Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

13 files changed, 104 insertions, 74 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index a65fc2ae15..77e788e928 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -81,7 +81,6 @@ config XEN_PVH
 	bool "Xen PVH guest support"
 	depends on XEN && XEN_PVHVM && ACPI
 	select PVH
-	def_bool n
 	help
 	  Support for running as a Xen PVH guest.
 
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 9dd5490b33..8b045dd251 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -33,12 +33,6 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 	return 0xfd;
 }
 
-static u32 xen_set_apic_id(u32 x)
-{
-	WARN_ON(1);
-	return x;
-}
-
 static u32 xen_get_apic_id(u32 x)
 {
 	return ((x)>>24) & 0xFFu;
@@ -49,20 +43,20 @@ static u32 xen_apic_read(u32 reg)
 	struct xen_platform_op op = {
 		.cmd = XENPF_get_cpuinfo,
 		.interface_version = XENPF_INTERFACE_VERSION,
-		.u.pcpu_info.xen_cpuid = 0,
 	};
-	int ret;
-
-	/* Shouldn't need this as APIC is turned off for PV, and we only
-	 * get called on the bootup processor. But just in case. */
-	if (!xen_initial_domain() || smp_processor_id())
-		return 0;
+	int ret, cpu;
 
 	if (reg == APIC_LVR)
 		return 0x14;
 	if (reg != APIC_ID)
 		return 0;
 
+	cpu = smp_processor_id();
+	if (!xen_initial_domain())
+		return cpu ? cpuid_to_apicid[cpu] << 24 : 0;
+
+	op.u.pcpu_info.xen_cpuid = cpu;
+
 	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		op.u.pcpu_info.apic_id = BAD_APICID;
@@ -110,11 +104,6 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
 	return xen_pv_domain();
 }
 
-static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb)
-{
-	return initial_apic_id >> index_msb;
-}
-
 static u32 xen_cpu_present_to_apicid(int cpu)
 {
 	if (cpu_present(cpu))
@@ -133,11 +122,9 @@ static struct apic xen_pv_apic __ro_after_init = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= xen_cpu_present_to_apicid,
-	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */
 
 	.max_apic_id			= UINT_MAX,
 	.get_apic_id			= xen_get_apic_id,
-	.set_apic_id			= xen_set_apic_id,
 
 	.calc_dest_apicid		= apic_flat_calc_apicid,
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a01ca255b0..b88722dfc4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -382,3 +382,36 @@ 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/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 3f8c34707c..c001a22965 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -148,7 +148,9 @@ static void xen_hvm_shutdown(void)
 	if (kexec_in_progress)
 		xen_reboot(SHUTDOWN_soft_reset);
 }
+#endif
 
+#ifdef CONFIG_CRASH_DUMP
 static void xen_hvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_machine_crash_shutdown(regs);
@@ -168,7 +170,7 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	 */
 	xen_uninit_lock_cpu(cpu);
 
-	if (cpu_acpi_id(cpu) != U32_MAX)
+	if (cpu_acpi_id(cpu) != CPU_ACPIID_INVALID)
 		per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
@@ -236,6 +238,8 @@ static void __init xen_hvm_guest_init(void)
 
 #ifdef CONFIG_KEXEC_CORE
 	machine_ops.shutdown = xen_hvm_shutdown;
+#endif
+#ifdef CONFIG_CRASH_DUMP
 	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
 #endif
 }
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index aeb33e0a3f..9ba53814ed 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -200,6 +200,9 @@ static void __init xen_pv_init_platform(void)
 		xen_set_mtrr_data();
 	else
 		mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
+
+	/* Adjust nr_cpu_ids before "enumeration" happens */
+	xen_smp_count_cpus();
 }
 
 static void __init xen_pv_guest_late_init(void)
@@ -216,13 +219,21 @@ static __read_mostly unsigned int cpuid_leaf5_edx_val;
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		      unsigned int *cx, unsigned int *dx)
 {
-	unsigned maskebx = ~0;
+	unsigned int maskebx = ~0;
+	unsigned int or_ebx = 0;
 
 	/*
 	 * Mask out inconvenient features, to try and disable as many
 	 * unsupported kernel subsystems as possible.
 	 */
 	switch (*ax) {
+	case 0x1:
+		/* Replace initial APIC ID in bits 24-31 of EBX. */
+		/* See xen_pv_smp_config() for related topology preparations. */
+		maskebx = 0x00ffffff;
+		or_ebx = smp_processor_id() << 24;
+		break;
+
 	case CPUID_MWAIT_LEAF:
 		/* Synthesize the values.. */
 		*ax = 0;
@@ -245,6 +256,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		: "0" (*ax), "2" (*cx));
 
 	*bx &= maskebx;
+	*bx |= or_ebx;
 }
 
 static bool __init xen_check_mwait(void)
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index c28f073c1d..27a2a02ef8 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -5,6 +5,7 @@
 
 #include <xen/hvc-console.h>
 
+#include <asm/bootparam.h>
 #include <asm/io_apic.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 994aef4473..54e0d311dc 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -913,7 +913,7 @@ static void drop_mm_ref_this_cpu(void *info)
 	struct mm_struct *mm = info;
 
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm)
-		leave_mm(smp_processor_id());
+		leave_mm();
 
 	/*
 	 * If this cpu still has a stale cr3 reference, then make sure
@@ -1059,7 +1059,7 @@ static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin)
 	pte_t *pte_tbl;
 	int i;
 
-	if (pmd_large(*pmd)) {
+	if (pmd_leaf(*pmd)) {
 		pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
 		xen_free_ro_pages(pa, PMD_SIZE);
 		return;
@@ -1104,7 +1104,7 @@ static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin)
 	pud_t *pud_tbl;
 	int i;
 
-	if (p4d_large(*p4d)) {
+	if (p4d_leaf(*p4d)) {
 		pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK;
 		xen_free_ro_pages(pa, P4D_SIZE);
 		return;
@@ -1871,7 +1871,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 	if (!pmd_present(pmd))
 		return 0;
 	pa = pmd_val(pmd) & PTE_PFN_MASK;
-	if (pmd_large(pmd))
+	if (pmd_leaf(pmd))
 		return pa + (vaddr & ~PMD_MASK);
 
 	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
@@ -2520,7 +2520,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(xen_remap_pfn);
 
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_VMCORE_INFO
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 1fb9a1644d..935771726f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -135,8 +135,6 @@ void __init xen_smp_cpus_done(unsigned int max_cpus)
 {
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
-	else
-		calculate_max_logical_packages();
 }
 
 void xen_smp_send_reschedule(int cpu)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c20cbb14c8..b8efdbc693 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -19,6 +19,7 @@ extern void xen_smp_intr_free(unsigned int cpu);
 int xen_smp_intr_init_pv(unsigned int cpu);
 void xen_smp_intr_free_pv(unsigned int cpu);
 
+void xen_smp_count_cpus(void);
 void xen_smp_cpus_done(unsigned int max_cpus);
 
 void xen_smp_send_reschedule(int cpu);
@@ -44,6 +45,7 @@ static inline int xen_smp_intr_init_pv(unsigned int cpu)
 	return 0;
 }
 static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
+static inline void xen_smp_count_cpus(void) { }
 #endif /* CONFIG_SMP */
 
 #endif
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index a0f07bbfcd..ac41d83b38 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -29,6 +29,7 @@
 #include <asm/idtentry.h>
 #include <asm/desc.h>
 #include <asm/cpu.h>
+#include <asm/apic.h>
 #include <asm/io_apic.h>
 
 #include <xen/interface/xen.h>
@@ -73,7 +74,6 @@ static void cpu_bringup(void)
 	}
 	cpu = smp_processor_id();
 	smp_store_cpu_info(cpu);
-	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
@@ -149,39 +149,16 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	return rc;
 }
 
-static void __init _get_smp_config(unsigned int early)
+static void __init xen_pv_smp_config(void)
 {
-	int i, rc;
-	unsigned int subtract = 0;
-
-	if (early)
-		return;
-
-	num_processors = 0;
-	disabled_cpus = 0;
-	for (i = 0; i < nr_cpu_ids; i++) {
-		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
-		if (rc >= 0) {
-			num_processors++;
-			set_cpu_possible(i, true);
-		} else {
-			set_cpu_possible(i, false);
-			set_cpu_present(i, false);
-			subtract++;
-		}
-	}
-#ifdef CONFIG_HOTPLUG_CPU
-	/* This is akin to using 'nr_cpus' on the Linux command line.
-	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
-	 * have up to X, while nr_cpu_ids is greater than X. This
-	 * normally is not a problem, except when CPU hotplugging
-	 * is involved and then there might be more than X CPUs
-	 * in the guest - which will not work as there is no
-	 * hypercall to expand the max number of VCPUs an already
-	 * running guest has. So cap it up to X. */
-	if (subtract)
-		set_nr_cpu_ids(nr_cpu_ids - subtract);
-#endif
+	u32 apicid = 0;
+	int i;
+
+	topology_register_boot_apic(apicid);
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		topology_register_apic(apicid++, CPU_ACPIID_INVALID, true);
+
 	/* Pretend to be a proper enumerated system */
 	smp_found_config = 1;
 }
@@ -224,8 +201,6 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 
 	smp_prepare_cpus_common();
 
-	cpu_data(0).x86_max_cores = 1;
-
 	speculative_store_bypass_ht_init();
 
 	xen_pmu_init(0);
@@ -434,6 +409,20 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+void __init xen_smp_count_cpus(void)
+{
+	unsigned int cpus;
+
+	for (cpus = 0; cpus < nr_cpu_ids; cpus++) {
+		if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0)
+			break;
+	}
+
+	pr_info("Xen PV: Detected %u vCPUS\n", cpus);
+	if (cpus < nr_cpu_ids)
+		set_nr_cpu_ids(cpus);
+}
+
 static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
@@ -458,6 +447,12 @@ void __init xen_smp_init(void)
 	smp_ops = xen_smp_ops;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = _get_smp_config;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+
+	/* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */
+	if (xen_initial_domain())
+		x86_init.mpparse.parse_smp_cfg	= x86_init_noop;
+	else
+		x86_init.mpparse.parse_smp_cfg	= xen_pv_smp_config;
 }
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index d97adab842..f7547807b0 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -2,7 +2,6 @@
 #include <linux/screen_info.h>
 #include <linux/init.h>
 
-#include <asm/bootparam.h>
 #include <asm/setup.h>
 
 #include <xen/interface/xen.h>
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1a9cd18dfb..83189cf5cd 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -28,7 +28,7 @@
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
-	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
 
@@ -69,7 +69,7 @@ SYM_FUNC_END(check_events)
 SYM_FUNC_START(xen_irq_enable_direct)
 	FRAME_BEGIN
 	/* Unmask events */
-	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 
 	/*
 	 * Preempt here doesn't matter because that will deal with any
@@ -78,7 +78,7 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	 */
 
 	/* Test for pending */
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
 	jz 1f
 
 	call check_events
@@ -97,7 +97,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
 	RET
@@ -113,7 +113,7 @@ SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_BEGIN
-	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
+	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
 	RET
 SYM_FUNC_END(xen_read_cr2_direct);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index a0ea285878..04101b984f 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen)
 	ANNOTATE_NOENDBR
 	cld
 
-	leaq	(__end_init_task - PTREGS_SIZE)(%rip), %rsp
+	leaq	(__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
 
 	/* Set up %gs.
 	 *