1 files changed, 240 insertions, 37 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 93c60c0c9d4a..51cc9c7cb9bd 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -19,12 +19,14 @@
 #include <linux/nospec.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/init.h>
 
 #ifdef CONFIG_XEN_PV
 #include <xen/xen-ops.h>
 #include <xen/events.h>
 #endif
 
+#include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -47,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
 
 	if (likely(unr < NR_syscalls)) {
 		unr = array_index_nospec(unr, NR_syscalls);
-		regs->ax = sys_call_table[unr](regs);
+		regs->ax = x64_sys_call(regs, unr);
 		return true;
 	}
 	return false;
@@ -64,13 +66,14 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
 
 	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
 		xnr = array_index_nospec(xnr, X32_NR_syscalls);
-		regs->ax = x32_sys_call_table[xnr](regs);
+		regs->ax = x32_sys_call(regs, xnr);
 		return true;
 	}
 	return false;
 }
 
-__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
+/* Returns true to return using SYSRET, or false to use IRET */
+__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
 {
 	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);
@@ -84,6 +87,46 @@ __visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
 
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
+
+	/*
+	 * Check that the register state is valid for using SYSRET to exit
+	 * to userspace.  Otherwise use the slower but fully capable IRET
+	 * exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
+	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
+		return false;
+
+	/*
+	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+	 * in kernel space.  This essentially lets the user take over
+	 * the kernel, since userspace controls RSP.
+	 *
+	 * TASK_SIZE_MAX covers all user-accessible addresses other than
+	 * the deprecated vsyscall page.
+	 */
+	if (unlikely(regs->ip >= TASK_SIZE_MAX))
+		return false;
+
+	/*
+	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.
+	 */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
+		return false;
+
+	/* Use SYSRET to exit to userspace */
+	return true;
 }
 #endif
 
@@ -96,6 +139,16 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs)
 	return (int)regs->orig_ax;
 }
 
+#ifdef CONFIG_IA32_EMULATION
+bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
+
+static int ia32_emulation_override_cmdline(char *arg)
+{
+	return kstrtobool(arg, &__ia32_enabled);
+}
+early_param("ia32_emulation", ia32_emulation_override_cmdline);
+#endif
+
 /*
  * Invoke a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.
  */
@@ -109,13 +162,167 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 
 	if (likely(unr < IA32_NR_syscalls)) {
 		unr = array_index_nospec(unr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call_table[unr](regs);
+		regs->ax = ia32_sys_call(regs, unr);
 	} else if (nr != -1) {
 		regs->ax = __ia32_sys_ni_syscall(regs);
 	}
 }
 
-/* Handles int $0x80 */
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+
+#ifdef CONFIG_X86_FRED
+/*
+ * A FRED-specific INT80 handler is warranted for the follwing reasons:
+ *
+ * 1) As INT instructions and hardware interrupts are separate event
+ *    types, FRED does not preclude the use of vector 0x80 for external
+ *    interrupts. As a result, the FRED setup code does not reserve
+ *    vector 0x80 and calling int80_is_external() is not merely
+ *    suboptimal but actively incorrect: it could cause a system call
+ *    to be incorrectly ignored.
+ *
+ * 2) It is called only for handling vector 0x80 of event type
+ *    EVENT_TYPE_SWINT and will never be called to handle any external
+ *    interrupt (event type EVENT_TYPE_EXTINT).
+ *
+ * 3) FRED has separate entry flows depending on if the event came from
+ *    user space or kernel space, and because the kernel does not use
+ *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
+ *    falls through to fred_bad_type() if the event type is
+ *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
+ *    an INT insn, it can only be from a user level.
+ *
+ * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
+ *    likely take a different approach if it is ever needed: it
+ *    probably belongs in either fred_intx()/ fred_other() or
+ *    asm_fred_entrypoint_user(), depending on if this ought to be done
+ *    for all entries from userspace or only system
+ *    calls.
+ *
+ * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
+ */
+DEFINE_FREDENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/*
+	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
+	 * syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	int nr = syscall_32_enter(regs);
@@ -134,6 +341,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
+#endif /* !CONFIG_IA32_EMULATION */
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
@@ -182,8 +390,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 	return true;
 }
 
-/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
 {
 	/*
 	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
@@ -201,41 +409,36 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
 
 	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
 	if (!__do_fast_syscall_32(regs))
-		return 0;
+		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 static_cpu_has(X86_FEATURE_SEP) &&
-		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 the 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 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
 {
 	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
 	regs->sp = regs->bp;