From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
To: x86@kernel.org, David Kaplan <david.kaplan@amd.com>,
Nikolay Borisov <nik.borisov@suse.com>,
"H. Peter Anvin" <hpa@zytor.com>,
Josh Poimboeuf <jpoimboe@kernel.org>,
Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Asit Mallick <asit.k.mallick@intel.com>,
Tao Zhang <tao1.zhang@intel.com>
Subject: [PATCH v4 01/11] x86/bhi: x86/vmscape: Move LFENCE out of clear_bhb_loop()
Date: Wed, 19 Nov 2025 22:17:48 -0800 [thread overview]
Message-ID: <20251119-vmscape-bhb-v4-1-1adad4e69ddc@linux.intel.com> (raw)
In-Reply-To: <20251119-vmscape-bhb-v4-0-1adad4e69ddc@linux.intel.com>
Currently, BHB clearing sequence is followed by an LFENCE to prevent
transient execution of subsequent indirect branches prematurely. However,
LFENCE barrier could be unnecessary in certain cases. For example, when
kernel is using BHI_DIS_S mitigation, and BHB clearing is only needed for
userspace. In such cases, LFENCE is redundant because ring transitions
would provide the necessary serialization.
Below is a quick recap of BHI mitigation options:
On Alder Lake and newer
- BHI_DIS_S: Hardware control to mitigate BHI in ring0. This has low
performance overhead.
- Long loop: Alternatively, longer version of BHB clearing sequence
on older processors can be used to mitigate BHI. This
is not yet implemented in Linux.
On older CPUs
- Short loop: Clears BHB at kernel entry and VMexit.
On Alder Lake and newer CPUs, eIBRS isolates the indirect targets between
guest and host. But when affected by the BHI variant of VMSCAPE, a guest's
branch history may still influence indirect branches in userspace. This
also means the big hammer IBPB could be replaced with a cheaper option that
clears the BHB at exit-to-userspace after a VMexit.
In preparation for adding the support for BHB sequence (without LFENCE) on
newer CPUs, move the LFENCE to the caller side after clear_bhb_loop() is
executed. This allows callers to decide whether they need the LFENCE or
not. This does adds a few extra bytes to the call sites, but it obviates
the need for multiple variants of clear_bhb_loop().
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
arch/x86/entry/entry_64.S | 5 ++++-
arch/x86/include/asm/nospec-branch.h | 4 ++--
arch/x86/net/bpf_jit_comp.c | 2 ++
3 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ed04a968cc7d0095ab0185b2e3b5beffb7680afd..886f86790b4467347031bc27d3d761d5cc286da1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1528,6 +1528,9 @@ SYM_CODE_END(rewind_stack_and_make_dead)
* refactored in the future if needed. The .skips are for safety, to ensure
* that all RETs are in the second half of a cacheline to mitigate Indirect
* Target Selection, rather than taking the slowpath via its_return_thunk.
+ *
+ * Note, callers should use a speculation barrier like LFENCE immediately after
+ * a call to this function to ensure BHB is cleared before indirect branches.
*/
SYM_FUNC_START(clear_bhb_loop)
ANNOTATE_NOENDBR
@@ -1562,7 +1565,7 @@ SYM_FUNC_START(clear_bhb_loop)
sub $1, %ecx
jnz 1b
.Lret2: RET
-5: lfence
+5:
pop %rbp
RET
SYM_FUNC_END(clear_bhb_loop)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 08ed5a2e46a5fd790bcb1b73feb6469518809c06..ec5ebf96dbb9e240f402f39efc6929ae45ec8f0b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -329,11 +329,11 @@
#ifdef CONFIG_X86_64
.macro CLEAR_BRANCH_HISTORY
- ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
+ ALTERNATIVE "", "call clear_bhb_loop; lfence", X86_FEATURE_CLEAR_BHB_LOOP
.endm
.macro CLEAR_BRANCH_HISTORY_VMEXIT
- ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT
+ ALTERNATIVE "", "call clear_bhb_loop; lfence", X86_FEATURE_CLEAR_BHB_VMEXIT
.endm
#else
#define CLEAR_BRANCH_HISTORY
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index de5083cb1d3747bba00effca3703a4f6eea80d8d..c1ec14c559119b120edfac079aeb07948e9844b8 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1603,6 +1603,8 @@ static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
if (emit_call(&prog, func, ip))
return -EINVAL;
+ /* Don't speculate past this until BHB is cleared */
+ EMIT_LFENCE();
EMIT1(0x59); /* pop rcx */
EMIT1(0x58); /* pop rax */
}
--
2.34.1
next prev parent reply other threads:[~2025-11-20 6:17 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-20 6:17 [PATCH v4 00/11] VMSCAPE optimization for BHI variant Pawan Gupta
2025-11-20 6:17 ` Pawan Gupta [this message]
2025-11-20 16:15 ` [PATCH v4 01/11] x86/bhi: x86/vmscape: Move LFENCE out of clear_bhb_loop() Nikolay Borisov
2025-11-20 16:56 ` Pawan Gupta
2025-11-20 16:58 ` Nikolay Borisov
2025-11-20 6:18 ` [PATCH v4 02/11] x86/bhi: Move the BHB sequence to a macro for reuse Pawan Gupta
2025-11-20 16:28 ` Nikolay Borisov
2025-11-20 16:57 ` Pawan Gupta
2025-11-25 0:21 ` Pawan Gupta
2025-11-20 6:18 ` [PATCH v4 03/11] x86/bhi: Make the depth of BHB-clearing configurable Pawan Gupta
2025-11-20 17:02 ` Nikolay Borisov
2025-11-20 6:18 ` [PATCH v4 04/11] x86/bhi: Make clear_bhb_loop() effective on newer CPUs Pawan Gupta
2025-11-21 12:33 ` Nikolay Borisov
2025-11-21 16:40 ` Dave Hansen
2025-11-21 16:45 ` Nikolay Borisov
2025-11-21 16:50 ` Dave Hansen
2025-11-21 18:16 ` Pawan Gupta
2025-11-21 18:42 ` Dave Hansen
2025-11-21 21:26 ` Pawan Gupta
2025-11-21 21:36 ` Dave Hansen
2025-11-24 19:21 ` Pawan Gupta
2025-11-22 11:05 ` david laight
2025-11-24 19:31 ` Pawan Gupta
2025-11-25 11:34 ` david laight
2025-12-04 1:40 ` Pawan Gupta
2025-12-04 9:15 ` david laight
2025-12-04 21:56 ` Pawan Gupta
2025-12-05 9:21 ` david laight
2025-11-26 19:23 ` Pawan Gupta
2026-03-06 21:00 ` Jim Mattson
2026-03-06 22:32 ` Pawan Gupta
2026-03-06 22:57 ` Jim Mattson
2026-03-06 23:29 ` Pawan Gupta
2026-03-07 0:35 ` Jim Mattson
2026-03-07 1:00 ` Pawan Gupta
2026-03-07 1:10 ` Jim Mattson
2026-03-07 2:41 ` Pawan Gupta
2026-03-07 5:05 ` Jim Mattson
2026-03-09 22:29 ` Pawan Gupta
2026-03-09 23:05 ` Jim Mattson
2026-03-10 0:00 ` Pawan Gupta
2026-03-10 0:08 ` Jim Mattson
2026-03-10 0:52 ` Pawan Gupta
2025-11-20 6:18 ` [PATCH v4 05/11] x86/vmscape: Rename x86_ibpb_exit_to_user to x86_predictor_flush_exit_to_user Pawan Gupta
2025-11-20 6:19 ` [PATCH v4 06/11] x86/vmscape: Move mitigation selection to a switch() Pawan Gupta
2025-11-21 14:27 ` Nikolay Borisov
2025-11-24 23:09 ` Pawan Gupta
2025-11-25 10:19 ` Nikolay Borisov
2025-11-25 17:45 ` Pawan Gupta
2025-11-20 6:19 ` [PATCH v4 07/11] x86/vmscape: Use write_ibpb() instead of indirect_branch_prediction_barrier() Pawan Gupta
2025-11-21 12:59 ` Nikolay Borisov
2025-11-20 6:19 ` [PATCH v4 08/11] x86/vmscape: Use static_call() for predictor flush Pawan Gupta
2025-11-20 6:19 ` [PATCH v4 09/11] x86/vmscape: Deploy BHB clearing mitigation Pawan Gupta
2025-11-21 14:18 ` Nikolay Borisov
2025-11-21 18:29 ` Pawan Gupta
2025-11-21 14:23 ` Nikolay Borisov
2025-11-21 18:41 ` Pawan Gupta
2025-11-21 18:53 ` Nikolay Borisov
2025-11-21 21:29 ` Pawan Gupta
2025-11-20 6:20 ` [PATCH v4 10/11] x86/vmscape: Override conflicting attack-vector controls with =force Pawan Gupta
2025-11-21 18:04 ` Nikolay Borisov
2025-11-20 6:20 ` [PATCH v4 11/11] x86/vmscape: Add cmdline vmscape=on to override attack vector controls Pawan Gupta
2025-11-25 11:41 ` Nikolay Borisov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251119-vmscape-bhb-v4-1-1adad4e69ddc@linux.intel.com \
--to=pawan.kumar.gupta@linux.intel.com \
--cc=asit.k.mallick@intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david.kaplan@amd.com \
--cc=hpa@zytor.com \
--cc=jpoimboe@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nik.borisov@suse.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=tao1.zhang@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.