7 files changed, 47 insertions, 292 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 78a881b7fc41..bd8b8459c3d0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1494,10 +1494,10 @@ static void xen_pvh_set_cr_flags(int cpu)
 	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
 	*/
 	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
+		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	if (cpu_has_pge)
-		set_in_cr4(X86_CR4_PGE);
+		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 }
 
 /*
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5c1f9ace7ae7..adca9e2b6553 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1489,7 +1489,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 	native_set_pte(ptep, pte);
 }
 
-static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 {
 	struct mmuext_op op;
 	op.cmd = cmd;
@@ -1657,7 +1657,7 @@ void __init xen_reserve_top(void)
  * Like __va(), but returns address in the kernel mapping (which is
  * all we have until the physical memory mapping has been set up.
  */
-static void *__ka(phys_addr_t paddr)
+static void * __init __ka(phys_addr_t paddr)
 {
 #ifdef CONFIG_X86_64
 	return (void *)(paddr + __START_KERNEL_map);
@@ -1667,7 +1667,7 @@ static void *__ka(phys_addr_t paddr)
 }
 
 /* Convert a machine address to physical address */
-static unsigned long m2p(phys_addr_t maddr)
+static unsigned long __init m2p(phys_addr_t maddr)
 {
 	phys_addr_t paddr;
 
@@ -1678,13 +1678,14 @@ static unsigned long m2p(phys_addr_t maddr)
 }
 
 /* Convert a machine address to kernel virtual */
-static void *m2v(phys_addr_t maddr)
+static void * __init m2v(phys_addr_t maddr)
 {
 	return __ka(m2p(maddr));
 }
 
 /* Set the page permissions on an identity-mapped pages */
-static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags)
+static void __init set_page_prot_flags(void *addr, pgprot_t prot,
+				       unsigned long flags)
 {
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
 	pte_t pte = pfn_pte(pfn, prot);
@@ -1696,7 +1697,7 @@ static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags)
 	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
 		BUG();
 }
-static void set_page_prot(void *addr, pgprot_t prot)
+static void __init set_page_prot(void *addr, pgprot_t prot)
 {
 	return set_page_prot_flags(addr, prot, UVMF_NONE);
 }
@@ -1733,10 +1734,8 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
-#ifdef CONFIG_X86_32
 			if (pfn > max_pfn_mapped)
 				max_pfn_mapped = pfn;
-#endif
 
 			if (!pte_none(pte_page[pteidx]))
 				continue;
@@ -1769,7 +1768,7 @@ void __init xen_setup_machphys_mapping(void)
 }
 
 #ifdef CONFIG_X86_64
-static void convert_pfn_mfn(void *v)
+static void __init convert_pfn_mfn(void *v)
 {
 	pte_t *pte = v;
 	int i;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 70fb5075c901..740ae3026a14 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -84,8 +84,6 @@
 
 #define PMDS_PER_MID_PAGE	(P2M_MID_PER_PAGE / PTRS_PER_PTE)
 
-static void __init m2p_override_init(void);
-
 unsigned long *xen_p2m_addr __read_mostly;
 EXPORT_SYMBOL_GPL(xen_p2m_addr);
 unsigned long xen_p2m_size __read_mostly;
@@ -402,8 +400,6 @@ void __init xen_vmalloc_p2m_tree(void)
 	xen_p2m_size = xen_max_p2m_pfn;
 
 	xen_inv_extra_mem();
-
-	m2p_override_init();
 }
 
 unsigned long get_phys_to_machine(unsigned long pfn)
@@ -554,7 +550,7 @@ static bool alloc_p2m(unsigned long pfn)
 		mid_mfn = NULL;
 	}
 
-	p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep));
+	p2m_pfn = pte_pfn(READ_ONCE(*ptep));
 	if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
 	    p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
 		/* p2m leaf page is missing */
@@ -652,100 +648,21 @@ bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 	return true;
 }
 
-#define M2P_OVERRIDE_HASH_SHIFT	10
-#define M2P_OVERRIDE_HASH	(1 << M2P_OVERRIDE_HASH_SHIFT)
-
-static struct list_head *m2p_overrides;
-static DEFINE_SPINLOCK(m2p_override_lock);
-
-static void __init m2p_override_init(void)
-{
-	unsigned i;
-
-	m2p_overrides = alloc_bootmem_align(
-				sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
-				sizeof(unsigned long));
-
-	for (i = 0; i < M2P_OVERRIDE_HASH; i++)
-		INIT_LIST_HEAD(&m2p_overrides[i]);
-}
-
-static unsigned long mfn_hash(unsigned long mfn)
-{
-	return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT);
-}
-
-/* Add an MFN override for a particular page */
-static int m2p_add_override(unsigned long mfn, struct page *page,
-			    struct gnttab_map_grant_ref *kmap_op)
-{
-	unsigned long flags;
-	unsigned long pfn;
-	unsigned long uninitialized_var(address);
-	unsigned level;
-	pte_t *ptep = NULL;
-
-	pfn = page_to_pfn(page);
-	if (!PageHighMem(page)) {
-		address = (unsigned long)__va(pfn << PAGE_SHIFT);
-		ptep = lookup_address(address, &level);
-		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
-			 "m2p_add_override: pfn %lx not mapped", pfn))
-			return -EINVAL;
-	}
-
-	if (kmap_op != NULL) {
-		if (!PageHighMem(page)) {
-			struct multicall_space mcs =
-				xen_mc_entry(sizeof(*kmap_op));
-
-			MULTI_grant_table_op(mcs.mc,
-					GNTTABOP_map_grant_ref, kmap_op, 1);
-
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-		}
-	}
-	spin_lock_irqsave(&m2p_override_lock, flags);
-	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
-	spin_unlock_irqrestore(&m2p_override_lock, flags);
-
-	/* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
-	 * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
-	 * pfn so that the following mfn_to_pfn(mfn) calls will return the
-	 * pfn from the m2p_override (the backend pfn) instead.
-	 * We need to do this because the pages shared by the frontend
-	 * (xen-blkfront) can be already locked (lock_page, called by
-	 * do_read_cache_page); when the userspace backend tries to use them
-	 * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
-	 * do_blockdev_direct_IO is going to try to lock the same pages
-	 * again resulting in a deadlock.
-	 * As a side effect get_user_pages_fast might not be safe on the
-	 * frontend pages while they are being shared with the backend,
-	 * because mfn_to_pfn (that ends up being called by GUPF) will
-	 * return the backend pfn rather than the frontend pfn. */
-	pfn = mfn_to_pfn_no_overrides(mfn);
-	if (__pfn_to_mfn(pfn) == mfn)
-		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
-
-	return 0;
-}
-
 int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 			    struct gnttab_map_grant_ref *kmap_ops,
 			    struct page **pages, unsigned int count)
 {
 	int i, ret = 0;
-	bool lazy = false;
 	pte_t *pte;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
-	if (kmap_ops &&
-	    !in_interrupt() &&
-	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
-		arch_enter_lazy_mmu_mode();
-		lazy = true;
+	if (kmap_ops) {
+		ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref,
+						kmap_ops, count);
+		if (ret)
+			goto out;
 	}
 
 	for (i = 0; i < count; i++) {
@@ -764,170 +681,28 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 		}
 		pfn = page_to_pfn(pages[i]);
 
-		WARN_ON(PagePrivate(pages[i]));
-		SetPagePrivate(pages[i]);
-		set_page_private(pages[i], mfn);
-		pages[i]->index = pfn_to_mfn(pfn);
+		WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned");
 
 		if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
 			ret = -ENOMEM;
 			goto out;
 		}
-
-		if (kmap_ops) {
-			ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
-			if (ret)
-				goto out;
-		}
 	}
 
 out:
-	if (lazy)
-		arch_leave_lazy_mmu_mode();
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
 
-static struct page *m2p_find_override(unsigned long mfn)
-{
-	unsigned long flags;
-	struct list_head *bucket;
-	struct page *p, *ret;
-
-	if (unlikely(!m2p_overrides))
-		return NULL;
-
-	ret = NULL;
-	bucket = &m2p_overrides[mfn_hash(mfn)];
-
-	spin_lock_irqsave(&m2p_override_lock, flags);
-
-	list_for_each_entry(p, bucket, lru) {
-		if (page_private(p) == mfn) {
-			ret = p;
-			break;
-		}
-	}
-
-	spin_unlock_irqrestore(&m2p_override_lock, flags);
-
-	return ret;
-}
-
-static int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
-			       unsigned long mfn)
-{
-	unsigned long flags;
-	unsigned long pfn;
-	unsigned long uninitialized_var(address);
-	unsigned level;
-	pte_t *ptep = NULL;
-
-	pfn = page_to_pfn(page);
-
-	if (!PageHighMem(page)) {
-		address = (unsigned long)__va(pfn << PAGE_SHIFT);
-		ptep = lookup_address(address, &level);
-
-		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
-			 "m2p_remove_override: pfn %lx not mapped", pfn))
-			return -EINVAL;
-	}
-
-	spin_lock_irqsave(&m2p_override_lock, flags);
-	list_del(&page->lru);
-	spin_unlock_irqrestore(&m2p_override_lock, flags);
-
-	if (kmap_op != NULL) {
-		if (!PageHighMem(page)) {
-			struct multicall_space mcs;
-			struct gnttab_unmap_and_replace *unmap_op;
-			struct page *scratch_page = get_balloon_scratch_page();
-			unsigned long scratch_page_address = (unsigned long)
-				__va(page_to_pfn(scratch_page) << PAGE_SHIFT);
-
-			/*
-			 * It might be that we queued all the m2p grant table
-			 * hypercalls in a multicall, then m2p_remove_override
-			 * get called before the multicall has actually been
-			 * issued. In this case handle is going to -1 because
-			 * it hasn't been modified yet.
-			 */
-			if (kmap_op->handle == -1)
-				xen_mc_flush();
-			/*
-			 * Now if kmap_op->handle is negative it means that the
-			 * hypercall actually returned an error.
-			 */
-			if (kmap_op->handle == GNTST_general_error) {
-				pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings",
-					pfn, mfn);
-				put_balloon_scratch_page();
-				return -1;
-			}
-
-			xen_mc_batch();
-
-			mcs = __xen_mc_entry(
-				sizeof(struct gnttab_unmap_and_replace));
-			unmap_op = mcs.args;
-			unmap_op->host_addr = kmap_op->host_addr;
-			unmap_op->new_addr = scratch_page_address;
-			unmap_op->handle = kmap_op->handle;
-
-			MULTI_grant_table_op(mcs.mc,
-				GNTTABOP_unmap_and_replace, unmap_op, 1);
-
-			mcs = __xen_mc_entry(0);
-			MULTI_update_va_mapping(mcs.mc, scratch_page_address,
-					pfn_pte(page_to_pfn(scratch_page),
-					PAGE_KERNEL_RO), 0);
-
-			xen_mc_issue(PARAVIRT_LAZY_MMU);
-
-			kmap_op->host_addr = 0;
-			put_balloon_scratch_page();
-		}
-	}
-
-	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
-	 * somewhere in this domain, even before being added to the
-	 * m2p_override (see comment above in m2p_add_override).
-	 * If there are no other entries in the m2p_override corresponding
-	 * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
-	 * the original pfn (the one shared by the frontend): the backend
-	 * cannot do any IO on this page anymore because it has been
-	 * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
-	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
-	 * pfn again. */
-	mfn &= ~FOREIGN_FRAME_BIT;
-	pfn = mfn_to_pfn_no_overrides(mfn);
-	if (__pfn_to_mfn(pfn) == FOREIGN_FRAME(mfn) &&
-			m2p_find_override(mfn) == NULL)
-		set_phys_to_machine(pfn, mfn);
-
-	return 0;
-}
-
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
-			      struct gnttab_map_grant_ref *kmap_ops,
+			      struct gnttab_unmap_grant_ref *kunmap_ops,
 			      struct page **pages, unsigned int count)
 {
 	int i, ret = 0;
-	bool lazy = false;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
-	if (kmap_ops &&
-	    !in_interrupt() &&
-	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
-		arch_enter_lazy_mmu_mode();
-		lazy = true;
-	}
-
 	for (i = 0; i < count; i++) {
 		unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
 		unsigned long pfn = page_to_pfn(pages[i]);
@@ -937,36 +712,16 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 			goto out;
 		}
 
-		set_page_private(pages[i], INVALID_P2M_ENTRY);
-		WARN_ON(!PagePrivate(pages[i]));
-		ClearPagePrivate(pages[i]);
-		set_phys_to_machine(pfn, pages[i]->index);
-
-		if (kmap_ops)
-			ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
-		if (ret)
-			goto out;
+		set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 	}
-
+	if (kunmap_ops)
+		ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref,
+						kunmap_ops, count);
 out:
-	if (lazy)
-		arch_leave_lazy_mmu_mode();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
 
-unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
-{
-	struct page *p = m2p_find_override(mfn);
-	unsigned long ret = pfn;
-
-	if (p)
-		ret = page_to_pfn(p);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
-
 #ifdef CONFIG_XEN_DEBUG_FS
 #include <linux/debugfs.h>
 #include "debugfs.h"
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 865e56cea7a0..55f388ef481a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -32,16 +32,6 @@
 #include "p2m.h"
 #include "mmu.h"
 
-/* These are code, but not functions.  Defined in entry.S */
-extern const char xen_hypervisor_callback[];
-extern const char xen_failsafe_callback[];
-#ifdef CONFIG_X86_64
-extern asmlinkage void nmi(void);
-#endif
-extern void xen_sysenter_target(void);
-extern void xen_syscall_target(void);
-extern void xen_syscall32_target(void);
-
 /* Amount of extra memory space we add to the e820 ranges */
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
@@ -74,7 +64,7 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
  */
 #define EXTRA_MEM_RATIO		(10)
 
-static void __init xen_add_extra_mem(u64 start, u64 size)
+static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size)
 {
 	int i;
 
@@ -97,10 +87,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	memblock_reserve(start, size);
 }
 
-static void __init xen_del_extra_mem(u64 start, u64 size)
+static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size)
 {
 	int i;
-	u64 start_r, size_r;
+	phys_addr_t start_r, size_r;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
 		start_r = xen_extra_mem[i].start;
@@ -267,7 +257,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
 {
 	struct mmu_update update = {
-		.ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
+		.ptr = ((uint64_t)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
 		.val = pfn
 	};
 
@@ -545,20 +535,21 @@ static unsigned long __init xen_get_max_pages(void)
 	return min(max_pages, MAX_DOMAIN_PAGES);
 }
 
-static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
+static void __init xen_align_and_add_e820_region(phys_addr_t start,
+						 phys_addr_t size, int type)
 {
-	u64 end = start + size;
+	phys_addr_t end = start + size;
 
 	/* Align RAM regions to page boundaries. */
 	if (type == E820_RAM) {
 		start = PAGE_ALIGN(start);
-		end &= ~((u64)PAGE_SIZE - 1);
+		end &= ~((phys_addr_t)PAGE_SIZE - 1);
 	}
 
 	e820_add_region(start, end - start, type);
 }
 
-void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size)
 {
 	struct e820entry *entry;
 	unsigned int i;
@@ -577,7 +568,7 @@ char * __init xen_memory_setup(void)
 	static struct e820entry map[E820MAX] __initdata;
 
 	unsigned long max_pfn = xen_start_info->nr_pages;
-	unsigned long long mem_end;
+	phys_addr_t mem_end;
 	int rc;
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
@@ -652,16 +643,16 @@ char * __init xen_memory_setup(void)
 			  extra_pages);
 	i = 0;
 	while (i < memmap.nr_entries) {
-		u64 addr = map[i].addr;
-		u64 size = map[i].size;
+		phys_addr_t addr = map[i].addr;
+		phys_addr_t size = map[i].size;
 		u32 type = map[i].type;
 
 		if (type == E820_RAM) {
 			if (addr < mem_end) {
 				size = min(size, mem_end - addr);
 			} else if (extra_pages) {
-				size = min(size, (u64)extra_pages * PAGE_SIZE);
-				extra_pages -= size / PAGE_SIZE;
+				size = min(size, PFN_PHYS(extra_pages));
+				extra_pages -= PFN_DOWN(size);
 				xen_add_extra_mem(addr, size);
 				xen_max_p2m_pfn = PFN_DOWN(addr + size);
 			} else
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4c071aeb8417..08e8489c47f1 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -507,7 +507,7 @@ static int xen_cpu_disable(void)
 static void xen_cpu_die(unsigned int cpu)
 {
 	while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
-		current->state = TASK_UNINTERRUPTIBLE;
+		__set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(HZ/10);
 	}
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 69087341d9ae..55da33b1d51c 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -479,6 +479,10 @@ static void __init xen_time_init(void)
 	int cpu = smp_processor_id();
 	struct timespec tp;
 
+	/* As Dom0 is never moved, no penalty on using TSC there */
+	if (xen_initial_domain())
+		xen_clocksource.rating = 275;
+
 	clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 5686bd9d58cc..9e195c683549 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -10,6 +10,12 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
+void xen_sysenter_target(void);
+#ifdef CONFIG_X86_64
+void xen_syscall_target(void);
+void xen_syscall32_target(void);
+#endif
+
 extern void *xen_initial_gdt;
 
 struct trap_info;