static int pSeries_lpar_hpte_removebolted(unsigned long ea,
int psize, int ssize)
{
unsigned long vpn;
unsigned long slot, vsid;
vsid = get_kernel_vsid(ea, ssize);
vpn = hpt_vpn(ea, vsid, ssize);
slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
if (slot == -1)
return -ENOENT;
/*
* lpar doesn't use the passed actual page size
*/
pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
return 0;
}
/*
* Build an entry for the base kernel segment and put it into
* the segment table or SLB. All other segment table or SLB
* entries are faulted in.
*/
void stab_initialize(unsigned long stab)
{
unsigned long esid, vsid;
esid = GET_ESID(KERNELBASE);
vsid = get_kernel_vsid(esid << SID_SHIFT);
if (cur_cpu_spec->cpu_features & CPU_FTR_SLB) {
/* Invalidate the entire SLB & all the ERATS */
#ifdef CONFIG_PPC_ISERIES
asm volatile("isync; slbia; isync":::"memory");
#else
asm volatile("isync":::"memory");
asm volatile("slbmte %0,%0"::"r" (0) : "memory");
asm volatile("isync; slbia; isync":::"memory");
make_slbe(esid, vsid, 0, 1);
asm volatile("isync":::"memory");
#endif
} else {
static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
unsigned long lpar_rc, slot, vsid, va, dummy0, dummy1;
vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
va = (vsid << 28) | (ea & 0x0fffffff);
spin_lock(&beat_htab_lock);
slot = beat_lpar_hpte_find(va, psize);
BUG_ON(slot == -1);
lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7,
&dummy0, &dummy1);
spin_unlock(&beat_htab_lock);
BUG_ON(lpar_rc != 0);
}
static inline void
create_pte_mapping(unsigned long start, unsigned long end,
unsigned long mode, unsigned long mask, int large)
{
unsigned long addr;
HPTE *htab = (HPTE *)__v2a(htab_data.htab);
unsigned int step;
if (large)
step = 16*MB;
else
step = 4*KB;
for (addr = start; addr < end; addr += step) {
unsigned long vsid = get_kernel_vsid(addr);
unsigned long va = (vsid << 28) | (addr & 0xfffffff);
make_pte(htab, va, (unsigned long)__v2a(addr),
mode, mask, large);
}
}
static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
unsigned long vpn;
unsigned long lpar_rc, slot, vsid;
u64 dummy0, dummy1;
vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
vpn = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M);
raw_spin_lock(&beat_htab_lock);
slot = beat_lpar_hpte_find(vpn, psize);
BUG_ON(slot == -1);
lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7,
&dummy0, &dummy1);
raw_spin_unlock(&beat_htab_lock);
BUG_ON(lpar_rc != 0);
}
static long map_to_linear(ulong paddr)
{
unsigned long vaddr;
int psize;
unsigned long mode;
int slot;
uint shift;
unsigned long tmp_mode;
psize = MMU_PAGE_4K;
shift = mmu_psize_defs[psize].shift;
mode = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
vaddr = (ulong)__va(paddr);
{
unsigned long vpn, hash, hpteg;
unsigned long vsid = get_kernel_vsid(vaddr);
unsigned long va = (vsid << 28) | (vaddr & 0x0fffffff);
vpn = va >> shift;
tmp_mode = mode;
/* Make non-kernel text non-executable */
if (!in_kernel_text(vaddr))
tmp_mode = mode | HPTE_R_N;
hash = hpt_hash(va, shift);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
BUG_ON(!ppc_md.hpte_insert);
slot = ppc_md.hpte_insert(hpteg, va, paddr,
tmp_mode, HPTE_V_BOLTED, psize);
if (slot < 0)
printk(KERN_EMERG
"%s: no more bolted entries "
"HTAB[0x%lx]: 0x%lx\n",
__func__, hpteg, paddr);
}
return slot;
}
static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
unsigned long vpn;
unsigned long lpar_rc, slot, vsid, flags;
vsid = get_kernel_vsid(ea, ssize);
vpn = hpt_vpn(ea, vsid, ssize);
slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
flags = newpp & 7;
if (mmu_has_feature(MMU_FTR_KERNEL_RO))
/* Move pp0 into bit 8 (IBM 55) */
flags |= (newpp & HPTE_R_PP0) >> 55;
lpar_rc = plpar_pte_protect(flags, slot, 0);
BUG_ON(lpar_rc != H_SUCCESS);
}
/*
* Bolt the kernel addr space into the HPT
*/
static void __init iSeries_bolt_kernel(unsigned long saddr, unsigned long eaddr)
{
unsigned long pa;
unsigned long mode_rw = _PAGE_ACCESSED | _PAGE_COHERENT | PP_RWXX;
HPTE hpte;
for (pa=saddr; pa < eaddr ;pa+=PAGE_SIZE) {
unsigned long ea = (unsigned long)__va(pa);
unsigned long vsid = get_kernel_vsid( ea );
unsigned long va = ( vsid << 28 ) | ( pa & 0xfffffff );
unsigned long vpn = va >> PAGE_SHIFT;
unsigned long slot = HvCallHpt_findValid( &hpte, vpn );
if (hpte.dw0.dw0.v) {
/* HPTE exists, so just bolt it */
HvCallHpt_setSwBits(slot, 0x10, 0);
} else {
/* No HPTE exists, so create a new bolted one */
make_pte(NULL, va, (unsigned long)__v2a(ea),
mode_rw, 0, 0);
}
}
}
int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
unsigned long pstart, unsigned long mode, int psize)
{
unsigned long vaddr, paddr;
unsigned int step, shift;
unsigned long tmp_mode;
int ret = 0;
shift = mmu_psize_defs[psize].shift;
step = 1 << shift;
for (vaddr = vstart, paddr = pstart; vaddr < vend;
vaddr += step, paddr += step) {
unsigned long vpn, hash, hpteg;
unsigned long vsid = get_kernel_vsid(vaddr);
unsigned long va = (vsid << 28) | (vaddr & 0x0fffffff);
vpn = va >> shift;
tmp_mode = mode;
/* Make non-kernel text non-executable */
if (!in_kernel_text(vaddr))
tmp_mode = mode | HPTE_R_N;
hash = hpt_hash(va, shift);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
DBG("htab_bolt_mapping: calling %p\n", ppc_md.hpte_insert);
BUG_ON(!ppc_md.hpte_insert);
ret = ppc_md.hpte_insert(hpteg, va, paddr,
tmp_mode, HPTE_V_BOLTED, psize);
if (ret < 0)
break;
}
return ret < 0 ? ret : 0;
}
/*
* A linux PTE was changed and the corresponding hash table entry
* neesd to be flushed. This function will either perform the flush
* immediately or will batch it up if the current CPU has an active
* batch on it.
*/
void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge)
{
unsigned long vpn;
struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
unsigned long vsid;
unsigned int psize;
int ssize;
real_pte_t rpte;
int i;
i = batch->index;
/* Get page size (maybe move back to caller).
*
* NOTE: when using special 64K mappings in 4K environment like
* for SPEs, we obtain the page size from the slice, which thus
* must still exist (and thus the VMA not reused) at the time
* of this call
*/
if (huge) {
#ifdef CONFIG_HUGETLB_PAGE
psize = get_slice_psize(mm, addr);
/* Mask the address for the correct page size */
addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1);
#else
BUG();
psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */
#endif
} else {
psize = pte_pagesize_index(mm, addr, pte);
/* Mask the address for the standard page size. If we
* have a 64k page kernel, but the hardware does not
* support 64k pages, this might be different from the
* hardware page size encoded in the slice table. */
addr &= PAGE_MASK;
}
/* Build full vaddr */
if (!is_kernel_addr(addr)) {
ssize = user_segment_size(addr);
vsid = get_vsid(mm->context.id, addr, ssize);
} else {
vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
ssize = mmu_kernel_ssize;
}
WARN_ON(vsid == 0);
vpn = hpt_vpn(addr, vsid, ssize);
rpte = __real_pte(__pte(pte), ptep);
/*
* Check if we have an active batch on this CPU. If not, just
* flush now and return. For now, we don global invalidates
* in that case, might be worth testing the mm cpu mask though
* and decide to use local invalidates instead...
*/
if (!batch->active) {
flush_hash_page(vpn, rpte, psize, ssize, 0);
put_cpu_var(ppc64_tlb_batch);
return;
}
/*
* This can happen when we are in the middle of a TLB batch and
* we encounter memory pressure (eg copy_page_range when it tries
* to allocate a new pte). If we have to reclaim memory and end
* up scanning and resetting referenced bits then our batch context
* will change mid stream.
*
* We also need to ensure only one page size is present in a given
* batch
*/
if (i != 0 && (mm != batch->mm || batch->psize != psize ||
batch->ssize != ssize)) {
__flush_tlb_pending(batch);
i = 0;
}
if (i == 0) {
batch->mm = mm;
batch->psize = psize;
batch->ssize = ssize;
}
batch->pte[i] = rpte;
batch->vpn[i] = vpn;
batch->index = ++i;
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
put_cpu_var(ppc64_tlb_batch);
}
pgdp = pgd_offset_i(ea);
pmdp = pmd_alloc(&ioremap_mm, pgdp, ea);
ptep = pte_alloc_kernel(&ioremap_mm, pmdp, ea);
pa = abs_to_phys(pa);
set_pte(ptep, pfn_pte(pa >> PAGE_SHIFT, __pgprot(flags)));
spin_unlock(&ioremap_mm.page_table_lock);
} else {
unsigned long va, vpn, hash, hpteg;
/*
* If the mm subsystem is not fully up, we cannot create a
* linux page table entry for this mapping. Simply bolt an
* entry in the hardware page table.
*/
vsid = get_kernel_vsid(ea);
va = (vsid << 28) | (ea & 0xFFFFFFF);
vpn = va >> PAGE_SHIFT;
hash = hpt_hash(vpn, 0);
hpteg = ((hash & htab_data.htab_hash_mask)*HPTES_PER_GROUP);
/* Panic if a pte grpup is full */
if (ppc_md.hpte_insert(hpteg, va, pa >> PAGE_SHIFT, 0,
_PAGE_NO_CACHE|_PAGE_GUARDED|PP_RWXX,
1, 0) == -1) {
panic("map_io_page: could not insert mapping");
}
}
}
/* Result code is:
* 0 - handled
* 1 - normal page fault
* -1 - critical hash insertion error
*/
int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
{
void *pgdir;
unsigned long vsid;
struct mm_struct *mm;
pte_t *ptep;
cpumask_t tmp;
int rc, user_region = 0, local = 0;
int psize;
DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
ea, access, trap);
if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) {
DBG_LOW(" out of pgtable range !\n");
return 1;
}
/* Get region & vsid */
switch (REGION_ID(ea)) {
case USER_REGION_ID:
user_region = 1;
mm = current->mm;
if (! mm) {
DBG_LOW(" user region with no mm !\n");
return 1;
}
vsid = get_vsid(mm->context.id, ea);
psize = mm->context.user_psize;
break;
case VMALLOC_REGION_ID:
mm = &init_mm;
vsid = get_kernel_vsid(ea);
if (ea < VMALLOC_END)
psize = mmu_vmalloc_psize;
else
psize = mmu_io_psize;
break;
default:
/* Not a valid range
* Send the problem up to do_page_fault
*/
return 1;
}
DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);
/* Get pgdir */
pgdir = mm->pgd;
if (pgdir == NULL)
return 1;
/* Check CPU locality */
tmp = cpumask_of_cpu(smp_processor_id());
if (user_region && cpus_equal(mm->cpu_vm_mask, tmp))
local = 1;
/* Handle hugepage regions */
if (unlikely(in_hugepage_area(mm->context, ea))) {
DBG_LOW(" -> huge page !\n");
return hash_huge_page(mm, access, ea, vsid, local, trap);
}
/* Get PTE and page size from page tables */
ptep = find_linux_pte(pgdir, ea);
if (ptep == NULL || !pte_present(*ptep)) {
DBG_LOW(" no PTE !\n");
return 1;
}
#ifndef CONFIG_PPC_64K_PAGES
DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
#else
DBG_LOW(" i-pte: %016lx %016lx\n", pte_val(*ptep),
pte_val(*(ptep + PTRS_PER_PTE)));
#endif
/* Pre-check access permissions (will be re-checked atomically
* in __hash_page_XX but this pre-check is a fast path
*/
if (access & ~pte_val(*ptep)) {
DBG_LOW(" no access !\n");
return 1;
}
/* Do actual hashing */
#ifndef CONFIG_PPC_64K_PAGES
rc = __hash_page_4K(ea, access, vsid, ptep, trap, local);
#else
if (mmu_ci_restrictions) {
/* If this PTE is non-cacheable, switch to 4k */
if (psize == MMU_PAGE_64K &&
(pte_val(*ptep) & _PAGE_NO_CACHE)) {
if (user_region) {
psize = MMU_PAGE_4K;
mm->context.user_psize = MMU_PAGE_4K;
mm->context.sllp = SLB_VSID_USER |
mmu_psize_defs[MMU_PAGE_4K].sllp;
} else if (ea < VMALLOC_END) {
/*
* some driver did a non-cacheable mapping
* in vmalloc space, so switch vmalloc
* to 4k pages
*/
printk(KERN_ALERT "Reducing vmalloc segment "
"to 4kB pages because of "
"non-cacheable mapping\n");
psize = mmu_vmalloc_psize = MMU_PAGE_4K;
}
}
if (user_region) {
if (psize != get_paca()->context.user_psize) {
get_paca()->context = mm->context;
slb_flush_and_rebolt();
}
} else if (get_paca()->vmalloc_sllp !=
mmu_psize_defs[mmu_vmalloc_psize].sllp) {
get_paca()->vmalloc_sllp =
mmu_psize_defs[mmu_vmalloc_psize].sllp;
slb_flush_and_rebolt();
}
}
if (psize == MMU_PAGE_64K)
rc = __hash_page_64K(ea, access, vsid, ptep, trap, local);
else
rc = __hash_page_4K(ea, access, vsid, ptep, trap, local);
#endif /* CONFIG_PPC_64K_PAGES */
#ifndef CONFIG_PPC_64K_PAGES
DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
#else
DBG_LOW(" o-pte: %016lx %016lx\n", pte_val(*ptep),
pte_val(*(ptep + PTRS_PER_PTE)));
#endif
DBG_LOW(" -> rc=%d\n", rc);
return rc;
}
/*
* A linux PTE was changed and the corresponding hash table entry
* neesd to be flushed. This function will either perform the flush
* immediately or will batch it up if the current CPU has an active
* batch on it.
*
* Must be called from within some kind of spinlock/non-preempt region...
*/
void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge)
{
struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
unsigned long vsid, vaddr;
unsigned int psize;
real_pte_t rpte;
int i;
i = batch->index;
/* We mask the address for the base page size. Huge pages will
* have applied their own masking already
*/
addr &= PAGE_MASK;
/* Get page size (maybe move back to caller).
*
* NOTE: when using special 64K mappings in 4K environment like
* for SPEs, we obtain the page size from the slice, which thus
* must still exist (and thus the VMA not reused) at the time
* of this call
*/
if (huge) {
#ifdef CONFIG_HUGETLB_PAGE
psize = mmu_huge_psize;
#else
BUG();
psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */
#endif
} else
psize = pte_pagesize_index(mm, addr, pte);
/* Build full vaddr */
if (!is_kernel_addr(addr)) {
vsid = get_vsid(mm->context.id, addr);
WARN_ON(vsid == 0);
} else
vsid = get_kernel_vsid(addr);
vaddr = (vsid << 28 ) | (addr & 0x0fffffff);
rpte = __real_pte(__pte(pte), ptep);
/*
* Check if we have an active batch on this CPU. If not, just
* flush now and return. For now, we don global invalidates
* in that case, might be worth testing the mm cpu mask though
* and decide to use local invalidates instead...
*/
if (!batch->active) {
flush_hash_page(vaddr, rpte, psize, 0);
return;
}
/*
* This can happen when we are in the middle of a TLB batch and
* we encounter memory pressure (eg copy_page_range when it tries
* to allocate a new pte). If we have to reclaim memory and end
* up scanning and resetting referenced bits then our batch context
* will change mid stream.
*
* We also need to ensure only one page size is present in a given
* batch
*/
if (i != 0 && (mm != batch->mm || batch->psize != psize)) {
__flush_tlb_pending(batch);
i = 0;
}
if (i == 0) {
batch->mm = mm;
batch->psize = psize;
}
batch->pte[i] = rpte;
batch->vaddr[i] = vaddr;
batch->index = ++i;
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
}