Power management fixes for v4.7-rc7

- Fix a recent performance regression on Power systems (powernv
    and pseries) introduced by a core cpuidle commit that decreased
    the precision of the last_residency conversion from nano- to
    microseconds, which should not matter in theory, but turned out
    to play not-so-well with the special "snooze" idle state on Power
    (Shreyas B Prabhu).
 
  - Fix a crash during resume from hibernation on x86-64 caused by
    possible corruption of the kernel text part of page tables in the
    last phase of image restoration exposed by a security-related
    change during the 4.3 development cycle (Rafael Wysocki).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJXfuVmAAoJEILEb/54YlRx/TUQALIrIgVMtNpPhC0Mu0DQp+1y
 S2t/vWfLnMqfl1lzH/scDi4OC3cqEbEsYB5CUJPRysc1KB0fjJbW+BEuQuJyEhgf
 ac95mv1IU7DKiJ1Rp4qWvvBoovY3fjb1rhHMzvo9uh6HmKrSlWLL4PmnbGw/BaFL
 PgqEazsy/a9FgGT7VnvamVL6bGXgVMEf8VqoBeZFd0krH4qvBZHrS97OLqU685vT
 VW0IDZr0sI3u0pG9ropJ5b8ETtnyZ4lmTO5D4TzD9P8kZyjl2TBnSZ/ls/1YLh4N
 WdBZXbsfmFFt4jyDnOjilWOBA8R3IDteCDmG1l8XhK4Smbl7TRh2XVuRAHHEjG6b
 oMPHTeqIil3ExBS2gdzVEFNzYfHsyg3N9cXSochqnp3vboyZOiKaxIPCiVeBOZ+t
 bDPwtbovIly1aEnsJKUbHvBxJ4A9uPUqw99YbBtMK1VpQXZFg+s/0mBVNynkuu/k
 EUOuU6KcY6Br4JJPsqfb26NmARgLrrI+gTJbC3pFDHARtALnCbkkbmNZRRVRS3Zs
 7CzGaYqgZ0ejMv/46jFPsHYKXU52AJ5HDhfXfELd8X3AvdhtmIszfqTkBgKx4gto
 fyTVzi2c6+RJJr5Jc07msYawaz86nEUjeXFsM59g6jC5dguSWnRxUuWV2zUM/ENb
 GDkzNdzif0t2DheJ4bKc
 =XL6s
 -----END PGP SIGNATURE-----

Merge tag 'pm-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "One fix for a recent cpuidle core change that, against all odds,
  introduced a functional regression on Power systems and the fix for
  the crash during resume from hibernation on x86-64 that has been in
  the works for the last few weeks (it actually was ready last week, but
  I wanted to allow the reporters to test if for some more time).

  Specifics:

   - Fix a recent performance regression on Power systems (powernv and
     pseries) introduced by a core cpuidle commit that decreased the
     precision of the last_residency conversion from nano- to
     microseconds, which should not matter in theory, but turned out to
     play not-so-well with the special "snooze" idle state on Power
     (Shreyas B Prabhu).

   - Fix a crash during resume from hibernation on x86-64 caused by
     possible corruption of the kernel text part of page tables in the
     last phase of image restoration exposed by a security-related
     change during the 4.3 development cycle (Rafael Wysocki)"

* tag 'pm-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpuidle: Fix last_residency division
  x86/power/64: Fix kernel text mapping corruption during image restoration

arch/x86/power/hibernate_64.c

@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void);
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible;
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void)
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
+	/* Prepare a temporary mapping for the kernel text */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
+	result = set_up_temporary_text_mapping();
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void)
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
+	error = relocate_restore_code();
-	if (!relocated_restore_code)
+	if (error)
-		return -ENOMEM;
+		return error;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn)
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr)
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }

arch/x86/power/hibernate_asm_64.S

@@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
 	/* save cr3 */
 	movq	%cr3, %rax
 	movq	%rax, restore_cr3(%rip)
@@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend)
 ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
 	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
+	movq	restore_jump_address(%rip), %r8
-	movq	restore_cr3(%rip), %rbx
+	movq	restore_cr3(%rip), %r9
+
+	/* prepare to switch to temporary page tables */
+	movq	temp_level4_pgt(%rip), %rax
+	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */
 	movq	restore_pblist(%rip), %rdx
+
+	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rcx
+	subq	%rcx, %rax
+	movq	%rax, %cr3
+	/* flush TLB */
+	movq	%rbx, %rcx
+	andq	$~(X86_CR4_PGE), %rcx
+	movq	%rcx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rbx, %cr4;  # turn PGE back on
 .Lloop:
 	testq	%rdx, %rdx
 	jz	.Ldone
@@ -96,24 +96,17 @@ ENTRY(core_restore_code)
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
 	jmp	.Lloop
+
 .Ldone:
 	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
+	jmpq	*%r8
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
 ENTRY(restore_registers)
 	FRAME_BEGIN
 	/* go back to the original page tables */
-	movq    %rbx, %cr3
+	movq    %r9, %cr3
 
 	/* Flush TLB, including "global" things (vmalloc) */
 	movq	mmu_cr4_features(%rip), %rax

drivers/cpuidle/cpuidle.c

@@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
-	u64 time_start, time_end;
+	ktime_t time_start, time_end;
 	s64 diff;
 
 	/*
@@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
-	time_start = local_clock();
+	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
-	time_end = local_clock();
+	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
@@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
-	/*
+	diff = ktime_us_delta(time_end, time_start);
-	 * local_clock() returns the time in nanosecond, let's shift
-	 * by 10 (divide by 1024) to have microsecond based time.
-	 */
-	diff = (time_end - time_start) >> 10;
 	if (diff > INT_MAX)
 		diff = INT_MAX;