Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Add the call depth tracking mitigation for Retbleed which has been
   long in the making. It is a lighterweight software-only fix for
   Skylake-based cores where enabling IBRS is a big hammer and causes a
   significant performance impact.

   What it basically does is, it aligns all kernel functions to 16 bytes
   boundary and adds a 16-byte padding before the function, objtool
   collects all functions' locations and when the mitigation gets
   applied, it patches a call accounting thunk which is used to track
   the call depth of the stack at any time.

   When that call depth reaches a magical, microarchitecture-specific
   value for the Return Stack Buffer, the code stuffs that RSB and
   avoids its underflow which could otherwise lead to the Intel variant
   of Retbleed.

   This software-only solution brings a lot of the lost performance
   back, as benchmarks suggest:

       https://lore.kernel.org/all/20220915111039.092790446@infradead.org/

   That page above also contains a lot more detailed explanation of the
   whole mechanism

 - Implement a new control flow integrity scheme called FineIBT which is
   based on the software kCFI implementation and uses hardware IBT
   support where present to annotate and track indirect branches using a
   hash to validate them

 - Other misc fixes and cleanups

* tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits)
  x86/paravirt: Use common macro for creating simple asm paravirt functions
  x86/paravirt: Remove clobber bitmask from .parainstructions
  x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al
  x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit
  x86/Kconfig: Enable kernel IBT by default
  x86,pm: Force out-of-line memcpy()
  objtool: Fix weak hole vs prefix symbol
  objtool: Optimize elf_dirty_reloc_sym()
  x86/cfi: Add boot time hash randomization
  x86/cfi: Boot time selection of CFI scheme
  x86/ibt: Implement FineIBT
  objtool: Add --cfi to generate the .cfi_sites section
  x86: Add prefix symbols for function padding
  objtool: Add option to generate prefix symbols
  objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf
  objtool: Slice up elf_create_section_symbol()
  kallsyms: Revert "Take callthunks into account"
  x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces
  x86/retpoline: Fix crash printing warning
  x86/paravirt: Fix a !PARAVIRT build warning
  ...

5 files changed, 12 insertions, 0 deletions

diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index 39146fa83e20..de5a0f67f320 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -3,6 +3,7 @@
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func1(void);
 extern void my_direct_func2(void);
@@ -34,6 +35,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	call my_direct_func1\n"
 "	leave\n"
 "	.size		my_tramp1, .-my_tramp1\n"
@@ -45,6 +47,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	call my_direct_func2\n"
 "	leave\n"
 	ASM_RET
diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c
index 65aa94d96f4e..d52370cad0b6 100644
--- a/samples/ftrace/ftrace-direct-multi-modify.c
+++ b/samples/ftrace/ftrace-direct-multi-modify.c
@@ -3,6 +3,7 @@
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func1(unsigned long ip);
 extern void my_direct_func2(unsigned long ip);
@@ -32,6 +33,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func1\n"
@@ -46,6 +48,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func2\n"
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index 41ded7c615c7..ec1088922517 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -5,6 +5,7 @@
 #include <linux/ftrace.h>
 #include <linux/sched/stat.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(unsigned long ip);
 
@@ -27,6 +28,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	movq 8(%rbp), %rdi\n"
 "	call my_direct_func\n"
diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c
index 6690468c5cc2..e13fb59a2b47 100644
--- a/samples/ftrace/ftrace-direct-too.c
+++ b/samples/ftrace/ftrace-direct-too.c
@@ -4,6 +4,7 @@
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(struct vm_area_struct *vma,
 			   unsigned long address, unsigned int flags);
@@ -29,6 +30,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	pushq %rsi\n"
 "	pushq %rdx\n"
diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c
index e8f1e440b9b8..1f769d0db20f 100644
--- a/samples/ftrace/ftrace-direct.c
+++ b/samples/ftrace/ftrace-direct.c
@@ -4,6 +4,7 @@
 #include <linux/sched.h> /* for wake_up_process() */
 #include <linux/ftrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/nospec-branch.h>
 
 extern void my_direct_func(struct task_struct *p);
 
@@ -26,6 +27,7 @@ asm (
 	ASM_ENDBR
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
+	CALL_DEPTH_ACCOUNT
 "	pushq %rdi\n"
 "	call my_direct_func\n"
 "	popq %rdi\n"