Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rmk/linux

Pull ARM updates from Russell King:

 - disable jump label and high PTE for PREEMPT RT kernels

 - fix input operand modification in load_unaligned_zeropad()

 - fix hash_name() / fault path induced warnings

 - fix branch predictor hardening

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rmk/linux:
  ARM: fix branch predictor hardening
  ARM: fix hash_name() fault
  ARM: allow __do_kernel_fault() to report execution of memory faults
  ARM: group is_permission_fault() with is_translation_fault()
  ARM: 9464/1: fix input-only operand modification in load_unaligned_zeropad()
  ARM: 9461/1: Disable HIGHPTE on PREEMPT_RT kernels
  ARM: 9459/1: Disable jump-label on PREEMPT_RT

Author: torvalds

arch/arm/Kconfig

@@ -82,7 +82,7 @@ config ARM
 	select HAS_IOPORT
 	select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && (!PREEMPT_RT || !SMP)
 	select HAVE_ARCH_KFENCE if MMU && !XIP_KERNEL
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
@@ -1213,7 +1213,7 @@ config HIGHMEM
 
 config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem" if EXPERT
-	depends on HIGHMEM
+	depends on HIGHMEM && !PREEMPT_RT
 	default y
 	help
 	  The VM uses one page of physical memory for each page table.

arch/arm/include/asm/word-at-a-time.h

@@ -67,17 +67,17 @@ static inline unsigned long find_zero(unsigned long mask)
  */
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, offset;
+	unsigned long ret, tmp;
 
 	/* Load word from unaligned pointer addr */
 	asm(
 	"1:	ldr	%0, [%2]\n"
 	"2:\n"
 	"	.pushsection .text.fixup,\"ax\"\n"
 	"	.align 2\n"
-	"3:	and	%1, %2, #0x3\n"
-	"	bic	%2, %2, #0x3\n"
-	"	ldr	%0, [%2]\n"
+	"3:	bic	%1, %2, #0x3\n"
+	"	ldr	%0, [%1]\n"
+	"	and	%1, %2, #0x3\n"
 	"	lsl	%1, %1, #0x3\n"
 #ifndef __ARMEB__
 	"	lsr	%0, %0, %1\n"
@@ -90,7 +90,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	"	.align	3\n"
 	"	.long	1b, 3b\n"
 	"	.popsection"
-	: "=&r" (ret), "=&r" (offset)
+	: "=&r" (ret), "=&r" (tmp)
 	: "r" (addr), "Qo" (*(unsigned long *)addr));
 
 	return ret;

arch/arm/mm/alignment.c

@@ -19,10 +19,11 @@
 #include <linux/init.h>
 #include <linux/sched/signal.h>
 #include <linux/uaccess.h>
+#include <linux/unaligned.h>
 
 #include <asm/cp15.h>
 #include <asm/system_info.h>
-#include <linux/unaligned.h>
+#include <asm/system_misc.h>
 #include <asm/opcodes.h>
 
 #include "fault.h"
@@ -809,6 +810,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	int thumb2_32b = 0;
 	int fault;
 
+	if (addr >= TASK_SIZE && user_mode(regs))
+		harden_branch_predictor();
+
 	if (interrupts_enabled(regs))
 		local_irq_enable();
 

arch/arm/mm/fault.c

@@ -128,6 +128,19 @@ static inline bool is_translation_fault(unsigned int fsr)
 	return false;
 }
 
+static inline bool is_permission_fault(unsigned int fsr)
+{
+	int fs = fsr_fs(fsr);
+#ifdef CONFIG_ARM_LPAE
+	if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
+		return true;
+#else
+	if (fs == FS_L1_PERM || fs == FS_L2_PERM)
+		return true;
+#endif
+	return false;
+}
+
 static void die_kernel_fault(const char *msg, struct mm_struct *mm,
 			     unsigned long addr, unsigned int fsr,
 			     struct pt_regs *regs)
@@ -162,6 +175,8 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 	 */
 	if (addr < PAGE_SIZE) {
 		msg = "NULL pointer dereference";
+	} else if (is_permission_fault(fsr) && fsr & FSR_LNX_PF) {
+		msg = "execution of memory";
 	} else {
 		if (is_translation_fault(fsr) &&
 		    kfence_handle_page_fault(addr, is_write_fault(fsr), regs))
@@ -183,9 +198,6 @@ __do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
 {
 	struct task_struct *tsk = current;
 
-	if (addr > TASK_SIZE)
-		harden_branch_predictor();
-
 #ifdef CONFIG_DEBUG_USER
 	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
 	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
@@ -225,19 +237,6 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_MMU
-static inline bool is_permission_fault(unsigned int fsr)
-{
-	int fs = fsr_fs(fsr);
-#ifdef CONFIG_ARM_LPAE
-	if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
-		return true;
-#else
-	if (fs == FS_L1_PERM || fs == FS_L2_PERM)
-		return true;
-#endif
-	return false;
-}
-
 #ifdef CONFIG_CPU_TTBR0_PAN
 static inline bool ttbr0_usermode_access_allowed(struct pt_regs *regs)
 {
@@ -259,6 +258,37 @@ static inline bool ttbr0_usermode_access_allowed(struct pt_regs *regs)
 }
 #endif
 
+static int __kprobes
+do_kernel_address_page_fault(struct mm_struct *mm, unsigned long addr,
+			     unsigned int fsr, struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		/*
+		 * Fault from user mode for a kernel space address. User mode
+		 * should not be faulting in kernel space, which includes the
+		 * vector/khelper page. Handle the branch predictor hardening
+		 * while interrupts are still disabled, then send a SIGSEGV.
+		 */
+		harden_branch_predictor();
+		__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
+	} else {
+		/*
+		 * Fault from kernel mode. Enable interrupts if they were
+		 * enabled in the parent context. Section (upper page table)
+		 * translation faults are handled via do_translation_fault(),
+		 * so we will only get here for a non-present kernel space
+		 * PTE or PTE permission fault. This may happen in exceptional
+		 * circumstances and need the fixup tables to be walked.
+		 */
+		if (interrupts_enabled(regs))
+			local_irq_enable();
+
+		__do_kernel_fault(mm, addr, fsr, regs);
+	}
+
+	return 0;
+}
+
 static int __kprobes
 do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
@@ -272,6 +302,12 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (kprobe_page_fault(regs, fsr))
 		return 0;
 
+	/*
+	 * Handle kernel addresses faults separately, which avoids touching
+	 * the mmap lock from contexts that are not able to sleep.
+	 */
+	if (addr >= TASK_SIZE)
+		return do_kernel_address_page_fault(mm, addr, fsr, regs);
 
 	/* Enable interrupts if they were enabled in the parent context. */
 	if (interrupts_enabled(regs))
@@ -448,16 +484,20 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
  * We enter here because the first level page table doesn't contain
  * a valid entry for the address.
  *
- * If the address is in kernel space (>= TASK_SIZE), then we are
- * probably faulting in the vmalloc() area.
+ * If this is a user address (addr < TASK_SIZE), we handle this as a
+ * normal page fault. This leaves the remainder of the function to handle
+ * kernel address translation faults.
+ *
+ * Since user mode is not permitted to access kernel addresses, pass these
+ * directly to do_kernel_address_page_fault() to handle.
  *
- * If the init_task's first level page tables contains the relevant
- * entry, we copy the it to this task.  If not, we send the process
- * a signal, fixup the exception, or oops the kernel.
+ * Otherwise, we're probably faulting in the vmalloc() area, so try to fix
+ * that up. Note that we must not take any locks or enable interrupts in
+ * this case.
  *
- * 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.
+ * If vmalloc() fixup fails, that means the non-leaf page tables did not
+ * contain an entry for this address, so handle this via
+ * do_kernel_address_page_fault().
  */
 #ifdef CONFIG_MMU
 static int __kprobes
@@ -523,7 +563,8 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	return 0;
 
 bad_area:
-	do_bad_area(addr, fsr, regs);
+	do_kernel_address_page_fault(current->mm, addr, fsr, regs);
+
 	return 0;
 }
 #else					/* CONFIG_MMU */
@@ -543,7 +584,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+	/*
+	 * If this is a kernel address, but from user mode, then userspace
+	 * is trying bad stuff. Invoke the branch predictor handling.
+	 * Interrupts are disabled here.
+	 */
+	if (addr >= TASK_SIZE && user_mode(regs))
+		harden_branch_predictor();
+
 	do_bad_area(addr, fsr, regs);
+
 	return 0;
 }
 #endif /* CONFIG_ARM_LPAE */