mm/x86: support large pfn mappings

Helpers to install and detect special pmd/pud entries.  In short, bit 9 on
x86 is not used for pmd/pud, so we can directly define them the same as
the pte level.  One note is that it's also used in _PAGE_BIT_CPA_TEST but
that is only used in the debug test, and shouldn't conflict in this case.

One note is that pxx_set|clear_flags() for pmd/pud will need to be moved
upper so that they can be referenced by the new special bit helpers. 
There's no change in the code that was moved.

Link: https://lkml.kernel.org/r/20240826204353.2228736-18-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 53 insertions, 28 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b74b9ee484da..d4dbe9717e96 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,6 +28,7 @@ config X86_64
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 8d12bfad6a1d..4c2d080d26b4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -120,6 +120,34 @@ extern pmdval_t early_pmd_flags;
 #define arch_end_context_switch(prev)	do {} while(0)
 #endif	/* CONFIG_PARAVIRT_XXL */
 
+static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	return native_make_pmd(v | set);
+}
+
+static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	return native_make_pmd(v & ~clear);
+}
+
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return native_make_pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return native_make_pud(v & ~clear);
+}
+
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -317,6 +345,30 @@ static inline int pud_devmap(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+static inline bool pmd_special(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_SPECIAL;
+}
+
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_SPECIAL);
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */
+
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+static inline bool pud_special(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_SPECIAL;
+}
+
+static inline pud_t pud_mkspecial(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_SPECIAL);
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
+
 static inline int pgd_devmap(pgd_t pgd)
 {
 	return 0;
@@ -487,20 +539,6 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
 }
 
-static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
-{
-	pmdval_t v = native_pmd_val(pmd);
-
-	return native_make_pmd(v | set);
-}
-
-static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
-{
-	pmdval_t v = native_pmd_val(pmd);
-
-	return native_make_pmd(v & ~clear);
-}
-
 /* See comments above mksaveddirty_shift() */
 static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
 {
@@ -595,20 +633,6 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 #define pmd_mkwrite pmd_mkwrite
 
-static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
-{
-	pudval_t v = native_pud_val(pud);
-
-	return native_make_pud(v | set);
-}
-
-static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
-{
-	pudval_t v = native_pud_val(pud);
-
-	return native_make_pud(v & ~clear);
-}
-
 /* See comments above mksaveddirty_shift() */
 static inline pud_t pud_mksaveddirty(pud_t pud)
 {