Merge tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Slightly delayed due to the issue with printk() calling
  probe_kernel_read() interacting with our new user access prevention
  stuff, but all fixed now.

  The only out-of-area changes are the addition of a cpuhp_state, small
  additions to Documentation and MAINTAINERS updates.

  Highlights:

   - Support for Kernel Userspace Access/Execution Prevention (like
     SMAP/SMEP/PAN/PXN) on some 64-bit and 32-bit CPUs. This prevents
     the kernel from accidentally accessing userspace outside
     copy_to/from_user(), or ever executing userspace.

   - KASAN support on 32-bit.

   - Rework of where we map the kernel, vmalloc, etc. on 64-bit hash to
     use the same address ranges we use with the Radix MMU.

   - A rewrite into C of large parts of our idle handling code for
     64-bit Book3S (ie. power8 & power9).

   - A fast path entry for syscalls on 32-bit CPUs, for a 12-17% speedup
     in the null_syscall benchmark.

   - On 64-bit bare metal we have support for recovering from errors
     with the time base (our clocksource), however if that fails
     currently we hang in __delay() and never crash. We now have support
     for detecting that case and short circuiting __delay() so we at
     least panic() and reboot.

   - Add support for optionally enabling the DAWR on Power9, which had
     to be disabled by default due to a hardware erratum. This has the
     effect of enabling hardware breakpoints for GDB, the downside is a
     badly behaved program could crash the machine by pointing the DAWR
     at cache inhibited memory. This is opt-in obviously.

   - xmon, our crash handler, gets support for a read only mode where
     operations that could change memory or otherwise disturb the system
     are disabled.

  Plus many clean-ups, reworks and minor fixes etc.

  Thanks to: Christophe Leroy, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar,
  Anton Blanchard, Ben Hutchings, Bo YU, Breno Leitao, Cédric Le Goater,
  Christopher M. Riedl, Christoph Hellwig, Colin Ian King, David Gibson,
  Ganesh Goudar, Gautham R. Shenoy, George Spelvin, Greg Kroah-Hartman,
  Greg Kurz, Horia Geantă, Jagadeesh Pagadala, Joel Stanley, Joe
  Perches, Julia Lawall, Laurentiu Tudor, Laurent Vivier, Lukas Bulwahn,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Neuling, Mukesh Ojha, Nathan Fontenot, Nathan Lynch, Nicholas Piggin,
  Nick Desaulniers, Oliver O'Halloran, Peng Hao, Qian Cai, Ravi
  Bangoria, Rick Lindsley, Russell Currey, Sachin Sant, Stewart Smith,
  Sukadev Bhattiprolu, Thomas Huth, Tobin C. Harding, Tyrel Datwyler,
  Valentin Schneider, Wei Yongjun, Wen Yang, YueHaibing"

* tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (205 commits)
  powerpc/64s: Use early_mmu_has_feature() in set_kuap()
  powerpc/book3s/64: check for NULL pointer in pgd_alloc()
  powerpc/mm: Fix hugetlb page initialization
  ocxl: Fix return value check in afu_ioctl()
  powerpc/mm: fix section mismatch for setup_kup()
  powerpc/mm: fix redundant inclusion of pgtable-frag.o in Makefile
  powerpc/mm: Fix makefile for KASAN
  powerpc/kasan: add missing/lost Makefile
  selftests/powerpc: Add a signal fuzzer selftest
  powerpc/booke64: set RI in default MSR
  ocxl: Provide global MMIO accessors for external drivers
  ocxl: move event_fd handling to frontend
  ocxl: afu_irq only deals with IRQ IDs, not offsets
  ocxl: Allow external drivers to use OpenCAPI contexts
  ocxl: Create a clear delineation between ocxl backend & frontend
  ocxl: Don't pass pci_dev around
  ocxl: Split pci.c
  ocxl: Remove some unused exported symbols
  ocxl: Remove superfluous 'extern' from headers
  ocxl: read_pasid never returns an error, so make it void
  ...

5 files changed, 1447 insertions, 0 deletions

diff --git a/arch/powerpc/mm/book3s32/Makefile b/arch/powerpc/mm/book3s32/Makefile
new file mode 100644
index 000000000000..1732eaa740a9
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KASAN_SANITIZE_mmu.o := n
+
+ifdef CONFIG_KASAN
+CFLAGS_mmu.o  		+= -DDISABLE_BRANCH_PROFILING
+endif
+
+obj-y += mmu.o hash_low.o mmu_context.o tlb.o
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
new file mode 100644
index 000000000000..e27792d0b744
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -0,0 +1,705 @@
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ *  Adapted for Power Macintosh by Paul Mackerras.
+ *  Low-level exception handlers and MMU support
+ *  rewritten by Paul Mackerras.
+ *    Copyright (C) 1996 Paul Mackerras.
+ *
+ *  This file contains low-level assembler routines for managing
+ *  the PowerPC MMU hash table.  (PPC 8xx processors don't use a
+ *  hash table, so this file is not used on them.)
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+#include <asm/feature-fixups.h>
+#include <asm/code-patching-asm.h>
+
+#ifdef CONFIG_SMP
+	.section .bss
+	.align	2
+mmu_hash_lock:
+	.space	4
+#endif /* CONFIG_SMP */
+
+/*
+ * Load a PTE into the hash table, if possible.
+ * The address is in r4, and r3 contains an access flag:
+ * _PAGE_RW (0x400) if a write.
+ * r9 contains the SRR1 value, from which we use the MSR_PR bit.
+ * SPRG_THREAD contains the physical address of the current task's thread.
+ *
+ * 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 - r6, r8, r10, ctr, lr.
+ */
+	.text
+_GLOBAL(hash_page)
+#ifdef CONFIG_SMP
+	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)
+	cmpwi	0,r6,0
+	bne	11b
+10:	lwarx	r6,0,r8
+	cmpwi	0,r6,0
+	bne-	11b
+	stwcx.	r0,0,r8
+	bne-	10b
+	isync
+#endif
+	/* Get PTE (linux-style) and check access */
+	lis	r0,KERNELBASE@h		/* check if kernel address */
+	cmplw	0,r4,r0
+	ori	r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
+	mfspr	r5, SPRN_SPRG_PGDIR	/* phys page-table root */
+	blt+	112f			/* assume user more likely */
+	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
+	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
+112:
+#ifndef CONFIG_PTE_64BIT
+	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
+	lwz	r8,0(r5)		/* get pmd entry */
+	rlwinm.	r8,r8,0,0,19		/* extract address of pte page */
+#else
+	rlwinm	r8,r4,13,19,29		/* Compute pgdir/pmd offset */
+	lwzx	r8,r8,r5		/* Get L1 entry */
+	rlwinm.	r8,r8,0,0,20		/* extract pt base address */
+#endif
+#ifdef CONFIG_SMP
+	beq-	hash_page_out		/* return if no mapping */
+#else
+	/* XXX it seems like the 601 will give a machine fault on the
+	   rfi if its alignment is wrong (bottom 4 bits of address are
+	   8 or 0xc) and we have had a not-taken conditional branch
+	   to the address following the rfi. */
+	beqlr-
+#endif
+#ifndef CONFIG_PTE_64BIT
+	rlwimi	r8,r4,22,20,29		/* insert next 10 bits of address */
+#else
+	rlwimi	r8,r4,23,20,28		/* compute pte address */
+#endif
+	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
+	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
+
+	/*
+	 * Update the linux PTE atomically.  We do the lwarx up-front
+	 * because almost always, there won't be a permission violation
+	 * and there won't already be an HPTE, and thus we will have
+	 * to update the PTE to set _PAGE_HASHPTE.  -- paulus.
+	 *
+	 * If PTE_64BIT is set, the low word is the flags word; use that
+	 * word for locking since it contains all the interesting bits.
+	 */
+#if (PTE_FLAGS_OFFSET != 0)
+	addi	r8,r8,PTE_FLAGS_OFFSET
+#endif
+retry:
+	lwarx	r6,0,r8			/* get linux-style pte, flag word */
+	andc.	r5,r3,r6		/* check access & ~permission */
+#ifdef CONFIG_SMP
+	bne-	hash_page_out		/* return if access not permitted */
+#else
+	bnelr-
+#endif
+	or	r5,r0,r6		/* set accessed/dirty bits */
+#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_SMP
+	subf	r10,r6,r8		/* create false data dependency */
+	subi	r10,r10,PTE_FLAGS_OFFSET
+	lwzx	r10,r6,r10		/* Get upper PTE word */
+#else
+	lwz	r10,-PTE_FLAGS_OFFSET(r8)
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_PTE_64BIT */
+	stwcx.	r5,0,r8			/* attempt to update PTE */
+	bne-	retry			/* retry if someone got there first */
+
+	mfsrin	r3,r4			/* get segment reg for segment */
+	mfctr	r0
+	stw	r0,_CTR(r11)
+	bl	create_hpte		/* add the hash table entry */
+
+#ifdef CONFIG_SMP
+	eieio
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
+	li	r0,0
+	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	r8,GPR8(r11)
+	b	fast_exception_return
+
+#ifdef CONFIG_SMP
+hash_page_out:
+	eieio
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
+	li	r0,0
+	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
+	blr
+#endif /* CONFIG_SMP */
+
+/*
+ * Add an entry for a particular page to the hash table.
+ *
+ * add_hash_page(unsigned context, unsigned long va, unsigned long pmdval)
+ *
+ * We assume any necessary modifications to the pte (e.g. setting
+ * the accessed bit) have already been done and that there is actually
+ * a hash table in use (i.e. we're not on a 603).
+ */
+_GLOBAL(add_hash_page)
+	mflr	r0
+	stw	r0,4(r1)
+
+	/* Convert context and va to VSID */
+	mulli	r3,r3,897*16		/* multiply context by context skew */
+	rlwinm	r0,r4,4,28,31		/* get ESID (top 4 bits of va) */
+	mulli	r0,r0,0x111		/* multiply by ESID skew */
+	add	r3,r3,r0		/* note create_hpte trims to 24 bits */
+
+#ifdef CONFIG_SMP
+	lwz	r8,TASK_CPU(r2)		/* to go in mmu_hash_lock */
+	oris	r8,r8,12
+#endif /* CONFIG_SMP */
+
+	/*
+	 * We disable interrupts here, even on UP, because we don't
+	 * want to race with hash_page, and because we want the
+	 * _PAGE_HASHPTE bit to be a reliable indication of whether
+	 * the HPTE exists (or at least whether one did once).
+	 * We also turn off the MMU for data accesses so that we
+	 * we can't take a hash table miss (assuming the code is
+	 * covered by a BAT).  -- paulus
+	 */
+	mfmsr	r9
+	SYNC
+	rlwinm	r0,r9,0,17,15		/* clear bit 16 (MSR_EE) */
+	rlwinm	r0,r0,0,28,26		/* clear MSR_DR */
+	mtmsr	r0
+	SYNC_601
+	isync
+
+#ifdef CONFIG_SMP
+	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
+	stwcx.	r8,0,r6
+	beq+	12f
+11:	lwz	r0,0(r6)
+	cmpi	0,r0,0
+	beq	10b
+	b	11b
+12:	isync
+#endif
+
+	/*
+	 * Fetch the linux pte and test and set _PAGE_HASHPTE atomically.
+	 * If _PAGE_HASHPTE was already set, we don't replace the existing
+	 * HPTE, so we just unlock and return.
+	 */
+	mr	r8,r5
+#ifndef CONFIG_PTE_64BIT
+	rlwimi	r8,r4,22,20,29
+#else
+	rlwimi	r8,r4,23,20,28
+	addi	r8,r8,PTE_FLAGS_OFFSET
+#endif
+1:	lwarx	r6,0,r8
+	andi.	r0,r6,_PAGE_HASHPTE
+	bne	9f			/* if HASHPTE already set, done */
+#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_SMP
+	subf	r10,r6,r8		/* create false data dependency */
+	subi	r10,r10,PTE_FLAGS_OFFSET
+	lwzx	r10,r6,r10		/* Get upper PTE word */
+#else
+	lwz	r10,-PTE_FLAGS_OFFSET(r8)
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_PTE_64BIT */
+	ori	r5,r6,_PAGE_HASHPTE
+	stwcx.	r5,0,r8
+	bne-	1b
+
+	bl	create_hpte
+
+9:
+#ifdef CONFIG_SMP
+	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 */
+#endif
+
+	/* reenable interrupts and DR */
+	mtmsr	r9
+	SYNC_601
+	isync
+
+	lwz	r0,4(r1)
+	mtlr	r0
+	blr
+
+/*
+ * This routine adds a hardware PTE to the hash table.
+ * 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). 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
+ * be the old linux PTE value; if it doesn't have _PAGE_HASHPTE set
+ * this routine will skip the search for an existing HPTE.
+ * This procedure modifies r0, r3 - r6, r8, cr0.
+ *  -- paulus.
+ *
+ * For speed, 4 of the instructions get patched once the size and
+ * physical address of the hash table are known.  These definitions
+ * of Hash_base and Hash_bits below are just an example.
+ */
+Hash_base = 0xc0180000
+Hash_bits = 12				/* e.g. 256kB hash table */
+Hash_msk = (((1 << Hash_bits) - 1) * 64)
+
+/* defines for the PTE format for 32-bit PPCs */
+#define HPTE_SIZE	8
+#define PTEG_SIZE	64
+#define LG_PTEG_SIZE	6
+#define LDPTEu		lwzu
+#define LDPTE		lwz
+#define STPTE		stw
+#define CMPPTE		cmpw
+#define PTE_H		0x40
+#define PTE_V		0x80000000
+#define TST_V(r)	rlwinm. r,r,0,0,0
+#define SET_V(r)	oris r,r,PTE_V@h
+#define CLR_V(r,t)	rlwinm r,r,0,1,31
+
+#define HASH_LEFT	31-(LG_PTEG_SIZE+Hash_bits-1)
+#define HASH_RIGHT	31-LG_PTEG_SIZE
+
+_GLOBAL(create_hpte)
+	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
+	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> PP msb */
+	rlwinm	r0,r5,32-6,30,30	/* _PAGE_DIRTY -> PP msb */
+	and	r8,r8,r0		/* writable if _RW & _DIRTY */
+	rlwimi	r5,r5,32-1,30,30	/* _PAGE_USER -> PP msb */
+	rlwimi	r5,r5,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	ori	r8,r8,0xe04		/* clear out reserved bits */
+	andc	r8,r5,r8		/* PP = user? (rw&dirty? 1: 3): 0 */
+BEGIN_FTR_SECTION
+	rlwinm	r8,r8,0,~_PAGE_COHERENT	/* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
+#ifdef CONFIG_PTE_64BIT
+	/* Put the XPN bits into the PTE */
+	rlwimi	r8,r10,8,20,22
+	rlwimi	r8,r10,2,29,29
+#endif
+
+	/* Construct the high word of the PPC-style PTE (r5) */
+	rlwinm	r5,r3,7,1,24		/* put VSID in 0x7fffff80 bits */
+	rlwimi	r5,r4,10,26,31		/* put in API (abbrev page index) */
+	SET_V(r5)			/* set V (valid) bit */
+
+	patch_site	0f, patch__hash_page_A0
+	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:	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 */
+	li	r0,8			/* PTEs/group */
+
+	/*
+	 * Test the _PAGE_HASHPTE bit in the old linux PTE, and skip the search
+	 * if it is clear, meaning that the HPTE isn't there already...
+	 */
+	andi.	r6,r6,_PAGE_HASHPTE
+	beq+	10f			/* no PTE: go look for an empty slot */
+	tlbie	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 - PAGE_OFFSET)@l(r4)
+
+	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
+	mtctr	r0
+	addi	r4,r3,-HPTE_SIZE
+1:	LDPTEu	r6,HPTE_SIZE(r4)	/* get next PTE */
+	CMPPTE	0,r6,r5
+	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
+	beq+	found_slot
+
+	patch_site	0f, patch__hash_page_B
+	/* Search the secondary PTEG for a matching PTE */
+	ori	r5,r5,PTE_H		/* set H (secondary hash) bit */
+0:	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
+	xori	r4,r4,(-PTEG_SIZE & 0xffff)
+	addi	r4,r4,-HPTE_SIZE
+	mtctr	r0
+2:	LDPTEu	r6,HPTE_SIZE(r4)
+	CMPPTE	0,r6,r5
+	bdnzf	2,2b
+	beq+	found_slot
+	xori	r5,r5,PTE_H		/* clear H bit again */
+
+	/* Search the primary PTEG for an empty slot */
+10:	mtctr	r0
+	addi	r4,r3,-HPTE_SIZE	/* search primary PTEG */
+1:	LDPTEu	r6,HPTE_SIZE(r4)	/* get next PTE */
+	TST_V(r6)			/* test valid bit */
+	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
+	beq+	found_empty
+
+	/* update counter of times that the primary PTEG is full */
+	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 - PAGE_OFFSET)@l(r4)
+
+	patch_site	0f, patch__hash_page_C
+	/* Search the secondary PTEG for an empty slot */
+	ori	r5,r5,PTE_H		/* set H (secondary hash) bit */
+0:	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
+	xori	r4,r4,(-PTEG_SIZE & 0xffff)
+	addi	r4,r4,-HPTE_SIZE
+	mtctr	r0
+2:	LDPTEu	r6,HPTE_SIZE(r4)
+	TST_V(r6)
+	bdnzf	2,2b
+	beq+	found_empty
+	xori	r5,r5,PTE_H		/* clear H bit again */
+
+	/*
+	 * Choose an arbitrary slot in the primary PTEG to overwrite.
+	 * Since both the primary and secondary PTEGs are full, and we
+	 * have no information that the PTEs in the primary PTEG are
+	 * more important or useful than those in the secondary PTEG,
+	 * and we know there is a definite (although small) speed
+	 * advantage to putting the PTE in the primary PTEG, we always
+	 * put the PTE in the primary PTEG.
+	 *
+	 * In addition, we skip any slot that is mapping kernel text in
+	 * order to avoid a deadlock when not using BAT mappings if
+	 * trying to hash in the kernel hash code itself after it has
+	 * already taken the hash table lock. This works in conjunction
+	 * with pre-faulting of the kernel text.
+	 *
+	 * If the hash table bucket is full of kernel text entries, we'll
+	 * lockup here but that shouldn't happen
+	 */
+
+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)
+	add	r4,r3,r6
+	LDPTE	r0,HPTE_SIZE/2(r4)		/* get PTE second word */
+	clrrwi	r0,r0,12
+	lis	r6,etext@h
+	ori	r6,r6,etext@l			/* get etext */
+	tophys(r6,r6)
+	cmpl	cr0,r0,r6			/* compare and try again */
+	blt	1b
+
+#ifndef CONFIG_SMP
+	/* Store PTE in PTEG */
+found_empty:
+	STPTE	r5,0(r4)
+found_slot:
+	STPTE	r8,HPTE_SIZE/2(r4)
+
+#else /* CONFIG_SMP */
+/*
+ * Between the tlbie above and updating the hash table entry below,
+ * another CPU could read the hash table entry and put it in its TLB.
+ * There are 3 cases:
+ * 1. using an empty slot
+ * 2. updating an earlier entry to change permissions (i.e. enable write)
+ * 3. taking over the PTE for an unrelated address
+ *
+ * In each case it doesn't really matter if the other CPUs have the old
+ * PTE in their TLB.  So we don't need to bother with another tlbie here,
+ * which is convenient as we've overwritten the register that had the
+ * address. :-)  The tlbie above is mainly to make sure that this CPU comes
+ * and gets the new PTE from the hash table.
+ *
+ * We do however have to make sure that the PTE is never in an invalid
+ * state with the V bit set.
+ */
+found_empty:
+found_slot:
+	CLR_V(r5,r0)		/* clear V (valid) bit in PTE */
+	STPTE	r5,0(r4)
+	sync
+	TLBSYNC
+	STPTE	r8,HPTE_SIZE/2(r4) /* put in correct RPN, WIMG, PP bits */
+	sync
+	SET_V(r5)
+	STPTE	r5,0(r4)	/* finally set V bit in PTE */
+#endif /* CONFIG_SMP */
+
+	sync		/* make sure pte updates get to memory */
+	blr
+
+	.section .bss
+	.align	2
+next_slot:
+	.space	4
+primary_pteg_full:
+	.space	4
+htab_hash_searches:
+	.space	4
+	.previous
+
+/*
+ * Flush the entry for a particular page from the hash table.
+ *
+ * flush_hash_pages(unsigned context, unsigned long va, unsigned long pmdval,
+ *		    int count)
+ *
+ * We assume that there is a hash table in use (Hash != 0).
+ */
+_GLOBAL(flush_hash_pages)
+	/*
+	 * We disable interrupts here, even on UP, because we want
+	 * the _PAGE_HASHPTE bit to be a reliable indication of
+	 * whether the HPTE exists (or at least whether one did once).
+	 * We also turn off the MMU for data accesses so that we
+	 * we can't take a hash table miss (assuming the code is
+	 * covered by a BAT).  -- paulus
+	 */
+	mfmsr	r10
+	SYNC
+	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
+	rlwinm	r0,r0,0,28,26		/* clear MSR_DR */
+	mtmsr	r0
+	SYNC_601
+	isync
+
+	/* First find a PTE in the range that has _PAGE_HASHPTE set */
+#ifndef CONFIG_PTE_64BIT
+	rlwimi	r5,r4,22,20,29
+#else
+	rlwimi	r5,r4,23,20,28
+#endif
+1:	lwz	r0,PTE_FLAGS_OFFSET(r5)
+	cmpwi	cr1,r6,1
+	andi.	r0,r0,_PAGE_HASHPTE
+	bne	2f
+	ble	cr1,19f
+	addi	r4,r4,0x1000
+	addi	r5,r5,PTE_SIZE
+	addi	r6,r6,-1
+	b	1b
+
+	/* Convert context and va to VSID */
+2:	mulli	r3,r3,897*16		/* multiply context by context skew */
+	rlwinm	r0,r4,4,28,31		/* get ESID (top 4 bits of va) */
+	mulli	r0,r0,0x111		/* multiply by ESID skew */
+	add	r3,r3,r0		/* note code below trims to 24 bits */
+
+	/* Construct the high word of the PPC-style PTE (r11) */
+	rlwinm	r11,r3,7,1,24		/* put VSID in 0x7fffff80 bits */
+	rlwimi	r11,r4,10,26,31		/* put in API (abbrev page index) */
+	SET_V(r11)			/* set V (valid) bit */
+
+#ifdef CONFIG_SMP
+	lis	r9, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r9, r9, (mmu_hash_lock - PAGE_OFFSET)@l
+	lwz	r8,TASK_CPU(r2)
+	oris	r8,r8,9
+10:	lwarx	r0,0,r9
+	cmpi	0,r0,0
+	bne-	11f
+	stwcx.	r8,0,r9
+	beq+	12f
+11:	lwz	r0,0(r9)
+	cmpi	0,r0,0
+	beq	10b
+	b	11b
+12:	isync
+#endif
+
+	/*
+	 * Check the _PAGE_HASHPTE bit in the linux PTE.  If it is
+	 * already clear, we're done (for this pte).  If not,
+	 * clear it (atomically) and proceed.  -- paulus.
+	 */
+#if (PTE_FLAGS_OFFSET != 0)
+	addi	r5,r5,PTE_FLAGS_OFFSET
+#endif
+33:	lwarx	r8,0,r5			/* fetch the pte flags word */
+	andi.	r0,r8,_PAGE_HASHPTE
+	beq	8f			/* done if HASHPTE is already clear */
+	rlwinm	r8,r8,0,31,29		/* clear HASHPTE bit */
+	stwcx.	r8,0,r5			/* update the pte */
+	bne-	33b
+
+	patch_site	0f, patch__flush_hash_A0
+	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:	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 */
+
+	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
+	li	r0,8			/* PTEs/group */
+	mtctr	r0
+	addi	r12,r8,-HPTE_SIZE
+1:	LDPTEu	r0,HPTE_SIZE(r12)	/* get next PTE */
+	CMPPTE	0,r0,r11
+	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
+	beq+	3f
+
+	patch_site	0f, patch__flush_hash_B
+	/* Search the secondary PTEG for a matching PTE */
+	ori	r11,r11,PTE_H		/* set H (secondary hash) bit */
+	li	r0,8			/* PTEs/group */
+0:	xoris	r12,r8,Hash_msk>>16	/* compute secondary hash */
+	xori	r12,r12,(-PTEG_SIZE & 0xffff)
+	addi	r12,r12,-HPTE_SIZE
+	mtctr	r0
+2:	LDPTEu	r0,HPTE_SIZE(r12)
+	CMPPTE	0,r0,r11
+	bdnzf	2,2b
+	xori	r11,r11,PTE_H		/* clear H again */
+	bne-	4f			/* should rarely fail to find it */
+
+3:	li	r0,0
+	STPTE	r0,0(r12)		/* invalidate entry */
+4:	sync
+	tlbie	r4			/* in hw tlb too */
+	sync
+
+8:	ble	cr1,9f			/* if all ptes checked */
+81:	addi	r6,r6,-1
+	addi	r5,r5,PTE_SIZE
+	addi	r4,r4,0x1000
+	lwz	r0,0(r5)		/* check next pte */
+	cmpwi	cr1,r6,1
+	andi.	r0,r0,_PAGE_HASHPTE
+	bne	33b
+	bgt	cr1,81b
+
+9:
+#ifdef CONFIG_SMP
+	TLBSYNC
+	li	r0,0
+	stw	r0,0(r9)		/* clear mmu_hash_lock */
+#endif
+
+19:	mtmsr	r10
+	SYNC_601
+	isync
+	blr
+EXPORT_SYMBOL(flush_hash_pages)
+
+/*
+ * Flush an entry from the TLB
+ */
+_GLOBAL(_tlbie)
+#ifdef CONFIG_SMP
+	lwz	r8,TASK_CPU(r2)
+	oris	r8,r8,11
+	mfmsr	r10
+	SYNC
+	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
+	rlwinm	r0,r0,0,28,26		/* clear DR */
+	mtmsr	r0
+	SYNC_601
+	isync
+	lis	r9,mmu_hash_lock@h
+	ori	r9,r9,mmu_hash_lock@l
+	tophys(r9,r9)
+10:	lwarx	r7,0,r9
+	cmpwi	0,r7,0
+	bne-	10b
+	stwcx.	r8,0,r9
+	bne-	10b
+	eieio
+	tlbie	r3
+	sync
+	TLBSYNC
+	li	r0,0
+	stw	r0,0(r9)		/* clear mmu_hash_lock */
+	mtmsr	r10
+	SYNC_601
+	isync
+#else /* CONFIG_SMP */
+	tlbie	r3
+	sync
+#endif /* CONFIG_SMP */
+	blr
+
+/*
+ * Flush the entire TLB. 603/603e only
+ */
+_GLOBAL(_tlbia)
+#if defined(CONFIG_SMP)
+	lwz	r8,TASK_CPU(r2)
+	oris	r8,r8,10
+	mfmsr	r10
+	SYNC
+	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
+	rlwinm	r0,r0,0,28,26		/* clear DR */
+	mtmsr	r0
+	SYNC_601
+	isync
+	lis	r9,mmu_hash_lock@h
+	ori	r9,r9,mmu_hash_lock@l
+	tophys(r9,r9)
+10:	lwarx	r7,0,r9
+	cmpwi	0,r7,0
+	bne-	10b
+	stwcx.	r8,0,r9
+	bne-	10b
+	sync
+	tlbia
+	sync
+	TLBSYNC
+	li	r0,0
+	stw	r0,0(r9)		/* clear mmu_hash_lock */
+	mtmsr	r10
+	SYNC_601
+	isync
+#else /* CONFIG_SMP */
+	sync
+	tlbia
+	sync
+#endif /* CONFIG_SMP */
+	blr
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
new file mode 100644
index 000000000000..fc073cb2c517
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -0,0 +1,442 @@
+/*
+ * This file contains the routines for handling the MMU on those
+ * PowerPC implementations where the MMU substantially follows the
+ * architecture specification.  This includes the 6xx, 7xx, 7xxx,
+ * and 8260 implementations but excludes the 8xx and 4xx.
+ *  -- paulus
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+
+#include <asm/prom.h>
+#include <asm/mmu.h>
+#include <asm/machdep.h>
+#include <asm/code-patching.h>
+#include <asm/sections.h>
+
+#include <mm/mmu_decl.h>
+
+struct hash_pte *Hash;
+static unsigned long Hash_size, Hash_mask;
+unsigned long _SDR1;
+static unsigned int hash_mb, hash_mb2;
+
+struct ppc_bat BATS[8][2];	/* 8 pairs of IBAT, DBAT */
+
+struct batrange {		/* stores address ranges mapped by BATs */
+	unsigned long start;
+	unsigned long limit;
+	phys_addr_t phys;
+} bat_addrs[8];
+
+/*
+ * Return PA for this VA if it is mapped by a BAT, or 0
+ */
+phys_addr_t v_block_mapped(unsigned long va)
+{
+	int b;
+	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
+		if (va >= bat_addrs[b].start && va < bat_addrs[b].limit)
+			return bat_addrs[b].phys + (va - bat_addrs[b].start);
+	return 0;
+}
+
+/*
+ * Return VA for a given PA or 0 if not mapped
+ */
+unsigned long p_block_mapped(phys_addr_t pa)
+{
+	int b;
+	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
+		if (pa >= bat_addrs[b].phys
+	    	    && pa < (bat_addrs[b].limit-bat_addrs[b].start)
+		              +bat_addrs[b].phys)
+			return bat_addrs[b].start+(pa-bat_addrs[b].phys);
+	return 0;
+}
+
+static int find_free_bat(void)
+{
+	int b;
+
+	if (cpu_has_feature(CPU_FTR_601)) {
+		for (b = 0; b < 4; b++) {
+			struct ppc_bat *bat = BATS[b];
+
+			if (!(bat[0].batl & 0x40))
+				return b;
+		}
+	} else {
+		int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+
+		for (b = 0; b < n; b++) {
+			struct ppc_bat *bat = BATS[b];
+
+			if (!(bat[1].batu & 3))
+				return b;
+		}
+	}
+	return -1;
+}
+
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ *   is identified by the lowest bit set to 1 in the base address (for instance
+ *   if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ *   highest bit set to 1.
+ */
+static unsigned int block_size(unsigned long base, unsigned long top)
+{
+	unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
+	unsigned int base_shift = (ffs(base) - 1) & 31;
+	unsigned int block_shift = (fls(top - base) - 1) & 31;
+
+	return min3(max_size, 1U << base_shift, 1U << block_shift);
+}
+
+/*
+ * Set up one of the IBAT (block address translation) register pairs.
+ * The parameters are not checked; in particular size must be a power
+ * of 2 between 128k and 256M.
+ * Only for 603+ ...
+ */
+static void setibat(int index, unsigned long virt, phys_addr_t phys,
+		    unsigned int size, pgprot_t prot)
+{
+	unsigned int bl = (size >> 17) - 1;
+	int wimgxpp;
+	struct ppc_bat *bat = BATS[index];
+	unsigned long flags = pgprot_val(prot);
+
+	if (!cpu_has_feature(CPU_FTR_NEED_COHERENT))
+		flags &= ~_PAGE_COHERENT;
+
+	wimgxpp = (flags & _PAGE_COHERENT) | (_PAGE_EXEC ? BPP_RX : BPP_XX);
+	bat[0].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
+	bat[0].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
+	if (flags & _PAGE_USER)
+		bat[0].batu |= 1;	/* Vp = 1 */
+}
+
+static void clearibat(int index)
+{
+	struct ppc_bat *bat = BATS[index];
+
+	bat[0].batu = 0;
+	bat[0].batl = 0;
+}
+
+static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+	int idx;
+
+	while ((idx = find_free_bat()) != -1 && base != top) {
+		unsigned int size = block_size(base, top);
+
+		if (size < 128 << 10)
+			break;
+		setbat(idx, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
+		base += size;
+	}
+
+	return base;
+}
+
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+	unsigned long done;
+	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
+
+	if (__map_without_bats) {
+		pr_debug("RAM mapped without BATs\n");
+		return base;
+	}
+
+	if (!strict_kernel_rwx_enabled() || base >= border || top <= border)
+		return __mmu_mapin_ram(base, top);
+
+	done = __mmu_mapin_ram(base, border);
+	if (done != border)
+		return done;
+
+	return __mmu_mapin_ram(border, top);
+}
+
+void mmu_mark_initmem_nx(void)
+{
+	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+	int i;
+	unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
+	unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
+	unsigned long size;
+
+	if (cpu_has_feature(CPU_FTR_601))
+		return;
+
+	for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) {
+		size = block_size(base, top);
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		base += size;
+	}
+	if (base < top) {
+		size = block_size(base, top);
+		size = max(size, 128UL << 10);
+		if ((top - base) > size) {
+			if (strict_kernel_rwx_enabled())
+				pr_warn("Kernel _etext not properly aligned\n");
+			size <<= 1;
+		}
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		base += size;
+	}
+	for (; i < nb; i++)
+		clearibat(i);
+
+	update_bats();
+
+	for (i = TASK_SIZE >> 28; i < 16; i++) {
+		/* Do not set NX on VM space for modules */
+		if (IS_ENABLED(CONFIG_MODULES) &&
+		    (VMALLOC_START & 0xf0000000) == i << 28)
+			break;
+		mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
+	}
+}
+
+void mmu_mark_rodata_ro(void)
+{
+	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+	int i;
+
+	if (cpu_has_feature(CPU_FTR_601))
+		return;
+
+	for (i = 0; i < nb; i++) {
+		struct ppc_bat *bat = BATS[i];
+
+		if (bat_addrs[i].start < (unsigned long)__init_begin)
+			bat[1].batl = (bat[1].batl & ~BPP_RW) | BPP_RX;
+	}
+
+	update_bats();
+}
+
+/*
+ * Set up one of the I/D BAT (block address translation) register pairs.
+ * The parameters are not checked; in particular size must be a power
+ * of 2 between 128k and 256M.
+ * On 603+, only set IBAT when _PAGE_EXEC is set
+ */
+void __init setbat(int index, unsigned long virt, phys_addr_t phys,
+		   unsigned int size, pgprot_t prot)
+{
+	unsigned int bl;
+	int wimgxpp;
+	struct ppc_bat *bat = BATS[index];
+	unsigned long flags = pgprot_val(prot);
+
+	if ((flags & _PAGE_NO_CACHE) ||
+	    (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0))
+		flags &= ~_PAGE_COHERENT;
+
+	bl = (size >> 17) - 1;
+	if (PVR_VER(mfspr(SPRN_PVR)) != 1) {
+		/* 603, 604, etc. */
+		/* Do DBAT first */
+		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
+				   | _PAGE_COHERENT | _PAGE_GUARDED);
+		wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX;
+		bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
+		bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
+		if (flags & _PAGE_USER)
+			bat[1].batu |= 1; 	/* Vp = 1 */
+		if (flags & _PAGE_GUARDED) {
+			/* G bit must be zero in IBATs */
+			flags &= ~_PAGE_EXEC;
+		}
+		if (flags & _PAGE_EXEC)
+			bat[0] = bat[1];
+		else
+			bat[0].batu = bat[0].batl = 0;
+	} else {
+		/* 601 cpu */
+		if (bl > BL_8M)
+			bl = BL_8M;
+		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
+				   | _PAGE_COHERENT);
+		wimgxpp |= (flags & _PAGE_RW)?
+			((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX;
+		bat->batu = virt | wimgxpp | 4;	/* Ks=0, Ku=1 */
+		bat->batl = phys | bl | 0x40;	/* V=1 */
+	}
+
+	bat_addrs[index].start = virt;
+	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
+	bat_addrs[index].phys = phys;
+}
+
+/*
+ * Preload a translation in the hash table
+ */
+void hash_preload(struct mm_struct *mm, unsigned long ea,
+		  bool is_exec, unsigned long trap)
+{
+	pmd_t *pmd;
+
+	if (!Hash)
+		return;
+	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
+	if (!pmd_none(*pmd))
+		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
+}
+
+/*
+ * Initialize the hash table and patch the instructions in hashtable.S.
+ */
+void __init MMU_init_hw(void)
+{
+	unsigned int n_hpteg, lg_n_hpteg;
+
+	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return;
+
+	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);
+
+#define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
+#define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
+#define MIN_N_HPTEG	1024		/* min 64kB hash table */
+
+	/*
+	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
+	 * This is less than the recommended amount, but then
+	 * Linux ain't AIX.
+	 */
+	n_hpteg = total_memory / (PAGE_SIZE * 8);
+	if (n_hpteg < MIN_N_HPTEG)
+		n_hpteg = MIN_N_HPTEG;
+	lg_n_hpteg = __ilog2(n_hpteg);
+	if (n_hpteg & (n_hpteg - 1)) {
+		++lg_n_hpteg;		/* round up if not power of 2 */
+		n_hpteg = 1 << lg_n_hpteg;
+	}
+	Hash_size = n_hpteg << LG_HPTEG_SIZE;
+
+	/*
+	 * Find some memory for the hash table.
+	 */
+	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
+	Hash = memblock_alloc(Hash_size, Hash_size);
+	if (!Hash)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+		      __func__, Hash_size, Hash_size);
+	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
+
+	pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
+		(unsigned long long)(total_memory >> 20), Hash_size >> 10);
+
+
+	Hash_mask = n_hpteg - 1;
+	hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
+	if (lg_n_hpteg > 16)
+		hash_mb2 = 16 - LG_HPTEG_SIZE;
+}
+
+void __init MMU_init_hw_patch(void)
+{
+	unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
+
+	if (ppc_md.progress)
+		ppc_md.progress("hash:patch", 0x345);
+	if (ppc_md.progress)
+		ppc_md.progress("hash:done", 0x205);
+
+	/* WARNING: Make sure nothing can trigger a KASAN check past this point */
+
+	/*
+	 * Patch up the instructions in hashtable.S:create_hpte
+	 */
+	modify_instruction_site(&patch__hash_page_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
+	modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6);
+	modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6);
+	modify_instruction_site(&patch__hash_page_B, 0xffff, hmask);
+	modify_instruction_site(&patch__hash_page_C, 0xffff, hmask);
+
+	/*
+	 * Patch up the instructions in hashtable.S:flush_hash_page
+	 */
+	modify_instruction_site(&patch__flush_hash_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
+	modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6);
+	modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6);
+	modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask);
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 601 can only access 16MB at the moment */
+	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+	else /* Anything else has 256M mapped */
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}
+
+void __init print_system_hash_info(void)
+{
+	pr_info("Hash_size         = 0x%lx\n", Hash_size);
+	if (Hash_mask)
+		pr_info("Hash_mask         = 0x%lx\n", Hash_mask);
+}
+
+#ifdef CONFIG_PPC_KUEP
+void __init setup_kuep(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Execution Prevention\n");
+
+	if (cpu_has_feature(CPU_FTR_601))
+		pr_warn("KUEP is not working on powerpc 601 (No NX bit in Seg Regs)\n");
+
+	if (disabled)
+		pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n");
+}
+#endif
+
+#ifdef CONFIG_PPC_KUAP
+void __init setup_kuap(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Access Protection\n");
+
+	if (disabled)
+		pr_warn("KUAP cannot be disabled yet on 6xx when compiled in\n");
+}
+#endif
diff --git a/arch/powerpc/mm/book3s32/mmu_context.c b/arch/powerpc/mm/book3s32/mmu_context.c
new file mode 100644
index 000000000000..921c1e33e941
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/mmu_context.c
@@ -0,0 +1,118 @@
+/*
+ * This file contains the routines for handling the MMU on those
+ * PowerPC implementations where the MMU substantially follows the
+ * architecture specification.  This includes the 6xx, 7xx, 7xxx,
+ * and 8260 implementations but excludes the 8xx and 4xx.
+ *  -- paulus
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/export.h>
+
+#include <asm/mmu_context.h>
+
+/*
+ * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs
+ * (virtual segment identifiers) for each context.  Although the
+ * hardware supports 24-bit VSIDs, and thus >1 million contexts,
+ * we only use 32,768 of them.  That is ample, since there can be
+ * at most around 30,000 tasks in the system anyway, and it means
+ * that we can use a bitmap to indicate which contexts are in use.
+ * Using a bitmap means that we entirely avoid all of the problems
+ * that we used to have when the context number overflowed,
+ * particularly on SMP systems.
+ *  -- paulus.
+ */
+#define NO_CONTEXT      	((unsigned long) -1)
+#define LAST_CONTEXT    	32767
+#define FIRST_CONTEXT    	1
+
+/*
+ * This function defines the mapping from contexts to VSIDs (virtual
+ * segment IDs).  We use a skew on both the context and the high 4 bits
+ * of the 32-bit virtual address (the "effective segment ID") in order
+ * to spread out the entries in the MMU hash table.  Note, if this
+ * function is changed then arch/ppc/mm/hashtable.S will have to be
+ * changed to correspond.
+ *
+ *
+ * CTX_TO_VSID(ctx, va)	(((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \
+ *				 & 0xffffff)
+ */
+
+static unsigned long next_mmu_context;
+static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1];
+
+unsigned long __init_new_context(void)
+{
+	unsigned long ctx = next_mmu_context;
+
+	while (test_and_set_bit(ctx, context_map)) {
+		ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx);
+		if (ctx > LAST_CONTEXT)
+			ctx = 0;
+	}
+	next_mmu_context = (ctx + 1) & LAST_CONTEXT;
+
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(__init_new_context);
+
+/*
+ * Set up the context for a new address space.
+ */
+int init_new_context(struct task_struct *t, struct mm_struct *mm)
+{
+	mm->context.id = __init_new_context();
+
+	return 0;
+}
+
+/*
+ * Free a context ID. Make sure to call this with preempt disabled!
+ */
+void __destroy_context(unsigned long ctx)
+{
+	clear_bit(ctx, context_map);
+}
+EXPORT_SYMBOL_GPL(__destroy_context);
+
+/*
+ * We're finished using the context for an address space.
+ */
+void destroy_context(struct mm_struct *mm)
+{
+	preempt_disable();
+	if (mm->context.id != NO_CONTEXT) {
+		__destroy_context(mm->context.id);
+		mm->context.id = NO_CONTEXT;
+	}
+	preempt_enable();
+}
+
+/*
+ * Initialize the context management stuff.
+ */
+void __init mmu_context_init(void)
+{
+	/* Reserve context 0 for kernel use */
+	context_map[0] = (1 << FIRST_CONTEXT) - 1;
+	next_mmu_context = FIRST_CONTEXT;
+}
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
new file mode 100644
index 000000000000..8d56f0417f87
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -0,0 +1,173 @@
+/*
+ * This file contains the routines for TLB flushing.
+ * On machines where the MMU uses a hash table to store virtual to
+ * physical translations, these routines flush entries from the
+ * hash table also.
+ *  -- paulus
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/export.h>
+
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+#include <mm/mmu_decl.h>
+
+/*
+ * Called when unmapping pages to flush entries from the TLB/hash table.
+ */
+void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr)
+{
+	unsigned long ptephys;
+
+	if (Hash) {
+		ptephys = __pa(ptep) & PAGE_MASK;
+		flush_hash_pages(mm->context.id, addr, ptephys, 1);
+	}
+}
+EXPORT_SYMBOL(flush_hash_entry);
+
+/*
+ * Called at the end of a mmu_gather operation to make sure the
+ * TLB flush is completely done.
+ */
+void tlb_flush(struct mmu_gather *tlb)
+{
+	if (!Hash) {
+		/*
+		 * 603 needs to flush the whole TLB here since
+		 * it doesn't use a hash table.
+		 */
+		_tlbia();
+	}
+}
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes kernel pages
+ *
+ * since the hardware hash table functions as an extension of the
+ * tlb as far as the linux tables are concerned, flush it too.
+ *    -- Cort
+ */
+
+static void flush_range(struct mm_struct *mm, unsigned long start,
+			unsigned long end)
+{
+	pmd_t *pmd;
+	unsigned long pmd_end;
+	int count;
+	unsigned int ctx = mm->context.id;
+
+	if (!Hash) {
+		_tlbia();
+		return;
+	}
+	start &= PAGE_MASK;
+	if (start >= end)
+		return;
+	end = (end - 1) | ~PAGE_MASK;
+	pmd = pmd_offset(pud_offset(pgd_offset(mm, start), start), start);
+	for (;;) {
+		pmd_end = ((start + PGDIR_SIZE) & PGDIR_MASK) - 1;
+		if (pmd_end > end)
+			pmd_end = end;
+		if (!pmd_none(*pmd)) {
+			count = ((pmd_end - start) >> PAGE_SHIFT) + 1;
+			flush_hash_pages(ctx, start, pmd_val(*pmd), count);
+		}
+		if (pmd_end == end)
+			break;
+		start = pmd_end + 1;
+		++pmd;
+	}
+}
+
+/*
+ * Flush kernel TLB entries in the given range
+ */
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	flush_range(&init_mm, start, end);
+}
+EXPORT_SYMBOL(flush_tlb_kernel_range);
+
+/*
+ * Flush all the (user) entries for the address space described by mm.
+ */
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	struct vm_area_struct *mp;
+
+	if (!Hash) {
+		_tlbia();
+		return;
+	}
+
+	/*
+	 * It is safe to go down the mm's list of vmas when called
+	 * from dup_mmap, holding mmap_sem.  It would also be safe from
+	 * unmap_region or exit_mmap, but not from vmtruncate on SMP -
+	 * but it seems dup_mmap is the only SMP case which gets here.
+	 */
+	for (mp = mm->mmap; mp != NULL; mp = mp->vm_next)
+		flush_range(mp->vm_mm, mp->vm_start, mp->vm_end);
+}
+EXPORT_SYMBOL(flush_tlb_mm);
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+	struct mm_struct *mm;
+	pmd_t *pmd;
+
+	if (!Hash) {
+		_tlbie(vmaddr);
+		return;
+	}
+	mm = (vmaddr < TASK_SIZE)? vma->vm_mm: &init_mm;
+	pmd = pmd_offset(pud_offset(pgd_offset(mm, vmaddr), vmaddr), vmaddr);
+	if (!pmd_none(*pmd))
+		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
+}
+EXPORT_SYMBOL(flush_tlb_page);
+
+/*
+ * For each address in the range, find the pte for the address
+ * and check _PAGE_HASHPTE bit; if it is set, find and destroy
+ * the corresponding HPTE.
+ */
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+{
+	flush_range(vma->vm_mm, start, end);
+}
+EXPORT_SYMBOL(flush_tlb_range);
+
+void __init early_init_mmu(void)
+{
+}