkif_completion(unsigned long *id, } /* Add the persistent grant into the list of free grants */ for (i = 0; i < num_grant; i++) { - if (gnttab_query_foreign_access(s->grants_used[i]->gref)) { + if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) { /* * If the grant is still mapped by the backend (the * backend has chosen to make this grant persistent) * we add it at the head of the list, so it will be * reused first. */ - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->grants_used[i]->gref); + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->grants_used[i]->gref); + return -1; + } list_add(&s->grants_used[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { /* - * If the grant is not mapped by the backend we end the - * foreign access and add it to the tail of the list, - * so it will not be picked again unless we run out of - * persistent grants. + * If the grant is not mapped by the backend we add it + * to the tail of the list, so it will not be picked + * again unless we run out of persistent grants. */ - gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL); s->grants_used[i]->gref = GRANT_INVALID_REF; list_add_tail(&s->grants_used[i]->node, &rinfo->grants); } } if (s->req.operation == BLKIF_OP_INDIRECT) { for (i = 0; i < INDIRECT_GREFS(num_grant); i++) { - if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) { - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->indirect_grants[i]->gref); + if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) { + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->indirect_grants[i]->gref); + return -1; + } list_add(&s->indirect_grants[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { struct page *indirect_page;
- gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL); /* * Add the used indirect page back to the list of * available pages for indirect grefs. @@ -1562,7 +1570,7 @@ static bool blkif_completion(unsigned long *id, } }
- return true; + return 1; }
static irqreturn_t blkif_interrupt(int irq, void *dev_id) @@ -1628,12 +1636,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) }
if (bret.operation != BLKIF_OP_DISCARD) { + int ret; + /* * We may need to wait for an extra response if the * I/O request is split in 2 */ - if (!blkif_completion(&id, rinfo, &bret)) + ret = blkif_completion(&id, rinfo, &bret); + if (!ret) continue; + if (unlikely(ret < 0)) + goto err; }
if (add_id_to_freelist(rinfo, id)) { @@ -1740,8 +1753,7 @@ static int setup_blkring(struct xenbus_device *dev, for (i = 0; i < info->nr_ring_pages; i++) rinfo->ring_ref[i] = GRANT_INVALID_REF;
- sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH, - get_order(ring_size)); + sring = alloc_pages_exact(ring_size, GFP_NOIO); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; @@ -1751,7 +1763,7 @@ static int setup_blkring(struct xenbus_device *dev,
err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref); if (err < 0) { - free_pages((unsigned long)sring, get_order(ring_size)); + free_pages_exact(sring, ring_size); rinfo->ring.sring = NULL; goto fail; } @@ -2729,11 +2741,10 @@ static void purge_persistent_grants(struct blkfront_info *info) list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, node) { if (gnt_list_entry->gref == GRANT_INVALID_REF || - gnttab_query_foreign_access(gnt_list_entry->gref)) + !gnttab_try_end_foreign_access(gnt_list_entry->gref)) continue;
list_del(&gnt_list_entry->node); - gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL); rinfo->persistent_gnts_c--; gnt_list_entry->gref = GRANT_INVALID_REF; list_add_tail(&gnt_list_entry->node, &rinfo->grants);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit f6690dd9446a2a4bd9b024f00f71dd827a98317f bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50W9L CVE: CVE-2022-23037
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 31185df7e2b1d2fa1de4900247a12d7b9c7087eb upstream.
It isn't enough to check whether a grant is still being in use by calling gnttab_query_foreign_access(), as a mapping could be realized by the other side just after having called that function.
In case the call was done in preparation of revoking a grant it is better to do so via gnttab_end_foreign_access_ref() and check the success of that operation instead.
This is CVE-2022-23037 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/xen-netfront.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index fce3a90a335c..59887a34f08d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -424,14 +424,12 @@ static bool xennet_tx_buf_gc(struct netfront_queue *queue) queue->tx_link[id] = TX_LINK_NONE; skb = queue->tx_skbs[id]; queue->tx_skbs[id] = NULL; - if (unlikely(gnttab_query_foreign_access( - queue->grant_tx_ref[id]) != 0)) { + if (unlikely(!gnttab_end_foreign_access_ref( + queue->grant_tx_ref[id], GNTMAP_readonly))) { dev_alert(dev, "Grant still in use by backend domain\n"); goto err; } - gnttab_end_foreign_access_ref( - queue->grant_tx_ref[id], GNTMAP_readonly); gnttab_release_grant_reference( &queue->gref_tx_head, queue->grant_tx_ref[id]); queue->grant_tx_ref[id] = GRANT_INVALID_REF;
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 3047255182774266950b22acc29c22a2d76e859e bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WAC CVE: CVE-2022-23038
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 33172ab50a53578a95691310f49567c9266968b0 upstream.
It isn't enough to check whether a grant is still being in use by calling gnttab_query_foreign_access(), as a mapping could be realized by the other side just after having called that function.
In case the call was done in preparation of revoking a grant it is better to do so via gnttab_try_end_foreign_access() and check the success of that operation instead.
This is CVE-2022-23038 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/scsi/xen-scsifront.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 259fc248d06c..a25c9386fdf7 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -233,12 +233,11 @@ static void scsifront_gnttab_done(struct vscsifrnt_info *info, return;
for (i = 0; i < shadow->nr_grants; i++) { - if (unlikely(gnttab_query_foreign_access(shadow->gref[i]))) { + if (unlikely(!gnttab_try_end_foreign_access(shadow->gref[i]))) { shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME "grant still in use by backend\n"); BUG(); } - gnttab_end_foreign_access(shadow->gref[i], 0, 0UL); }
kfree(shadow->sg);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 5f36ae75b847e7f87e4144602f418a624ca074b7 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50W9S CVE: CVE-2022-23039
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit d3b6372c5881cb54925212abb62c521df8ba4809 upstream.
Using gnttab_query_foreign_access() is unsafe, as it is racy by design.
The use case in the gntalloc driver is not needed at all. While at it replace the call of gnttab_end_foreign_access_ref() with a call of gnttab_end_foreign_access(), which is what is really wanted there. In case the grant wasn't used due to an allocation failure, just free the grant via gnttab_free_grant_reference().
This is CVE-2022-23039 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/gntalloc.c | 25 +++++++------------------ 1 file changed, 7 insertions(+), 18 deletions(-)
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 3fa40c723e8e..edb0acd0b832 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -169,20 +169,14 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op, __del_gref(gref); }
- /* It's possible for the target domain to map the just-allocated grant - * references by blindly guessing their IDs; if this is done, then - * __del_gref will leave them in the queue_gref list. They need to be - * added to the global list so that we can free them when they are no - * longer referenced. - */ - if (unlikely(!list_empty(&queue_gref))) - list_splice_tail(&queue_gref, &gref_list); mutex_unlock(&gref_mutex); return rc; }
static void __del_gref(struct gntalloc_gref *gref) { + unsigned long addr; + if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { uint8_t *tmp = kmap(gref->page); tmp[gref->notify.pgoff] = 0; @@ -196,21 +190,16 @@ static void __del_gref(struct gntalloc_gref *gref) gref->notify.flags = 0;
if (gref->gref_id) { - if (gnttab_query_foreign_access(gref->gref_id)) - return; - - if (!gnttab_end_foreign_access_ref(gref->gref_id, 0)) - return; - - gnttab_free_grant_reference(gref->gref_id); + if (gref->page) { + addr = (unsigned long)page_to_virt(gref->page); + gnttab_end_foreign_access(gref->gref_id, 0, addr); + } else + gnttab_free_grant_reference(gref->gref_id); }
gref_size--; list_del(&gref->next_gref);
- if (gref->page) - __free_page(gref->page); - kfree(gref); }
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 17f01b7206af1916111fa7bcf38aec084ae4b217 bugzilla: 186480 https://gitee.com/openeuler/kernel/issues/I53AQO CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 1dbd11ca75fe664d3e54607547771d021f531f59 upstream.
Remove gnttab_query_foreign_access(), as it is unused and unsafe to use.
All previous use cases assumed a grant would not be in use after gnttab_query_foreign_access() returned 0. This information is useless in best case, as it only refers to a situation in the past, which could have changed already.
Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/grant-table.c | 25 ------------------------- include/xen/grant_table.h | 2 -- 2 files changed, 27 deletions(-)
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 1b82e7a3722a..e6548910e79f 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -133,13 +133,6 @@ struct gnttab_ops { * return the frame. */ unsigned long (*end_foreign_transfer_ref)(grant_ref_t ref); - /* - * Query the status of a grant entry. Ref parameter is reference of - * queried grant entry, return value is the status of queried entry. - * Detailed status(writing/reading) can be gotten from the return value - * by bit operations. - */ - int (*query_foreign_access)(grant_ref_t ref); };
struct unmap_refs_callback_data { @@ -284,22 +277,6 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, } EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
-static int gnttab_query_foreign_access_v1(grant_ref_t ref) -{ - return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing); -} - -static int gnttab_query_foreign_access_v2(grant_ref_t ref) -{ - return grstatus[ref] & (GTF_reading|GTF_writing); -} - -int gnttab_query_foreign_access(grant_ref_t ref) -{ - return gnttab_interface->query_foreign_access(ref); -} -EXPORT_SYMBOL_GPL(gnttab_query_foreign_access); - static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly) { u16 flags, nflags; @@ -1427,7 +1404,6 @@ static const struct gnttab_ops gnttab_v1_ops = { .update_entry = gnttab_update_entry_v1, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v1, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v1, - .query_foreign_access = gnttab_query_foreign_access_v1, };
static const struct gnttab_ops gnttab_v2_ops = { @@ -1439,7 +1415,6 @@ static const struct gnttab_ops gnttab_v2_ops = { .update_entry = gnttab_update_entry_v2, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v2, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2, - .query_foreign_access = gnttab_query_foreign_access_v2, };
static bool gnttab_need_v2(void) diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index dbbb00dd7fb0..ddaa586ba418 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -118,8 +118,6 @@ int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); unsigned long gnttab_end_foreign_transfer(grant_ref_t ref);
-int gnttab_query_foreign_access(grant_ref_t ref); - /* * operations on reserved batches of grant references */
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 8357d75bfdb85ea63253cf369f405830c7b13d78 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WAF CVE: CVE-2022-23041
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 5cadd4bb1d7fc9ab201ac14620d1a478357e4ebd upstream.
Instead of __get_free_pages() and free_pages() use alloc_pages_exact() and free_pages_exact(). This is in preparation of a change of gnttab_end_foreign_access() which will prohibit use of high-order pages.
By using the local variable "order" instead of ring->intf->ring_order in the error path of xen_9pfs_front_alloc_dataring() another bug is fixed, as the error path can be entered before ring->intf->ring_order is being set.
By using alloc_pages_exact() the size in bytes is specified for the allocation, which fixes another bug for the case of order < (PAGE_SHIFT - XEN_PAGE_SHIFT).
This is part of CVE-2022-23041 / XSA-396.
Reported-by: Simon Gaiser simon@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/9p/trans_xen.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 3ec1a51a6944..432ac5a16f2e 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -304,9 +304,9 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) ref = priv->rings[i].intf->ref[j]; gnttab_end_foreign_access(ref, 0, 0); } - free_pages((unsigned long)priv->rings[i].data.in, - priv->rings[i].intf->ring_order - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(priv->rings[i].data.in, + 1UL << (priv->rings[i].intf->ring_order + + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(priv->rings[i].ref, 0, 0); free_page((unsigned long)priv->rings[i].intf); @@ -345,8 +345,8 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, if (ret < 0) goto out; ring->ref = ret; - bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - order - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + bytes = alloc_pages_exact(1UL << (order + XEN_PAGE_SHIFT), + GFP_KERNEL | __GFP_ZERO); if (!bytes) { ret = -ENOMEM; goto out; @@ -377,9 +377,7 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, if (bytes) { for (i--; i >= 0; i--) gnttab_end_foreign_access(ring->intf->ref[i], 0, 0); - free_pages((unsigned long)bytes, - ring->intf->ring_order - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(ring->ref, 0, 0); free_page((unsigned long)ring->intf);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit c4b16486d6023f6365a4f8671351961e97428f2d bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WAF CVE: CVE-2022-23041
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit b0576cc9c6b843d99c6982888d59a56209341888 upstream.
Instead of __get_free_pages() and free_pages() use alloc_pages_exact() and free_pages_exact(). This is in preparation of a change of gnttab_end_foreign_access() which will prohibit use of high-order pages.
This is part of CVE-2022-23041 / XSA-396.
Reported-by: Simon Gaiser simon@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/pvcalls-front.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 7984645b5956..bbe337dc296e 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -337,8 +337,8 @@ static void free_active_ring(struct sock_mapping *map) if (!map->active.ring) return;
- free_pages((unsigned long)map->active.data.in, - map->active.ring->ring_order); + free_pages_exact(map->active.data.in, + PAGE_SIZE << map->active.ring->ring_order); free_page((unsigned long)map->active.ring); }
@@ -352,8 +352,8 @@ static int alloc_active_ring(struct sock_mapping *map) goto out;
map->active.ring->ring_order = PVCALLS_RING_ORDER; - bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - PVCALLS_RING_ORDER); + bytes = alloc_pages_exact(PAGE_SIZE << PVCALLS_RING_ORDER, + GFP_KERNEL | __GFP_ZERO); if (!bytes) goto out;
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 39c00d09286c67567cdf23ebc8e00e47722ef769 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WAF CVE: CVE-2022-23041
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 42baefac638f06314298087394b982ead9ec444b upstream.
gnttab_end_foreign_access() is used to free a grant reference and optionally to free the associated page. In case the grant is still in use by the other side processing is being deferred. This leads to a problem in case no page to be freed is specified by the caller: the caller doesn't know that the page is still mapped by the other side and thus should not be used for other purposes.
The correct way to handle this situation is to take an additional reference to the granted page in case handling is being deferred and to drop that reference when the grant reference could be freed finally.
This requires that there are no users of gnttab_end_foreign_access() left directly repurposing the granted page after the call, as this might result in clobbered data or information leaks via the not yet freed grant reference.
This is part of CVE-2022-23041 / XSA-396.
Reported-by: Simon Gaiser simon@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/xen/grant-table.c | 36 +++++++++++++++++++++++++++++------- include/xen/grant_table.h | 7 ++++++- 2 files changed, 35 insertions(+), 8 deletions(-)
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index e6548910e79f..5c83d41766c8 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -133,6 +133,10 @@ struct gnttab_ops { * return the frame. */ unsigned long (*end_foreign_transfer_ref)(grant_ref_t ref); + /* + * Read the frame number related to a given grant reference. + */ + unsigned long (*read_frame)(grant_ref_t ref); };
struct unmap_refs_callback_data { @@ -330,6 +334,16 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) } EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
+static unsigned long gnttab_read_frame_v1(grant_ref_t ref) +{ + return gnttab_shared.v1[ref].frame; +} + +static unsigned long gnttab_read_frame_v2(grant_ref_t ref) +{ + return gnttab_shared.v2[ref].full_page.frame; +} + struct deferred_entry { struct list_head list; grant_ref_t ref; @@ -359,12 +373,9 @@ static void gnttab_handle_deferred(struct timer_list *unused) spin_unlock_irqrestore(&gnttab_list_lock, flags); if (_gnttab_end_foreign_access_ref(entry->ref, entry->ro)) { put_free_entry(entry->ref); - if (entry->page) { - pr_debug("freeing g.e. %#x (pfn %#lx)\n", - entry->ref, page_to_pfn(entry->page)); - put_page(entry->page); - } else - pr_info("freeing g.e. %#x\n", entry->ref); + pr_debug("freeing g.e. %#x (pfn %#lx)\n", + entry->ref, page_to_pfn(entry->page)); + put_page(entry->page); kfree(entry); entry = NULL; } else { @@ -389,9 +400,18 @@ static void gnttab_handle_deferred(struct timer_list *unused) static void gnttab_add_deferred(grant_ref_t ref, bool readonly, struct page *page) { - struct deferred_entry *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); + struct deferred_entry *entry; + gfp_t gfp = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL; const char *what = KERN_WARNING "leaking";
+ entry = kmalloc(sizeof(*entry), gfp); + if (!page) { + unsigned long gfn = gnttab_interface->read_frame(ref); + + page = pfn_to_page(gfn_to_pfn(gfn)); + get_page(page); + } + if (entry) { unsigned long flags;
@@ -1404,6 +1424,7 @@ static const struct gnttab_ops gnttab_v1_ops = { .update_entry = gnttab_update_entry_v1, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v1, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v1, + .read_frame = gnttab_read_frame_v1, };
static const struct gnttab_ops gnttab_v2_ops = { @@ -1415,6 +1436,7 @@ static const struct gnttab_ops gnttab_v2_ops = { .update_entry = gnttab_update_entry_v2, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v2, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2, + .read_frame = gnttab_read_frame_v2, };
static bool gnttab_need_v2(void) diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index ddaa586ba418..57b4ae6a4a18 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -100,7 +100,12 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); * Note that the granted page might still be accessed (read or write) by the * other side after gnttab_end_foreign_access() returns, so even if page was * specified as 0 it is not allowed to just reuse the page for other - * purposes immediately. + * purposes immediately. gnttab_end_foreign_access() will take an additional + * reference to the granted page in this case, which is dropped only after + * the grant is no longer in use. + * This requires that multi page allocations for areas subject to + * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing + * via free_pages_exact()) in order to avoid high order pages. */ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page);
From: Juergen Gross jgross@suse.com
stable inclusion from stable-v5.10.105 commit 206c8e271ba2630f1d809123945d9c428f93b0f0 bugzilla: 186480 https://gitee.com/src-openeuler/kernel/issues/I50WAI CVE: CVE-2022-23042
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
Commit 66e3531b33ee51dad17c463b4d9c9f52e341503d upstream.
When calling gnttab_end_foreign_access_ref() the returned value must be tested and the reaction to that value should be appropriate.
In case of failure in xennet_get_responses() the reaction should not be to crash the system, but to disable the network device.
The calls in setup_netfront() can be replaced by calls of gnttab_end_foreign_access(). While at it avoid double free of ring pages and grant references via xennet_disconnect_backend() in this case.
This is CVE-2022-23042 / part of XSA-396.
Reported-by: Demi Marie Obenour demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/xen-netfront.c | 48 ++++++++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 17 deletions(-)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 59887a34f08d..0776b567504d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -968,7 +968,6 @@ static int xennet_get_responses(struct netfront_queue *queue, struct device *dev = &queue->info->netdev->dev; struct bpf_prog *xdp_prog; struct xdp_buff xdp; - unsigned long ret; int slots = 1; int err = 0; u32 verdict; @@ -1010,8 +1009,13 @@ static int xennet_get_responses(struct netfront_queue *queue, goto next; }
- ret = gnttab_end_foreign_access_ref(ref, 0); - BUG_ON(!ret); + if (!gnttab_end_foreign_access_ref(ref, 0)) { + dev_alert(dev, + "Grant still in use by backend domain\n"); + queue->info->broken = true; + dev_alert(dev, "Disabled for further use\n"); + return -EINVAL; + }
gnttab_release_grant_reference(&queue->gref_rx_head, ref);
@@ -1232,6 +1236,10 @@ static int xennet_poll(struct napi_struct *napi, int budget) &need_xdp_flush);
if (unlikely(err)) { + if (queue->info->broken) { + spin_unlock(&queue->rx_lock); + return 0; + } err: while ((skb = __skb_dequeue(&tmpq))) __skb_queue_tail(&errq, skb); @@ -1895,7 +1903,7 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_queue *queue, unsigned int feature_split_evtchn) { struct xen_netif_tx_sring *txs; - struct xen_netif_rx_sring *rxs; + struct xen_netif_rx_sring *rxs = NULL; grant_ref_t gref; int err;
@@ -1915,21 +1923,21 @@ static int setup_netfront(struct xenbus_device *dev,
err = xenbus_grant_ring(dev, txs, 1, &gref); if (err < 0) - goto grant_tx_ring_fail; + goto fail; queue->tx_ring_ref = gref;
rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); if (!rxs) { err = -ENOMEM; xenbus_dev_fatal(dev, err, "allocating rx ring page"); - goto alloc_rx_ring_fail; + goto fail; } SHARED_RING_INIT(rxs); FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE);
err = xenbus_grant_ring(dev, rxs, 1, &gref); if (err < 0) - goto grant_rx_ring_fail; + goto fail; queue->rx_ring_ref = gref;
if (feature_split_evtchn) @@ -1942,22 +1950,28 @@ static int setup_netfront(struct xenbus_device *dev, err = setup_netfront_single(queue);
if (err) - goto alloc_evtchn_fail; + goto fail;
return 0;
/* If we fail to setup netfront, it is safe to just revoke access to * granted pages because backend is not accessing it at this point. */ -alloc_evtchn_fail: - gnttab_end_foreign_access_ref(queue->rx_ring_ref, 0); -grant_rx_ring_fail: - free_page((unsigned long)rxs); -alloc_rx_ring_fail: - gnttab_end_foreign_access_ref(queue->tx_ring_ref, 0); -grant_tx_ring_fail: - free_page((unsigned long)txs); -fail: + fail: + if (queue->rx_ring_ref != GRANT_INVALID_REF) { + gnttab_end_foreign_access(queue->rx_ring_ref, 0, + (unsigned long)rxs); + queue->rx_ring_ref = GRANT_INVALID_REF; + } else { + free_page((unsigned long)rxs); + } + if (queue->tx_ring_ref != GRANT_INVALID_REF) { + gnttab_end_foreign_access(queue->tx_ring_ref, 0, + (unsigned long)txs); + queue->tx_ring_ref = GRANT_INVALID_REF; + } else { + free_page((unsigned long)txs); + } return err; }
-
Zheng Zengkai