x86: Convert the rest of the code to support p4d_t

This patch converts x86 to use proper folding of a new (fifth) page table level
with <asm-generic/pgtable-nop4d.h>.

That's a bit of a kitchen sink patch, but I don't see how to split it further
without hurting bisectability.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20170317185515.8636-7-kirill.shutemov@linux.intel.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/paravirt.h

@@ -536,7 +536,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
 			    val);
 }
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 static inline pud_t __pud(pudval_t val)
 {
 	pudval_t ret;
@@ -565,6 +565,32 @@ static inline pudval_t pud_val(pud_t pud)
 	return ret;
 }
 
+static inline void pud_clear(pud_t *pudp)
+{
+	set_pud(pudp, __pud(0));
+}
+
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	p4dval_t val = native_p4d_val(p4d);
+
+	if (sizeof(p4dval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp,
+			    val, (u64)val >> 32);
+	else
+		PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp,
+			    val);
+}
+
+static inline void p4d_clear(p4d_t *p4dp)
+{
+	set_p4d(p4dp, __p4d(0));
+}
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+
+#error FIXME
+
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	pgdval_t val = native_pgd_val(pgd);
@@ -582,10 +608,7 @@ static inline void pgd_clear(pgd_t *pgdp)
 	set_pgd(pgdp, __pgd(0));
 }
 
-static inline void pud_clear(pud_t *pudp)
-{
-	set_pud(pudp, __pud(0));
-}
+#endif  /* CONFIG_PGTABLE_LEVELS == 5 */
 
 #endif	/* CONFIG_PGTABLE_LEVELS == 4 */
 

arch/x86/include/asm/paravirt_types.h

@@ -279,12 +279,18 @@ struct pv_mmu_ops {
 	struct paravirt_callee_save pmd_val;
 	struct paravirt_callee_save make_pmd;
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	struct paravirt_callee_save pud_val;
 	struct paravirt_callee_save make_pud;
 
-	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
-#endif	/* CONFIG_PGTABLE_LEVELS == 4 */
+	void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval);
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+#error FIXME
+#endif	/* CONFIG_PGTABLE_LEVELS >= 5 */
+
+#endif	/* CONFIG_PGTABLE_LEVELS >= 4 */
+
 #endif	/* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	struct pv_lazy_ops lazy_mode;

arch/x86/include/asm/pgalloc.h

@@ -121,10 +121,10 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 #endif	/* CONFIG_X86_PAE */
 
 #if CONFIG_PGTABLE_LEVELS > 3
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
 {
 	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
-	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
+	set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud)));
 }
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -150,6 +150,37 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 	___pud_free_tlb(tlb, pud);
 }
 
+#if CONFIG_PGTABLE_LEVELS > 4
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
+{
+	paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
+	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
+}
+
+static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_KERNEL_ACCOUNT;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	return (p4d_t *)get_zeroed_page(gfp);
+}
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	free_page((unsigned long)p4d);
+}
+
+extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
+
+static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
+				  unsigned long address)
+{
+	___p4d_free_tlb(tlb, p4d);
+}
+
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 2 */
 

arch/x86/include/asm/pgtable.h

@@ -53,11 +53,19 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 
 #define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)
 
-#ifndef __PAGETABLE_PUD_FOLDED
+#ifndef __PAGETABLE_P4D_FOLDED
 #define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
 #define pgd_clear(pgd)			native_pgd_clear(pgd)
 #endif
 
+#ifndef set_p4d
+# define set_p4d(p4dp, p4d)		native_set_p4d(p4dp, p4d)
+#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define p4d_clear(p4d)			native_p4d_clear(p4d)
+#endif
+
 #ifndef set_pud
 # define set_pud(pudp, pud)		native_set_pud(pudp, pud)
 #endif
@@ -74,6 +82,11 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)
 
+#ifndef __PAGETABLE_P4D_FOLDED
+#define p4d_val(x)	native_p4d_val(x)
+#define __p4d(x)	native_make_p4d(x)
+#endif
+
 #ifndef __PAGETABLE_PUD_FOLDED
 #define pud_val(x)	native_pud_val(x)
 #define __pud(x)	native_make_pud(x)
@@ -554,6 +567,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define pte_pgprot(x) __pgprot(pte_flags(x))
 #define pmd_pgprot(x) __pgprot(pmd_flags(x))
 #define pud_pgprot(x) __pgprot(pud_flags(x))
+#define p4d_pgprot(x) __pgprot(p4d_flags(x))
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
@@ -792,12 +806,47 @@ static inline unsigned long pud_index(unsigned long address)
 	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
 }
 
+#if CONFIG_PGTABLE_LEVELS > 3
+static inline int p4d_none(p4d_t p4d)
+{
+	return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+	return p4d_flags(p4d) & _PAGE_PRESENT;
+}
+
+static inline unsigned long p4d_page_vaddr(p4d_t p4d)
+{
+	return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(p4d));
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define p4d_page(p4d)		\
+	pfn_to_page((p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT)
+
+/* Find an entry in the third-level page table.. */
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address);
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+#endif  /* CONFIG_PGTABLE_LEVELS > 3 */
+
 static inline unsigned long p4d_index(unsigned long address)
 {
 	return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1);
 }
 
-#if CONFIG_PGTABLE_LEVELS > 3
+#if CONFIG_PGTABLE_LEVELS > 4
 static inline int pgd_present(pgd_t pgd)
 {
 	return pgd_flags(pgd) & _PAGE_PRESENT;
@@ -815,9 +864,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 #define pgd_page(pgd)		pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
 
 /* to find an entry in a page-table-directory. */
-static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -835,7 +884,7 @@ static inline int pgd_none(pgd_t pgd)
 	 */
 	return !native_pgd_val(pgd);
 }
-#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 
 #endif	/* __ASSEMBLY__ */
 

arch/x86/include/asm/pgtable_64.h

@@ -41,9 +41,9 @@ extern void paging_init(void);
 
 struct mm_struct;
 
+void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
 void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
 
-
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
@@ -121,6 +121,16 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	*p4dp = p4d;
+}
+
+static inline void native_p4d_clear(p4d_t *p4d)
+{
+	native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)});
+}
+
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	*pgdp = pgd;

arch/x86/include/asm/pgtable_types.h

@@ -277,11 +277,11 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
 #error FIXME
 
 #else
-#include <asm-generic/5level-fixup.h>
+#include <asm-generic/pgtable-nop4d.h>
 
 static inline p4dval_t native_p4d_val(p4d_t p4d)
 {
-	return native_pgd_val(p4d);
+	return native_pgd_val(p4d.pgd);
 }
 #endif
 
@@ -298,12 +298,11 @@ static inline pudval_t native_pud_val(pud_t pud)
 	return pud.pud;
 }
 #else
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 static inline pudval_t native_pud_val(pud_t pud)
 {
-	return native_pgd_val(pud.pgd);
+	return native_pgd_val(pud.p4d.pgd);
 }
 #endif
 
@@ -320,12 +319,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 	return pmd.pmd;
 }
 #else
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
-	return native_pgd_val(pmd.pud.pgd);
+	return native_pgd_val(pmd.pud.p4d.pgd);
 }
 #endif
 

arch/x86/include/asm/xen/page.h

@@ -279,13 +279,17 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pmd_val_ma(v) ((v).pmd)
 #ifdef __PAGETABLE_PUD_FOLDED
-#define pud_val_ma(v) ((v).pgd.pgd)
+#define pud_val_ma(v) ((v).p4d.pgd.pgd)
 #else
 #define pud_val_ma(v) ((v).pud)
 #endif
 #define __pmd_ma(x)	((pmd_t) { (x) } )
 
-#define pgd_val_ma(x)	((x).pgd)
+#ifdef __PAGETABLE_P4D_FOLDED
+#define p4d_val_ma(x)	((x).pgd.pgd)
+#else
+#define p4d_val_ma(x)	((x).p4d)
+#endif
 
 void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 

arch/x86/kernel/paravirt.c

@@ -430,12 +430,16 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.pmd_val = PTE_IDENT,
 	.make_pmd = PTE_IDENT,
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	.pud_val = PTE_IDENT,
 	.make_pud = PTE_IDENT,
 
-	.set_pgd = native_set_pgd,
-#endif
+	.set_p4d = native_set_p4d,
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+#error FIXME
+#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
+#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
 #endif /* CONFIG_PGTABLE_LEVELS >= 3 */
 
 	.pte_val = PTE_IDENT,

arch/x86/xen/mmu.c

@@ -535,40 +535,41 @@ static pgd_t *xen_get_user_pgd(pgd_t *pgd)
 	return user_ptr;
 }
 
-static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 {
 	struct mmu_update u;
 
 	u.ptr = virt_to_machine(ptr).maddr;
-	u.val = pgd_val_ma(val);
+	u.val = p4d_val_ma(val);
 	xen_extend_mmu_update(&u);
 }
 
 /*
- * Raw hypercall-based set_pgd, intended for in early boot before
+ * Raw hypercall-based set_p4d, intended for in early boot before
  * there's a page structure.  This implies:
  *  1. The only existing pagetable is the kernel's
  *  2. It is always pinned
  *  3. It has no user pagetable attached to it
  */
-static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 {
 	preempt_disable();
 
 	xen_mc_batch();
 
-	__xen_set_pgd_hyper(ptr, val);
+	__xen_set_p4d_hyper(ptr, val);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 
 	preempt_enable();
 }
 
-static void xen_set_pgd(pgd_t *ptr, pgd_t val)
+static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 {
-	pgd_t *user_ptr = xen_get_user_pgd(ptr);
+	pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr);
+	pgd_t pgd_val;
 
-	trace_xen_mmu_set_pgd(ptr, user_ptr, val);
+	trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val);
 
 	/* If page is not pinned, we can just update the entry
 	   directly */
@@ -576,7 +577,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 		*ptr = val;
 		if (user_ptr) {
 			WARN_ON(xen_page_pinned(user_ptr));
-			*user_ptr = val;
+			pgd_val.pgd = p4d_val_ma(val);
+			*user_ptr = pgd_val;
 		}
 		return;
 	}
@@ -585,9 +587,9 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val)
 	   user updates together. */
 	xen_mc_batch();
 
-	__xen_set_pgd_hyper(ptr, val);
+	__xen_set_p4d_hyper(ptr, val);
 	if (user_ptr)
-		__xen_set_pgd_hyper(user_ptr, val);
+		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
@@ -1591,7 +1593,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
 	}
 #endif
-
 	return ret;
 }
 
@@ -1783,7 +1784,7 @@ static void xen_release_pmd(unsigned long pfn)
 	xen_release_ptpage(pfn, PT_PMD);
 }
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -2124,21 +2125,27 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
  */
 void __init xen_relocate_p2m(void)
 {
-	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys;
 	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
-	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
+	int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d;
 	pte_t *pt;
 	pmd_t *pmd;
 	pud_t *pud;
+	p4d_t *p4d = NULL;
 	pgd_t *pgd;
 	unsigned long *new_p2m;
+	int save_pud;
 
 	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
 	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
 	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
 	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
-	n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
-	n_frames = n_pte + n_pt + n_pmd + n_pud;
+	n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT;
+	if (PTRS_PER_P4D > 1)
+		n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	else
+		n_p4d = 0;
+	n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d;
 
 	new_area = xen_find_free_area(PFN_PHYS(n_frames));
 	if (!new_area) {
@@ -2154,13 +2161,22 @@ void __init xen_relocate_p2m(void)
 	 * To avoid any possible virtual address collision, just use
 	 * 2 * PUD_SIZE for the new area.
 	 */
-	pud_phys = new_area;
+	p4d_phys = new_area;
+	pud_phys = p4d_phys + PFN_PHYS(n_p4d);
 	pmd_phys = pud_phys + PFN_PHYS(n_pud);
 	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
 	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
 
 	pgd = __va(read_cr3());
 	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
+	idx_p4d = 0;
+	save_pud = n_pud;
+	do {
+		if (n_p4d > 0) {
+			p4d = early_memremap(p4d_phys, PAGE_SIZE);
+			clear_page(p4d);
+			n_pud = min(save_pud, PTRS_PER_P4D);
+		}
 		for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
 			pud = early_memremap(pud_phys, PAGE_SIZE);
 			clear_page(pud);
@@ -2200,9 +2216,21 @@ void __init xen_relocate_p2m(void)
 			early_memunmap(pud, PAGE_SIZE);
 			make_lowmem_page_readonly(__va(pud_phys));
 			pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+			if (n_p4d > 0)
+				set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys));
+			else
 				set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
 			pud_phys += PAGE_SIZE;
 		}
+		if (n_p4d > 0) {
+			save_pud -= PTRS_PER_P4D;
+			early_memunmap(p4d, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(p4d_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys));
+			set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys));
+			p4d_phys += PAGE_SIZE;
+		}
+	} while (++idx_p4d < n_p4d);
 
 	/* Now copy the old p2m info to the new area. */
 	memcpy(new_p2m, xen_p2m_addr, size);
@@ -2432,8 +2460,8 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
-#if CONFIG_PGTABLE_LEVELS == 4
-	pv_mmu_ops.set_pgd = xen_set_pgd;
+#if CONFIG_PGTABLE_LEVELS >= 4
+	pv_mmu_ops.set_p4d = xen_set_p4d;
 #endif
 
 	/* This will work as long as patching hasn't happened yet
@@ -2442,7 +2470,7 @@ static void __init xen_post_allocator_init(void)
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
@@ -2508,10 +2536,10 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
 	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-#if CONFIG_PGTABLE_LEVELS == 4
+#if CONFIG_PGTABLE_LEVELS >= 4
 	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
 	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
-	.set_pgd = xen_set_pgd_hyper,
+	.set_p4d = xen_set_p4d_hyper,
 
 	.alloc_pud = xen_alloc_pmd_init,
 	.release_pud = xen_release_pmd_init,

include/trace/events/xen.h

@@ -241,21 +241,21 @@ TRACE_EVENT(xen_mmu_set_pud,
 		      (int)sizeof(pudval_t) * 2, (unsigned long long)__entry->pudval)
 	);
 
-TRACE_EVENT(xen_mmu_set_pgd,
-	    TP_PROTO(pgd_t *pgdp, pgd_t *user_pgdp, pgd_t pgdval),
-	    TP_ARGS(pgdp, user_pgdp, pgdval),
+TRACE_EVENT(xen_mmu_set_p4d,
+	    TP_PROTO(p4d_t *p4dp, p4d_t *user_p4dp, p4d_t p4dval),
+	    TP_ARGS(p4dp, user_p4dp, p4dval),
 	    TP_STRUCT__entry(
-		    __field(pgd_t *, pgdp)
-		    __field(pgd_t *, user_pgdp)
-		    __field(pgdval_t, pgdval)
-		    ),
-	    TP_fast_assign(__entry->pgdp = pgdp;
-			   __entry->user_pgdp = user_pgdp;
-			   __entry->pgdval = pgdval.pgd),
-	    TP_printk("pgdp %p user_pgdp %p pgdval %0*llx (raw %0*llx)",
-		      __entry->pgdp, __entry->user_pgdp,
-		      (int)sizeof(pgdval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->pgdval)),
-		      (int)sizeof(pgdval_t) * 2, (unsigned long long)__entry->pgdval)
+		    __field(p4d_t *, p4dp)
+		    __field(p4d_t *, user_p4dp)
+		    __field(p4dval_t, p4dval)
+		    ),
+	    TP_fast_assign(__entry->p4dp = p4dp;
+			   __entry->user_p4dp = user_p4dp;
+			   __entry->p4dval = p4d_val(p4dval)),
+	    TP_printk("p4dp %p user_p4dp %p p4dval %0*llx (raw %0*llx)",
+		      __entry->p4dp, __entry->user_p4dp,
+		      (int)sizeof(p4dval_t) * 2, (unsigned long long)pgd_val(native_make_pgd(__entry->p4dval)),
+		      (int)sizeof(p4dval_t) * 2, (unsigned long long)__entry->p4dval)
 	);
 
 TRACE_EVENT(xen_mmu_pud_clear,