summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r--arch/powerpc/mm/book3s32/hash_low.S27
-rw-r--r--arch/powerpc/mm/book3s32/mmu.c2
-rw-r--r--arch/powerpc/mm/book3s32/tlb.c11
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c12
-rw-r--r--arch/powerpc/mm/book3s64/iommu_api.c39
-rw-r--r--arch/powerpc/mm/book3s64/pgtable.c7
-rw-r--r--arch/powerpc/mm/book3s64/pkeys.c14
-rw-r--r--arch/powerpc/mm/book3s64/radix_pgtable.c19
-rw-r--r--arch/powerpc/mm/book3s64/radix_tlb.c7
-rw-r--r--arch/powerpc/mm/fault.c22
-rw-r--r--arch/powerpc/mm/ioremap.c21
-rw-r--r--arch/powerpc/mm/kasan/kasan_init_32.c19
-rw-r--r--arch/powerpc/mm/mem.c16
-rw-r--r--arch/powerpc/mm/nohash/40x.c4
-rw-r--r--arch/powerpc/mm/nohash/tlb_low.S12
-rw-r--r--arch/powerpc/mm/numa.c97
-rw-r--r--arch/powerpc/mm/pgtable_32.c41
-rw-r--r--arch/powerpc/mm/ptdump/bats.c8
-rw-r--r--arch/powerpc/mm/ptdump/hashpagetable.c7
-rw-r--r--arch/powerpc/mm/ptdump/ptdump.c8
-rw-r--r--arch/powerpc/mm/ptdump/segment_regs.c8
21 files changed, 214 insertions, 187 deletions
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 2015c4f96238..6d236080cb1a 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -35,7 +35,7 @@ mmu_hash_lock:
/*
* 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.
+ * _PAGE_RW (0x002) 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.
*
@@ -69,7 +69,7 @@ _GLOBAL(hash_page)
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 */
+ rlwimi r3,r9,32-14,31,31 /* MSR_PR -> _PAGE_USER */
112:
#ifndef CONFIG_PTE_64BIT
rlwimi r5,r4,12,20,29 /* insert top 10 bits of address */
@@ -94,7 +94,7 @@ _GLOBAL(hash_page)
#else
rlwimi r8,r4,23,20,28 /* compute pte address */
#endif
- rlwinm r0,r3,32-3,24,24 /* _PAGE_RW access -> _PAGE_DIRTY */
+ rlwinm r0,r3,6,24,24 /* _PAGE_RW access -> _PAGE_DIRTY */
ori r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
/*
@@ -310,11 +310,9 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
_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 */
+ and r8,r5,r0 /* writable if _RW & _DIRTY */
+ rlwimi r5,r5,1,30,30 /* _PAGE_USER -> PP msb */
ori r8,r8,0xe04 /* clear out reserved bits */
andc r8,r5,r8 /* PP = user? (rw&dirty? 1: 3): 0 */
BEGIN_FTR_SECTION
@@ -566,7 +564,7 @@ _GLOBAL(flush_hash_pages)
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 */
+ rlwinm r8,r8,0,~_PAGE_HASHPTE /* clear HASHPTE bit */
stwcx. r8,0,r5 /* update the pte */
bne- 33b
@@ -690,18 +688,21 @@ _GLOBAL(_tlbia)
bne- 10b
stwcx. r8,0,r9
bne- 10b
+#endif /* CONFIG_SMP */
+ li r5, 32
+ lis r4, KERNELBASE@h
+ mtctr r5
sync
- tlbia
+0: tlbie r4
+ addi r4, r4, 0x1000
+ bdnz 0b
sync
+#ifdef CONFIG_SMP
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
index f888cbb109b9..39ba53ca5bb5 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -312,7 +312,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea)
if (!Hash)
return;
- pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
+ pmd = pmd_ptr(mm, ea);
if (!pmd_none(*pmd))
add_hash_page(mm->context.id, ea, pmd_val(*pmd));
}
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
index 2fcd321040ff..dc9039a170aa 100644
--- a/arch/powerpc/mm/book3s32/tlb.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -79,15 +79,18 @@ static void flush_range(struct mm_struct *mm, unsigned long start,
int count;
unsigned int ctx = mm->context.id;
+ start &= PAGE_MASK;
if (!Hash) {
- _tlbia();
+ if (end - start <= PAGE_SIZE)
+ _tlbie(start);
+ else
+ _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);
+ pmd = pmd_ptr(mm, start);
for (;;) {
pmd_end = ((start + PGDIR_SIZE) & PGDIR_MASK) - 1;
if (pmd_end > end)
@@ -145,7 +148,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
return;
}
mm = (vmaddr < TASK_SIZE)? vma->vm_mm: &init_mm;
- pmd = pmd_offset(pud_offset(pgd_offset(mm, vmaddr), vmaddr), vmaddr);
+ pmd = pmd_ptr(mm, vmaddr);
if (!pmd_none(*pmd))
flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
}
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 523d4d39d11e..8ed2411c3f39 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -809,7 +809,8 @@ int resize_hpt_for_hotplug(unsigned long new_mem_size)
return 0;
}
-int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
+int hash__create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot)
{
int rc;
@@ -819,7 +820,7 @@ int hash__create_section_mapping(unsigned long start, unsigned long end, int nid
}
rc = htab_bolt_mapping(start, end, __pa(start),
- pgprot_val(PAGE_KERNEL), mmu_linear_psize,
+ pgprot_val(prot), mmu_linear_psize,
mmu_kernel_ssize);
if (rc < 0) {
@@ -2018,11 +2019,8 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n")
static int __init hash64_debugfs(void)
{
- if (!debugfs_create_file_unsafe("hpt_order", 0600, powerpc_debugfs_root,
- NULL, &fops_hpt_order)) {
- pr_err("lpar: unable to create hpt_order debugsfs file\n");
- }
-
+ debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, NULL,
+ &fops_hpt_order);
return 0;
}
machine_device_initcall(pseries, hash64_debugfs);
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index eba73ebd8ae5..fa05bbd1f682 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -121,24 +121,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
goto free_exit;
}
- pageshift = PAGE_SHIFT;
- for (i = 0; i < entries; ++i) {
- struct page *page = mem->hpages[i];
-
- /*
- * Allow to use larger than 64k IOMMU pages. Only do that
- * if we are backed by hugetlb.
- */
- if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
- pageshift = page_shift(compound_head(page));
- mem->pageshift = min(mem->pageshift, pageshift);
- /*
- * We don't need struct page reference any more, switch
- * to physical address.
- */
- mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
- }
-
good_exit:
atomic64_set(&mem->mapped, 1);
mem->used = 1;
@@ -158,6 +140,27 @@ good_exit:
}
}
+ if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
+ /*
+ * Allow to use larger than 64k IOMMU pages. Only do that
+ * if we are backed by hugetlb. Skip device memory as it is not
+ * backed with page structs.
+ */
+ pageshift = PAGE_SHIFT;
+ for (i = 0; i < entries; ++i) {
+ struct page *page = mem->hpages[i];
+
+ if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
+ pageshift = page_shift(compound_head(page));
+ mem->pageshift = min(mem->pageshift, pageshift);
+ /*
+ * We don't need struct page reference any more, switch
+ * to physical address.
+ */
+ mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+ }
+ }
+
list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
mutex_unlock(&mem_list_mutex);
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 2bf7e1b4fd82..e0bb69c616e4 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -171,12 +171,13 @@ void mmu_cleanup_all(void)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-int __meminit create_section_mapping(unsigned long start, unsigned long end, int nid)
+int __meminit create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot)
{
if (radix_enabled())
- return radix__create_section_mapping(start, end, nid);
+ return radix__create_section_mapping(start, end, nid, prot);
- return hash__create_section_mapping(start, end, nid);
+ return hash__create_section_mapping(start, end, nid, prot);
}
int __meminit remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 59e0ebbd8036..1199fc2bfaec 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -315,7 +315,7 @@ int __execute_only_pkey(struct mm_struct *mm)
static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
{
/* Do this check first since the vm_flags should be hot */
- if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC)
+ if ((vma->vm_flags & VM_ACCESS_FLAGS) != VM_EXEC)
return false;
return (vma_pkey(vma) == vma->vm_mm->context.execute_only_pkey);
@@ -381,18 +381,6 @@ bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
* So do not enforce things if the VMA is not from the current mm, or if we are
* in a kernel thread.
*/
-static inline bool vma_is_foreign(struct vm_area_struct *vma)
-{
- if (!current->mm)
- return true;
-
- /* if it is not our ->mm, it has to be foreign */
- if (current->mm != vma->vm_mm)
- return true;
-
- return false;
-}
-
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
bool execute, bool foreign)
{
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index dd1bea45325c..8f9edf07063a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -26,6 +26,7 @@
#include <asm/firmware.h>
#include <asm/powernv.h>
#include <asm/sections.h>
+#include <asm/smp.h>
#include <asm/trace.h>
#include <asm/uaccess.h>
#include <asm/ultravisor.h>
@@ -253,7 +254,7 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
static int __meminit create_physical_mapping(unsigned long start,
unsigned long end,
- int nid)
+ int nid, pgprot_t _prot)
{
unsigned long vaddr, addr, mapping_size = 0;
bool prev_exec, exec = false;
@@ -289,7 +290,7 @@ static int __meminit create_physical_mapping(unsigned long start,
prot = PAGE_KERNEL_X;
exec = true;
} else {
- prot = PAGE_KERNEL;
+ prot = _prot;
exec = false;
}
@@ -333,7 +334,7 @@ static void __init radix_init_pgtable(void)
WARN_ON(create_physical_mapping(reg->base,
reg->base + reg->size,
- -1));
+ -1, PAGE_KERNEL));
}
/* Find out how many PID bits are supported */
@@ -712,8 +713,10 @@ static int __meminit stop_machine_change_mapping(void *data)
spin_unlock(&init_mm.page_table_lock);
pte_clear(&init_mm, params->aligned_start, params->pte);
- create_physical_mapping(__pa(params->aligned_start), __pa(params->start), -1);
- create_physical_mapping(__pa(params->end), __pa(params->aligned_end), -1);
+ create_physical_mapping(__pa(params->aligned_start),
+ __pa(params->start), -1, PAGE_KERNEL);
+ create_physical_mapping(__pa(params->end), __pa(params->aligned_end),
+ -1, PAGE_KERNEL);
spin_lock(&init_mm.page_table_lock);
return 0;
}
@@ -870,14 +873,16 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
radix__flush_tlb_kernel_range(start, end);
}
-int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
+int __meminit radix__create_section_mapping(unsigned long start,
+ unsigned long end, int nid,
+ pgprot_t prot)
{
if (end >= RADIX_VMALLOC_START) {
pr_warn("Outside the supported range\n");
return -1;
}
- return create_physical_mapping(__pa(start), __pa(end), nid);
+ return create_physical_mapping(__pa(start), __pa(end), nid, prot);
}
int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 03f43c924e00..758ade2c2b6e 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -587,6 +587,11 @@ void radix__local_flush_all_mm(struct mm_struct *mm)
preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_all_mm);
+
+static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
+{
+ radix__local_flush_all_mm(mm);
+}
#endif /* CONFIG_SMP */
void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
@@ -777,7 +782,7 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
EXPORT_SYMBOL(radix__flush_tlb_page);
#else /* CONFIG_SMP */
-#define radix__flush_all_mm radix__local_flush_all_mm
+static inline void exit_flush_lazy_tlbs(struct mm_struct *mm) { }
#endif /* CONFIG_SMP */
static void do_tlbiel_kernel(void *info)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8db0507619e2..84af6c8eecf7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -314,7 +314,7 @@ static bool access_error(bool is_write, bool is_exec,
return false;
}
- if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+ if (unlikely(!vma_is_accessible(vma)))
return true;
/*
* We should ideally do the vma pkey access check here. But in the
@@ -434,7 +434,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ unsigned int flags = FAULT_FLAG_DEFAULT;
int is_exec = TRAP(regs) == 0x400;
int is_user = user_mode(regs);
int is_write = page_fault_is_write(error_code);
@@ -582,28 +582,18 @@ good_area:
major |= fault & VM_FAULT_MAJOR;
+ if (fault_signal_pending(fault, regs))
+ return user_mode(regs) ? 0 : SIGBUS;
+
/*
* Handle the retry right now, the mmap_sem has been released in that
* case.
*/
if (unlikely(fault & VM_FAULT_RETRY)) {
- /* We retry only once */
if (flags & FAULT_FLAG_ALLOW_RETRY) {
- /*
- * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
- * of starvation.
- */
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
- if (!fatal_signal_pending(current))
- goto retry;
+ goto retry;
}
-
- /*
- * User mode? Just return to handle the fatal exception otherwise
- * return to bad_page_fault
- */
- return is_user ? 0 : SIGBUS;
}
up_read(&current->mm->mmap_sem);
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index fc669643ce6a..b1a0aebe8c48 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -2,6 +2,7 @@
#include <linux/io.h>
#include <linux/slab.h>
+#include <linux/mmzone.h>
#include <linux/vmalloc.h>
#include <asm/io-workarounds.h>
@@ -97,3 +98,23 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
return NULL;
}
+
+#ifdef CONFIG_ZONE_DEVICE
+/*
+ * Override the generic version in mm/memremap.c.
+ *
+ * With hash translation, the direct-map range is mapped with just one
+ * page size selected by htab_init_page_sizes(). Consult
+ * mmu_psize_defs[] to determine the minimum page size alignment.
+*/
+unsigned long memremap_compat_align(void)
+{
+ unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift;
+
+ if (radix_enabled())
+ return SUBSECTION_SIZE;
+ return max(SUBSECTION_SIZE, 1UL << shift);
+
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index db5664dde5ff..cbcad369fcb2 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -36,7 +36,7 @@ static int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned
unsigned long k_cur, k_next;
pte_t *new = NULL;
- pmd = pmd_offset(pud_offset(pgd_offset_k(k_start), k_start), k_start);
+ pmd = pmd_ptr_k(k_start);
for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++) {
k_next = pgd_addr_end(k_cur, k_end);
@@ -78,7 +78,7 @@ static int __init kasan_init_region(void *start, size_t size)
block = memblock_alloc(k_end - k_start, PAGE_SIZE);
for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
- pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+ pmd_t *pmd = pmd_ptr_k(k_cur);
void *va = block + k_cur - k_start;
pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
@@ -101,8 +101,8 @@ static void __init kasan_remap_early_shadow_ro(void)
kasan_populate_pte(kasan_early_shadow_pte, prot);
- for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
- pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+ for (k_cur = k_start & PAGE_MASK; k_cur != k_end; k_cur += PAGE_SIZE) {
+ pmd_t *pmd = pmd_ptr_k(k_cur);
pte_t *ptep = pte_offset_kernel(pmd, k_cur);
if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
@@ -120,12 +120,6 @@ static void __init kasan_unmap_early_shadow_vmalloc(void)
unsigned long k_cur;
phys_addr_t pa = __pa(kasan_early_shadow_page);
- if (!early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
- int ret = kasan_init_shadow_page_tables(k_start, k_end);
-
- if (ret)
- panic("kasan: kasan_init_shadow_page_tables() failed");
- }
for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
pte_t *ptep = pte_offset_kernel(pmd, k_cur);
@@ -143,7 +137,8 @@ void __init kasan_mmu_init(void)
int ret;
struct memblock_region *reg;
- if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
+ IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
if (ret)
@@ -201,7 +196,7 @@ void __init kasan_early_init(void)
unsigned long addr = KASAN_SHADOW_START;
unsigned long end = KASAN_SHADOW_END;
unsigned long next;
- pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(addr), addr), addr);
+ pmd_t *pmd = pmd_ptr_k(addr);
BUILD_BUG_ON(KASAN_SHADOW_START & ~PGDIR_MASK);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1c07d5a3f543..041ed7cfd341 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -66,12 +66,6 @@ pte_t *kmap_pte;
EXPORT_SYMBOL(kmap_pte);
pgprot_t kmap_prot;
EXPORT_SYMBOL(kmap_prot);
-
-static inline pte_t *virt_to_kpte(unsigned long vaddr)
-{
- return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
- vaddr), vaddr), vaddr);
-}
#endif
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -96,7 +90,8 @@ int memory_add_physaddr_to_nid(u64 start)
}
#endif
-int __weak create_section_mapping(unsigned long start, unsigned long end, int nid)
+int __weak create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot)
{
return -ENODEV;
}
@@ -128,7 +123,7 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
}
int __ref arch_add_memory(int nid, u64 start, u64 size,
- struct mhp_restrictions *restrictions)
+ struct mhp_params *params)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -137,14 +132,15 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
resize_hpt_for_hotplug(memblock_phys_mem_size());
start = (unsigned long)__va(start);
- rc = create_section_mapping(start, start + size, nid);
+ rc = create_section_mapping(start, start + size, nid,
+ params->pgprot);
if (rc) {
pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
start, start + size, rc);
return -EFAULT;
}
- return __add_pages(nid, start_pfn, nr_pages, restrictions);
+ return __add_pages(nid, start_pfn, nr_pages, params);
}
void __ref arch_remove_memory(int nid, u64 start, u64 size,
diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c
index f348104eb461..82862723ab42 100644
--- a/arch/powerpc/mm/nohash/40x.c
+++ b/arch/powerpc/mm/nohash/40x.c
@@ -104,7 +104,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
pmd_t *pmdp;
unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_HWWRITE;
- pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+ pmdp = pmd_ptr_k(v);
*pmdp++ = __pmd(val);
*pmdp++ = __pmd(val);
*pmdp++ = __pmd(val);
@@ -119,7 +119,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
pmd_t *pmdp;
unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_HWWRITE;
- pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+ pmdp = pmd_ptr_k(v);
*pmdp = __pmd(val);
v += LARGE_PAGE_SIZE_4M;
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index 2ca407cedbe7..eaeee402f96e 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -397,7 +397,7 @@ _GLOBAL(set_context)
* extern void loadcam_entry(unsigned int index)
*
* Load TLBCAM[index] entry in to the L2 CAM MMU
- * Must preserve r7, r8, r9, and r10
+ * Must preserve r7, r8, r9, r10 and r11
*/
_GLOBAL(loadcam_entry)
mflr r5
@@ -433,6 +433,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
*/
_GLOBAL(loadcam_multi)
mflr r8
+ /* Don't switch to AS=1 if already there */
+ mfmsr r11
+ andi. r11,r11,MSR_IS
+ bne 10f
/*
* Set up temporary TLB entry that is the same as what we're
@@ -458,6 +462,7 @@ _GLOBAL(loadcam_multi)
mtmsr r6
isync
+10:
mr r9,r3
add r10,r3,r4
2: bl loadcam_entry
@@ -466,6 +471,10 @@ _GLOBAL(loadcam_multi)
mr r3,r9
blt 2b
+ /* Don't return to AS=0 if we were in AS=1 at function start */
+ andi. r11,r11,MSR_IS
+ bne 3f
+
/* Return to AS=0 and clear the temporary entry */
mfmsr r6
rlwinm. r6,r6,0,~(MSR_IS|MSR_DS)
@@ -481,6 +490,7 @@ _GLOBAL(loadcam_multi)
tlbwe
isync
+3:
mtlr r8
blr
#endif
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3c7dec70cda0..9fcf2d195830 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -461,25 +461,69 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
return nid;
}
+#ifdef CONFIG_PPC_SPLPAR
+static int vphn_get_nid(long lcpu)
+{
+ __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+ long rc, hwid;
+
+ /*
+ * On a shared lpar, device tree will not have node associativity.
+ * At this time lppaca, or its __old_status field may not be
+ * updated. Hence kernel cannot detect if its on a shared lpar. So
+ * request an explicit associativity irrespective of whether the
+ * lpar is shared or dedicated. Use the device tree property as a
+ * fallback. cpu_to_phys_id is only valid between
+ * smp_setup_cpu_maps() and smp_setup_pacas().
+ */
+ if (firmware_has_feature(FW_FEATURE_VPHN)) {
+ if (cpu_to_phys_id)
+ hwid = cpu_to_phys_id[lcpu];
+ else
+ hwid = get_hard_smp_processor_id(lcpu);
+
+ rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
+ if (rc == H_SUCCESS)
+ return associativity_to_nid(associativity);
+ }
+
+ return NUMA_NO_NODE;
+}
+#else
+static int vphn_get_nid(long unused)
+{
+ return NUMA_NO_NODE;
+}
+#endif /* CONFIG_PPC_SPLPAR */
+
/*
* Figure out to which domain a cpu belongs and stick it there.
* Return the id of the domain used.
*/
static int numa_setup_cpu(unsigned long lcpu)
{
- int nid = NUMA_NO_NODE;
struct device_node *cpu;
+ int fcpu = cpu_first_thread_sibling(lcpu);
+ int nid = NUMA_NO_NODE;
/*
* If a valid cpu-to-node mapping is already available, use it
* directly instead of querying the firmware, since it represents
* the most recent mapping notified to us by the platform (eg: VPHN).
+ * Since cpu_to_node binding remains the same for all threads in the
+ * core. If a valid cpu-to-node mapping is already available, for
+ * the first thread in the core, use it.
*/
- if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+ nid = numa_cpu_lookup_table[fcpu];
+ if (nid >= 0) {
map_cpu_to_node(lcpu, nid);
return nid;
}
+ nid = vphn_get_nid(lcpu);
+ if (nid != NUMA_NO_NODE)
+ goto out_present;
+
cpu = of_get_cpu_node(lcpu, NULL);
if (!cpu) {
@@ -491,13 +535,26 @@ static int numa_setup_cpu(unsigned long lcpu)
}
nid = of_node_to_nid_single(cpu);
+ of_node_put(cpu);
out_present:
if (nid < 0 || !node_possible(nid))
nid = first_online_node;
+ /*
+ * Update for the first thread of the core. All threads of a core
+ * have to be part of the same node. This not only avoids querying
+ * for every other thread in the core, but always avoids a case
+ * where virtual node associativity change causes subsequent threads
+ * of a core to be associated with different nid. However if first
+ * thread is already online, expect it to have a valid mapping.
+ */
+ if (fcpu != lcpu) {
+ WARN_ON(cpu_online(fcpu));
+ map_cpu_to_node(fcpu, nid);
+ }
+
map_cpu_to_node(lcpu, nid);
- of_node_put(cpu);
out:
return nid;
}
@@ -1191,23 +1248,30 @@ static long vphn_get_associativity(unsigned long cpu,
VPHN_FLAG_VCPU, associativity);
switch (rc) {
+ case H_SUCCESS:
+ dbg("VPHN hcall succeeded. Reset polling...\n");
+ timed_topology_update(0);
+ goto out;
+
case H_FUNCTION:
- printk_once(KERN_INFO
- "VPHN is not supported. Disabling polling...\n");
- stop_topology_update();
+ pr_err_ratelimited("VPHN unsupported. Disabling polling...\n");
break;
case H_HARDWARE:
- printk(KERN_ERR
- "hcall_vphn() experienced a hardware fault "
+ pr_err_ratelimited("hcall_vphn() experienced a hardware fault "
"preventing VPHN. Disabling polling...\n");
- stop_topology_update();
break;
- case H_SUCCESS:
- dbg("VPHN hcall succeeded. Reset polling...\n");
- timed_topology_update(0);
+ case H_PARAMETER:
+ pr_err_ratelimited("hcall_vphn() was passed an invalid parameter. "
+ "Disabling polling...\n");
+ break;
+ default:
+ pr_err_ratelimited("hcall_vphn() returned %ld. Disabling polling...\n"
+ , rc);
break;
}
+ stop_topology_update();
+out:
return rc;
}
@@ -1568,15 +1632,6 @@ int prrn_is_enabled(void)
return prrn_enabled;
}
-void __init shared_proc_topology_init(void)
-{
- if (lppaca_shared_proc(get_lppaca())) {
- bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
- nr_cpumask_bits);
- numa_update_cpu_topology(false);
- }
-}
-
static int topology_read(struct seq_file *file, void *v)
{
if (vphn_enabled || prrn_enabled)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 5fb90edd865e..f62de06e3d07 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -63,7 +63,7 @@ int __ref map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
int err = -ENOMEM;
/* Use upper 10 bits of VA to index the first level map */
- pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
+ pd = pmd_ptr_k(va);
/* Use middle 10 bits of VA to index the second-level map */
if (likely(slab_is_available()))
pg = pte_alloc_kernel(pd, va);
@@ -121,44 +121,9 @@ void __init mapin_ram(void)
}
}
-/* Scan the real Linux page tables and return a PTE pointer for
- * a virtual address in a context.
- * Returns true (1) if PTE was found, zero otherwise. The pointer to
- * the PTE pointer is unmodified if PTE is not found.
- */
-static int
-get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
- int retval = 0;
-
- pgd = pgd_offset(mm, addr & PAGE_MASK);
- if (pgd) {
- pud = pud_offset(pgd, addr & PAGE_MASK);
- if (pud && pud_present(*pud)) {
- pmd = pmd_offset(pud, addr & PAGE_MASK);
- if (pmd_present(*pmd)) {
- pte = pte_offset_map(pmd, addr & PAGE_MASK);
- if (pte) {
- retval = 1;
- *ptep = pte;
- if (pmdp)
- *pmdp = pmd;
- /* XXX caller needs to do pte_unmap, yuck */
- }
- }
- }
- }
- return(retval);
-}
-
static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
{
pte_t *kpte;
- pmd_t *kpmd;
unsigned long address;
BUG_ON(PageHighMem(page));
@@ -166,10 +131,10 @@ static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
if (v_block_mapped(address))
return 0;
- if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
+ kpte = virt_to_kpte(address);
+ if (!kpte)
return -EINVAL;
__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
- pte_unmap(kpte);
return 0;
}
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index 4154feac1da3..d3a5d6b318d1 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -164,10 +164,8 @@ static const struct file_operations bats_fops = {
static int __init bats_init(void)
{
- struct dentry *debugfs_file;
-
- debugfs_file = debugfs_create_file("block_address_translation", 0400,
- powerpc_debugfs_root, NULL, &bats_fops);
- return debugfs_file ? 0 : -ENOMEM;
+ debugfs_create_file("block_address_translation", 0400,
+ powerpc_debugfs_root, NULL, &bats_fops);
+ return 0;
}
device_initcall(bats_init);
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index a07278027c6f..b6ed9578382f 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -527,13 +527,10 @@ static const struct file_operations ptdump_fops = {
static int ptdump_init(void)
{
- struct dentry *debugfs_file;
-
if (!radix_enabled()) {
populate_markers();
- debugfs_file = debugfs_create_file("kernel_hash_pagetable",
- 0400, NULL, NULL, &ptdump_fops);
- return debugfs_file ? 0 : -ENOMEM;
+ debugfs_create_file("kernel_hash_pagetable", 0400, NULL, NULL,
+ &ptdump_fops);
}
return 0;
}
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 206156255247..d92bb8ea229c 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -417,12 +417,10 @@ void ptdump_check_wx(void)
static int ptdump_init(void)
{
- struct dentry *debugfs_file;
-
populate_markers();
build_pgtable_complete_mask();
- debugfs_file = debugfs_create_file("kernel_page_tables", 0400, NULL,
- NULL, &ptdump_fops);
- return debugfs_file ? 0 : -ENOMEM;
+ debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+ &ptdump_fops);
+ return 0;
}
device_initcall(ptdump_init);
diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c
index 501843664bb9..dde2fe8de4b2 100644
--- a/arch/powerpc/mm/ptdump/segment_regs.c
+++ b/arch/powerpc/mm/ptdump/segment_regs.c
@@ -55,10 +55,8 @@ static const struct file_operations sr_fops = {
static int __init sr_init(void)
{
- struct dentry *debugfs_file;
-
- debugfs_file = debugfs_create_file("segment_registers", 0400,
- powerpc_debugfs_root, NULL, &sr_fops);
- return debugfs_file ? 0 : -ENOMEM;
+ debugfs_create_file("segment_registers", 0400, powerpc_debugfs_root,
+ NULL, &sr_fops);
+ return 0;
}
device_initcall(sr_init);