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

Pull x86 fixes and cleanups from Thomas Gleixner:
 "This set of updates contains:

   - Robustification for the logical package managment. Cures the AMD
     and virtualization issues.

   - Put the correct start_cpu() return address on the stack of the idle
     task.

   - Fixups for the fallout of the nodeid <-> cpuid persistent mapping
     modifciations

   - Move the x86/MPX specific mm_struct member to the arch specific
     mm_context where it belongs

   - Cleanups for C89 struct initializers and useless function
     arguments"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/floppy: Use designated initializers
  x86/mpx: Move bd_addr to mm_context_t
  x86/mm: Drop unused argument 'removed' from sync_global_pgds()
  ACPI/NUMA: Do not map pxm to node when NUMA is turned off
  x86/acpi: Use proper macro for invalid node
  x86/smpboot: Prevent false positive out of bounds cpumask access warning
  x86/boot/64: Push correct start_cpu() return address
  x86/boot/64: Use 'push' instead of 'call' in start_cpu()
  x86/smpboot: Make logical package management more robust

arch/arm64/include/asm/numa.h

@@ -15,6 +15,8 @@ int __node_distance(int from, int to);
 
 extern nodemask_t numa_nodes_parsed __initdata;
 
+extern bool numa_off;
+
 /* Mappings between node number and cpus on that node. */
 extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 void numa_clear_node(unsigned int cpu);

arch/arm64/mm/numa.c

@@ -35,7 +35,7 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
 
 static int numa_distance_cnt;
 static u8 *numa_distance;
-static bool numa_off;
+bool numa_off;
 
 static __init int numa_parse_early_param(char *opt)
 {

arch/ia64/include/asm/numa.h

@@ -65,6 +65,8 @@ extern int paddr_to_nid(unsigned long paddr);
 
 #define local_nodeid (cpu_to_node_map[smp_processor_id()])
 
+#define numa_off     0
+
 extern void map_cpu_to_node(int cpu, int nid);
 extern void unmap_cpu_from_node(int cpu, int nid);
 extern void numa_clear_node(int cpu);

arch/x86/include/asm/floppy.h

@@ -229,18 +229,18 @@ static struct fd_routine_l {
 	int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
 } fd_routine[] = {
 	{
-		request_dma,
+		._request_dma		= request_dma,
-		free_dma,
+		._free_dma		= free_dma,
-		get_dma_residue,
+		._get_dma_residue	= get_dma_residue,
-		dma_mem_alloc,
+		._dma_mem_alloc		= dma_mem_alloc,
-		hard_dma_setup
+		._dma_setup		= hard_dma_setup
 	},
 	{
-		vdma_request_dma,
+		._request_dma		= vdma_request_dma,
-		vdma_nop,
+		._free_dma		= vdma_nop,
-		vdma_get_dma_residue,
+		._get_dma_residue	= vdma_get_dma_residue,
-		vdma_mem_alloc,
+		._dma_mem_alloc		= vdma_mem_alloc,
-		vdma_dma_setup
+		._dma_setup		= vdma_dma_setup
 	}
 };
 

arch/x86/include/asm/mmu.h

@@ -31,6 +31,10 @@ typedef struct {
 	u16 pkey_allocation_map;
 	s16 execute_only_pkey;
 #endif
+#ifdef CONFIG_X86_INTEL_MPX
+	/* address of the bounds directory */
+	void __user *bd_addr;
+#endif
 } mm_context_t;
 
 #ifdef CONFIG_SMP

arch/x86/include/asm/mpx.h

@@ -59,7 +59,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
 int mpx_handle_bd_fault(void);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
-	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
+	return (mm->context.bd_addr != MPX_INVALID_BOUNDS_DIR);
 }
 static inline void mpx_mm_init(struct mm_struct *mm)
 {
@@ -67,7 +67,7 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 	 * NULL is theoretically a valid place to put the bounds
 	 * directory, so point this at an invalid address.
 	 */
-	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+	mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
 }
 void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);

arch/x86/include/asm/pgtable_64.h

@@ -116,8 +116,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
-extern void sync_global_pgds(unsigned long start, unsigned long end,
+extern void sync_global_pgds(unsigned long start, unsigned long end);
-			     int removed);
 
 /*
  * Conversion functions: convert a page and protection to a page entry,

arch/x86/kernel/acpi/boot.c

@@ -715,7 +715,7 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	int nid;
 
 	nid = acpi_get_node(handle);
-	if (nid != -1) {
+	if (nid != NUMA_NO_NODE) {
 		set_apicid_to_node(physid, nid);
 		numa_set_node(cpu, nid);
 	}

arch/x86/kernel/apic/apic.c

@@ -2159,21 +2159,6 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 		}
 	}
 
-	/*
-	 * This can happen on physical hotplug. The sanity check at boot time
-	 * is done from native_smp_prepare_cpus() after num_possible_cpus() is
-	 * established.
-	 */
-	if (topology_update_package_map(apicid, cpu) < 0) {
-		int thiscpu = max + disabled_cpus;
-
-		pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
-			   thiscpu, apicid);
-
-		disabled_cpus++;
-		return -ENOSPC;
-	}
-
 	/*
 	 * Validate version
 	 */

arch/x86/kernel/cpu/common.c

@@ -979,29 +979,21 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
 }
 
 /*
- * The physical to logical package id mapping is initialized from the
+ * Validate that ACPI/mptables have the same information about the
- * acpi/mptables information. Make sure that CPUID actually agrees with
+ * effective APIC id and update the package map.
- * that.
  */
-static void sanitize_package_id(struct cpuinfo_x86 *c)
+static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	unsigned int pkg, apicid, cpu = smp_processor_id();
+	unsigned int apicid, cpu = smp_processor_id();
 
 	apicid = apic->cpu_present_to_apicid(cpu);
-	pkg = apicid >> boot_cpu_data.x86_coreid_bits;
 
-	if (apicid != c->initial_apicid) {
+	if (apicid != c->apicid) {
-		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n",
+		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
 		       cpu, apicid, c->initial_apicid);
-		c->initial_apicid = apicid;
 	}
-	if (pkg != c->phys_proc_id) {
+	BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
-		pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n",
-		       cpu, pkg, c->phys_proc_id);
-		c->phys_proc_id = pkg;
-	}
-	c->logical_proc_id = topology_phys_to_logical_pkg(pkg);
 #else
 	c->logical_proc_id = 0;
 #endif
@@ -1132,7 +1124,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
-	sanitize_package_id(c);
 }
 
 /*
@@ -1187,6 +1178,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	enable_sep_cpu();
 #endif
 	mtrr_ap_init();
+	validate_apic_and_package_id(c);
 }
 
 static __init int setup_noclflush(char *arg)

arch/x86/kernel/head_64.S

@@ -298,12 +298,13 @@ ENTRY(start_cpu)
 	 *	REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
 	 *		address given in m16:64.
 	 */
-	call	1f		# put return address on stack for unwinder
+	pushq	$.Lafter_lret	# put return address on stack for unwinder
-1:	xorq	%rbp, %rbp	# clear frame pointer
+	xorq	%rbp, %rbp	# clear frame pointer
 	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
 	lretq
+.Lafter_lret:
 ENDPROC(start_cpu)
 
 #include "verify_cpu.S"

arch/x86/kernel/smpboot.c

@@ -103,7 +103,6 @@ static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
-static bool logical_packages_frozen __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
 int __max_smt_threads __read_mostly;
@@ -273,9 +272,14 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-int topology_update_package_map(unsigned int apicid, unsigned int cpu)
+/**
+ * topology_update_package_map - Update the physical to logical package map
+ * @pkg:	The physical package id as retrieved via CPUID
+ * @cpu:	The cpu for which this is updated
+ */
+int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 {
-	unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+	unsigned int new;
 
 	/* Called from early boot ? */
 	if (!physical_package_map)
@@ -288,16 +292,17 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu)
 	if (test_and_set_bit(pkg, physical_package_map))
 		goto found;
 
-	if (logical_packages_frozen) {
+	if (logical_packages >= __max_logical_packages) {
-		physical_to_logical_pkg[pkg] = -1;
+		pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n",
-		pr_warn("APIC(%x) Package %u exceeds logical package max\n",
+			logical_packages, cpu, __max_logical_packages);
-			apicid, pkg);
 		return -ENOSPC;
 	}
 
 	new = logical_packages++;
-	pr_info("APIC(%x) Converting physical %u to logical package %u\n",
+	if (new != pkg) {
-		apicid, pkg, new);
+		pr_info("CPU %u Converting physical %u to logical package %u\n",
+			cpu, pkg, new);
+	}
 	physical_to_logical_pkg[pkg] = new;
 
 found:
@@ -318,9 +323,9 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg)
 }
 EXPORT_SYMBOL(topology_phys_to_logical_pkg);
 
-static void __init smp_init_package_map(void)
+static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
 {
-	unsigned int ncpus, cpu;
+	unsigned int ncpus;
 	size_t size;
 
 	/*
@@ -365,27 +370,9 @@ static void __init smp_init_package_map(void)
 	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
 	physical_package_map = kzalloc(size, GFP_KERNEL);
 
-	for_each_present_cpu(cpu) {
-		unsigned int apicid = apic->cpu_present_to_apicid(cpu);
-
-		if (apicid == BAD_APICID || !apic->apic_id_valid(apicid))
-			continue;
-		if (!topology_update_package_map(apicid, cpu))
-			continue;
-		pr_warn("CPU %u APICId %x disabled\n", cpu, apicid);
-		per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID;
-		set_cpu_possible(cpu, false);
-		set_cpu_present(cpu, false);
-	}
-
-	if (logical_packages > __max_logical_packages) {
-		pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n",
-			logical_packages, __max_logical_packages);
-		logical_packages_frozen = true;
-		__max_logical_packages  = logical_packages;
-	}
-
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
+
+	topology_update_package_map(c->phys_proc_id, cpu);
 }
 
 void __init smp_store_boot_cpu_info(void)
@@ -395,7 +382,7 @@ void __init smp_store_boot_cpu_info(void)
 
 	*c = boot_cpu_data;
 	c->cpu_index = id;
-	smp_init_package_map();
+	smp_init_package_map(c, id);
 }
 
 /*
@@ -1476,15 +1463,15 @@ __init void prefill_possible_map(void)
 		possible = i;
 	}
 
+	nr_cpu_ids = possible;
+
 	pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
 		possible, max_t(int, possible - num_processors, 0));
 
+	reset_cpu_possible_mask();
+
 	for (i = 0; i < possible; i++)
 		set_cpu_possible(i, true);
-	for (; i < NR_CPUS; i++)
-		set_cpu_possible(i, false);
-
-	nr_cpu_ids = possible;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

arch/x86/mm/fault.c

@@ -413,7 +413,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0);
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
 /*

arch/x86/mm/init_64.c

@@ -89,10 +89,10 @@ static int __init nonx32_setup(char *str)
 __setup("noexec32=", nonx32_setup);
 
 /*
- * When memory was added/removed make sure all the processes MM have
+ * When memory was added make sure all the processes MM have
  * suitable PGD entries in the local PGD level page.
  */
-void sync_global_pgds(unsigned long start, unsigned long end, int removed)
+void sync_global_pgds(unsigned long start, unsigned long end)
 {
 	unsigned long address;
 
@@ -100,12 +100,7 @@ void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		struct page *page;
 
-		/*
+		if (pgd_none(*pgd_ref))
-		 * When it is called after memory hot remove, pgd_none()
-		 * returns true. In this case (removed == 1), we must clear
-		 * the PGD entries in the local PGD level page.
-		 */
-		if (pgd_none(*pgd_ref) && !removed)
 			continue;
 
 		spin_lock(&pgd_lock);
@@ -122,13 +117,8 @@ void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 				BUG_ON(pgd_page_vaddr(*pgd)
 				       != pgd_page_vaddr(*pgd_ref));
 
-			if (removed) {
+			if (pgd_none(*pgd))
-				if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+				set_pgd(pgd, *pgd_ref);
-					pgd_clear(pgd);
-			} else {
-				if (pgd_none(*pgd))
-					set_pgd(pgd, *pgd_ref);
-			}
 
 			spin_unlock(pgt_lock);
 		}
@@ -596,7 +586,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(vaddr_start, vaddr_end - 1, 0);
+		sync_global_pgds(vaddr_start, vaddr_end - 1);
 
 	__flush_tlb_all();
 
@@ -1239,7 +1229,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	} else
 		err = vmemmap_populate_basepages(start, end, node);
 	if (!err)
-		sync_global_pgds(start, end - 1, 0);
+		sync_global_pgds(start, end - 1);
 	return err;
 }
 

arch/x86/mm/mpx.c

@@ -350,12 +350,12 @@ int mpx_enable_management(void)
 	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
 	 * expected to be relatively expensive. Storing the bounds
 	 * directory here means that we do not have to do xsave in the
-	 * unmap path; we can just use mm->bd_addr instead.
+	 * unmap path; we can just use mm->context.bd_addr instead.
 	 */
 	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
-	mm->bd_addr = bd_base;
+	mm->context.bd_addr = bd_base;
-	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
+	if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR)
 		ret = -ENXIO;
 
 	up_write(&mm->mmap_sem);
@@ -370,7 +370,7 @@ int mpx_disable_management(void)
 		return -ENXIO;
 
 	down_write(&mm->mmap_sem);
-	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+	mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
 	up_write(&mm->mmap_sem);
 	return 0;
 }
@@ -947,7 +947,7 @@ static int try_unmap_single_bt(struct mm_struct *mm,
 		end = bta_end_vaddr;
 	}
 
-	bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+	bde_vaddr = mm->context.bd_addr + mpx_get_bd_entry_offset(mm, start);
 	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
 	/*
 	 * No bounds table there, so nothing to unmap.

arch/x86/mm/numa.c

@@ -19,7 +19,7 @@
 
 #include "numa_internal.h"
 
-int __initdata numa_off;
+int numa_off;
 nodemask_t numa_nodes_parsed __initdata;
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;

arch/x86/xen/smp.c

@@ -87,12 +87,6 @@ static void cpu_bringup(void)
 	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
-	/*
-	 * identify_cpu() may have set logical_pkg_id to -1 due
-	 * to incorrect phys_proc_id. Let's re-comupte it.
-	 */
-	topology_update_package_map(apic->cpu_present_to_apicid(cpu), cpu);
-
 	xen_setup_cpu_clockevents();
 
 	notify_cpu_starting(cpu);

drivers/acpi/numa.c

@@ -70,7 +70,7 @@ int acpi_map_pxm_to_node(int pxm)
 {
 	int node;
 
-	if (pxm < 0 || pxm >= MAX_PXM_DOMAINS)
+	if (pxm < 0 || pxm >= MAX_PXM_DOMAINS || numa_off)
 		return NUMA_NO_NODE;
 
 	node = pxm_to_node_map[pxm];

include/linux/cpumask.h

@@ -722,6 +722,11 @@ void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
 void init_cpu_online(const struct cpumask *src);
 
+static inline void reset_cpu_possible_mask(void)
+{
+	bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS);
+}
+
 static inline void
 set_cpu_possible(unsigned int cpu, bool possible)
 {

include/linux/mm_types.h

@@ -509,10 +509,6 @@ struct mm_struct {
 	bool tlb_flush_pending;
 #endif
 	struct uprobes_state uprobes_state;
-#ifdef CONFIG_X86_INTEL_MPX
-	/* address of the bounds directory */
-	void __user *bd_addr;
-#endif
 #ifdef CONFIG_HUGETLB_PAGE
 	atomic_long_t hugetlb_usage;
 #endif