Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-Id: <b782d3ab02a8c900011548f348cd0b806b02db05.1543405086.git.christophe.leroy@c-s.fr>
In-Reply-To: <cover.1543405086.git.christophe.leroy@c-s.fr>
References: <cover.1543405086.git.christophe.leroy@c-s.fr>
From:   Christophe Leroy <christophe.leroy@c-s.fr>
Subject: [PATCH v7 14/16] powerpc/mm: reintroduce 16K pages with HW assistance
 on 8xx
To:     Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Michael Ellerman <mpe@ellerman.id.au>
Cc:     linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Date:   Wed, 28 Nov 2018 11:46:50 +0000 (UTC)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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>
---
 arch/powerpc/Kconfig                         |  2 +-
 arch/powerpc/include/asm/nohash/32/mmu-8xx.h |  1 +
 arch/powerpc/include/asm/nohash/32/pgtable.h | 19 ++++++++++++++++++-
 arch/powerpc/include/asm/nohash/pgtable.h    |  4 ++++
 arch/powerpc/include/asm/pgtable-types.h     |  4 ++++
 5 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ddfccdf004fe..8be31261aec8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -689,7 +689,7 @@ config PPC_4K_PAGES
 
 config PPC_16K_PAGES
 	bool "16k page size"
-	depends on 44x
+	depends on 44x || PPC_8xx
 
 config PPC_64K_PAGES
 	bool "64k page size"
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index fa05aa566ece..25f05131afd5 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)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 31a03e9a42c4..e3e81b078432 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -19,7 +19,14 @@ extern int icache_44x_need_flush;
 
 #endif /* __ASSEMBLY__ */
 
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+#define PTE_INDEX_SIZE  (PTE_SHIFT - 2)
+#define PTE_FRAG_NR		4
+#define PTE_FRAG_SIZE_SHIFT	12
+#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+#else
 #define PTE_INDEX_SIZE	PTE_SHIFT
+#endif
 
 #define PMD_INDEX_SIZE	0
 #define PUD_INDEX_SIZE	0
@@ -49,7 +56,11 @@ extern int icache_44x_need_flush;
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
+#ifdef CONFIG_PPC_8xx
+#define PGDIR_SHIFT	22
+#else
 #define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#endif
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
@@ -233,7 +244,13 @@ 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
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index eccb30b38b47..3b0edf041b2e 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -3,7 +3,11 @@
 #define _ASM_POWERPC_PGTABLE_TYPES_H
 
 /* PTE level */
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t;
+#else
 typedef struct { pte_basic_t pte; } pte_t;
+#endif
 #define __pte(x)	((pte_t) { (x) })
 static inline pte_basic_t pte_val(pte_t x)
 {
-- 
2.13.3