Merge branch 'x86/urgent' into x86/cache

Pick up pending upstream fixes to meet dependencies

11 files changed, 62 insertions, 41 deletions

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 9e27fa05a7ae..4c95c365058a 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -536,7 +536,7 @@ static inline void __fpregs_load_activate(void)
 	struct fpu *fpu = &current->thread.fpu;
 	int cpu = smp_processor_id();
 
-	if (WARN_ON_ONCE(current->mm == NULL))
+	if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
 		return;
 
 	if (!fpregs_state_valid(fpu, cpu)) {
@@ -567,11 +567,11 @@ static inline void __fpregs_load_activate(void)
  * otherwise.
  *
  * The FPU context is only stored/restored for a user task and
- * ->mm is used to distinguish between kernel and user threads.
+ * PF_KTHREAD is used to distinguish between kernel and user threads.
  */
 static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (static_cpu_has(X86_FEATURE_FPU) && current->mm) {
+	if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 9f15384c504a..310118805f57 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -52,6 +52,9 @@
 
 #define INTEL_FAM6_CANNONLAKE_MOBILE	0x66
 
+#define INTEL_FAM6_ICELAKE_X		0x6A
+#define INTEL_FAM6_ICELAKE_XEON_D	0x6C
+#define INTEL_FAM6_ICELAKE_DESKTOP	0x7D
 #define INTEL_FAM6_ICELAKE_MOBILE	0x7E
 
 /* "Small Core" Processors (Atom) */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 177aa8ef2afa..85be316665b4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1464,7 +1464,8 @@ static void apic_pending_intr_clear(void)
 		if (queued) {
 			if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
 				ntsc = rdtsc();
-				max_loops = (cpu_khz << 10) - (ntsc - tsc);
+				max_loops = (long long)cpu_khz << 10;
+				max_loops -= ntsc - tsc;
 			} else {
 				max_loops--;
 			}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 70a04436380e..cb0fdcaf1415 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -789,13 +789,16 @@ static struct syscore_ops mc_syscore_ops = {
 	.resume			= mc_bp_resume,
 };
 
-static int mc_cpu_online(unsigned int cpu)
+static int mc_cpu_starting(unsigned int cpu)
 {
-	struct device *dev;
-
-	dev = get_cpu_device(cpu);
 	microcode_update_cpu(cpu);
 	pr_debug("CPU%d added\n", cpu);
+	return 0;
+}
+
+static int mc_cpu_online(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
 
 	if (sysfs_create_group(&dev->kobj, &mc_attr_group))
 		pr_err("Failed to create group for CPU%d\n", cpu);
@@ -872,6 +875,8 @@ int __init microcode_init(void)
 		goto out_ucode_group;
 
 	register_syscore_ops(&mc_syscore_ops);
+	cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
+				  mc_cpu_starting, NULL);
 	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
 				  mc_cpu_online, mc_cpu_down_prep);
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 7ee93125a211..397206f23d14 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -360,6 +360,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	struct list_head *head;
 	struct rdtgroup *entry;
 
+	if (!is_mbm_local_enabled())
+		return;
+
 	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 2f48f208f7e2..2f4824793798 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -796,8 +796,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
-	u32 sw_shareable = 0, hw_shareable = 0;
-	u32 exclusive = 0, pseudo_locked = 0;
+	/*
+	 * Use unsigned long even though only 32 bits are used to ensure
+	 * test_bit() is used safely.
+	 */
+	unsigned long sw_shareable = 0, hw_shareable = 0;
+	unsigned long exclusive = 0, pseudo_locked = 0;
 	struct rdt_domain *dom;
 	int i, hwb, swb, excl, psl;
 	enum rdtgrp_mode mode;
@@ -842,10 +846,10 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 		}
 		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
 			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
-			hwb = test_bit(i, (unsigned long *)&hw_shareable);
-			swb = test_bit(i, (unsigned long *)&sw_shareable);
-			excl = test_bit(i, (unsigned long *)&exclusive);
-			psl = test_bit(i, (unsigned long *)&pseudo_locked);
+			hwb = test_bit(i, &hw_shareable);
+			swb = test_bit(i, &sw_shareable);
+			excl = test_bit(i, &exclusive);
+			psl = test_bit(i, &pseudo_locked);
 			if (hwb && swb)
 				seq_putc(seq, 'X');
 			else if (hwb && !swb)
@@ -2486,26 +2490,19 @@ out_destroy:
  */
 static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
 {
-	/*
-	 * Convert the u32 _val to an unsigned long required by all the bit
-	 * operations within this function. No more than 32 bits of this
-	 * converted value can be accessed because all bit operations are
-	 * additionally provided with cbm_len that is initialized during
-	 * hardware enumeration using five bits from the EAX register and
-	 * thus never can exceed 32 bits.
-	 */
-	unsigned long *val = (unsigned long *)_val;
+	unsigned long val = *_val;
 	unsigned int cbm_len = r->cache.cbm_len;
 	unsigned long first_bit, zero_bit;
 
-	if (*val == 0)
+	if (val == 0)
 		return;
 
-	first_bit = find_first_bit(val, cbm_len);
-	zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
 	/* Clear any remaining bits to ensure contiguous region */
-	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
+	*_val = (u32)val;
 }
 
 /*
@@ -2534,7 +2531,12 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
 		if (closid_allocated(i) && i != closid) {
 			mode = rdtgroup_mode_by_closid(i);
 			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
-				break;
+				/*
+				 * ctrl values for locksetup aren't relevant
+				 * until the schemata is written, and the mode
+				 * becomes RDT_MODE_PSEUDO_LOCKED.
+				 */
+				continue;
 			/*
 			 * If CDP is active include peer domain's
 			 * usage to ensure there is no overlap
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 466fca686fb9..649fbc3fcf9f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -102,7 +102,7 @@ static void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (current->mm) {
+	if (!(current->flags & PF_KTHREAD)) {
 		if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
 			set_thread_flag(TIF_NEED_FPU_LOAD);
 			/*
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 5a8d118bc423..0071b794ed19 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -5,6 +5,7 @@
 
 #include <linux/compat.h>
 #include <linux/cpu.h>
+#include <linux/pagemap.h>
 
 #include <asm/fpu/internal.h>
 #include <asm/fpu/signal.h>
@@ -61,6 +62,11 @@ static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
 		struct user_i387_ia32_struct env;
 		struct _fpstate_32 __user *fp = buf;
 
+		fpregs_lock();
+		if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+			copy_fxregs_to_kernel(&tsk->thread.fpu);
+		fpregs_unlock();
+
 		convert_from_fxsr(&env, tsk);
 
 		if (__copy_to_user(buf, &env, sizeof(env)) ||
@@ -189,15 +195,7 @@ retry:
 	fpregs_unlock();
 
 	if (ret) {
-		int aligned_size;
-		int nr_pages;
-
-		aligned_size = offset_in_page(buf_fx) + fpu_user_xstate_size;
-		nr_pages = DIV_ROUND_UP(aligned_size, PAGE_SIZE);
-
-		ret = get_user_pages_unlocked((unsigned long)buf_fx, nr_pages,
-					      NULL, FOLL_WRITE);
-		if (ret == nr_pages)
+		if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size))
 			goto retry;
 		return -EFAULT;
 	}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 9a8c1648fc9a..6690c5652aeb 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -758,7 +758,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 		       BREAK_INSTR_SIZE);
 	bpt->type = BP_POKE_BREAKPOINT;
 
-	return err;
+	return 0;
 }
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 8dc0fc0b1382..296da58f3013 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -199,7 +199,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
 	if (!pgtable_l5_enabled())
 		return (p4d_t *)pgd;
 
-	p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
+	p4d = pgd_val(*pgd) & PTE_PFN_MASK;
 	p4d += __START_KERNEL_map - phys_base;
 	return (p4d_t *)p4d + p4d_index(addr);
 }
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index dc3f058bdf9b..dc6182eecefa 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -52,7 +52,7 @@ static __initdata struct kaslr_memory_region {
 } kaslr_regions[] = {
 	{ &page_offset_base, 0 },
 	{ &vmalloc_base, 0 },
-	{ &vmemmap_base, 1 },
+	{ &vmemmap_base, 0 },
 };
 
 /* Get size in bytes used by the memory region */
@@ -78,6 +78,7 @@ void __init kernel_randomize_memory(void)
 	unsigned long rand, memory_tb;
 	struct rnd_state rand_state;
 	unsigned long remain_entropy;
+	unsigned long vmemmap_size;
 
 	vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
 	vaddr = vaddr_start;
@@ -109,6 +110,14 @@ void __init kernel_randomize_memory(void)
 	if (memory_tb < kaslr_regions[0].size_tb)
 		kaslr_regions[0].size_tb = memory_tb;
 
+	/*
+	 * Calculate the vmemmap region size in TBs, aligned to a TB
+	 * boundary.
+	 */
+	vmemmap_size = (kaslr_regions[0].size_tb << (TB_SHIFT - PAGE_SHIFT)) *
+			sizeof(struct page);
+	kaslr_regions[2].size_tb = DIV_ROUND_UP(vmemmap_size, 1UL << TB_SHIFT);
+
 	/* Calculate entropy available between regions */
 	remain_entropy = vaddr_end - vaddr_start;
 	for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++)