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

…inux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "This is bigger than usual - the reason is partly a pent-up stream of
  fixes after the merge window and partly accidental.  The fixes are:

   - five patches to fix a boot failure on Andy Lutomirsky's laptop
   - four SGI UV platform fixes
   - KASAN fix
   - warning fix
   - documentation update
   - swap entry definition fix
   - pkeys fix
   - irq stats fix"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic/x2apic, smp/hotplug: Don't use before alloc in x2apic_cluster_probe()
  x86/efi: Allocate a trampoline if needed in efi_free_boot_services()
  x86/boot: Rework reserve_real_mode() to allow multiple tries
  x86/boot: Defer setup_real_mode() to early_initcall time
  x86/boot: Synchronize trampoline_cr4_features and mmu_cr4_features directly
  x86/boot: Run reserve_bios_regions() after we initialize the memory map
  x86/irq: Do not substract irq_tlb_count from irq_call_count
  x86/mm: Fix swap entry comment and macro
  x86/mm/kaslr: Fix -Wformat-security warning
  x86/mm/pkeys: Fix compact mode by removing protection keys' XSAVE buffer manipulation
  x86/build: Reduce the W=1 warnings noise when compiling x86 syscall tables
  x86/platform/UV: Fix kernel panic running RHEL kdump kernel on UV systems
  x86/platform/UV: Fix problem with UV4 BIOS providing incorrect PXM values
  x86/platform/UV: Fix bug with iounmap() of the UV4 EFI System Table causing a crash
  x86/platform/UV: Fix problem with UV4 Socket IDs not being contiguous
  x86/entry: Clarify the RF saving/restoring situation with SYSCALL/SYSRET
  x86/mm: Disable preemption during CR3 read+write
  x86/mm/KASLR: Increase BRK pages for KASLR memory randomization
  x86/mm/KASLR: Fix physical memory calculation on KASLR memory randomization
  x86, kasan, ftrace: Put APIC interrupt handlers into .irqentry.text

arch/x86/entry/Makefile

@@ -5,6 +5,8 @@
 OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
 OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
+CFLAGS_syscall_64.o		+= -Wno-override-init
+CFLAGS_syscall_32.o		+= -Wno-override-init
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 

arch/x86/entry/entry_64.S

@@ -288,11 +288,15 @@ return_from_SYSCALL_64:
 	jne	opportunistic_sysret_failed
 
 	/*
-	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
-	 * restoring TF results in a trap from userspace immediately after
-	 * SYSRET.  This would cause an infinite loop whenever #DB happens
-	 * with register state that satisfies the opportunistic SYSRET
-	 * conditions.  For example, single-stepping this user code:
+	 * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+	 * restore RF properly. If the slowpath sets it for whatever reason, we
+	 * need to restore it correctly.
+	 *
+	 * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+	 * trap from userspace immediately after SYSRET.  This would cause an
+	 * infinite loop whenever #DB happens with register state that satisfies
+	 * the opportunistic SYSRET conditions.  For example, single-stepping
+	 * this user code:
 	 *
 	 *           movq	$stuck_here, %rcx
 	 *           pushfq
@@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym)
 .endm
 #endif
 
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+# define PUSH_SECTION_IRQENTRY	.pushsection .irqentry.text, "ax"
+# define POP_SECTION_IRQENTRY	.popsection
+#else
+# define PUSH_SECTION_IRQENTRY
+# define POP_SECTION_IRQENTRY
+#endif
+
 .macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
 apicinterrupt3 \num \sym \do_sym
 trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
 .endm
 
 #ifdef CONFIG_SMP

arch/x86/include/asm/hardirq.h

@@ -22,10 +22,6 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	/*
-	 * irq_tlb_count is double-counted in irq_call_count, so it must be
-	 * subtracted from irq_call_count when displaying irq_call_count
-	 */
 	unsigned int irq_tlb_count;
 #endif
 #ifdef CONFIG_X86_THERMAL_VECTOR

arch/x86/include/asm/pgtable_64.h

@@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2|1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ * | OFFSET (14->63) | TYPE (9-13)  |0|X|X|X| X| X|X|X|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
 #define SWP_TYPE_BITS 5
 /* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 

arch/x86/include/asm/realmode.h

@@ -58,7 +58,15 @@ extern unsigned char boot_gdt[];
 extern unsigned char secondary_startup_64[];
 #endif
 
+static inline size_t real_mode_size_needed(void)
+{
+	if (real_mode_header)
+		return 0;	/* already allocated. */
+
+	return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
+}
+
+void set_real_mode_mem(phys_addr_t mem, size_t size);
 void reserve_real_mode(void);
-void setup_real_mode(void);
 
 #endif /* _ARCH_X86_REALMODE_H */

arch/x86/include/asm/tlbflush.h

@@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }
 
 static inline void __native_flush_tlb_global_irq_disabled(void)

arch/x86/include/asm/uv/bios.h

@@ -79,7 +79,7 @@ struct uv_gam_range_entry {
 	u16	nasid;		/* HNasid */
 	u16	sockid;		/* Socket ID, high bits of APIC ID */
 	u16	pnode;		/* Index to MMR and GRU spaces */
-	u32	pxm;		/* ACPI proximity domain number */
+	u32	unused2;
 	u32	limit;		/* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
 };
 
@@ -88,7 +88,8 @@ struct uv_gam_range_entry {
 #define	UV_SYSTAB_VERSION_UV4		0x400	/* UV4 BIOS base version */
 #define	UV_SYSTAB_VERSION_UV4_1		0x401	/* + gpa_shift */
 #define	UV_SYSTAB_VERSION_UV4_2		0x402	/* + TYPE_NVRAM/WINDOW/MBOX */
-#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_2
+#define	UV_SYSTAB_VERSION_UV4_3		0x403	/* - GAM Range PXM Value */
+#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_3
 
 #define	UV_SYSTAB_TYPE_UNUSED		0	/* End of table (offset == 0) */
 #define	UV_SYSTAB_TYPE_GAM_PARAMS	1	/* GAM PARAM conversions */

arch/x86/kernel/apic/x2apic_cluster.c

@@ -155,7 +155,7 @@ static void init_x2apic_ldr(void)
 /*
  * At CPU state changes, update the x2apic cluster sibling info.
  */
-int x2apic_prepare_cpu(unsigned int cpu)
+static int x2apic_prepare_cpu(unsigned int cpu)
 {
 	if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
 		return -ENOMEM;
@@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu)
 	return 0;
 }
 
-int x2apic_dead_cpu(unsigned int this_cpu)
+static int x2apic_dead_cpu(unsigned int this_cpu)
 {
 	int cpu;
 
@@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu)
 static int x2apic_cluster_probe(void)
 {
 	int cpu = smp_processor_id();
+	int ret;
 
 	if (!x2apic_mode)
 		return 0;
 
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+				x2apic_prepare_cpu, x2apic_dead_cpu);
+	if (ret < 0) {
+		pr_err("Failed to register X2APIC_PREPARE\n");
+		return 0;
+	}
 	cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
-	cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
-			  x2apic_prepare_cpu, x2apic_dead_cpu);
 	return 1;
 }
 

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (strncmp(oem_id, "SGI", 3) != 0)
 		return 0;
 
+	if (numa_off) {
+		pr_err("UV: NUMA is off, disabling UV support\n");
+		return 0;
+	}
+
 	/* Setup early hub type field in uv_hub_info for Node 0 */
 	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
 
@@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void)
 	struct uv_gam_range_entry *gre = uv_gre_table;
 	struct uv_gam_range_s *grt;
 	unsigned long last_limit = 0, ram_limit = 0;
-	int bytes, i, sid, lsid = -1;
+	int bytes, i, sid, lsid = -1, indx = 0, lindx = -1;
 
 	if (!gre)
 		return;
@@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void)
 		}
 		sid = gre->sockid - _min_socket;
 		if (lsid < sid) {		/* new range */
-			grt = &_gr_table[sid];
-			grt->base = lsid;
+			grt = &_gr_table[indx];
+			grt->base = lindx;
 			grt->nasid = gre->nasid;
 			grt->limit = last_limit = gre->limit;
 			lsid = sid;
+			lindx = indx++;
 			continue;
 		}
 		if (lsid == sid && !ram_limit) {	/* update range */
@@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void)
 		}
 		if (!ram_limit) {		/* non-contiguous ram range */
 			grt++;
-			grt->base = sid - 1;
+			grt->base = lindx;
 			grt->nasid = gre->nasid;
 			grt->limit = last_limit = gre->limit;
 			continue;
@@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
-			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n",
 				"Range", "", "Size", "Type", "NASID",
-				"SID", "PN", "PXM");
+				"SID", "PN");
 		}
 		pr_info(
-		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x %3d\n",
+		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
 			((unsigned long)(gre->limit - lgre)) >>
 				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
-			gre->type, gre->nasid, gre->sockid,
-			gre->pnode, gre->pxm);
+			gre->type, gre->nasid, gre->sockid, gre->pnode);
 
 		lgre = gre->limit;
 		if (sock_min > gre->sockid)
@@ -1286,28 +1291,26 @@ static void __init build_socket_tables(void)
 		_pnode_to_socket[i] = SOCK_EMPTY;
 
 	/* fill in pnode/node/addr conversion list values */
-	pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+	pr_info("UV: GAM Building socket/pnode conversion tables\n");
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
 			continue;
 		i = gre->sockid - minsock;
 		if (_socket_to_pnode[i] != SOCK_EMPTY)
 			continue;	/* duplicate */
 		_socket_to_pnode[i] = gre->pnode;
-		_socket_to_node[i] = gre->pxm;
 
 		i = gre->pnode - minpnode;
 		_pnode_to_socket[i] = gre->sockid;
 
 		pr_info(
-		"UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+		"UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
 			gre->sockid, gre->type, gre->nasid,
 			_socket_to_pnode[gre->sockid - minsock],
-			_socket_to_node[gre->sockid - minsock],
 			_pnode_to_socket[gre->pnode - minpnode]);
 	}
 
-	/* check socket -> node values */
+	/* Set socket -> node values */
 	lnid = -1;
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
@@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void)
 		lnid = nid;
 		apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		sockid = apicid >> uv_cpuid.socketid_shift;
-		i = sockid - minsock;
-
-		if (nid != _socket_to_node[i]) {
-			pr_warn(
-			"UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
-				i, sockid, gre->type, _socket_to_node[i], nid);
-			_socket_to_node[i] = nid;
-		}
+		_socket_to_node[sockid - minsock] = nid;
+		pr_info("UV: sid:%02x: apicid:%04x node:%2d\n",
+			sockid, apicid, nid);
 	}
 
 	/* Setup physical blade to pnode translation from GAM Range Table */