x86/cpufeature: Replace X86_FEATURE_SYSENTER32 with X86_FEATURE_SYSFAST32

In most cases, the use of "fast 32-bit system call" depends either on
X86_FEATURE_SEP or X86_FEATURE_SYSENTER32 || X86_FEATURE_SYSCALL32.
However, nearly all the logic for both is identical.

Define X86_FEATURE_SYSFAST32 which indicates that *either* SYSENTER32 or
SYSCALL32 should be used, for either 32- or 64-bit kernels.  This
defaults to SYSENTER; use SYSCALL if the SYSCALL32 bit is also set.

As this removes ALL existing uses of X86_FEATURE_SYSENTER32, which is
a kernel-only synthetic feature bit, simply remove it and replace it
with X86_FEATURE_SYSFAST32.

This leaves an unused alternative for a true 32-bit kernel, but that
should really not matter in any way.

The clearing of X86_FEATURE_SYSCALL32 can be removed once the patches
for automatically clearing disabled features has been merged.

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://patch.msgid.link/20251216212606.1325678-10-hpa@zytor.com

Author: H. Peter Anvin

arch/x86/Kconfig.cpufeatures

@@ -56,6 +56,10 @@ config X86_REQUIRED_FEATURE_MOVBE
 	def_bool y
 	depends on MATOM
 
+config X86_REQUIRED_FEATURE_SYSFAST32
+	def_bool y
+	depends on X86_64 && !X86_FRED
+
 config X86_REQUIRED_FEATURE_CPUID
 	def_bool y
 	depends on X86_64
@@ -120,6 +124,10 @@ config X86_DISABLED_FEATURE_CENTAUR_MCR
 	def_bool y
 	depends on X86_64
 
+config X86_DISABLED_FEATURE_SYSCALL32
+	def_bool y
+	depends on !X86_64
+
 config X86_DISABLED_FEATURE_PCID
 	def_bool y
 	depends on !X86_64

arch/x86/entry/vdso/vdso32/system_call.S

@@ -52,13 +52,9 @@ __kernel_vsyscall:
 	#define SYSENTER_SEQUENCE	"movl %esp, %ebp; sysenter"
 	#define SYSCALL_SEQUENCE	"movl %ecx, %ebp; syscall"
 
-#ifdef BUILD_VDSO32_64
 	/* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */
-	ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \
-	                  SYSCALL_SEQUENCE,  X86_FEATURE_SYSCALL32
-#else
-	ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP
-#endif
+	ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSFAST32, \
+			  SYSCALL_SEQUENCE,  X86_FEATURE_SYSCALL32
 
 	/* Enter using int $0x80 */
 	int	$0x80

arch/x86/include/asm/cpufeatures.h

@@ -84,7 +84,7 @@
 #define X86_FEATURE_PEBS		( 3*32+12) /* "pebs" Precise-Event Based Sampling */
 #define X86_FEATURE_BTS			( 3*32+13) /* "bts" Branch Trace Store */
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* syscall in IA32 userspace */
-#define X86_FEATURE_SYSENTER32		( 3*32+15) /* sysenter in IA32 userspace */
+#define X86_FEATURE_SYSFAST32		( 3*32+15) /* sysenter/syscall in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* "rep_good" REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
 #define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* Clear CPU buffers using VERW */

arch/x86/kernel/cpu/centaur.c

@@ -102,9 +102,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 	    (c->x86 >= 7))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
-#ifdef CONFIG_X86_64
-	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
-#endif
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);

arch/x86/kernel/cpu/common.c

@@ -1068,6 +1068,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
 
+	if (IS_ENABLED(CONFIG_X86_64) || cpu_has(c, X86_FEATURE_SEP))
+		set_cpu_cap(c, X86_FEATURE_SYSFAST32);
+
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
 	 * This needs to happen each time we re-probe, which may happen
@@ -1813,6 +1816,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 * that it can't be enabled in 32-bit mode.
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
+
+	/*
+	 * Never use SYSCALL on a 32-bit kernel
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
 #endif
 
 	/*

arch/x86/kernel/cpu/intel.c

@@ -236,9 +236,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		clear_cpu_cap(c, X86_FEATURE_PSE);
 	}
 
-#ifdef CONFIG_X86_64
-	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
-#else
+#ifndef CONFIG_X86_64
 	/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
 	if (c->x86 == 15 && c->x86_cache_alignment == 64)
 		c->x86_cache_alignment = 128;

arch/x86/kernel/cpu/zhaoxin.c

@@ -59,9 +59,7 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c)
 {
 	if (c->x86 >= 0x6)
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-#ifdef CONFIG_X86_64
-	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
-#endif
+
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);

arch/x86/kernel/fred.c

@@ -68,7 +68,7 @@ void cpu_init_fred_exceptions(void)
 	idt_invalidate();
 
 	/* Use int $0x80 for 32-bit system calls in FRED mode */
-	setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
+	setup_clear_cpu_cap(X86_FEATURE_SYSFAST32);
 	setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
 }
 

arch/x86/xen/setup.c

@@ -990,13 +990,6 @@ static int register_callback(unsigned type, const void *func)
 	return HYPERVISOR_callback_op(CALLBACKOP_register, &callback);
 }
 
-void xen_enable_sysenter(void)
-{
-	if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) &&
-	    register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat))
-		setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
-}
-
 void xen_enable_syscall(void)
 {
 	int ret;
@@ -1008,11 +1001,27 @@ void xen_enable_syscall(void)
 		   mechanism for syscalls. */
 	}
 
-	if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) &&
-	    register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat))
+	if (!cpu_feature_enabled(X86_FEATURE_SYSFAST32))
+		return;
+
+	if (cpu_feature_enabled(X86_FEATURE_SYSCALL32)) {
+		/* Use SYSCALL32 */
+		ret = register_callback(CALLBACKTYPE_syscall32,
+					xen_entry_SYSCALL_compat);
+
+	} else {
+		/* Use SYSENTER32 */
+		ret = register_callback(CALLBACKTYPE_sysenter,
+					xen_entry_SYSENTER_compat);
+	}
+
+	if (ret) {
 		setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
+		setup_clear_cpu_cap(X86_FEATURE_SYSFAST32);
+	}
 }
 
+
 static void __init xen_pvmmu_arch_setup(void)
 {
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
@@ -1022,7 +1031,6 @@ static void __init xen_pvmmu_arch_setup(void)
 	    register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))
 		BUG();
 
-	xen_enable_sysenter();
 	xen_enable_syscall();
 }
 

arch/x86/xen/smp_pv.c

@@ -65,10 +65,9 @@ static void cpu_bringup(void)
 	touch_softlockup_watchdog();
 
 	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
-	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
-		xen_enable_sysenter();
+	if (!xen_feature(XENFEAT_supervisor_mode_kernel))
 		xen_enable_syscall();
-	}
+
 	cpu = smp_processor_id();
 	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);