Merge tag 'v6.8-rc4' into x86/percpu, to resolve conflicts and refresh the branch

Conflicts:
	arch/x86/include/asm/percpu.h
	arch/x86/include/asm/text-patching.h

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 90 insertions, 42 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 9b1ec5d8c99c..a65fc2ae15b4 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,6 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 7ad91225fdf4..9dd5490b3318 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -33,13 +33,13 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 	return 0xfd;
 }
 
-static u32 xen_set_apic_id(unsigned int x)
+static u32 xen_set_apic_id(u32 x)
 {
 	WARN_ON(1);
 	return x;
 }
 
-static unsigned int xen_get_apic_id(unsigned long x)
+static u32 xen_get_apic_id(u32 x)
 {
 	return ((x)>>24) & 0xFFu;
 }
@@ -110,15 +110,15 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
 	return xen_pv_domain();
 }
 
-static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
+static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb)
 {
 	return initial_apic_id >> index_msb;
 }
 
-static int xen_cpu_present_to_apicid(int cpu)
+static u32 xen_cpu_present_to_apicid(int cpu)
 {
 	if (cpu_present(cpu))
-		return cpu_data(cpu).apicid;
+		return cpu_data(cpu).topo.apicid;
 	else
 		return BAD_APICID;
 }
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 863d0d6b3edc..7250d0e0e1a9 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -138,7 +138,7 @@ void __init xen_efi_init(struct boot_params *boot_params)
 	if (efi_systab_xen == NULL)
 		return;
 
-	strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
+	strscpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
 			sizeof(boot_params->efi_info.efi_loader_signature));
 	boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
 	boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b8db2148c07d..3c61bb98c10e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -32,10 +32,13 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
  * but during boot it is switched to point to xen_vcpu_info.
- * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events.
+ * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
+ * Make sure that xen_vcpu_info doesn't cross a page boundary by making it
+ * cache-line aligned (the struct is guaranteed to have a size of 64 bytes,
+ * which matches the cache line size of 64-bit x86 processors).
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
-DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
@@ -160,6 +163,7 @@ void xen_vcpu_setup(int cpu)
 	int err;
 	struct vcpu_info *vcpup;
 
+	BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES);
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
 	/*
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9a192f51f1b0..3f8c34707c50 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -136,7 +136,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 49352fad7d1d..aeb33e0a3f76 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -101,6 +101,17 @@ struct tls_descs {
 	struct desc_struct desc[3];
 };
 
+DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE;
+DEFINE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+enum xen_lazy_mode xen_get_lazy_mode(void)
+{
+	if (in_interrupt())
+		return XEN_LAZY_NONE;
+
+	return this_cpu_read(xen_lazy_mode);
+}
+
 /*
  * Updating the 3 TLS descriptors in the GDT on every task switch is
  * surprisingly expensive so we avoid updating them if they haven't
@@ -362,10 +373,25 @@ static noinstr unsigned long xen_get_debugreg(int reg)
 	return HYPERVISOR_get_debugreg(reg);
 }
 
+static void xen_start_context_switch(struct task_struct *prev)
+{
+	BUG_ON(preemptible());
+
+	if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
+	enter_lazy(XEN_LAZY_CPU);
+}
+
 static void xen_end_context_switch(struct task_struct *next)
 {
+	BUG_ON(preemptible());
+
 	xen_mc_flush();
-	paravirt_end_context_switch(next);
+	leave_lazy(XEN_LAZY_CPU);
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 static unsigned long xen_store_tr(void)
@@ -472,7 +498,7 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gdt(const struct desc_ptr *dtr)
@@ -568,7 +594,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	 * exception between the new %fs descriptor being loaded and
 	 * %fs being effectively cleared at __switch_to().
 	 */
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+	if (xen_get_lazy_mode() == XEN_LAZY_CPU)
 		loadsegment(fs, 0);
 
 	xen_mc_batch();
@@ -577,7 +603,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	load_TLS_descriptor(t, cpu, 1);
 	load_TLS_descriptor(t, cpu, 2);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gs_index(unsigned int idx)
@@ -678,7 +704,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION
-	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
+	TRAP_ENTRY(int80_emulation,			false ),
 #endif
 	TRAP_ENTRY(exc_page_fault,			false ),
 	TRAP_ENTRY(exc_divide_error,			false ),
@@ -909,7 +935,7 @@ static void xen_load_sp0(unsigned long sp0)
 
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
@@ -973,7 +999,7 @@ static void xen_write_cr0(unsigned long cr0)
 
 	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_write_cr4(unsigned long cr4)
@@ -1156,7 +1182,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
 #endif
 		.io_delay = xen_io_delay,
 
-		.start_context_switch = paravirt_start_context_switch,
+		.start_context_switch = xen_start_context_switch,
 		.end_context_switch = xen_end_context_switch,
 	},
 };
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 6092fea7d651..39982f955cfe 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -45,7 +45,7 @@ static const typeof(pv_ops) xen_irq_ops __initconst = {
 		/* Initial interrupt flag handling only called while interrupts off. */
 		.save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0),
 		.irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop),
-		.irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG),
+		.irq_enable = __PV_IS_CALLEE_SAVE(BUG_func),
 
 		.safe_halt = xen_safe_halt,
 		.halt = xen_halt,
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1652c39e3dfb..72af496a160c 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -34,7 +34,7 @@
  * would need to validate the whole pagetable before going on.
  * Naturally, this is quite slow.  The solution is to "pin" a
  * pagetable, which enforces all the constraints on the pagetable even
- * when it is not actively in use.  This menas that Xen can be assured
+ * when it is not actively in use.  This means that Xen can be assured
  * that it is still valid when you do load it into %cr3, and doesn't
  * need to revalidate it.
  *
@@ -236,7 +236,7 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 	u.val = pmd_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -270,7 +270,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 {
 	struct mmu_update u;
 
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+	if (xen_get_lazy_mode() != XEN_LAZY_MMU)
 		return false;
 
 	xen_mc_batch();
@@ -279,7 +279,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 	u.val = pte_val_ma(pteval);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	return true;
 }
@@ -325,7 +325,7 @@ void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	u.val = pte_val_ma(pte);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 /* Assume pteval_t is equivalent to all the other *val_t types. */
@@ -419,7 +419,7 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 	u.val = pud_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -499,7 +499,7 @@ static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 
 	__xen_set_p4d_hyper(ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -531,7 +531,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 	if (user_ptr)
 		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 #if CONFIG_PGTABLE_LEVELS >= 5
@@ -1245,7 +1245,7 @@ static noinline void xen_flush_tlb(void)
 	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1265,7 +1265,7 @@ static void xen_flush_tlb_one_user(unsigned long addr)
 	op->arg1.linear_addr = addr & PAGE_MASK;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1302,7 +1302,7 @@ static void xen_flush_tlb_multi(const struct cpumask *cpus,
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 static unsigned long xen_read_cr3(void)
@@ -1361,7 +1361,7 @@ static void xen_write_cr3(unsigned long cr3)
 	else
 		__xen_write_cr3(false, 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 /*
@@ -1396,7 +1396,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 
 	__xen_write_cr3(true, cr3);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 static int xen_pgd_alloc(struct mm_struct *mm)
@@ -1557,7 +1557,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 	}
 }
 
@@ -1587,7 +1587,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 
 		__set_pfn_prot(pfn, PAGE_KERNEL);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 
 		ClearPagePinned(page);
 	}
@@ -1804,7 +1804,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	 */
 	xen_mc_batch();
 	__xen_write_cr3(true, __pa(init_top_pgt));
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 
 	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
 	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
@@ -2083,6 +2083,23 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
+static void xen_enter_lazy_mmu(void)
+{
+	enter_lazy(XEN_LAZY_MMU);
+}
+
+static void xen_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (xen_get_lazy_mode() == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 static void __init xen_post_allocator_init(void)
 {
 	pv_ops.mmu.set_pte = xen_set_pte;
@@ -2107,7 +2124,7 @@ static void xen_leave_lazy_mmu(void)
 {
 	preempt_disable();
 	xen_mc_flush();
-	paravirt_leave_lazy_mmu();
+	leave_lazy(XEN_LAZY_MMU);
 	preempt_enable();
 }
 
@@ -2166,9 +2183,9 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.exit_mmap = xen_exit_mmap,
 
 		.lazy_mode = {
-			.enter = paravirt_enter_lazy_mmu,
+			.enter = xen_enter_lazy_mmu,
 			.leave = xen_leave_lazy_mmu,
-			.flush = paravirt_flush_lazy_mmu,
+			.flush = xen_flush_lazy_mmu,
 		},
 
 		.set_fixmap = xen_set_fixmap,
@@ -2385,7 +2402,7 @@ static noinline void xen_flush_tlb_all(void)
 	op->cmd = MMUEXT_TLB_FLUSH_ALL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 1c51b2c87f30..c3867b585e0d 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -26,7 +26,7 @@ static inline void xen_mc_batch(void)
 
 	/* need to disable interrupts until this entry is complete */
 	local_irq_save(flags);
-	trace_xen_mc_batch(paravirt_get_lazy_mode());
+	trace_xen_mc_batch(xen_get_lazy_mode());
 	__this_cpu_write(xen_mc_irq_flags, flags);
 }
 
@@ -44,7 +44,7 @@ static inline void xen_mc_issue(unsigned mode)
 {
 	trace_xen_mc_issue(mode);
 
-	if ((paravirt_get_lazy_mode() & mode) == 0)
+	if ((xen_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
 	/* restore flags saved in xen_mc_batch */
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 448958ddbaf8..83189cf5cdce 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check
 #endif /* CONFIG_X86_MCE */
 xen_pv_trap asm_exc_simd_coprocessor_error
 #ifdef CONFIG_IA32_EMULATION
-xen_pv_trap entry_INT80_compat
+xen_pv_trap asm_int80_emulation
 #endif
 xen_pv_trap asm_exc_xen_unknown_trap
 xen_pv_trap asm_exc_xen_hypervisor_callback
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 408a2aa66c69..a87ab36889e7 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -21,7 +21,7 @@ extern void *xen_initial_gdt;
 struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
-DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 DECLARE_PER_CPU(unsigned long, xen_cr3);
 DECLARE_PER_CPU(unsigned long, xen_current_cr3);