Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Brian Gerst <brgerst@gmail.com>
To:     linux-kernel@vger.kernel.org, x86@kernel.org
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>,
        "H . Peter Anvin" <hpa@zytor.com>,
        Andy Lutomirski <luto@kernel.org>,
        =?UTF-8?q?Mika=20Penttil=C3=A4?= <mpenttil@redhat.com>,
        Brian Gerst <brgerst@gmail.com>
Subject: [PATCH v2 6/6] x86/entry/32: Clean up syscall fast exit tests
Date:   Fri, 21 Jul 2023 12:10:17 -0400
Message-ID: <20230721161018.50214-7-brgerst@gmail.com>
In-Reply-To: <20230721161018.50214-1-brgerst@gmail.com>
References: <20230721161018.50214-1-brgerst@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Merge compat and native code and clarify comments.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
---
 arch/x86/entry/common.c          | 48 +++++++++++++++-----------------
 arch/x86/entry/entry_64_compat.S |  5 ++--
 2 files changed, 24 insertions(+), 29 deletions(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 4d7d6d25dda9..800664325542 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -241,34 +241,30 @@ __visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
 	if (!__do_fast_syscall_32(regs))
 		return false;
 
-#ifdef CONFIG_X86_64
 	/*
-	 * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
-	 * SYSRETL is available on all 64-bit CPUs, so we don't need to
-	 * bother with SYSEXIT.
-	 *
-	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
-	 * because the ECX fixup above will ensure that this is essentially
-	 * never the case.
+	 * Check that the register state is valid for using SYSRETL/SYSEXIT
+	 * to exit to userspace.  Otherwise use the slower but fully capable
+	 * IRET exit path.
 	 */
-	return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
-		regs->ip == landing_pad &&
-		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
-#else
-	/*
-	 * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
-	 *
-	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
-	 * because the ECX fixup above will ensure that this is essentially
-	 * never the case.
-	 *
-	 * We don't allow syscalls at all from VM86 mode, but we still
-	 * need to check VM, because we might be returning from sys_vm86.
-	 */
-	return regs->cs == __USER_CS && regs->ss == __USER_DS &&
-		regs->ip == landing_pad &&
-		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
-#endif
+
+	/* XEN PV guests always use IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* EIP must point to the VDSO landing pad */
+	if (unlikely(regs->ip != landing_pad))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
+		return false;
+
+	/* If the TF, RF, or VM flags are set, use IRET */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
+		return false;
+
+	/* Use SYSRETL/SYSEXIT to exit to userspace */
+	return true;
 }
 
 /* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 27c05d08558a..84e21d1ebf10 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -211,9 +211,8 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 	call	do_fast_syscall_32
 
 sysret32_from_system_call:
-	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
-		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+	testb	%al, %al		/* Is SYSRET allowed? */
+	jz	swapgs_restore_regs_and_return_to_usermode
 
 	/*
 	 * Opportunistic SYSRET
-- 
2.41.0