lib/ioremap: ensure break-before-make is used for huge p4d mappings

Whilst no architectures actually enable support for huge p4d mappings in
the vmap area, the code that is implemented should be using
break-before-make, as we do for pud and pmd huge entries.

Link: http://lkml.kernel.org/r/1544120495-17438-6-git-send-email-will.deacon@arm.com
Signed-off-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Chintan Pandya <cpandya@codeaurora.org>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm64/mm/mmu.c

@@ -1043,6 +1043,11 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 	return 1;
 }
 
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+	return 0;	/* Don't attempt a block mapping */
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		    bool want_memblock)

arch/x86/mm/pgtable.c

@@ -794,6 +794,14 @@ int pmd_clear_huge(pmd_t *pmd)
 	return 0;
 }
 
+/*
+ * Until we support 512GB pages, skip them in the vmap area.
+ */
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+	return 0;
+}
+
 #ifdef CONFIG_X86_64
 /**
  * pud_free_pmd_page - Clear pud entry and free pmd page.

include/asm-generic/pgtable.h

@@ -1057,6 +1057,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
 int pud_free_pmd_page(pud_t *pud, unsigned long addr);
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
@@ -1084,6 +1085,10 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 {
 	return 0;
 }
+static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+	return 0;
+}
 static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return 0;

lib/ioremap.c

@@ -156,6 +156,25 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 	return 0;
 }
 
+static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
+				unsigned long end, phys_addr_t phys_addr,
+				pgprot_t prot)
+{
+	if (!ioremap_p4d_enabled())
+		return 0;
+
+	if ((end - addr) != P4D_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
+		return 0;
+
+	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
+		return 0;
+
+	return p4d_set_huge(p4d, phys_addr, prot);
+}
+
 static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
@@ -168,12 +187,8 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
 	do {
 		next = p4d_addr_end(addr, end);
 
-		if (ioremap_p4d_enabled() &&
-		    ((next - addr) == P4D_SIZE) &&
-		    IS_ALIGNED(phys_addr, P4D_SIZE)) {
-			if (p4d_set_huge(p4d, phys_addr, prot))
-				continue;
-		}
+		if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot))
+			continue;
 
 		if (ioremap_pud_range(p4d, addr, next, phys_addr, prot))
 			return -ENOMEM;