lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:   Sat, 26 Aug 2023 16:05:47 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org, akpm@...ux-foundation.org,
        torvalds@...ux-foundation.org, stable@...r.kernel.org
Cc:     lwn@....net, jslaby@...e.cz,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Subject: Re: Linux 6.1.48

diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst
index 2f923c805802..f79cb11b080f 100644
--- a/Documentation/admin-guide/hw-vuln/srso.rst
+++ b/Documentation/admin-guide/hw-vuln/srso.rst
@@ -124,8 +124,8 @@ sequence.
 To ensure the safety of this mitigation, the kernel must ensure that the
 safe return sequence is itself free from attacker interference.  In Zen3
 and Zen4, this is accomplished by creating a BTB alias between the
-untraining function srso_untrain_ret_alias() and the safe return
-function srso_safe_ret_alias() which results in evicting a potentially
+untraining function srso_alias_untrain_ret() and the safe return
+function srso_alias_safe_ret() which results in evicting a potentially
 poisoned BTB entry and using that safe one for all function returns.
 
 In older Zen1 and Zen2, this is accomplished using a reinterpretation
diff --git a/Makefile b/Makefile
index 375efcfb91f8..8bb8dd199c55 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 1
-SUBLEVEL = 47
+SUBLEVEL = 48
 EXTRAVERSION =
 NAME = Curry Ramen
 
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 674ed46d3ced..11203a9fe0a8 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -92,6 +92,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 static __always_inline void arch_exit_to_user_mode(void)
 {
 	mds_user_clear_cpu_buffers();
+	amd_clear_divider();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 31fa631c8587..2f123d4fb85b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -168,9 +168,9 @@
 .endm
 
 #ifdef CONFIG_CPU_UNRET_ENTRY
-#define CALL_ZEN_UNTRAIN_RET	"call zen_untrain_ret"
+#define CALL_UNTRAIN_RET	"call entry_untrain_ret"
 #else
-#define CALL_ZEN_UNTRAIN_RET	""
+#define CALL_UNTRAIN_RET	""
 #endif
 
 /*
@@ -178,7 +178,7 @@
  * return thunk isn't mapped into the userspace tables (then again, AMD
  * typically has NO_MELTDOWN).
  *
- * While zen_untrain_ret() doesn't clobber anything but requires stack,
+ * While retbleed_untrain_ret() doesn't clobber anything but requires stack,
  * entry_ibpb() will clobber AX, CX, DX.
  *
  * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
@@ -189,14 +189,9 @@
 	defined(CONFIG_CPU_SRSO)
 	ANNOTATE_UNRET_END
 	ALTERNATIVE_2 "",						\
-	              CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
+		      CALL_UNTRAIN_RET, X86_FEATURE_UNRET,		\
 		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
 #endif
-
-#ifdef CONFIG_CPU_SRSO
-	ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \
-			  "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS
-#endif
 .endm
 
 #else /* __ASSEMBLY__ */
@@ -210,10 +205,21 @@
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
 extern retpoline_thunk_t __x86_indirect_thunk_array[];
 
+#ifdef CONFIG_RETHUNK
 extern void __x86_return_thunk(void);
-extern void zen_untrain_ret(void);
+#else
+static inline void __x86_return_thunk(void) {}
+#endif
+
+extern void retbleed_return_thunk(void);
+extern void srso_return_thunk(void);
+extern void srso_alias_return_thunk(void);
+
+extern void retbleed_untrain_ret(void);
 extern void srso_untrain_ret(void);
-extern void srso_untrain_ret_alias(void);
+extern void srso_alias_untrain_ret(void);
+
+extern void entry_untrain_ret(void);
 extern void entry_ibpb(void);
 
 #ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 239b302973d7..f240c978d85e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1295,3 +1295,4 @@ void noinstr amd_clear_divider(void)
 	asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0)
 		     :: "a" (0), "d" (0), "r" (1));
 }
+EXPORT_SYMBOL_GPL(amd_clear_divider);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d98f33ea57e4..3a893ab398a0 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -62,6 +62,8 @@ EXPORT_SYMBOL_GPL(x86_pred_cmd);
 
 static DEFINE_MUTEX(spec_ctrl_mutex);
 
+void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+
 /* Update SPEC_CTRL MSR and its cached copy unconditionally */
 static void update_spec_ctrl(u64 val)
 {
@@ -164,8 +166,13 @@ void __init cpu_select_mitigations(void)
 	md_clear_select_mitigation();
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();
-	gds_select_mitigation();
+
+	/*
+	 * srso_select_mitigation() depends and must run after
+	 * retbleed_select_mitigation().
+	 */
 	srso_select_mitigation();
+	gds_select_mitigation();
 }
 
 /*
@@ -1013,6 +1020,9 @@ static void __init retbleed_select_mitigation(void)
 		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
 		setup_force_cpu_cap(X86_FEATURE_UNRET);
 
+		if (IS_ENABLED(CONFIG_RETHUNK))
+			x86_return_thunk = retbleed_return_thunk;
+
 		if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
 		    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 			pr_err(RETBLEED_UNTRAIN_MSG);
@@ -2388,9 +2398,10 @@ static void __init srso_select_mitigation(void)
 		 * Zen1/2 with SMT off aren't vulnerable after the right
 		 * IBPB microcode has been applied.
 		 */
-		if ((boot_cpu_data.x86 < 0x19) &&
-		    (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED)))
+		if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
 			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
+			return;
+		}
 	}
 
 	if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
@@ -2419,11 +2430,15 @@ static void __init srso_select_mitigation(void)
 			 * like ftrace, static_call, etc.
 			 */
 			setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+			setup_force_cpu_cap(X86_FEATURE_UNRET);
 
-			if (boot_cpu_data.x86 == 0x19)
+			if (boot_cpu_data.x86 == 0x19) {
 				setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
-			else
+				x86_return_thunk = srso_alias_return_thunk;
+			} else {
 				setup_force_cpu_cap(X86_FEATURE_SRSO);
+				x86_return_thunk = srso_return_thunk;
+			}
 			srso_mitigation = SRSO_MITIGATION_SAFE_RET;
 		} else {
 			pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
@@ -2672,6 +2687,9 @@ static ssize_t gds_show_state(char *buf)
 
 static ssize_t srso_show_state(char *buf)
 {
+	if (boot_cpu_has(X86_FEATURE_SRSO_NO))
+		return sysfs_emit(buf, "Mitigation: SMT disabled\n");
+
 	return sysfs_emit(buf, "%s%s\n",
 			  srso_strings[srso_mitigation],
 			  (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index a9b54b795ebf..3fbb49168827 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -184,6 +184,19 @@ EXPORT_SYMBOL_GPL(arch_static_call_transform);
  */
 bool __static_call_fixup(void *tramp, u8 op, void *dest)
 {
+	unsigned long addr = (unsigned long)tramp;
+	/*
+	 * Not all .return_sites are a static_call trampoline (most are not).
+	 * Check if the 3 bytes after the return are still kernel text, if not,
+	 * then this definitely is not a trampoline and we need not worry
+	 * further.
+	 *
+	 * This avoids the memcmp() below tripping over pagefaults etc..
+	 */
+	if (((addr >> PAGE_SHIFT) != ((addr + 7) >> PAGE_SHIFT)) &&
+	    !kernel_text_address(addr + 7))
+		return false;
+
 	if (memcmp(tramp+5, tramp_ud, 3)) {
 		/* Not a trampoline site, not our problem. */
 		return false;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7e8795d8b0f1..c0a5a4f225d9 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -206,8 +206,6 @@ DEFINE_IDTENTRY(exc_divide_error)
 {
 	do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE,
 		      FPE_INTDIV, error_get_trap_addr(regs));
-
-	amd_clear_divider();
 }
 
 DEFINE_IDTENTRY(exc_overflow)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e6939ebb606a..78ccb5ec3c0e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -134,18 +134,18 @@ SECTIONS
 		KPROBES_TEXT
 		ALIGN_ENTRY_TEXT_BEGIN
 #ifdef CONFIG_CPU_SRSO
-		*(.text.__x86.rethunk_untrain)
+		*(.text..__x86.rethunk_untrain)
 #endif
 
 		ENTRY_TEXT
 
 #ifdef CONFIG_CPU_SRSO
 		/*
-		 * See the comment above srso_untrain_ret_alias()'s
+		 * See the comment above srso_alias_untrain_ret()'s
 		 * definition.
 		 */
-		. = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20);
-		*(.text.__x86.rethunk_safe)
+		. = srso_alias_untrain_ret | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20);
+		*(.text..__x86.rethunk_safe)
 #endif
 		ALIGN_ENTRY_TEXT_END
 		SOFTIRQENTRY_TEXT
@@ -154,8 +154,8 @@ SECTIONS
 
 #ifdef CONFIG_RETPOLINE
 		__indirect_thunk_start = .;
-		*(.text.__x86.indirect_thunk)
-		*(.text.__x86.return_thunk)
+		*(.text..__x86.indirect_thunk)
+		*(.text..__x86.return_thunk)
 		__indirect_thunk_end = .;
 #endif
 	} :text =0xcccc
@@ -507,8 +507,8 @@ INIT_PER_CPU(irq_stack_backing_store);
            "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
- #ifdef CONFIG_RETHUNK
-. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned");
+#ifdef CONFIG_RETHUNK
+. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
 . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
 #endif
 
@@ -523,8 +523,8 @@ INIT_PER_CPU(irq_stack_backing_store);
  * Instead do: (A | B) - (A & B) in order to compute the XOR
  * of the two function addresses:
  */
-. = ASSERT(((ABSOLUTE(srso_untrain_ret_alias) | srso_safe_ret_alias) -
-		(ABSOLUTE(srso_untrain_ret_alias) & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)),
+. = ASSERT(((ABSOLUTE(srso_alias_untrain_ret) | srso_alias_safe_ret) -
+		(ABSOLUTE(srso_alias_untrain_ret) & srso_alias_safe_ret)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)),
 		"SRSO function pair won't alias");
 #endif
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index fdb6007f2eb8..a96f9a17e8b5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3947,6 +3947,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	amd_clear_divider();
+
 	if (sev_es_guest(vcpu->kvm))
 		__svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted);
 	else
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 30e76fab678a..65c5c44f006b 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -11,7 +11,7 @@
 #include <asm/frame.h>
 #include <asm/nops.h>
 
-	.section .text.__x86.indirect_thunk
+	.section .text..__x86.indirect_thunk
 
 .macro RETPOLINE reg
 	ANNOTATE_INTRA_FUNCTION_CALL
@@ -76,75 +76,106 @@ SYM_CODE_END(__x86_indirect_thunk_array)
 #ifdef CONFIG_RETHUNK
 
 /*
- * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at
+ * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
  * special addresses:
  *
- * - srso_untrain_ret_alias() is 2M aligned
- * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14
+ * - srso_alias_untrain_ret() is 2M aligned
+ * - srso_alias_safe_ret() is also in the same 2M page but bits 2, 8, 14
  * and 20 in its virtual address are set (while those bits in the
- * srso_untrain_ret_alias() function are cleared).
+ * srso_alias_untrain_ret() function are cleared).
  *
  * This guarantees that those two addresses will alias in the branch
  * target buffer of Zen3/4 generations, leading to any potential
  * poisoned entries at that BTB slot to get evicted.
  *
- * As a result, srso_safe_ret_alias() becomes a safe return.
+ * As a result, srso_alias_safe_ret() becomes a safe return.
  */
 #ifdef CONFIG_CPU_SRSO
-	.section .text.__x86.rethunk_untrain
+	.section .text..__x86.rethunk_untrain
 
-SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE)
+SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
 	ASM_NOP2
 	lfence
-	jmp __x86_return_thunk
-SYM_FUNC_END(srso_untrain_ret_alias)
-__EXPORT_THUNK(srso_untrain_ret_alias)
+	jmp srso_alias_return_thunk
+SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
 
-	.section .text.__x86.rethunk_safe
+	.section .text..__x86.rethunk_safe
+#else
+/* dummy definition for alternatives */
+SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_FUNC_END(srso_alias_untrain_ret)
 #endif
 
-/* Needs a definition for the __x86_return_thunk alternative below. */
-SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE)
-#ifdef CONFIG_CPU_SRSO
-	add $8, %_ASM_SP
+SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	lea 8(%_ASM_SP), %_ASM_SP
 	UNWIND_HINT_FUNC
-#endif
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
-SYM_FUNC_END(srso_safe_ret_alias)
+SYM_FUNC_END(srso_alias_safe_ret)
+
+	.section .text..__x86.return_thunk
 
-	.section .text.__x86.return_thunk
+SYM_CODE_START(srso_alias_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	call srso_alias_safe_ret
+	ud2
+SYM_CODE_END(srso_alias_return_thunk)
+
+/*
+ * Some generic notes on the untraining sequences:
+ *
+ * They are interchangeable when it comes to flushing potentially wrong
+ * RET predictions from the BTB.
+ *
+ * The SRSO Zen1/2 (MOVABS) untraining sequence is longer than the
+ * Retbleed sequence because the return sequence done there
+ * (srso_safe_ret()) is longer and the return sequence must fully nest
+ * (end before) the untraining sequence. Therefore, the untraining
+ * sequence must fully overlap the return sequence.
+ *
+ * Regarding alignment - the instructions which need to be untrained,
+ * must all start at a cacheline boundary for Zen1/2 generations. That
+ * is, instruction sequences starting at srso_safe_ret() and
+ * the respective instruction sequences at retbleed_return_thunk()
+ * must start at a cacheline boundary.
+ */
 
 /*
  * Safety details here pertain to the AMD Zen{1,2} microarchitecture:
- * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for
+ * 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for
  *    alignment within the BTB.
- * 2) The instruction at zen_untrain_ret must contain, and not
+ * 2) The instruction at retbleed_untrain_ret must contain, and not
  *    end with, the 0xc3 byte of the RET.
  * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread
  *    from re-poisioning the BTB prediction.
  */
 	.align 64
-	.skip 64 - (__ret - zen_untrain_ret), 0xcc
-SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	.skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc
+SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	ANNOTATE_NOENDBR
 	/*
-	 * As executed from zen_untrain_ret, this is:
+	 * As executed from retbleed_untrain_ret, this is:
 	 *
 	 *   TEST $0xcc, %bl
 	 *   LFENCE
-	 *   JMP __x86_return_thunk
+	 *   JMP retbleed_return_thunk
 	 *
 	 * Executing the TEST instruction has a side effect of evicting any BTB
 	 * prediction (potentially attacker controlled) attached to the RET, as
-	 * __x86_return_thunk + 1 isn't an instruction boundary at the moment.
+	 * retbleed_return_thunk + 1 isn't an instruction boundary at the moment.
 	 */
 	.byte	0xf6
 
 	/*
-	 * As executed from __x86_return_thunk, this is a plain RET.
+	 * As executed from retbleed_return_thunk, this is a plain RET.
 	 *
 	 * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8.
 	 *
@@ -156,13 +187,13 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	 * With SMT enabled and STIBP active, a sibling thread cannot poison
 	 * RET's prediction to a type of its choice, but can evict the
 	 * prediction due to competitive sharing. If the prediction is
-	 * evicted, __x86_return_thunk will suffer Straight Line Speculation
+	 * evicted, retbleed_return_thunk will suffer Straight Line Speculation
 	 * which will be contained safely by the INT3.
 	 */
-SYM_INNER_LABEL(__ret, SYM_L_GLOBAL)
+SYM_INNER_LABEL(retbleed_return_thunk, SYM_L_GLOBAL)
 	ret
 	int3
-SYM_CODE_END(__ret)
+SYM_CODE_END(retbleed_return_thunk)
 
 	/*
 	 * Ensure the TEST decoding / BTB invalidation is complete.
@@ -173,16 +204,16 @@ SYM_CODE_END(__ret)
 	 * Jump back and execute the RET in the middle of the TEST instruction.
 	 * INT3 is for SLS protection.
 	 */
-	jmp __ret
+	jmp retbleed_return_thunk
 	int3
-SYM_FUNC_END(zen_untrain_ret)
-__EXPORT_THUNK(zen_untrain_ret)
+SYM_FUNC_END(retbleed_untrain_ret)
+__EXPORT_THUNK(retbleed_untrain_ret)
 
 /*
- * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret()
+ * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
  * above. On kernel entry, srso_untrain_ret() is executed which is a
  *
- * movabs $0xccccccc308c48348,%rax
+ * movabs $0xccccc30824648d48,%rax
  *
  * and when the return thunk executes the inner label srso_safe_ret()
  * later, it is a stack manipulation and a RET which is mispredicted and
@@ -194,22 +225,44 @@ SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	ANNOTATE_NOENDBR
 	.byte 0x48, 0xb8
 
+/*
+ * This forces the function return instruction to speculate into a trap
+ * (UD2 in srso_return_thunk() below).  This RET will then mispredict
+ * and execution will continue at the return site read from the top of
+ * the stack.
+ */
 SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
-	add $8, %_ASM_SP
+	lea 8(%_ASM_SP), %_ASM_SP
 	ret
 	int3
 	int3
-	int3
+	/* end of movabs */
 	lfence
 	call srso_safe_ret
-	int3
+	ud2
 SYM_CODE_END(srso_safe_ret)
 SYM_FUNC_END(srso_untrain_ret)
 __EXPORT_THUNK(srso_untrain_ret)
 
-SYM_FUNC_START(__x86_return_thunk)
-	ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \
-			"call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS
+SYM_CODE_START(srso_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	call srso_safe_ret
+	ud2
+SYM_CODE_END(srso_return_thunk)
+
+SYM_FUNC_START(entry_untrain_ret)
+	ALTERNATIVE_2 "jmp retbleed_untrain_ret", \
+		      "jmp srso_untrain_ret", X86_FEATURE_SRSO, \
+		      "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
+SYM_FUNC_END(entry_untrain_ret)
+__EXPORT_THUNK(entry_untrain_ret)
+
+SYM_CODE_START(__x86_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
 	int3
 SYM_CODE_END(__x86_return_thunk)
 EXPORT_SYMBOL(__x86_return_thunk)
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index a60c5efe34b3..29c35279c7ed 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -799,5 +799,5 @@ bool arch_is_rethunk(struct symbol *sym)
 	return !strcmp(sym->name, "__x86_return_thunk") ||
 	       !strcmp(sym->name, "srso_untrain_ret") ||
 	       !strcmp(sym->name, "srso_safe_ret") ||
-	       !strcmp(sym->name, "__ret");
+	       !strcmp(sym->name, "retbleed_return_thunk");
 }
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index c2c350933a23..913bd361c368 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -379,7 +379,7 @@ static int decode_instructions(struct objtool_file *file)
 
 		if (!strcmp(sec->name, ".noinstr.text") ||
 		    !strcmp(sec->name, ".entry.text") ||
-		    !strncmp(sec->name, ".text.__x86.", 12))
+		    !strncmp(sec->name, ".text..__x86.", 13))
 			sec->noinstr = true;
 
 		for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) {
@@ -1430,7 +1430,7 @@ static int add_jump_destinations(struct objtool_file *file)
 			struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off);
 
 			/*
-			 * This is a special case for zen_untrain_ret().
+			 * This is a special case for retbleed_untrain_ret().
 			 * It jumps to __x86_return_thunk(), but objtool
 			 * can't find the thunk's starting RET
 			 * instruction, because the RET is also in the
@@ -2450,12 +2450,17 @@ static int decode_sections(struct objtool_file *file)
 	return 0;
 }
 
-static bool is_fentry_call(struct instruction *insn)
+static bool is_special_call(struct instruction *insn)
 {
-	if (insn->type == INSN_CALL &&
-	    insn->call_dest &&
-	    insn->call_dest->fentry)
-		return true;
+	if (insn->type == INSN_CALL) {
+		struct symbol *dest = insn->call_dest;
+
+		if (!dest)
+			return false;
+
+		if (dest->fentry)
+			return true;
+	}
 
 	return false;
 }
@@ -3448,7 +3453,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			if (ret)
 				return ret;
 
-			if (opts.stackval && func && !is_fentry_call(insn) &&
+			if (opts.stackval && func && !is_special_call(insn) &&
 			    !has_valid_stack_frame(&state)) {
 				WARN_FUNC("call without frame pointer save/setup",
 					  sec, insn->offset);

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ