s390/vmem: consolidate vmem_add_range() and vmem_remove_range()

We want to have only a single pagetable walker and reuse the same
functionality for vmemmap handling. Let's start by consolidating
vmem_add_range() and vmem_remove_range(), converting it into a
recursive implementation.

A recursive implementation makes it easier to expand individual cases
without harming readability. In addition, we minimize traversing the
whole hierarchy over and over again.

One change is that we don't unmap large PMDs/PUDs when not completely
covered by the request, something that should never happen with direct
mappings, unless one would be removing in other granularity than added,
which would be broken already.

Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20200722094558.9828-3-david@redhat.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
This commit is contained in:
David Hildenbrand 2020-07-22 11:45:51 +02:00 committed by Heiko Carstens
parent 8398b226b8
commit 3e0d3e408e

View File

@ -54,88 +54,218 @@ pte_t __ref *vmem_pte_alloc(void)
return pte;
}
static void modify_pte_table(pmd_t *pmd, unsigned long addr, unsigned long end,
bool add)
{
unsigned long prot, pages = 0;
pte_t *pte;
prot = pgprot_val(PAGE_KERNEL);
if (!MACHINE_HAS_NX)
prot &= ~_PAGE_NOEXEC;
pte = pte_offset_kernel(pmd, addr);
for (; addr < end; addr += PAGE_SIZE, pte++) {
if (!add) {
if (pte_none(*pte))
continue;
pte_clear(&init_mm, addr, pte);
} else if (pte_none(*pte)) {
pte_val(*pte) = addr | prot;
} else
continue;
pages++;
}
update_page_count(PG_DIRECT_MAP_4K, add ? pages : -pages);
}
static int modify_pmd_table(pud_t *pud, unsigned long addr, unsigned long end,
bool add)
{
unsigned long next, prot, pages = 0;
int ret = -ENOMEM;
pmd_t *pmd;
pte_t *pte;
prot = pgprot_val(SEGMENT_KERNEL);
if (!MACHINE_HAS_NX)
prot &= ~_SEGMENT_ENTRY_NOEXEC;
pmd = pmd_offset(pud, addr);
for (; addr < end; addr = next, pmd++) {
next = pmd_addr_end(addr, end);
if (!add) {
if (pmd_none(*pmd))
continue;
if (pmd_large(*pmd) && !add) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
pmd_clear(pmd);
pages++;
}
continue;
}
} else if (pmd_none(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE) &&
MACHINE_HAS_EDAT1 && addr &&
!debug_pagealloc_enabled()) {
pmd_val(*pmd) = addr | prot;
pages++;
continue;
}
pte = vmem_pte_alloc();
if (!pte)
goto out;
pmd_populate(&init_mm, pmd, pte);
} else if (pmd_large(*pmd))
continue;
modify_pte_table(pmd, addr, next, add);
}
ret = 0;
out:
update_page_count(PG_DIRECT_MAP_1M, add ? pages : -pages);
return ret;
}
static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
bool add)
{
unsigned long next, prot, pages = 0;
int ret = -ENOMEM;
pud_t *pud;
pmd_t *pmd;
prot = pgprot_val(REGION3_KERNEL);
if (!MACHINE_HAS_NX)
prot &= ~_REGION_ENTRY_NOEXEC;
pud = pud_offset(p4d, addr);
for (; addr < end; addr = next, pud++) {
next = pud_addr_end(addr, end);
if (!add) {
if (pud_none(*pud))
continue;
if (pud_large(*pud)) {
if (IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE)) {
pud_clear(pud);
pages++;
}
continue;
}
} else if (pud_none(*pud)) {
if (IS_ALIGNED(addr, PUD_SIZE) &&
IS_ALIGNED(next, PUD_SIZE) &&
MACHINE_HAS_EDAT2 && addr &&
!debug_pagealloc_enabled()) {
pud_val(*pud) = addr | prot;
pages++;
continue;
}
pmd = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
if (!pmd)
goto out;
pud_populate(&init_mm, pud, pmd);
} else if (pud_large(*pud))
continue;
ret = modify_pmd_table(pud, addr, next, add);
if (ret)
goto out;
}
ret = 0;
out:
update_page_count(PG_DIRECT_MAP_2G, add ? pages : -pages);
return ret;
}
static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end,
bool add)
{
unsigned long next;
int ret = -ENOMEM;
p4d_t *p4d;
pud_t *pud;
p4d = p4d_offset(pgd, addr);
for (; addr < end; addr = next, p4d++) {
next = p4d_addr_end(addr, end);
if (!add) {
if (p4d_none(*p4d))
continue;
} else if (p4d_none(*p4d)) {
pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
if (!pud)
goto out;
}
ret = modify_pud_table(p4d, addr, next, add);
if (ret)
goto out;
}
ret = 0;
out:
return ret;
}
static int modify_pagetable(unsigned long start, unsigned long end, bool add)
{
unsigned long addr, next;
int ret = -ENOMEM;
pgd_t *pgd;
p4d_t *p4d;
if (WARN_ON_ONCE(!PAGE_ALIGNED(start | end)))
return -EINVAL;
for (addr = start; addr < end; addr = next) {
next = pgd_addr_end(addr, end);
pgd = pgd_offset_k(addr);
if (!add) {
if (pgd_none(*pgd))
continue;
} else if (pgd_none(*pgd)) {
p4d = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
if (!p4d)
goto out;
pgd_populate(&init_mm, pgd, p4d);
}
ret = modify_p4d_table(pgd, addr, next, add);
if (ret)
goto out;
}
ret = 0;
out:
if (!add)
flush_tlb_kernel_range(start, end);
return ret;
}
static int add_pagetable(unsigned long start, unsigned long end)
{
return modify_pagetable(start, end, true);
}
static int remove_pagetable(unsigned long start, unsigned long end)
{
return modify_pagetable(start, end, false);
}
/*
* Add a physical memory range to the 1:1 mapping.
*/
static int vmem_add_range(unsigned long start, unsigned long size)
{
unsigned long pgt_prot, sgt_prot, r3_prot;
unsigned long pages4k, pages1m, pages2g;
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
int ret = -ENOMEM;
pgt_prot = pgprot_val(PAGE_KERNEL);
sgt_prot = pgprot_val(SEGMENT_KERNEL);
r3_prot = pgprot_val(REGION3_KERNEL);
if (!MACHINE_HAS_NX) {
pgt_prot &= ~_PAGE_NOEXEC;
sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
r3_prot &= ~_REGION_ENTRY_NOEXEC;
}
pages4k = pages1m = pages2g = 0;
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
if (!p4_dir)
goto out;
pgd_populate(&init_mm, pg_dir, p4_dir);
}
p4_dir = p4d_offset(pg_dir, address);
if (p4d_none(*p4_dir)) {
pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
if (!pu_dir)
goto out;
p4d_populate(&init_mm, p4_dir, pu_dir);
}
pu_dir = pud_offset(p4_dir, address);
if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
!(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
!debug_pagealloc_enabled()) {
pud_val(*pu_dir) = address | r3_prot;
address += PUD_SIZE;
pages2g++;
continue;
}
if (pud_none(*pu_dir)) {
pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
if (!pm_dir)
goto out;
pud_populate(&init_mm, pu_dir, pm_dir);
}
pm_dir = pmd_offset(pu_dir, address);
if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
!(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
!debug_pagealloc_enabled()) {
pmd_val(*pm_dir) = address | sgt_prot;
address += PMD_SIZE;
pages1m++;
continue;
}
if (pmd_none(*pm_dir)) {
pt_dir = vmem_pte_alloc();
if (!pt_dir)
goto out;
pmd_populate(&init_mm, pm_dir, pt_dir);
}
pt_dir = pte_offset_kernel(pm_dir, address);
pte_val(*pt_dir) = address | pgt_prot;
address += PAGE_SIZE;
pages4k++;
}
ret = 0;
out:
update_page_count(PG_DIRECT_MAP_4K, pages4k);
update_page_count(PG_DIRECT_MAP_1M, pages1m);
update_page_count(PG_DIRECT_MAP_2G, pages2g);
return ret;
return add_pagetable(start, start + size);
}
/*
@ -144,58 +274,7 @@ out:
*/
static void vmem_remove_range(unsigned long start, unsigned long size)
{
unsigned long pages4k, pages1m, pages2g;
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
pages4k = pages1m = pages2g = 0;
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
address += PGDIR_SIZE;
continue;
}
p4_dir = p4d_offset(pg_dir, address);
if (p4d_none(*p4_dir)) {
address += P4D_SIZE;
continue;
}
pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
address += PUD_SIZE;
continue;
}
if (pud_large(*pu_dir)) {
pud_clear(pu_dir);
address += PUD_SIZE;
pages2g++;
continue;
}
pm_dir = pmd_offset(pu_dir, address);
if (pmd_none(*pm_dir)) {
address += PMD_SIZE;
continue;
}
if (pmd_large(*pm_dir)) {
pmd_clear(pm_dir);
address += PMD_SIZE;
pages1m++;
continue;
}
pt_dir = pte_offset_kernel(pm_dir, address);
pte_clear(&init_mm, address, pt_dir);
address += PAGE_SIZE;
pages4k++;
}
flush_tlb_kernel_range(start, end);
update_page_count(PG_DIRECT_MAP_4K, -pages4k);
update_page_count(PG_DIRECT_MAP_1M, -pages1m);
update_page_count(PG_DIRECT_MAP_2G, -pages2g);
remove_pagetable(start, start + size);
}
/*