powerpc/8xx: reintroduce 16K pages with HW assistance

Using this HW assistance implies some constraints on the
page table structure:
- Regardless of the main page size used (4k or 16k), the
level 1 table (PGD) contains 1024 entries and each PGD entry covers
a 4Mbytes area which is managed by a level 2 table (PTE) containing
also 1024 entries each describing a 4k page.
- 16k pages require 4 identifical entries in the L2 table
- 512k pages PTE have to be spread every 128 bytes in the L2 table
- 8M pages PTE are at the address pointed by the L1 entry and each
8M page require 2 identical entries in the PGD.

In order to use hardware assistance with 16K pages, this patch does
the following modifications:
- Make PGD size independent of the main page size
- In 16k pages mode, redefine pte_t as a struct with 4 elements,
and populate those 4 elements in __set_pte_at() and pte_update()
- Adapt the size of the hugepage tables.
- Define a PTE_FRAGMENT_NB so that a 16k page contains 4 page tables.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 15 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index fa05aa566ece..b0f764c827c0 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -190,6 +190,7 @@ typedef struct {
 	struct slice_mask mask_8m;
 # endif
 #endif
+	void *pte_frag;
 } mm_context_t;
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
@@ -244,6 +245,9 @@ extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf;
 #define mmu_virtual_psize	MMU_PAGE_4K
 #elif defined(CONFIG_PPC_16K_PAGES)
 #define mmu_virtual_psize	MMU_PAGE_16K
+#define PTE_FRAG_NR		4
+#define PTE_FRAG_SIZE_SHIFT	12
+#define PTE_FRAG_SIZE		(1UL << 12)
 #else
 #error "Unsupported PAGE_SIZE"
 #endif
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index e9c8604cc8c5..bed433358260 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -232,7 +232,13 @@ static inline unsigned long pte_update(pte_t *p,
 	: "cc" );
 #else /* PTE_ATOMIC_UPDATES */
 	unsigned long old = pte_val(*p);
-	*p = __pte((old & ~clr) | set);
+	unsigned long new = (old & ~clr) | set;
+
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+	p->pte = p->pte1 = p->pte2 = p->pte3 = new;
+#else
+	*p = __pte(new);
+#endif
 #endif /* !PTE_ATOMIC_UPDATES */
 
 #ifdef CONFIG_44x
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 70ff23974b59..1ca1c1864b32 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -209,7 +209,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	/* Anything else just stores the PTE normally. That covers all 64-bit
 	 * cases, and 32-bit non-hash with 32-bit PTEs.
 	 */
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+	ptep->pte = ptep->pte1 = ptep->pte2 = ptep->pte3 = pte_val(pte);
+#else
 	*ptep = pte;
+#endif
 
 	/*
 	 * With hardware tablewalk, a sync is needed to ensure that