6 files changed, 147 insertions, 26 deletions
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 77e788e928cd..98d8a50d2aed 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,7 +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_64 || (X86_GENERIC || MPENTIUM4 || MATOM)
 	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/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5e57835e999d..dcc2041f8e61 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -73,6 +73,7 @@
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/cpu.h>
+#include <asm/irq_stack.h>
 #ifdef CONFIG_X86_IOPL_IOPERM
 #include <asm/io_bitmap.h>
 #endif
@@ -94,6 +95,44 @@ void *xen_initial_gdt;
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
 static int xen_cpu_dead_pv(unsigned int cpu);
 
+#ifndef CONFIG_PREEMPTION
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+/*
+ * In case of scheduling the flag must be cleared and restored after
+ * returning from schedule as the task might move to a different CPU.
+ */
+static __always_inline bool get_and_clear_inhcall(void)
+{
+	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
+
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+	return inhcall;
+}
+
+static __always_inline void restore_inhcall(bool inhcall)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
+}
+
+#else
+
+static __always_inline bool get_and_clear_inhcall(void) { return false; }
+static __always_inline void restore_inhcall(bool inhcall) { }
+
+#endif
+
 struct tls_descs {
 	struct desc_struct desc[3];
 };
@@ -687,6 +726,36 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check)
 }
 #endif
 
+static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	xen_evtchn_do_upcall();
+
+	set_irq_regs(old_regs);
+}
+
+__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+	bool inhcall;
+
+	instrumentation_begin();
+	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
+
+	inhcall = get_and_clear_inhcall();
+	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
+		irqentry_exit_cond_resched();
+		instrumentation_end();
+		restore_inhcall(inhcall);
+	} else {
+		instrumentation_end();
+		irqentry_exit(regs, state);
+	}
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c70cd35e72c..38971c6dcd4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
  */
 static DEFINE_SPINLOCK(xen_reservation_lock);
 
+/* Protected by xen_reservation_lock. */
+#define MIN_CONTIG_ORDER 9 /* 2MB */
+static unsigned int discontig_frames_order = MIN_CONTIG_ORDER;
+static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata;
+static unsigned long *discontig_frames __refdata = discontig_frames_early;
+static bool discontig_frames_dyn;
+
+static int alloc_discontig_frames(unsigned int order)
+{
+	unsigned long *new_array, *old_array;
+	unsigned int old_order;
+	unsigned long flags;
+
+	BUG_ON(order < MIN_CONTIG_ORDER);
+	BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE);
+
+	new_array = (unsigned long *)__get_free_pages(GFP_KERNEL,
+						      order - MIN_CONTIG_ORDER);
+	if (!new_array)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	old_order = discontig_frames_order;
+
+	if (order > discontig_frames_order || !discontig_frames_dyn) {
+		if (!discontig_frames_dyn)
+			old_array = NULL;
+		else
+			old_array = discontig_frames;
+
+		discontig_frames = new_array;
+		discontig_frames_order = order;
+		discontig_frames_dyn = true;
+	} else {
+		old_array = new_array;
+	}
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+
+	free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER);
+
+	return 0;
+}
+
 /*
  * Note about cr3 (pagetable base) values:
  *
@@ -814,6 +859,9 @@ static void __init xen_after_bootmem(void)
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
 	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
+
+	if (alloc_discontig_frames(MIN_CONTIG_ORDER))
+		BUG();
 }
 
 static void xen_unpin_page(struct mm_struct *mm, struct page *page,
@@ -2141,7 +2189,6 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.flush_tlb_kernel = xen_flush_tlb,
 		.flush_tlb_one_user = xen_flush_tlb_one_user,
 		.flush_tlb_multi = xen_flush_tlb_multi,
-		.tlb_remove_table = tlb_remove_table,
 
 		.pgd_alloc = xen_pgd_alloc,
 		.pgd_free = xen_pgd_free,
@@ -2203,10 +2250,6 @@ void __init xen_init_mmu_ops(void)
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
 
-/* Protected by xen_reservation_lock. */
-#define MAX_CONTIG_ORDER 9 /* 2MB */
-static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
-
 #define VOID_PTE (mfn_pte(0, __pgprot(0)))
 static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
 				unsigned long *in_frames,
@@ -2323,18 +2366,25 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
 {
-	unsigned long *in_frames = discontig_frames, out_frame;
+	unsigned long *in_frames, out_frame;
 	unsigned long  flags;
 	int            success;
 	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
 
-	if (unlikely(order > MAX_CONTIG_ORDER))
-		return -ENOMEM;
+	if (unlikely(order > discontig_frames_order)) {
+		if (!discontig_frames_dyn)
+			return -ENOMEM;
+
+		if (alloc_discontig_frames(order))
+			return -ENOMEM;
+	}
 
 	memset((void *) vstart, 0, PAGE_SIZE << order);
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
 
+	in_frames = discontig_frames;
+
 	/* 1. Zap current PTEs, remembering MFNs. */
 	xen_zap_pfn_range(vstart, order, in_frames, NULL);
 
@@ -2358,12 +2408,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
-	unsigned long *out_frames = discontig_frames, in_frame;
+	unsigned long *out_frames, in_frame;
 	unsigned long  flags;
 	int success;
 	unsigned long vstart;
 
-	if (unlikely(order > MAX_CONTIG_ORDER))
+	if (unlikely(order > discontig_frames_order))
 		return;
 
 	vstart = (unsigned long)phys_to_virt(pstart);
@@ -2371,6 +2421,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
 
+	out_frames = discontig_frames;
+
 	/* 1. Find start MFN of contiguous extent. */
 	in_frame = virt_to_mfn((void *)vstart);
 
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6863d3da7dec..688ff59318ae 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -70,7 +70,7 @@ static void cpu_bringup(void)
 		xen_enable_syscall();
 	}
 	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
+	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index b518f36d1ca2..109af12f7647 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -51,6 +51,7 @@ SYM_FUNC_END(xen_hypercall_pv)
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
+	ENDBR
 	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
@@ -90,6 +91,7 @@ SYM_FUNC_END(check_events)
  * then enter the hypervisor to get them handled.
  */
 SYM_FUNC_START(xen_irq_enable_direct)
+	ENDBR
 	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
@@ -120,6 +122,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
+	ENDBR
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
@@ -127,6 +130,7 @@ SYM_FUNC_START(xen_save_fl_direct)
 SYM_FUNC_END(xen_save_fl_direct)
 
 SYM_FUNC_START(xen_read_cr2)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
@@ -135,6 +139,7 @@ SYM_FUNC_START(xen_read_cr2)
 SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 9252652afe59..5dad6c51cdc3 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,16 +31,14 @@ SYM_CODE_START(startup_xen)
 
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
-	cdq
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi
@@ -100,9 +98,6 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	push %r10
 	push %r9
 	push %r8
-#ifdef CONFIG_FRAME_POINTER
-	pushq $0	/* Dummy push for stack alignment. */
-#endif
 #endif
 	/* Set the vendor specific function. */
 	call __xen_hypercall_setfunc
@@ -117,11 +112,8 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	pop %ebx
 	pop %eax
 #else
-	lea xen_hypercall_amd(%rip), %rbx
-	cmp %rax, %rbx
-#ifdef CONFIG_FRAME_POINTER
-	pop %rax	/* Dummy pop. */
-#endif
+	lea xen_hypercall_amd(%rip), %rcx
+	cmp %rax, %rcx
 	pop %r8
 	pop %r9
 	pop %r10
@@ -132,17 +124,20 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	pop %rcx
 	pop %rax
 #endif
+	FRAME_END
 	/* Use correct hypercall function. */
 	jz xen_hypercall_amd
 	jmp xen_hypercall_intel
 SYM_FUNC_END(xen_hypercall_hvm)
 
 SYM_FUNC_START(xen_hypercall_amd)
+	ANNOTATE_NOENDBR
 	vmmcall
 	RET
 SYM_FUNC_END(xen_hypercall_amd)
 
 SYM_FUNC_START(xen_hypercall_intel)
+	ANNOTATE_NOENDBR
 	vmcall
 	RET
 SYM_FUNC_END(xen_hypercall_intel)