25 files changed, 153 insertions, 57 deletions

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index c5d614d28a75..74777a97e394 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -248,6 +248,7 @@ config UNWINDER_ORC
 
 config UNWINDER_FRAME_POINTER
 	bool "Frame pointer unwinder"
+	select ARCH_WANT_FRAME_POINTERS
 	select FRAME_POINTER
 	help
 	  This option enables the frame pointer unwinder for unwinding kernel
@@ -271,7 +272,3 @@ config UNWINDER_GUESS
 	  overhead.
 
 endchoice
-
-config FRAME_POINTER
-	depends on !UNWINDER_ORC && !UNWINDER_GUESS
-	bool
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 5b25d2a58aeb..ef031655b2d3 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1223,14 +1223,14 @@ DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
  * implementation with ymm registers (256-bit vectors) will be used instead.
  */
 static const struct x86_cpu_id zmm_exclusion_list[] = {
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L },
-	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE },
+	X86_MATCH_VFM(INTEL_SKYLAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_D,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_L,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_NNPI,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE,		0),
 	/* Allow Rocket Lake and later, and Sapphire Rapids and later. */
 	/* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */
 	{},
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 5f8591ce7f25..7fd1f57ad3d3 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -466,3 +466,4 @@
 459	i386	lsm_get_self_attr	sys_lsm_get_self_attr
 460	i386	lsm_set_self_attr	sys_lsm_set_self_attr
 461	i386	lsm_list_modules	sys_lsm_list_modules
+462	i386	mseal 			sys_mseal
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index cc78226ffc35..a396f6e6ab5b 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -383,6 +383,7 @@
 459	common	lsm_get_self_attr	sys_lsm_get_self_attr
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
+462 	common  mseal			sys_mseal
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 970a232009c3..b6325ee30871 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -53,6 +53,9 @@
 #define X86_CENTAUR_FAM6_C7_D		0xd
 #define X86_CENTAUR_FAM6_NANO		0xf
 
+/* x86_cpu_id::flags */
+#define X86_CPU_ID_FLAG_ENTRY_VALID	BIT(0)
+
 #define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
  * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
@@ -79,6 +82,7 @@
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
 	.driver_data	= (unsigned long) _data				\
 }
 
@@ -89,6 +93,7 @@
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
 	.driver_data	= (unsigned long) _data				\
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 9eec52925fa3..557318145038 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -1035,7 +1035,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd)
 			add_timer_on(&cl->timer, cpu);
 		}
 	} else {
-		apicd->prev_vector = 0;
+		pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu);
+		free_moved_vector(apicd);
 	}
 	raw_spin_unlock(&vector_lock);
 }
@@ -1072,6 +1073,7 @@ void irq_complete_move(struct irq_cfg *cfg)
  */
 void irq_force_complete_move(struct irq_desc *desc)
 {
+	unsigned int cpu = smp_processor_id();
 	struct apic_chip_data *apicd;
 	struct irq_data *irqd;
 	unsigned int vector;
@@ -1096,10 +1098,11 @@ void irq_force_complete_move(struct irq_desc *desc)
 		goto unlock;
 
 	/*
-	 * If prev_vector is empty, no action required.
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
 	 */
 	vector = apicd->prev_vector;
-	if (!vector)
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
 		goto unlock;
 
 	/*
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 8651643bddae..8e7de733320a 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -38,9 +38,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match;
-	     m->vendor | m->family | m->model | m->steppings | m->feature;
-	     m++) {
+	for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index d17c9b71eb4a..621a151ccf7d 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -128,6 +128,9 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id)
 
 static __init bool check_for_real_bsp(u32 apic_id)
 {
+	bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6;
+	u64 msr;
+
 	/*
 	 * There is no real good way to detect whether this a kdump()
 	 * kernel, but except on the Voyager SMP monstrosity which is not
@@ -144,17 +147,61 @@ static __init bool check_for_real_bsp(u32 apic_id)
 	if (topo_info.real_bsp_apic_id != BAD_APICID)
 		return false;
 
+	/*
+	 * Check whether the enumeration order is broken by evaluating the
+	 * BSP bit in the APICBASE MSR. If the CPU does not have the
+	 * APICBASE MSR then the BSP detection is not possible and the
+	 * kernel must rely on the firmware enumeration order.
+	 */
+	if (has_apic_base) {
+		rdmsrl(MSR_IA32_APICBASE, msr);
+		is_bsp = !!(msr & MSR_IA32_APICBASE_BSP);
+	}
+
 	if (apic_id == topo_info.boot_cpu_apic_id) {
-		topo_info.real_bsp_apic_id = apic_id;
-		return false;
+		/*
+		 * If the boot CPU has the APIC BSP bit set then the
+		 * firmware enumeration is agreeing. If the CPU does not
+		 * have the APICBASE MSR then the only choice is to trust
+		 * the enumeration order.
+		 */
+		if (is_bsp || !has_apic_base) {
+			topo_info.real_bsp_apic_id = apic_id;
+			return false;
+		}
+		/*
+		 * If the boot APIC is enumerated first, but the APICBASE
+		 * MSR does not have the BSP bit set, then there is no way
+		 * to discover the real BSP here. Assume a crash kernel and
+		 * limit the number of CPUs to 1 as an INIT to the real BSP
+		 * would reset the machine.
+		 */
+		pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id);
+		pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n");
+		set_nr_cpu_ids(1);
+		goto fwbug;
 	}
 
-	pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n",
+	pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n",
 		topo_info.boot_cpu_apic_id, apic_id);
+
+	if (is_bsp) {
+		/*
+		 * The boot CPU has the APIC BSP bit set. Use it and complain
+		 * about the broken firmware enumeration.
+		 */
+		topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id;
+		goto fwbug;
+	}
+
 	pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n");
 
 	topo_info.real_bsp_apic_id = apic_id;
 	return true;
+
+fwbug:
+	pr_warn(FW_BUG "APIC enumeration order not specification compliant\n");
+	return false;
 }
 
 static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level,
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 83822fd42204..2fef3da55533 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -54,6 +54,8 @@ extern int ptrace_get_thread_area(struct task_struct *child, int idx,
 extern int ptrace_set_thread_area(struct task_struct *child, int idx,
                                   struct user_desc __user *user_desc);
 
+extern int arch_switch_tls(struct task_struct *to);
+
 #else
 
 #define PT_REGS_R8(r) UPT_R8(&(r)->regs)
@@ -83,5 +85,9 @@ extern long arch_prctl(struct task_struct *task, int option,
 		       unsigned long __user *addr);
 
 #endif
+
 #define user_stack_pointer(regs) PT_REGS_SP(regs)
+
+extern void arch_switch_to(struct task_struct *to);
+
 #endif /* __UM_X86_PTRACE_H */
diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c
index 33daff4dade4..d29929efcc07 100644
--- a/arch/x86/um/bugs_32.c
+++ b/arch/x86/um/bugs_32.c
@@ -3,6 +3,7 @@
  * Licensed under the GPL
  */
 
+#include <arch.h>
 #include <signal.h>
 #include <kern_util.h>
 #include <longjmp.h>
diff --git a/arch/x86/um/bugs_64.c b/arch/x86/um/bugs_64.c
index 8cc8256c698d..b01295e8a676 100644
--- a/arch/x86/um/bugs_64.c
+++ b/arch/x86/um/bugs_64.c
@@ -4,6 +4,7 @@
  * Licensed under the GPL
  */
 
+#include <arch.h>
 #include <sysdep/ptrace.h>
 
 void arch_check_bugs(void)
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 650cdbbdaf45..ef50662fc40d 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/elf.h>
+#include <linux/elfcore.h>
 #include <linux/coredump.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c
index 84ac7f7b0257..0dde4d613a87 100644
--- a/arch/x86/um/fault.c
+++ b/arch/x86/um/fault.c
@@ -3,6 +3,7 @@
  * Licensed under the GPL
  */
 
+#include <arch.h>
 #include <sysdep/ptrace.h>
 
 /* These two are from asm-um/uaccess.h and linux/module.h, check them. */
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
index 49c3744cac37..e80ab7d28117 100644
--- a/arch/x86/um/os-Linux/mcontext.c
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -3,6 +3,7 @@
 #define __FRAME_OFFSETS
 #include <asm/ptrace.h>
 #include <sysdep/ptrace.h>
+#include <sysdep/mcontext.h>
 
 void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 {
diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c
index df8f4b4bf98b..f3638dd09cec 100644
--- a/arch/x86/um/os-Linux/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -17,7 +17,7 @@
 #include <linux/elf.h>
 #include <registers.h>
 
-int have_xstate_support;
+static int have_xstate_support;
 
 int save_i387_registers(int pid, unsigned long *fp_regs)
 {
diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c
index 3e1b1bf6acbc..eed9efe29ade 100644
--- a/arch/x86/um/os-Linux/tls.c
+++ b/arch/x86/um/os-Linux/tls.c
@@ -6,6 +6,7 @@
 #include <sys/syscall.h>
 #include <unistd.h>
 
+#include <os.h>
 #include <sysdep/tls.h>
 
 #ifndef PTRACE_GET_THREAD_AREA
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 7f1abde2c84b..b0a71c6cdc6e 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -10,8 +10,6 @@
 #include <registers.h>
 #include <skas.h>
 
-extern int arch_switch_tls(struct task_struct *to);
-
 void arch_switch_to(struct task_struct *to)
 {
 	int err = arch_switch_tls(to);
diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h
index 166cedbab926..8c81d1a604a9 100644
--- a/arch/x86/um/shared/sysdep/archsetjmp.h
+++ b/arch/x86/um/shared/sysdep/archsetjmp.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H
+#define __X86_UM_SYSDEP_ARCHSETJMP_H
+
 #ifdef __i386__
 #include "archsetjmp_32.h"
 #else
 #include "archsetjmp_64.h"
 #endif
+
+unsigned long get_thread_reg(int reg, jmp_buf *buf);
+
+#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index a004bffb7b8d..48de3a71f845 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -6,6 +6,9 @@
 #include <linux/kbuild.h>
 #include <asm/mman.h>
 
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
 void foo(void)
 {
 #include <common-offsets.h>
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 263e1d08f216..2cc8c2309022 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -8,6 +8,7 @@
 #include <linux/personality.h>
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
+#include <linux/syscalls.h>
 #include <asm/unistd.h>
 #include <linux/uaccess.h>
 #include <asm/ucontext.h>
@@ -155,7 +156,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 			     struct sigcontext __user *from)
 {
 	struct sigcontext sc;
-	int err, pid;
+	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
@@ -201,10 +202,10 @@ static int copy_sc_from_user(struct pt_regs *regs,
 
 #undef GETREG
 
-	pid = userspace_pid[current_thread_info()->cpu];
 #ifdef CONFIG_X86_32
 	if (have_fpx_regs) {
 		struct user_fxsr_struct fpx;
+		int pid = userspace_pid[current_thread_info()->cpu];
 
 		err = copy_from_user(&fpx,
 			&((struct _fpstate __user *)sc.fpstate)->_fxsr_env[0],
@@ -240,7 +241,7 @@ static int copy_sc_to_user(struct sigcontext __user *to,
 {
 	struct sigcontext sc;
 	struct faultinfo * fi = &current->thread.arch.faultinfo;
-	int err, pid;
+	int err;
 	memset(&sc, 0, sizeof(struct sigcontext));
 
 #define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno]
@@ -288,10 +289,9 @@ static int copy_sc_to_user(struct sigcontext __user *to,
 	if (err)
 		return 1;
 
-	pid = userspace_pid[current_thread_info()->cpu];
-
 #ifdef CONFIG_X86_32
 	if (have_fpx_regs) {
+		int pid = userspace_pid[current_thread_info()->cpu];
 		struct user_fxsr_struct fpx;
 
 		err = save_fpx_registers(pid, (unsigned long *) &fpx);
@@ -450,7 +450,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 	return 0;
 }
 
-long sys_sigreturn(void)
+SYSCALL_DEFINE0(sigreturn)
 {
 	unsigned long sp = PT_REGS_SP(&current->thread.regs);
 	struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
@@ -557,7 +557,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 }
 #endif
 
-long sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
 {
 	unsigned long sp = PT_REGS_SP(&current->thread.regs);
 	struct rt_sigframe __user *frame =
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index 66162eafd8e8..d301deee041f 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -20,7 +20,7 @@
 static int host_supports_tls = -1;
 int host_gdt_entry_tls_min;
 
-int do_set_thread_area(struct user_desc *info)
+static int do_set_thread_area(struct user_desc *info)
 {
 	int ret;
 	u32 cpu;
@@ -36,22 +36,6 @@ int do_set_thread_area(struct user_desc *info)
 	return ret;
 }
 
-int do_get_thread_area(struct user_desc *info)
-{
-	int ret;
-	u32 cpu;
-
-	cpu = get_cpu();
-	ret = os_get_thread_area(info, userspace_pid[cpu]);
-	put_cpu();
-
-	if (ret)
-		printk(KERN_ERR "PTRACE_GET_THREAD_AREA failed, err = %d, "
-		       "index = %d\n", ret, info->entry_number);
-
-	return ret;
-}
-
 /*
  * sys_get_thread_area: get a yet unused TLS descriptor index.
  * XXX: Consider leaving one free slot for glibc usage at first place. This must
@@ -231,7 +215,6 @@ out:
 	return ret;
 }
 
-/* XXX: use do_get_thread_area to read the host value? I'm not at all sure! */
 static int get_tls_entry(struct task_struct *task, struct user_desc *info,
 			 int idx)
 {
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index e54a9814ccf1..1c77d9946199 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -14,6 +14,9 @@
 	COMMENT(#val " / sizeof(unsigned long)");	\
 	DEFINE(sym, val / sizeof(unsigned long))
 
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
 void foo(void)
 {
 #ifdef __i386__
diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index ff0f3b4b6c45..cbae2584124f 100644
--- a/arch/x86/um/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
@@ -13,6 +13,12 @@
 #include <linux/getcpu.h>
 #include <asm/unistd.h>
 
+/* workaround for -Wmissing-prototypes warnings */
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
+long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
+
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
 {
 	long ret;
@@ -54,7 +60,7 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
 __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time")));
 
 long
-__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
 {
 	/*
 	 * UML does not support SMP, we can cheat here. :)
@@ -68,5 +74,5 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 	return 0;
 }
 
-long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache)
 	__attribute__((weak, alias("__vdso_getcpu")));
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5f3a69f6ec34..0305485edcd3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -379,3 +379,36 @@ void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns)
 
 	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
 }
+
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+int __init arch_xen_unpopulated_init(struct resource **res)
+{
+	unsigned int i;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	/* Must be set strictly before calling xen_free_unpopulated_pages(). */
+	*res = &iomem_resource;
+
+	/*
+	 * Initialize with pages from the extra memory regions (see
+	 * arch/x86/xen/setup.c).
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		unsigned int j;
+
+		for (j = 0; j < xen_extra_mem[i].n_pfns; j++) {
+			struct page *pg =
+				pfn_to_page(xen_extra_mem[i].start_pfn + j);
+
+			xen_free_unpopulated_pages(1, &pg);
+		}
+
+		/* Zero so region is not also added to the balloon driver. */
+		xen_extra_mem[i].n_pfns = 0;
+	}
+
+	return 0;
+}
+#endif
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 9bdc3b656b2c..99918beccd80 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -555,7 +555,6 @@ int xen_alloc_p2m_entry(unsigned long pfn)
 			/* Separately check the mid mfn level */
 			unsigned long missing_mfn;
 			unsigned long mid_mfn_mfn;
-			unsigned long old_mfn;
 
 			mid_mfn = alloc_p2m_page();
 			if (!mid_mfn)
@@ -565,12 +564,12 @@ int xen_alloc_p2m_entry(unsigned long pfn)
 
 			missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
 			mid_mfn_mfn = virt_to_mfn(mid_mfn);
-			old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn);
-			if (old_mfn != missing_mfn) {
-				free_p2m_page(mid_mfn);
-				mid_mfn = mfn_to_virt(old_mfn);
-			} else {
+			/* try_cmpxchg() updates missing_mfn on failure. */
+			if (try_cmpxchg(top_mfn_p, &missing_mfn, mid_mfn_mfn)) {
 				p2m_top_mfn_p[topidx] = mid_mfn;
+			} else {
+				free_p2m_page(mid_mfn);
+				mid_mfn = mfn_to_virt(missing_mfn);
 			}
 		}
 	} else {