Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

torvalds · torvalds · commit bba072dfd7bf · 2015-11-15T09:32:59.000-08:00
Pull x86 fixes from Thomas Gleixner:
 "A couple of fixes and updates related to x86:

   - Fix the W+X check regression on XEN

   - The real fix for the low identity map trainwreck

   - Probe legacy PIC early instead of unconditionally allocating legacy
     irqs

   - Add cpu verification to long mode entry

   - Adjust the cache topology to AMD Fam17H systems

   - Let Merrifield use the TSC across S3"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Call verify_cpu() after having entered long mode too
  x86/setup: Fix low identity map for &gt;= 2GB kernel range
  x86/mm: Skip the hypervisor range when walking PGD
  x86/AMD: Fix last level cache topology for AMD Fam17h systems
  x86/irq: Probe for PIC presence before allocating descs for legacy IRQs
  x86/cpu/intel: Enable X86_FEATURE_NONSTOP_TSC_S3 for Merrifield
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
@@ -60,6 +60,7 @@ struct legacy_pic {
 	void (*mask_all)(void);
 	void (*restore_mask)(void);
 	void (*init)(int auto_eoi);
+	int (*probe)(void);
 	int (*irq_pending)(unsigned int irq);
 	void (*make_irq)(unsigned int irq);
 };
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
@@ -361,7 +361,11 @@ int __init arch_probe_nr_irqs(void)
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return nr_legacy_irqs();
+	/*
+	 * We don't know if PIC is present at this point so we need to do
+	 * probe() to get the right number of legacy IRQs.
+	 */
+	return legacy_pic->probe();
 }
 
 #ifdef	CONFIG_X86_IO_APIC
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
@@ -352,6 +352,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
+	unsigned int socket_id, core_complex_id;
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
@@ -361,6 +362,18 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 	amd_get_topology(c);
+
+	/*
+	 * Fix percpu cpu_llc_id here as LLC topology is different
+	 * for Fam17h systems.
+	 */
+	 if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
+		return;
+
+	socket_id	= (c->apicid >> bits) - 1;
+	core_complex_id	= (c->apicid & ((1 << bits) - 1)) >> 3;
+
+	per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
@@ -97,6 +97,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		switch (c->x86_model) {
 		case 0x27:	/* Penwell */
 		case 0x35:	/* Cloverview */
+		case 0x4a:	/* Merrifield */
 			set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
 			break;
 		default:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
@@ -65,6 +65,9 @@ startup_64:
 	 * tables and then reload them.
 	 */
 
+	/* Sanitize CPU configuration */
+	call verify_cpu
+
 	/*
 	 * Compute the delta between the address I am compiled to run at and the
 	 * address I am actually running at.
@@ -174,6 +177,9 @@ ENTRY(secondary_startup_64)
 	 * after the boot processor executes this code.
 	 */
 
+	/* Sanitize CPU configuration */
+	call verify_cpu
+
 	movq	$(init_level4_pgt - __START_KERNEL_map), %rax
 1:
 
@@ -288,6 +294,8 @@ ENTRY(secondary_startup_64)
 	pushq	%rax		# target address in negative space
 	lretq
 
+#include "verify_cpu.S"
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
@@ -295,33 +295,40 @@ static void unmask_8259A(void)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void init_8259A(int auto_eoi)
+static int probe_8259A(void)
 {
 	unsigned long flags;
 	unsigned char probe_val = ~(1 << PIC_CASCADE_IR);
 	unsigned char new_val;
-
-	i8259A_auto_eoi = auto_eoi;
-
-	raw_spin_lock_irqsave(&i8259A_lock, flags);
-
 	/*
 	 * Check to see if we have a PIC.
 	 * Mask all except the cascade and read
 	 * back the value we just wrote. If we don't
 	 * have a PIC, we will read 0xff as opposed to the
 	 * value we wrote.
 	 */
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
+
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
 	outb(probe_val, PIC_MASTER_IMR);
 	new_val = inb(PIC_MASTER_IMR);
 	if (new_val != probe_val) {
 		printk(KERN_INFO "Using NULL legacy PIC\n");
 		legacy_pic = &null_legacy_pic;
-		raw_spin_unlock_irqrestore(&i8259A_lock, flags);
-		return;
 	}
 
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
+	return nr_legacy_irqs();
+}
+
+static void init_8259A(int auto_eoi)
+{
+	unsigned long flags;
+
+	i8259A_auto_eoi = auto_eoi;
+
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
+
 	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 
 	/*
@@ -379,6 +386,10 @@ static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
 	return 0;
 }
+static int legacy_pic_probe(void)
+{
+	return 0;
+}
 
 struct legacy_pic null_legacy_pic = {
 	.nr_legacy_irqs = 0,
@@ -388,6 +399,7 @@ struct legacy_pic null_legacy_pic = {
 	.mask_all = legacy_pic_noop,
 	.restore_mask = legacy_pic_noop,
 	.init = legacy_pic_int_noop,
+	.probe = legacy_pic_probe,
 	.irq_pending = legacy_pic_irq_pending_noop,
 	.make_irq = legacy_pic_uint_noop,
 };
@@ -400,6 +412,7 @@ struct legacy_pic default_legacy_pic = {
 	.mask_all = mask_8259A,
 	.restore_mask = unmask_8259A,
 	.init = init_8259A,
+	.probe = probe_8259A,
 	.irq_pending = i8259A_irq_pending,
 	.make_irq = make_8259A_irq,
 };
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
@@ -1188,7 +1188,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	clone_pgd_range(initial_page_table,
 			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
 #endif
 
 	tboot_probe();
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
@@ -34,10 +34,11 @@
 #include <asm/msr-index.h>
 
 verify_cpu:
-	pushfl				# Save caller passed flags
-	pushl	$0			# Kill any dangerous flags
-	popfl
+	pushf				# Save caller passed flags
+	push	$0			# Kill any dangerous flags
+	popf
 
+#ifndef __x86_64__
 	pushfl				# standard way to check for cpuid
 	popl	%eax
 	movl	%eax,%ebx
@@ -48,6 +49,7 @@ verify_cpu:
 	popl	%eax
 	cmpl	%eax,%ebx
 	jz	verify_cpu_no_longmode	# cpu has no cpuid
+#endif
 
 	movl	$0x0,%eax		# See if cpuid 1 is implemented
 	cpuid
@@ -130,10 +132,10 @@ verify_cpu_sse_test:
 	jmp	verify_cpu_sse_test	# try again
 
 verify_cpu_no_longmode:
-	popfl				# Restore caller passed flags
+	popf				# Restore caller passed flags
 	movl $1,%eax
 	ret
 verify_cpu_sse_ok:
-	popfl				# Restore caller passed flags
+	popf				# Restore caller passed flags
 	xorl %eax, %eax
 	ret
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
@@ -358,6 +358,21 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 #define pgd_none(a)  pud_none(__pud(pgd_val(a)))
 #endif
 
+#ifdef CONFIG_X86_64
+static inline bool is_hypervisor_range(int idx)
+{
+	/*
+	 * ffff800000000000 - ffff87ffffffffff is reserved for
+	 * the hypervisor.
+	 */
+	return paravirt_enabled() &&
+		(idx >= pgd_index(__PAGE_OFFSET) - 16) &&
+		(idx < pgd_index(__PAGE_OFFSET));
+}
+#else
+static inline bool is_hypervisor_range(int idx) { return false; }
+#endif
+
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx)
 {
@@ -381,7 +396,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
-		if (!pgd_none(*start)) {
+		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
 			if (pgd_large(*start) || !pgd_present(*start)) {
 				prot = pgd_flags(*start);
 				note_page(m, &st, __pgprot(prot), 1);
