The check for a fast symlink in the presence of only an
external xattr inode is incorrect. If a fast symlink does
not have an xattr block (i_file_acl == 0), but does have
an external xattr inode that increases inode i_blocks, then
the check for a fast symlink will incorrectly fail and
__ext4_iget()->ext4_ind_check_inode() will report the inode
is corrupt when it "validates" i_data[] on the next read:
# ln -s foo /mnt/tmp/bar
# setfattr -h -n trusted.test \
-v "$(yes | head -n 4000)" /mnt/tmp/bar
# umount /mnt/tmp
# mount /mnt/tmp
# ls -l /mnt/tmp
ls: cannot access '/mnt/tmp/bar': Structure needs cleaning
total 4
? l?????????? ? ? ? ? ? bar
# dmesg | tail -1
EXT4-fs error (device dm-8): __ext4_iget:5098:
inode #24578: block 7303014: comm ls: invalid block
(note that "block 7303014" = 0x6f6f66 = "foo" in LE order).
ext4_inode_is_fast_symlink() should check the superblock
EXT4_FEATURE_INCOMPAT_EA_INODE feature flag, not the inode
EXT4_EA_INODE_FL, since the latter is only set on the xattr
inode itself, and not on the inode that uses this xattr.
Cc: stable(a)vger.kernel.org
Fixes: fc82228a5e38 ("ext4: support fast symlinks from ext3 file systems")
Signed-off-by: Andreas Dilger <adilger(a)whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli(a)ddn.com>
Reviewed-by: Alex Zhuravlev <bzzz(a)whamcloud.com>
Reviewed-by: Oleg Drokin <green(a)whamcloud.com>
Reviewed-on: https://review.whamcloud.com/59879
Lustre-bug-id: https://jira.whamcloud.com/browse/LU-19121
---
fs/ext4/inode.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index be9a4cba35fd..caca88521c75 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -146,7 +146,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode,
*/
int ext4_inode_is_fast_symlink(struct inode *inode)
{
- if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+ if (!ext4_has_feature_ea_inode(inode->i_sb)) {
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
--
2.43.5
netlink_attachskb() checks for the socket's read memory allocation
constraints. Firstly, it has:
rmem < READ_ONCE(sk->sk_rcvbuf)
to check if the just increased rmem value fits into the socket's receive
buffer. If not, it proceeds and tries to wait for the memory under:
rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)
The checks don't cover the case when skb->truesize + sk->sk_rmem_alloc is
equal to sk->sk_rcvbuf. Thus the function neither successfully accepts
these conditions, nor manages to reschedule the task - and is called in
retry loop for indefinite time which is caught as:
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: 0-....: (25999 ticks this GP) idle=ef2/1/0x4000000000000000 softirq=262269/262269 fqs=6212
(t=26000 jiffies g=230833 q=259957)
NMI backtrace for cpu 0
CPU: 0 PID: 22 Comm: kauditd Not tainted 5.10.240 #68
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc42 04/01/2014
Call Trace:
<IRQ>
dump_stack lib/dump_stack.c:120
nmi_cpu_backtrace.cold lib/nmi_backtrace.c:105
nmi_trigger_cpumask_backtrace lib/nmi_backtrace.c:62
rcu_dump_cpu_stacks kernel/rcu/tree_stall.h:335
rcu_sched_clock_irq.cold kernel/rcu/tree.c:2590
update_process_times kernel/time/timer.c:1953
tick_sched_handle kernel/time/tick-sched.c:227
tick_sched_timer kernel/time/tick-sched.c:1399
__hrtimer_run_queues kernel/time/hrtimer.c:1652
hrtimer_interrupt kernel/time/hrtimer.c:1717
__sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1113
asm_call_irq_on_stack arch/x86/entry/entry_64.S:808
</IRQ>
netlink_attachskb net/netlink/af_netlink.c:1234
netlink_unicast net/netlink/af_netlink.c:1349
kauditd_send_queue kernel/audit.c:776
kauditd_thread kernel/audit.c:897
kthread kernel/kthread.c:328
ret_from_fork arch/x86/entry/entry_64.S:304
Restore the original behavior of the check which commit in Fixes
accidentally missed when restructuring the code.
Found by Linux Verification Center (linuxtesting.org).
Fixes: ae8f160e7eb2 ("netlink: Fix wraparounds of sk->sk_rmem_alloc.")
Cc: stable(a)vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru>
---
Similar rmem and sk->sk_rcvbuf comparing pattern in
netlink_broadcast_deliver() accepts these values being equal, while
the netlink_dump() case does not - but it goes all the way down to
f9c2288837ba ("netlink: implement memory mapped recvmsg()") and looks
like an irrelevant issue without any real consequences. Though might be
cleaned up if needed.
Updated sk->sk_rmem_alloc vs sk->sk_rcvbuf checks throughout the kernel
diverse in treating the corner case of them being equal.
net/netlink/af_netlink.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 6332a0e06596..0fc3f045fb65 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1218,7 +1218,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
nlk = nlk_sk(sk);
rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
- if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+ if ((rmem == skb->truesize || rmem <= READ_ONCE(sk->sk_rcvbuf)) &&
!test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
netlink_skb_set_owner_r(skb, sk);
return 0;
--
2.50.1
Buffer bouncing is needed only when memory exists above the lowmem region,
i.e., when max_low_pfn < max_pfn. The previous check (max_low_pfn >=
max_pfn) was inverted and prevented bouncing when it could actually be
required.
Note that bouncing depends on CONFIG_HIGHMEM, which is typically enabled
on 32-bit ARM where not all memory is permanently mapped into the kernel’s
lowmem region.
Branch-Specific Note:
This fix is specific to this branch (6.6.y) only.
In the upstream “tip” kernel, bounce buffer support for highmem pages
was completely removed after kernel version 6.12. Therefore, this
modification is not possible or relevant in the tip branch.
Fixes: 9bb33f24abbd0 ("block: refactor the bounce buffering code")
Cc: stable(a)vger.kernel.org
Signed-off-by: Hardeep Sharma <quic_hardshar(a)quicinc.com>
---
block/blk.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/blk.h b/block/blk.h
index 67915b04b3c1..f8a1d64be5a2 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -383,7 +383,7 @@ static inline bool blk_queue_may_bounce(struct request_queue *q)
{
return IS_ENABLED(CONFIG_BOUNCE) &&
q->limits.bounce == BLK_BOUNCE_HIGH &&
- max_low_pfn >= max_pfn;
+ max_low_pfn < max_pfn;
}
static inline struct bio *blk_queue_bounce(struct bio *bio,
--
2.25.1
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 095686e6fcb4150f0a55b1a25987fad3d8af58d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081224-material-dismay-771d@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 095686e6fcb4150f0a55b1a25987fad3d8af58d6 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk(a)redhat.com>
Date: Tue, 10 Jun 2025 16:20:08 -0700
Subject: [PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested
VM-Enter
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values. Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity
is not worth carrying.
Cc: stable(a)vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com>
Co-developed-by: Sean Christopherson <seanjc(a)google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..1b8b0642fc2d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2663,7 +2663,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
@@ -3156,7 +3157,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -4608,6 +4610,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4f827a75d980..6a8b78e954cd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2174,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2193,8 +2193,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
return debugctl;
}
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
- bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
{
u64 invalid;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..392e66c7e5fe 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -414,6 +414,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 095686e6fcb4150f0a55b1a25987fad3d8af58d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081223-sugar-folic-11b0@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 095686e6fcb4150f0a55b1a25987fad3d8af58d6 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk(a)redhat.com>
Date: Tue, 10 Jun 2025 16:20:08 -0700
Subject: [PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested
VM-Enter
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values. Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity
is not worth carrying.
Cc: stable(a)vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com>
Co-developed-by: Sean Christopherson <seanjc(a)google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..1b8b0642fc2d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2663,7 +2663,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
@@ -3156,7 +3157,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -4608,6 +4610,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4f827a75d980..6a8b78e954cd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2174,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2193,8 +2193,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
return debugctl;
}
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
- bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
{
u64 invalid;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..392e66c7e5fe 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -414,6 +414,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
The patch below does not apply to the 6.12-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x 095686e6fcb4150f0a55b1a25987fad3d8af58d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081223-parameter-cope-c338@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 095686e6fcb4150f0a55b1a25987fad3d8af58d6 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk(a)redhat.com>
Date: Tue, 10 Jun 2025 16:20:08 -0700
Subject: [PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested
VM-Enter
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values. Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity
is not worth carrying.
Cc: stable(a)vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com>
Co-developed-by: Sean Christopherson <seanjc(a)google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..1b8b0642fc2d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2663,7 +2663,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
@@ -3156,7 +3157,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -4608,6 +4610,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4f827a75d980..6a8b78e954cd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2174,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2193,8 +2193,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
return debugctl;
}
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
- bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
{
u64 invalid;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..392e66c7e5fe 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -414,6 +414,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
The patch below does not apply to the 6.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y
git checkout FETCH_HEAD
git cherry-pick -x 095686e6fcb4150f0a55b1a25987fad3d8af58d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025081222-nearness-monogram-75ab@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 095686e6fcb4150f0a55b1a25987fad3d8af58d6 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk(a)redhat.com>
Date: Tue, 10 Jun 2025 16:20:08 -0700
Subject: [PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested
VM-Enter
Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values. Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.
Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12. Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.
Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken. I.e. the extra complexity
is not worth carrying.
Cc: stable(a)vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com>
Co-developed-by: Sean Christopherson <seanjc(a)google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..1b8b0642fc2d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2663,7 +2663,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
@@ -3156,7 +3157,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -4608,6 +4610,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4f827a75d980..6a8b78e954cd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2174,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2193,8 +2193,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
return debugctl;
}
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
- bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
{
u64 invalid;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..392e66c7e5fe 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -414,6 +414,9 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and