Re: [PATCH V6 07/35] powerpc/mm: Don't have generic headers introduce functions touching pte bits

We are going to drop pte_common.h in the later patch. The idea is to
enable hash code not require to define all PTE bits. Having PTE bits
defined in pte_common.h made the code unnecessarily complex.

Acked-by: Scott Wood <redacted>
Signed-off-by: Aneesh Kumar K.V <redacted>
---
 arch/powerpc/include/asm/book3s/pgtable.h          | 176 +++++++++++++++++++
 .../include/asm/{pgtable.h => pgtable-book3e.h}    |  96 +----------
 arch/powerpc/include/asm/pgtable.h                 | 192 +--------------------
 3 files changed, 185 insertions(+), 279 deletions(-)
 copy arch/powerpc/include/asm/{pgtable.h => pgtable-book3e.h} (70%)

diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
index 3818cc7bc9b7..fa270cfcf30a 100644
--- a/arch/powerpc/include/asm/book3s/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/pgtable.h

@@ -8,4 +8,180 @@
 #endif
 
 #define FIRST_USER_ADDRESS	0UL
+#ifndef __ASSEMBLY__
+
+/* Generic accessors to PTE bits */
+static inline int pte_write(pte_t pte)
+{
+	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO;
+}
+static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/* Conversion functions: convert a page and protection to a page entry,

+ * low level function in the respective pgtable-* files
+ */
+extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		       pte_t pte);
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
+	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
+	 * helper pte_update() which does an atomic update. We need to do that
+	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
+	 * the hash bits instead (ie, same as the non-SMP case)
+	 */
+	if (percpu)
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+	else
+		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
+
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
+	 * can just store as long as we do the two halves in the right order
+	 * with a barrier in between. This is possible because we take care,
+	 * in the hash code, to pre-invalidate if the PTE was already hashed,
+	 * which synchronizes us with any concurrent invalidation.
+	 * In the percpu case, we also fallback to the simple update preserving
+	 * the hash bits
+	 */
+	if (percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+			      | (pte_val(pte) & ~_PAGE_HASHPTE));
+		return;
+	}
+	if (pte_val(*ptep) & _PAGE_HASHPTE)
+		flush_hash_entry(mm, ptep, addr);
+	__asm__ __volatile__("\
+		stw%U0%X0 %2,%0\n\
+		eieio\n\
+		stw%U0%X0 %L2,%1"
+	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
+	: "r" (pte) : "memory");
+
+#elif defined(CONFIG_PPC_STD_MMU_32)
+	/* Third case is 32-bit hash table in UP mode, we need to preserve
+	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+	 * and see we need to keep track that this PTE needs invalidating
+	 */
+	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
+		      | (pte_val(pte) & ~_PAGE_HASHPTE));
+
+#else
+	/* Anything else just stores the PTE normally. That covers all 64-bit
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
+	 */
+	*ptep = pte;
+#endif
+}
+
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached(prot)	  (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_NO_CACHE))
+
+#define pgprot_cached(prot)       (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT))
+
+#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
+				            _PAGE_COHERENT | _PAGE_WRITETHRU))
+
+#define pgprot_cached_noncoherent(prot) \
+		(__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL))
+
+#define pgprot_writecombine pgprot_noncached_wc
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#endif /* __ASSEMBLY__ */
 #endif

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable-book3e.h
similarity index 70%
copy from arch/powerpc/include/asm/pgtable.h
copy to arch/powerpc/include/asm/pgtable-book3e.h
index c304d0767919..a3221cff2e31 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable-book3e.h

@@ -1,41 +1,19 @@
-#ifndef _ASM_POWERPC_PGTABLE_H
-#define _ASM_POWERPC_PGTABLE_H
-#ifdef __KERNEL__
+#ifndef _ASM_POWERPC_PGTABLE_BOOK3E_H
+#define _ASM_POWERPC_PGTABLE_BOOK3E_H
 
-#ifndef __ASSEMBLY__
-#include <linux/mmdebug.h>
-#include <linux/mmzone.h>
-#include <asm/processor.h>		/* For TASK_SIZE */
-#include <asm/mmu.h>
-#include <asm/page.h>
-
-struct mm_struct;
-
-#endif /* !__ASSEMBLY__ */
-
-#ifdef CONFIG_PPC_BOOK3S
-#include <asm/book3s/pgtable.h>
-#else
 #if defined(CONFIG_PPC64)
-#  include <asm/pgtable-ppc64.h>
+#include <asm/pgtable-ppc64.h>
 #else
-#  include <asm/pgtable-ppc32.h>
+#include <asm/pgtable-ppc32.h>
 #endif
-#endif /* !CONFIG_PPC_BOOK3S */
-
-/*
- * We save the slot number & secondary bit in the second half of the
- * PTE page. We use the 8 bytes per each pte entry.
- */
-#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8)
 
 #ifndef __ASSEMBLY__
 
-#include <asm/tlbflush.h>
-
 /* Generic accessors to PTE bits */
 static inline int pte_write(pte_t pte)
-{	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; }
+{
+	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO;
+}
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }

@@ -77,10 +55,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
 static inline unsigned long pte_pfn(pte_t pte)	{
 	return pte_val(pte) >> PTE_RPN_SHIFT; }
 
-/* Keep these as a macros to avoid include dependency mess */
-#define pte_page(x)		pfn_to_page(pte_pfn(x))
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte) {
 	pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE);

@@ -221,59 +195,5 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				     unsigned long size, pgprot_t vma_prot);
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
-extern pgd_t swapper_pg_dir[];
-
-void limit_zone_pfn(enum zone_type zone, unsigned long max_pfn);
-int dma_pfn_limit_to_zone(u64 pfn_limit);
-extern void paging_init(void);
-
-/*
- * kern_addr_valid is intended to indicate whether an address is a valid
- * kernel address.  Most 32-bit archs define it as always true (like this)
- * but most 64-bit archs actually perform a test.  What should we do here?
- */
-#define kern_addr_valid(addr)	(1)
-
-#include <asm-generic/pgtable.h>
-
-
-/*
- * This gets called at the end of handling a page fault, when
- * the kernel has put a new PTE into the page table for the process.
- * We use it to ensure coherency between the i-cache and d-cache
- * for the page which has just been mapped in.
- * On machines which use an MMU hash table, we use this to put a
- * corresponding HPTE into the hash table ahead of time, instead of
- * waiting for the inevitable extra hash-table miss exception.
- */
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
-
-extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write,
-		       struct page **pages, int *nr);
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_large(pmd)		0
-#define has_transparent_hugepage() 0
-#endif
-pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-				   bool *is_thp, unsigned *shift);
-static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-					       bool *is_thp, unsigned *shift)
-{
-	if (!arch_irqs_disabled()) {
-		pr_info("%s called with irq enabled\n", __func__);
-		dump_stack();
-	}
-	return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
-}