Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "Fix some more FP register fallout from the SVE patches and also some
  problems with the PGD tracking in our software PAN emulation code,
  after we received a crash report from a 3.18 kernel running a
  backport.

  Summary:

   - fix SW PAN pgd shadowing for kernel threads, EFI and exiting user
     tasks

   - fix FP register leak when a task_struct is re-allocated

   - fix potential use-after-free in FP state tracking used by KVM"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64/sve: Avoid dereference of dead task_struct in KVM guest entry
  arm64: SW PAN: Update saved ttbr0 value on enter_lazy_tlb
  arm64: SW PAN: Point saved ttbr0 at the zero page when switching to init_mm
  arm64: fpsimd: Abstract out binding of task's fpsimd context to the cpu.
  arm64: fpsimd: Prevent registers leaking from dead tasks

arch/arm64/include/asm/efi.h

@@ -132,11 +132,9 @@ static inline void efi_set_pgd(struct mm_struct *mm)
 			 * Defer the switch to the current thread's TTBR0_EL1
 			 * until uaccess_enable(). Restore the current
 			 * thread's saved ttbr0 corresponding to its active_mm
-			 * (if different from init_mm).
 			 */
 			cpu_set_reserved_ttbr0();
-			if (current->active_mm != &init_mm)
-				update_saved_ttbr0(current, current->active_mm);
+			update_saved_ttbr0(current, current->active_mm);
 		}
 	}
 }

arch/arm64/include/asm/mmu_context.h

@@ -156,29 +156,21 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
 #define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
-/*
- * This is called when "tsk" is about to enter lazy TLB mode.
- *
- * mm:  describes the currently active mm context
- * tsk: task which is entering lazy tlb
- * cpu: cpu number which is entering lazy tlb
- *
- * tsk->mm will be NULL
- */
-static inline void
-enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void update_saved_ttbr0(struct task_struct *tsk,
 				      struct mm_struct *mm)
 {
-	if (system_uses_ttbr0_pan()) {
-		BUG_ON(mm->pgd == swapper_pg_dir);
-		task_thread_info(tsk)->ttbr0 =
-			virt_to_phys(mm->pgd) | ASID(mm) << 48;
-	}
+	u64 ttbr;
+
+	if (!system_uses_ttbr0_pan())
+		return;
+
+	if (mm == &init_mm)
+		ttbr = __pa_symbol(empty_zero_page);
+	else
+		ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48;
+
+	task_thread_info(tsk)->ttbr0 = ttbr;
 }
 #else
 static inline void update_saved_ttbr0(struct task_struct *tsk,
@@ -187,6 +179,16 @@ static inline void update_saved_ttbr0(struct task_struct *tsk,
 }
 #endif
 
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	/*
+	 * We don't actually care about the ttbr0 mapping, so point it at the
+	 * zero page.
+	 */
+	update_saved_ttbr0(tsk, &init_mm);
+}
+
 static inline void __switch_mm(struct mm_struct *next)
 {
 	unsigned int cpu = smp_processor_id();
@@ -214,11 +216,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
 	 * value may have not been initialised yet (activate_mm caller) or the
 	 * ASID has changed since the last run (following the context switch
-	 * of another thread of the same process). Avoid setting the reserved
-	 * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+	 * of another thread of the same process).
 	 */
-	if (next != &init_mm)
-		update_saved_ttbr0(tsk, next);
+	update_saved_ttbr0(tsk, next);
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)

arch/arm64/kernel/fpsimd.c

@@ -114,7 +114,12 @@
  *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
-static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+struct fpsimd_last_state_struct {
+	struct fpsimd_state *st;
+	bool sve_in_use;
+};
+
+static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
 
 /* Default VL for tasks that don't set it explicitly: */
 static int sve_default_vl = -1;
@@ -905,7 +910,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 		 */
 		struct fpsimd_state *st = &next->thread.fpsimd_state;
 
-		if (__this_cpu_read(fpsimd_last_state) == st
+		if (__this_cpu_read(fpsimd_last_state.st) == st
 		    && st->cpu == smp_processor_id())
 			clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 		else
@@ -991,6 +996,21 @@ void fpsimd_signal_preserve_current_state(void)
 		sve_to_fpsimd(current);
 }
 
+/*
+ * Associate current's FPSIMD context with this cpu
+ * Preemption must be disabled when calling this function.
+ */
+static void fpsimd_bind_to_cpu(void)
+{
+	struct fpsimd_last_state_struct *last =
+		this_cpu_ptr(&fpsimd_last_state);
+	struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+	last->st = st;
+	last->sve_in_use = test_thread_flag(TIF_SVE);
+	st->cpu = smp_processor_id();
+}
+
 /*
  * Load the userland FPSIMD state of 'current' from memory, but only if the
  * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
@@ -1004,11 +1024,8 @@ void fpsimd_restore_current_state(void)
 	local_bh_disable();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
-
 		task_fpsimd_load();
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
+		fpsimd_bind_to_cpu();
 	}
 
 	local_bh_enable();
@@ -1032,12 +1049,8 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
 
 	task_fpsimd_load();
 
-	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
-
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
-	}
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_bind_to_cpu();
 
 	local_bh_enable();
 }
@@ -1052,7 +1065,7 @@ void fpsimd_flush_task_state(struct task_struct *t)
 
 static inline void fpsimd_flush_cpu_state(void)
 {
-	__this_cpu_write(fpsimd_last_state, NULL);
+	__this_cpu_write(fpsimd_last_state.st, NULL);
 }
 
 /*
@@ -1065,14 +1078,10 @@ static inline void fpsimd_flush_cpu_state(void)
 #ifdef CONFIG_ARM64_SVE
 void sve_flush_cpu_state(void)
 {
-	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
-	struct task_struct *tsk;
-
-	if (!fpstate)
-		return;
+	struct fpsimd_last_state_struct const *last =
+		this_cpu_ptr(&fpsimd_last_state);
 
-	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
-	if (test_tsk_thread_flag(tsk, TIF_SVE))
+	if (last->st && last->sve_in_use)
 		fpsimd_flush_cpu_state();
 }
 #endif /* CONFIG_ARM64_SVE */
@@ -1267,7 +1276,7 @@ static inline void fpsimd_pm_init(void) { }
 #ifdef CONFIG_HOTPLUG_CPU
 static int fpsimd_cpu_dead(unsigned int cpu)
 {
-	per_cpu(fpsimd_last_state, cpu) = NULL;
+	per_cpu(fpsimd_last_state.st, cpu) = NULL;
 	return 0;
 }
 

arch/arm64/kernel/process.c

@@ -314,6 +314,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	clear_tsk_thread_flag(p, TIF_SVE);
 	p->thread.sve_state = NULL;
 
+	/*
+	 * In case p was allocated the same task_struct pointer as some
+	 * other recently-exited task, make sure p is disassociated from
+	 * any cpu that may have run that now-exited task recently.
+	 * Otherwise we could erroneously skip reloading the FPSIMD
+	 * registers for p.
+	 */
+	fpsimd_flush_task_state(p);
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;