hash_utils_64.c

/*
 * PowerPC64 port by Mike Corrigan and Dave Engebretsen
 *   {mikejc|engebret}@us.ibm.com
 *
 *    Copyright (c) 2000 Mike Corrigan <mikejc@us.ibm.com>
 *
 * SMP scalability work:
 *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
 * 
 *    Module name: htab.c
 *
 *    Description:
 *      PowerPC Hashed Page Table functions
 *
 * 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.
 */

#undef DEBUG
#undef DEBUG_LOW

#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/export.h>
#include <linux/ctype.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/memblock.h>
#include <linux/context_tracking.h>

#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
#include <asm/types.h>
#include <asm/uaccess.h>
#include <asm/machdep.h>
#include <asm/prom.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <asm/eeh.h>
#include <asm/tlb.h>
#include <asm/cacheflush.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/copro.h>
#include <asm/udbg.h>
#include <asm/code-patching.h>
#include <asm/fadump.h>
#include <asm/firmware.h>
#include <asm/tm.h>
#include <asm/trace.h>

#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif

#ifdef DEBUG_LOW
#define DBG_LOW(fmt...) udbg_printf(fmt)
#else
#define DBG_LOW(fmt...)
#endif

#define KB (1024)
#define MB (1024*KB)
#define GB (1024L*MB)

/*
 * Note:  pte   --> Linux PTE
 *        HPTE  --> PowerPC Hashed Page Table Entry
 *
 * Execution context:
 *   htab_initialize is called with the MMU off (of course), but
 *   the kernel has been copied down to zero so it can directly
 *   reference global data.  At this point it is very difficult
 *   to print debug info.
 *
 */

#ifdef CONFIG_U3_DART
extern unsigned long dart_tablebase;
#endif /* CONFIG_U3_DART */

static unsigned long _SDR1;
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
EXPORT_SYMBOL_GPL(mmu_psize_defs);

struct hash_pte *htab_address;
unsigned long htab_size_bytes;
unsigned long htab_hash_mask;
EXPORT_SYMBOL_GPL(htab_hash_mask);
int mmu_linear_psize = MMU_PAGE_4K;
EXPORT_SYMBOL_GPL(mmu_linear_psize);
int mmu_virtual_psize = MMU_PAGE_4K;
int mmu_vmalloc_psize = MMU_PAGE_4K;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
int mmu_vmemmap_psize = MMU_PAGE_4K;
#endif
int mmu_io_psize = MMU_PAGE_4K;
int mmu_kernel_ssize = MMU_SEGSIZE_256M;
EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
EXPORT_SYMBOL_GPL(mmu_slb_size);
#ifdef CONFIG_PPC_64K_PAGES
int mmu_ci_restrictions;
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
static u8 *linear_map_hash_slots;
static unsigned long linear_map_hash_count;
static DEFINE_SPINLOCK(linear_map_hash_lock);
#endif /* CONFIG_DEBUG_PAGEALLOC */

/* There are definitions of page sizes arrays to be used when none
 * is provided by the firmware.
 */

/* Pre-POWER4 CPUs (4k pages only)
 */
static struct mmu_psize_def mmu_psize_defaults_old[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
		.avpnm	= 0,
		.tlbiel = 0,
	},
};

/* POWER4, GPUL, POWER5
 *
 * Support for 16Mb large pages
 */
static struct mmu_psize_def mmu_psize_defaults_gp[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
		.avpnm	= 0,
		.tlbiel = 1,
	},
	[MMU_PAGE_16M] = {
		.shift	= 24,
		.sllp	= SLB_VSID_L,
		.penc   = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0,
			    [MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 },
		.avpnm	= 0x1UL,
		.tlbiel = 0,
	},
};

/*
 * 'R' and 'C' update notes:
 *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
 *     create writeable HPTEs without C set, because the hcall H_PROTECT
 *     that we use in that case will not update C
 *  - The above is however not a problem, because we also don't do that
 *     fancy "no flush" variant of eviction and we use H_REMOVE which will
 *     do the right thing and thus we don't have the race I described earlier
 *
 *    - Under bare metal,  we do have the race, so we need R and C set
 *    - We make sure R is always set and never lost
 *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
 */
unsigned long htab_convert_pte_flags(unsigned long pteflags)
{
	unsigned long rflags = 0;

	/* _PAGE_EXEC -> NOEXEC */
	if ((pteflags & _PAGE_EXEC) == 0)
		rflags |= HPTE_R_N;
	/*
	 * PPP bits:
	 * Linux uses slb key 0 for kernel and 1 for user.
	 * kernel RW areas are mapped with PPP=0b000
	 * User area is mapped with PPP=0b010 for read/write
	 * or PPP=0b011 for read-only (including writeable but clean pages).
	 */
	if (pteflags & _PAGE_PRIVILEGED) {
		/*
		 * Kernel read only mapped with ppp bits 0b110
		 */
		if (!(pteflags & _PAGE_WRITE))
			rflags |= (HPTE_R_PP0 | 0x2);
	} else {
		if (pteflags & _PAGE_RWX)
			rflags |= 0x2;
		if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
			rflags |= 0x1;
	}