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: <d64b402fecd5088ce8ea607bb654c6226cf99c35.1550745320.git.christophe.leroy@c-s.fr>
In-Reply-To: <cover.1550745320.git.christophe.leroy@c-s.fr>
References: <cover.1550745320.git.christophe.leroy@c-s.fr>
From:   Christophe Leroy <christophe.leroy@c-s.fr>
Subject: [PATCH v2 05/10] powerpc/hash32: use physical address directly in
 hash handlers.
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:   Thu, 21 Feb 2019 10:37:57 +0000 (UTC)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Since commit c62ce9ef97ba ("powerpc: remove remaining bits from
CONFIG_APUS"), tophys() has become a pure constant operation.
PAGE_OFFSET is known at compile time so the physical address
can be builtin directly.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 arch/powerpc/mm/hash_low_32.S | 62 +++++++++++++++++++------------------------
 arch/powerpc/mm/ppc_mmu_32.c  |  6 +++--
 2 files changed, 31 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 82e7dd0c0220..d94fef524ef5 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -47,14 +47,13 @@ mmu_hash_lock:
  * Returns to the caller if the access is illegal or there is no
  * mapping for the address.  Otherwise it places an appropriate PTE
  * in the hash table and returns from the exception.
- * Uses r0, r3 - r8, r10, ctr, lr.
+ * Uses r0, r3 - r6, r8, r10, ctr, lr.
  */
 	.text
 _GLOBAL(hash_page)
-	tophys(r7,0)			/* gets -KERNELBASE into r7 */
 #ifdef CONFIG_SMP
-	addis	r8,r7,mmu_hash_lock@h
-	ori	r8,r8,mmu_hash_lock@l
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@h
+	ori	r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l
 	lis	r0,0x0fff
 	b	10f
 11:	lwz	r6,0(r8)
@@ -76,7 +75,7 @@ _GLOBAL(hash_page)
 	lis	r5,swapper_pg_dir@ha	/* if kernel address, use */
 	addi	r5,r5,swapper_pg_dir@l	/* kernel page table */
 	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
-112:	add	r5,r5,r7		/* convert to phys addr */
+112:	tophys(r5, r5)
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
 	lwz	r8,0(r5)		/* get pmd entry */
@@ -143,25 +142,24 @@ retry:
 
 #ifdef CONFIG_SMP
 	eieio
-	addis	r8,r7,mmu_hash_lock@ha
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
 	li	r0,0
-	stw	r0,mmu_hash_lock@l(r8)
+	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
 #endif
 
 	/* Return from the exception */
 	lwz	r5,_CTR(r11)
 	mtctr	r5
 	lwz	r0,GPR0(r11)
-	lwz	r7,GPR7(r11)
 	lwz	r8,GPR8(r11)
 	b	fast_exception_return
 
 #ifdef CONFIG_SMP
 hash_page_out:
 	eieio
-	addis	r8,r7,mmu_hash_lock@ha
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
 	li	r0,0
-	stw	r0,mmu_hash_lock@l(r8)
+	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
 	blr
 #endif /* CONFIG_SMP */
 
@@ -207,11 +205,9 @@ _GLOBAL(add_hash_page)
 	SYNC_601
 	isync
 
-	tophys(r7,0)
-
 #ifdef CONFIG_SMP
-	addis	r6,r7,mmu_hash_lock@ha
-	addi	r6,r6,mmu_hash_lock@l
+	lis	r6, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r6, r6, (mmu_hash_lock - PAGE_OFFSET)@l
 10:	lwarx	r0,0,r6			/* take the mmu_hash_lock */
 	cmpi	0,r0,0
 	bne-	11f
@@ -256,8 +252,8 @@ _GLOBAL(add_hash_page)
 
 9:
 #ifdef CONFIG_SMP
-	addis	r6,r7,mmu_hash_lock@ha
-	addi	r6,r6,mmu_hash_lock@l
+	lis	r6, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r6, r6, (mmu_hash_lock - PAGE_OFFSET)@l
 	eieio
 	li	r0,0
 	stw	r0,0(r6)		/* clear mmu_hash_lock */
@@ -277,10 +273,8 @@ _GLOBAL(add_hash_page)
  * It is designed to be called with the MMU either on or off.
  * r3 contains the VSID, r4 contains the virtual address,
  * r5 contains the linux PTE, r6 contains the old value of the
- * linux PTE (before setting _PAGE_HASHPTE) and r7 contains the
- * offset to be added to addresses (0 if the MMU is on,
- * -KERNELBASE if it is off).  r10 contains the upper half of
- * the PTE if CONFIG_PTE_64BIT.
+ * linux PTE (before setting _PAGE_HASHPTE). r10 contains the
+ * upper half of the PTE if CONFIG_PTE_64BIT.
  * On SMP, the caller should have the mmu_hash_lock held.
  * We assume that the caller has (or will) set the _PAGE_HASHPTE
  * bit in the linux PTE in memory.  The value passed in r6 should
@@ -341,7 +335,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	patch_site	1f, patch__hash_page_A1
 	patch_site	2f, patch__hash_page_A2
 	/* Get the address of the primary PTE group in the hash table (r3) */
-0:	addis	r0,r7,Hash_base@h	/* base address of hash table */
+0:	lis	r0, (Hash_base - PAGE_OFFSET)@h	/* base address of hash table */
 1:	rlwimi	r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
 2:	rlwinm	r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
 	xor	r3,r3,r0		/* make primary hash */
@@ -355,10 +349,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	beq+	10f			/* no PTE: go look for an empty slot */
 	tlbie	r4
 
-	addis	r4,r7,htab_hash_searches@ha
-	lwz	r6,htab_hash_searches@l(r4)
+	lis	r4, (htab_hash_searches - PAGE_OFFSET)@ha
+	lwz	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,1			/* count how many searches we do */
-	stw	r6,htab_hash_searches@l(r4)
+	stw	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
 
 	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
 	mtctr	r0
@@ -390,10 +384,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	beq+	found_empty
 
 	/* update counter of times that the primary PTEG is full */
-	addis	r4,r7,primary_pteg_full@ha
-	lwz	r6,primary_pteg_full@l(r4)
+	lis	r4, (primary_pteg_full - PAGE_OFFSET)@ha
+	lwz	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,1
-	stw	r6,primary_pteg_full@l(r4)
+	stw	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
 
 	patch_site	0f, patch__hash_page_C
 	/* Search the secondary PTEG for an empty slot */
@@ -427,8 +421,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	 * lockup here but that shouldn't happen
 	 */
 
-1:	addis	r4,r7,next_slot@ha		/* get next evict slot */
-	lwz	r6,next_slot@l(r4)
+1:	lis	r4, (next_slot - PAGE_OFFSET)@ha	/* get next evict slot */
+	lwz	r6, (next_slot - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,HPTE_SIZE			/* search for candidate */
 	andi.	r6,r6,7*HPTE_SIZE
 	stw	r6,next_slot@l(r4)
@@ -500,8 +494,6 @@ htab_hash_searches:
  * We assume that there is a hash table in use (Hash != 0).
  */
 _GLOBAL(flush_hash_pages)
-	tophys(r7,0)
-
 	/*
 	 * We disable interrupts here, even on UP, because we want
 	 * the _PAGE_HASHPTE bit to be a reliable indication of
@@ -546,10 +538,10 @@ _GLOBAL(flush_hash_pages)
 	SET_V(r11)			/* set V (valid) bit */
 
 #ifdef CONFIG_SMP
-	addis	r9,r7,mmu_hash_lock@ha
-	addi	r9,r9,mmu_hash_lock@l
+	lis	r9, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r9, r9, (mmu_hash_lock - PAGE_OFFSET)@l
 	CURRENT_THREAD_INFO(r8, r1)
-	add	r8,r8,r7
+	tophys(r8, r8)
 	lwz	r8,TI_CPU(r8)
 	oris	r8,r8,9
 10:	lwarx	r0,0,r9
@@ -583,7 +575,7 @@ _GLOBAL(flush_hash_pages)
 	patch_site	1f, patch__flush_hash_A1
 	patch_site	2f, patch__flush_hash_A2
 	/* Get the address of the primary PTE group in the hash table (r3) */
-0:	addis	r8,r7,Hash_base@h	/* base address of hash table */
+0:	lis	r8, (Hash_base - PAGE_OFFSET)@h	/* base address of hash table */
 1:	rlwimi	r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
 2:	rlwinm	r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
 	xor	r8,r0,r8		/* make primary hash */
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 3f4193201ee7..fb747bb0b3e4 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -231,7 +231,8 @@ void __init MMU_init_hw(void)
 	if (lg_n_hpteg > 16)
 		mb2 = 16 - LG_HPTEG_SIZE;
 
-	modify_instruction_site(&patch__hash_page_A0, 0xffff, (unsigned int)Hash >> 16);
+	modify_instruction_site(&patch__hash_page_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
 	modify_instruction_site(&patch__hash_page_A1, 0x7c0, mb << 6);
 	modify_instruction_site(&patch__hash_page_A2, 0x7c0, mb2 << 6);
 	modify_instruction_site(&patch__hash_page_B, 0xffff, hmask);
@@ -240,7 +241,8 @@ void __init MMU_init_hw(void)
 	/*
 	 * Patch up the instructions in hashtable.S:flush_hash_page
 	 */
-	modify_instruction_site(&patch__flush_hash_A0, 0xffff, (unsigned int)Hash >> 16);
+	modify_instruction_site(&patch__flush_hash_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
 	modify_instruction_site(&patch__flush_hash_A1, 0x7c0, mb << 6);
 	modify_instruction_site(&patch__flush_hash_A2, 0x7c0, mb2 << 6);
 	modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask);
-- 
2.13.3