s390: convert various pgalloc functions to use ptdescs

As part of the conversions to replace pgtable constructor/destructors with
ptdesc equivalents, convert various page table functions to use ptdescs.

Some of the functions use the *get*page*() helper functions.  Convert
these to use pagetable_alloc() and ptdesc_address() instead to help
standardize page tables further.

Link: https://lkml.kernel.org/r/20230807230513.102486-15-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Vishal Moola (Oracle) 2023-08-07 16:04:56 -07:00 committed by Andrew Morton
parent f92c494f42
commit 6326c26c15
3 changed files with 69 additions and 67 deletions

View File

@ -86,7 +86,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
if (!table)
return NULL;
crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) {
crst_table_free(mm, table);
return NULL;
}
@ -97,7 +97,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
if (mm_pmd_folded(mm))
return;
pgtable_pmd_page_dtor(virt_to_page(pmd));
pagetable_pmd_dtor(virt_to_ptdesc(pmd));
crst_table_free(mm, (unsigned long *) pmd);
}

View File

@ -89,12 +89,12 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
{
if (mm_pmd_folded(tlb->mm))
return;
pgtable_pmd_page_dtor(virt_to_page(pmd));
pagetable_pmd_dtor(virt_to_ptdesc(pmd));
__tlb_adjust_range(tlb, address, PAGE_SIZE);
tlb->mm->context.flush_mm = 1;
tlb->freed_tables = 1;
tlb->cleared_puds = 1;
tlb_remove_table(tlb, pmd);
tlb_remove_ptdesc(tlb, pmd);
}
/*

View File

@ -43,17 +43,17 @@ __initcall(page_table_register_sysctl);
unsigned long *crst_table_alloc(struct mm_struct *mm)
{
struct page *page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER);
if (!page)
if (!ptdesc)
return NULL;
arch_set_page_dat(page, CRST_ALLOC_ORDER);
return (unsigned long *) page_to_virt(page);
arch_set_page_dat(ptdesc_page(ptdesc), CRST_ALLOC_ORDER);
return (unsigned long *) ptdesc_to_virt(ptdesc);
}
void crst_table_free(struct mm_struct *mm, unsigned long *table)
{
free_pages((unsigned long)table, CRST_ALLOC_ORDER);
pagetable_free(virt_to_ptdesc(table));
}
static void __crst_table_upgrade(void *arg)
@ -140,21 +140,21 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
struct page *page_table_alloc_pgste(struct mm_struct *mm)
{
struct page *page;
struct ptdesc *ptdesc;
u64 *table;
page = alloc_page(GFP_KERNEL);
if (page) {
table = (u64 *)page_to_virt(page);
ptdesc = pagetable_alloc(GFP_KERNEL, 0);
if (ptdesc) {
table = (u64 *)ptdesc_to_virt(ptdesc);
memset64(table, _PAGE_INVALID, PTRS_PER_PTE);
memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
}
return page;
return ptdesc_page(ptdesc);
}
void page_table_free_pgste(struct page *page)
{
__free_page(page);
pagetable_free(page_ptdesc(page));
}
#endif /* CONFIG_PGSTE */
@ -242,7 +242,7 @@ void page_table_free_pgste(struct page *page)
unsigned long *page_table_alloc(struct mm_struct *mm)
{
unsigned long *table;
struct page *page;
struct ptdesc *ptdesc;
unsigned int mask, bit;
/* Try to get a fragment of a 4K page as a 2K page table */
@ -250,9 +250,9 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
table = NULL;
spin_lock_bh(&mm->context.lock);
if (!list_empty(&mm->context.pgtable_list)) {
page = list_first_entry(&mm->context.pgtable_list,
struct page, lru);
mask = atomic_read(&page->_refcount) >> 24;
ptdesc = list_first_entry(&mm->context.pgtable_list,
struct ptdesc, pt_list);
mask = atomic_read(&ptdesc->_refcount) >> 24;
/*
* The pending removal bits must also be checked.
* Failure to do so might lead to an impossible
@ -264,13 +264,13 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
*/
mask = (mask | (mask >> 4)) & 0x03U;
if (mask != 0x03U) {
table = (unsigned long *) page_to_virt(page);
table = (unsigned long *) ptdesc_to_virt(ptdesc);
bit = mask & 1; /* =1 -> second 2K */
if (bit)
table += PTRS_PER_PTE;
atomic_xor_bits(&page->_refcount,
atomic_xor_bits(&ptdesc->_refcount,
0x01U << (bit + 24));
list_del_init(&page->lru);
list_del_init(&ptdesc->pt_list);
}
}
spin_unlock_bh(&mm->context.lock);
@ -278,28 +278,28 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
return table;
}
/* Allocate a fresh page */
page = alloc_page(GFP_KERNEL);
if (!page)
ptdesc = pagetable_alloc(GFP_KERNEL, 0);
if (!ptdesc)
return NULL;
if (!pgtable_pte_page_ctor(page)) {
__free_page(page);
if (!pagetable_pte_ctor(ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
arch_set_page_dat(page, 0);
arch_set_page_dat(ptdesc_page(ptdesc), 0);
/* Initialize page table */
table = (unsigned long *) page_to_virt(page);
table = (unsigned long *) ptdesc_to_virt(ptdesc);
if (mm_alloc_pgste(mm)) {
/* Return 4K page table with PGSTEs */
INIT_LIST_HEAD(&page->lru);
atomic_xor_bits(&page->_refcount, 0x03U << 24);
INIT_LIST_HEAD(&ptdesc->pt_list);
atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);
memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
} else {
/* Return the first 2K fragment of the page */
atomic_xor_bits(&page->_refcount, 0x01U << 24);
atomic_xor_bits(&ptdesc->_refcount, 0x01U << 24);
memset64((u64 *)table, _PAGE_INVALID, 2 * PTRS_PER_PTE);
spin_lock_bh(&mm->context.lock);
list_add(&page->lru, &mm->context.pgtable_list);
list_add(&ptdesc->pt_list, &mm->context.pgtable_list);
spin_unlock_bh(&mm->context.lock);
}
return table;
@ -322,19 +322,18 @@ static void page_table_release_check(struct page *page, void *table,
static void pte_free_now(struct rcu_head *head)
{
struct page *page;
struct ptdesc *ptdesc;
page = container_of(head, struct page, rcu_head);
pgtable_pte_page_dtor(page);
__free_page(page);
ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
pagetable_pte_dtor(ptdesc);
pagetable_free(ptdesc);
}
void page_table_free(struct mm_struct *mm, unsigned long *table)
{
unsigned int mask, bit, half;
struct page *page;
struct ptdesc *ptdesc = virt_to_ptdesc(table);
page = virt_to_page(table);
if (!mm_alloc_pgste(mm)) {
/* Free 2K page table fragment of a 4K page */
bit = ((unsigned long) table & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
@ -344,51 +343,50 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
* will happen outside of the critical section from this
* function or from __tlb_remove_table()
*/
mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24));
mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24));
mask >>= 24;
if ((mask & 0x03U) && !PageActive(page)) {
if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) {
/*
* Other half is allocated, and neither half has had
* its free deferred: add page to head of list, to make
* this freed half available for immediate reuse.
*/
list_add(&page->lru, &mm->context.pgtable_list);
list_add(&ptdesc->pt_list, &mm->context.pgtable_list);
} else {
/* If page is on list, now remove it. */
list_del_init(&page->lru);
list_del_init(&ptdesc->pt_list);
}
spin_unlock_bh(&mm->context.lock);
mask = atomic_xor_bits(&page->_refcount, 0x10U << (bit + 24));
mask = atomic_xor_bits(&ptdesc->_refcount, 0x10U << (bit + 24));
mask >>= 24;
if (mask != 0x00U)
return;
half = 0x01U << bit;
} else {
half = 0x03U;
mask = atomic_xor_bits(&page->_refcount, 0x03U << 24);
mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
mask >>= 24;
}
page_table_release_check(page, table, half, mask);
if (TestClearPageActive(page))
call_rcu(&page->rcu_head, pte_free_now);
page_table_release_check(ptdesc_page(ptdesc), table, half, mask);
if (folio_test_clear_active(ptdesc_folio(ptdesc)))
call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
else
pte_free_now(&page->rcu_head);
pte_free_now(&ptdesc->pt_rcu_head);
}
void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
unsigned long vmaddr)
{
struct mm_struct *mm;
struct page *page;
unsigned int bit, mask;
struct ptdesc *ptdesc = virt_to_ptdesc(table);
mm = tlb->mm;
page = virt_to_page(table);
if (mm_alloc_pgste(mm)) {
gmap_unlink(mm, table, vmaddr);
table = (unsigned long *) ((unsigned long)table | 0x03U);
tlb_remove_table(tlb, table);
tlb_remove_ptdesc(tlb, table);
return;
}
bit = ((unsigned long) table & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
@ -398,19 +396,19 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
* outside of the critical section from __tlb_remove_table() or from
* page_table_free()
*/
mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24));
mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24));
mask >>= 24;
if ((mask & 0x03U) && !PageActive(page)) {
if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) {
/*
* Other half is allocated, and neither half has had
* its free deferred: add page to end of list, to make
* this freed half available for reuse once its pending
* bit has been cleared by __tlb_remove_table().
*/
list_add_tail(&page->lru, &mm->context.pgtable_list);
list_add_tail(&ptdesc->pt_list, &mm->context.pgtable_list);
} else {
/* If page is on list, now remove it. */
list_del_init(&page->lru);
list_del_init(&ptdesc->pt_list);
}
spin_unlock_bh(&mm->context.lock);
table = (unsigned long *) ((unsigned long) table | (0x01U << bit));
@ -421,30 +419,30 @@ void __tlb_remove_table(void *_table)
{
unsigned int mask = (unsigned long) _table & 0x03U, half = mask;
void *table = (void *)((unsigned long) _table ^ mask);
struct page *page = virt_to_page(table);
struct ptdesc *ptdesc = virt_to_ptdesc(table);
switch (half) {
case 0x00U: /* pmd, pud, or p4d */
free_pages((unsigned long)table, CRST_ALLOC_ORDER);
pagetable_free(ptdesc);
return;
case 0x01U: /* lower 2K of a 4K page table */
case 0x02U: /* higher 2K of a 4K page table */
mask = atomic_xor_bits(&page->_refcount, mask << (4 + 24));
mask = atomic_xor_bits(&ptdesc->_refcount, mask << (4 + 24));
mask >>= 24;
if (mask != 0x00U)
return;
break;
case 0x03U: /* 4K page table with pgstes */
mask = atomic_xor_bits(&page->_refcount, 0x03U << 24);
mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24);
mask >>= 24;
break;
}
page_table_release_check(page, table, half, mask);
if (TestClearPageActive(page))
call_rcu(&page->rcu_head, pte_free_now);
page_table_release_check(ptdesc_page(ptdesc), table, half, mask);
if (folio_test_clear_active(ptdesc_folio(ptdesc)))
call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
else
pte_free_now(&page->rcu_head);
pte_free_now(&ptdesc->pt_rcu_head);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@ -488,16 +486,20 @@ static void base_pgt_free(unsigned long *table)
static unsigned long *base_crst_alloc(unsigned long val)
{
unsigned long *table;
struct ptdesc *ptdesc;
table = (unsigned long *)__get_free_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
if (table)
crst_table_init(table, val);
ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, CRST_ALLOC_ORDER);
if (!ptdesc)
return NULL;
table = ptdesc_address(ptdesc);
crst_table_init(table, val);
return table;
}
static void base_crst_free(unsigned long *table)
{
free_pages((unsigned long)table, CRST_ALLOC_ORDER);
pagetable_free(virt_to_ptdesc(table));
}
#define BASE_ADDR_END_FUNC(NAME, SIZE) \