Merge tag 'x86-urgent-2020-09-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:

- more generic entry code ABI fallout

- debug register handling bugfixes

- fix vmalloc mappings on 32-bit kernels

- kprobes instrumentation output fix on 32-bit kernels

- fix over-eager WARN_ON_ONCE() on !SMAP hardware

- NUMA debugging fix

- fix Clang related crash on !RETPOLINE kernels

* tag 'x86-urgent-2020-09-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/entry: Unbreak 32bit fast syscall
x86/debug: Allow a single level of #DB recursion
x86/entry: Fix AC assertion
tracing/kprobes, x86/ptrace: Fix regs argument order for i386
x86, fakenuma: Fix invalid starting node ID
x86/mm/32: Bring back vmalloc faulting on x86_32
x86/cmdline: Disable jump tables for cmdline.c

arch/x86/entry/common.c

···
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
 {
-	unsigned int nr = (unsigned int)regs->orig_ax;
-
 	if (IS_ENABLED(CONFIG_IA32_EMULATION))
 		current_thread_info()->status |= TS_COMPAT;
-	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
-	 * orig_ax, the unsigned int return value truncates it.  This may
-	 * or may not be necessary, but it matches the old asm behavior.
-	 */
-	return (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
+	return (unsigned int)regs->orig_ax;
 }
 
 /*
···
 {
 	unsigned int nr = syscall_32_enter(regs);
 
+	/*
+	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
+	 * orig_ax, the unsigned int return value truncates it.  This may
+	 * or may not be necessary, but it matches the old asm behavior.
+	 */
+	nr = (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
 	do_syscall_32_irqs_on(regs, nr);
 	syscall_exit_to_user_mode(regs);
 }
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
-	unsigned int nr	= syscall_32_enter(regs);
+	unsigned int nr = syscall_32_enter(regs);
 	int res;
+
+	/*
+	 * This cannot use syscall_enter_from_user_mode() as it has to
+	 * fetch EBP before invoking any of the syscall entry work
+	 * functions.
+	 */
+	syscall_enter_from_user_mode_prepare(regs);
 
 	instrumentation_begin();
 	/* Fetch EBP from where the vDSO stashed it. */
···
 		syscall_exit_to_user_mode(regs);
 		return false;
 	}
+
+	/* The case truncates any ptrace induced syscall nr > 2^32 -1 */
+	nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr);
 
 	/* Now this is just like a normal syscall. */
 	do_syscall_32_irqs_on(regs, nr);

arch/x86/include/asm/entry-common.h

···
 		 * state, not the interrupt state as imagined by Xen.
 		 */
 		unsigned long flags = native_save_fl();
-		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
-				      X86_EFLAGS_NT));
+		unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT;
+
+		/*
+		 * For !SMAP hardware we patch out CLAC on entry.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMAP) ||
+		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+			mask |= X86_EFLAGS_AC;
+
+		WARN_ON_ONCE(flags & mask);
 
 		/* We think we came from user mode. Make sure pt_regs agrees. */
 		WARN_ON_ONCE(!user_mode(regs));

arch/x86/include/asm/ptrace.h

···
 	static const unsigned int argument_offs[] = {
 #ifdef __i386__
 		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
 		offsetof(struct pt_regs, dx),
+		offsetof(struct pt_regs, cx),
 #define NR_REG_ARGUMENTS 3
 #else
 		offsetof(struct pt_regs, di),

arch/x86/kernel/traps.c

···
 #endif
 }
 
-static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7)
+static __always_inline unsigned long debug_read_clear_dr6(void)
 {
-	/*
-	 * Disable breakpoints during exception handling; recursive exceptions
-	 * are exceedingly 'fun'.
-	 *
-	 * Since this function is NOKPROBE, and that also applies to
-	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
-	 * HW_BREAKPOINT_W on our stack)
-	 *
-	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
-	 * includes the entry stack is excluded for everything.
-	 */
-	*dr7 = local_db_save();
+	unsigned long dr6;
 
 	/*
 	 * The Intel SDM says:
···
 	 *
 	 * Keep it simple: clear DR6 immediately.
 	 */
-	get_debugreg(*dr6, 6);
+	get_debugreg(dr6, 6);
 	set_debugreg(0, 6);
 	/* Filter out all the reserved bits which are preset to 1 */
-	*dr6 &= ~DR6_RESERVED;
-}
+	dr6 &= ~DR6_RESERVED;
 
-static __always_inline void debug_exit(unsigned long dr7)
-{
-	local_db_restore(dr7);
+	return dr6;
 }
 
 /*
···
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
+	/*
+	 * Disable breakpoints during exception handling; recursive exceptions
+	 * are exceedingly 'fun'.
+	 *
+	 * Since this function is NOKPROBE, and that also applies to
+	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
+	 * HW_BREAKPOINT_W on our stack)
+	 *
+	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
+	 * includes the entry stack is excluded for everything.
+	 */
+	unsigned long dr7 = local_db_save();
 	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
 
···
 
 	instrumentation_end();
 	idtentry_exit_nmi(regs, irq_state);
+
+	local_db_restore(dr7);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
···
 	 * #DB, we will malfunction.
 	 */
 	WARN_ON_ONCE(!user_mode(regs));
+
+	/*
+	 * NB: We can't easily clear DR7 here because
+	 * idtentry_exit_to_usermode() can invoke ptrace, schedule, access
+	 * user memory, etc.  This means that a recursive #DB is possible.  If
+	 * this happens, that #DB will hit exc_debug_kernel() and clear DR7.
+	 * Since we're not on the IST stack right now, everything will be
+	 * fine.
+	 */
 
 	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
···
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_kernel(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_kernel(regs, debug_read_clear_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_user(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_user(regs, debug_read_clear_dr6());
 }
 #else
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
+	unsigned long dr6 = debug_read_clear_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);
 	else
 		exc_debug_kernel(regs, dr6);
-
-	debug_exit(dr7);
 }
 #endif
 

arch/x86/lib/Makefile

···
 CFLAGS_REMOVE_cmdline.o = -pg
 endif
 
-CFLAGS_cmdline.o := -fno-stack-protector
+CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
 endif
 
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk

arch/x86/mm/fault.c

···
 	return pmd_k;
 }
 
+/*
+ *   Handle a fault on the vmalloc or module mapping area
+ *
+ *   This is needed because there is a race condition between the time
+ *   when the vmalloc mapping code updates the PMD to the point in time
+ *   where it synchronizes this update with the other page-tables in the
+ *   system.
+ *
+ *   In this race window another thread/CPU can map an area on the same
+ *   PMD, finds it already present and does not synchronize it with the
+ *   rest of the system yet. As a result v[mz]alloc might return areas
+ *   which are not mapped in every page-table in the system, causing an
+ *   unhandled page-fault when they are accessed.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+	unsigned long pgd_paddr;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "current" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	pgd_paddr = read_cr3_pa();
+	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+	if (!pmd_k)
+		return -1;
+
+	if (pmd_large(*pmd_k))
+		return 0;
+
+	pte_k = pte_offset_kernel(pmd_k, address);
+	if (!pte_present(*pte_k))
+		return -1;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(vmalloc_fault);
+
 void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
···
 	 * space, so do not expect them here.
 	 */
 	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * We can fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * Before doing this on-demand faulting, ensure that the
+	 * fault is not any of the following:
+	 * 1. A fault on a PTE with a reserved bit set.
+	 * 2. A fault caused by a user-mode access.  (Do not demand-
+	 *    fault kernel memory due to user-mode accesses).
+	 * 3. A fault caused by a page-level protection violation.
+	 *    (A demand fault would be on a non-present page which
+	 *     would have X86_PF_PROT==0).
+	 *
+	 * This is only needed to close a race condition on x86-32 in
+	 * the vmalloc mapping/unmapping code. See the comment above
+	 * vmalloc_fault() for details. On x86-64 the race does not
+	 * exist as the vmalloc mappings don't need to be synchronized
+	 * there.
+	 */
+	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+		if (vmalloc_fault(address) >= 0)
+			return;
+	}
+#endif
 
 	/* Was the fault spurious, caused by lazy TLB invalidation? */
 	if (spurious_kernel_fault(hw_error_code, address))

arch/x86/mm/numa_emulation.c

···
 					      u64 addr, u64 max_addr, u64 size)
 {
 	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
-			0, NULL, NUMA_NO_NODE);
+			0, NULL, 0);
 }
 
 static int __init setup_emu2phys_nid(int *dfl_phys_nid)

include/linux/entry-common.h

···
 #endif
 
 /**
- * syscall_enter_from_user_mode - Check and handle work before invoking
- *				 a syscall
+ * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This handles lockdep, RCU (context tracking) and tracing state.
+ *
+ * This is invoked when there is extra architecture specific functionality
+ * to be done between establishing state and handling user mode entry work.
+ */
+void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
+
+/**
+ * syscall_enter_from_user_mode_work - Check and handle work before invoking
+ *				       a syscall
  * @regs:	Pointer to currents pt_regs
  * @syscall:	The syscall number
  *
  * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and the subsequent functions can be
- * instrumented.
+ * enabled after invoking syscall_enter_from_user_mode_prepare() and extra
+ * architecture specific work.
  *
  * Returns: The original or a modified syscall number
  *
···
  * syscall_set_return_value() first.  If neither of those are called and -1
  * is returned, then the syscall will fail with ENOSYS.
  *
- * The following functionality is handled here:
+ * It handles the following work items:
  *
- *  1) Establish state (lockdep, RCU (context tracking), tracing)
- *  2) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
+ *  1) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
  *     __secure_computing(), trace_sys_enter()
- *  3) Invocation of audit_syscall_entry()
+ *  2) Invocation of audit_syscall_entry()
+ */
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+
+/**
+ * syscall_enter_from_user_mode - Establish state and check and handle work
+ *				  before invoking a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This is combination of syscall_enter_from_user_mode_prepare() and
+ * syscall_enter_from_user_mode_work().
+ *
+ * Returns: The original or a modified syscall number. See
+ * syscall_enter_from_user_mode_work() for further explanation.
  */
 long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
 

kernel/entry/common.c

···
 	return ret ? : syscall_get_nr(current, regs);
 }
 
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+static __always_inline long
+__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
 	unsigned long ti_work;
 
-	enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	local_irq_enable();
 	ti_work = READ_ONCE(current_thread_info()->flags);
 	if (ti_work & SYSCALL_ENTER_WORK)
 		syscall = syscall_trace_enter(regs, syscall, ti_work);
-	instrumentation_end();
 
 	return syscall;
+}
+
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	return __syscall_enter_from_user_work(regs, syscall);
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = __syscall_enter_from_user_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
 }
 
 /**