Add a version of clear_bhb_loop() that works on CPUs with larger branch
history table such as Alder Lake and newer. This could serve as a cheaper
alternative to IBPB mitigation for VMSCAPE.

clear_bhb_loop() and the new clear_bhb_long_loop() only differ in the loop
counter. Convert the asm implementation of clear_bhb_loop() into a macro
that is used by both the variants, passing counter as an argument.

There is no difference in the output of:

  $ objdump --disassemble=clear_bhb_loop vmlinux

before and after this commit.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
 arch/x86/entry/entry_64.S            | 47 ++++++++++++++++++++++++++----------
 arch/x86/include/asm/nospec-branch.h |  3 +++
 2 files changed, 37 insertions(+), 13 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ed04a968cc7d0095ab0185b2e3b5beffb7680afd..f5f62af080d8ec6fe81e4dbe78ce44d08e62aa59 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1499,11 +1499,6 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * from the branch history tracker in the Branch Predictor, therefore removing
  * user influence on subsequent BTB lookups.
  *
- * It should be used on parts prior to Alder Lake. Newer parts should use the
- * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
- * virtualized on newer hardware the VMM should protect against BHI attacks by
- * setting BHI_DIS_S for the guests.
- *
  * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
  * and not clearing the branch history. The call tree looks like:
  *
@@ -1529,11 +1524,12 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * 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.
  */
-SYM_FUNC_START(clear_bhb_loop)
+.macro	__CLEAR_BHB_LOOP outer_loop_count:req, inner_loop_count:req
 	ANNOTATE_NOENDBR
 	push	%rbp
 	mov	%rsp, %rbp
-	movl	$5, %ecx
+
+	movl	$\outer_loop_count, %ecx
 	ANNOTATE_INTRA_FUNCTION_CALL
 	call	1f
 	jmp	5f
@@ -1542,29 +1538,54 @@ SYM_FUNC_START(clear_bhb_loop)
 	 * Shift instructions so that the RET is in the upper half of the
 	 * cacheline and don't take the slowpath to its_return_thunk.
 	 */
-	.skip 32 - (.Lret1 - 1f), 0xcc
+	.skip 32 - (.Lret1_\@ - 1f), 0xcc
 	ANNOTATE_INTRA_FUNCTION_CALL
 1:	call	2f
-.Lret1:	RET
+.Lret1_\@:
+	RET
 	.align 64, 0xcc
 	/*
-	 * As above shift instructions for RET at .Lret2 as well.
+	 * As above shift instructions for RET at .Lret2_\@ as well.
 	 *
-	 * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc
+	 * This should be ideally be: .skip 32 - (.Lret2_\@ - 2f), 0xcc
 	 * but some Clang versions (e.g. 18) don't like this.
 	 */
 	.skip 32 - 18, 0xcc
-2:	movl	$5, %eax
+2:	movl	$\inner_loop_count, %eax
 3:	jmp	4f
 	nop
 4:	sub	$1, %eax
 	jnz	3b
 	sub	$1, %ecx
 	jnz	1b
-.Lret2:	RET
+.Lret2_\@:
+	RET
 5:	lfence
+
 	pop	%rbp
 	RET
+.endm
+
+/*
+ * This should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+	__CLEAR_BHB_LOOP 5, 5
 SYM_FUNC_END(clear_bhb_loop)
 EXPORT_SYMBOL_GPL(clear_bhb_loop)
 STACK_FRAME_NON_STANDARD(clear_bhb_loop)
+
+/*
+ * A longer version of clear_bhb_loop to ensure that the BHB is cleared on CPUs
+ * with larger branch history tables (i.e. Alder Lake and newer). BHI_DIS_S
+ * protects the kernel, but to mitigate the guest influence on the host
+ * userspace either IBPB or this sequence should be used. See VMSCAPE bug.
+ */
+SYM_FUNC_START(clear_bhb_long_loop)
+	__CLEAR_BHB_LOOP 12, 7
+SYM_FUNC_END(clear_bhb_long_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_long_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_long_loop)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 08ed5a2e46a5fd790bcb1b73feb6469518809c06..49707e563bdf71bdd05d3827f10dd2b8ac6bca2c 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -388,6 +388,9 @@ extern void write_ibpb(void);
 
 #ifdef CONFIG_X86_64
 extern void clear_bhb_loop(void);
+extern void clear_bhb_long_loop(void);
+#else
+static inline void clear_bhb_long_loop(void) {}
 #endif
 
 extern void (*x86_return_thunk)(void);

-- 
2.34.1