6846787eed
commit d794734c9bbfe22f86686dc2909c25f5ffe1a572 upstream. When ident_pud_init() uses only gbpages to create identity maps, large ranges of addresses not actually requested can be included in the resulting table; a 4K request will map a full GB. On UV systems, this ends up including regions that will cause hardware to halt the system if accessed (these are marked "reserved" by BIOS). Even processor speculation into these regions is enough to trigger the system halt. Only use gbpages when map creation requests include the full GB page of space. Fall back to using smaller 2M pages when only portions of a GB page are included in the request. No attempt is made to coalesce mapping requests. If a request requires a map entry at the 2M (pmd) level, subsequent mapping requests within the same 1G region will also be at the pmd level, even if adjacent or overlapping such requests could have been combined to map a full gbpage. Existing usage starts with larger regions and then adds smaller regions, so this should not have any great consequence. [ dhansen: fix up comment formatting, simplifty changelog ] Signed-off-by: Steve Wahl <steve.wahl@hpe.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20240126164841.170866-1-steve.wahl%40hpe.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
160 lines
3.7 KiB
C
Executable file
160 lines
3.7 KiB
C
Executable file
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Helper routines for building identity mapping page tables. This is
|
|
* included by both the compressed kernel and the regular kernel.
|
|
*/
|
|
|
|
static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
|
|
unsigned long addr, unsigned long end)
|
|
{
|
|
addr &= PMD_MASK;
|
|
for (; addr < end; addr += PMD_SIZE) {
|
|
pmd_t *pmd = pmd_page + pmd_index(addr);
|
|
|
|
if (pmd_present(*pmd))
|
|
continue;
|
|
|
|
set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
|
|
}
|
|
}
|
|
|
|
static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
|
|
unsigned long addr, unsigned long end)
|
|
{
|
|
unsigned long next;
|
|
|
|
for (; addr < end; addr = next) {
|
|
pud_t *pud = pud_page + pud_index(addr);
|
|
pmd_t *pmd;
|
|
bool use_gbpage;
|
|
|
|
next = (addr & PUD_MASK) + PUD_SIZE;
|
|
if (next > end)
|
|
next = end;
|
|
|
|
/* if this is already a gbpage, this portion is already mapped */
|
|
if (pud_large(*pud))
|
|
continue;
|
|
|
|
/* Is using a gbpage allowed? */
|
|
use_gbpage = info->direct_gbpages;
|
|
|
|
/* Don't use gbpage if it maps more than the requested region. */
|
|
/* at the begining: */
|
|
use_gbpage &= ((addr & ~PUD_MASK) == 0);
|
|
/* ... or at the end: */
|
|
use_gbpage &= ((next & ~PUD_MASK) == 0);
|
|
|
|
/* Never overwrite existing mappings */
|
|
use_gbpage &= !pud_present(*pud);
|
|
|
|
if (use_gbpage) {
|
|
pud_t pudval;
|
|
|
|
pudval = __pud((addr - info->offset) | info->page_flag);
|
|
set_pud(pud, pudval);
|
|
continue;
|
|
}
|
|
|
|
if (pud_present(*pud)) {
|
|
pmd = pmd_offset(pud, 0);
|
|
ident_pmd_init(info, pmd, addr, next);
|
|
continue;
|
|
}
|
|
pmd = (pmd_t *)info->alloc_pgt_page(info->context);
|
|
if (!pmd)
|
|
return -ENOMEM;
|
|
ident_pmd_init(info, pmd, addr, next);
|
|
set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag));
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
|
|
unsigned long addr, unsigned long end)
|
|
{
|
|
unsigned long next;
|
|
int result;
|
|
|
|
for (; addr < end; addr = next) {
|
|
p4d_t *p4d = p4d_page + p4d_index(addr);
|
|
pud_t *pud;
|
|
|
|
next = (addr & P4D_MASK) + P4D_SIZE;
|
|
if (next > end)
|
|
next = end;
|
|
|
|
if (p4d_present(*p4d)) {
|
|
pud = pud_offset(p4d, 0);
|
|
result = ident_pud_init(info, pud, addr, next);
|
|
if (result)
|
|
return result;
|
|
|
|
continue;
|
|
}
|
|
pud = (pud_t *)info->alloc_pgt_page(info->context);
|
|
if (!pud)
|
|
return -ENOMEM;
|
|
|
|
result = ident_pud_init(info, pud, addr, next);
|
|
if (result)
|
|
return result;
|
|
|
|
set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
|
|
unsigned long pstart, unsigned long pend)
|
|
{
|
|
unsigned long addr = pstart + info->offset;
|
|
unsigned long end = pend + info->offset;
|
|
unsigned long next;
|
|
int result;
|
|
|
|
/* Set the default pagetable flags if not supplied */
|
|
if (!info->kernpg_flag)
|
|
info->kernpg_flag = _KERNPG_TABLE;
|
|
|
|
/* Filter out unsupported __PAGE_KERNEL_* bits: */
|
|
info->kernpg_flag &= __default_kernel_pte_mask;
|
|
|
|
for (; addr < end; addr = next) {
|
|
pgd_t *pgd = pgd_page + pgd_index(addr);
|
|
p4d_t *p4d;
|
|
|
|
next = (addr & PGDIR_MASK) + PGDIR_SIZE;
|
|
if (next > end)
|
|
next = end;
|
|
|
|
if (pgd_present(*pgd)) {
|
|
p4d = p4d_offset(pgd, 0);
|
|
result = ident_p4d_init(info, p4d, addr, next);
|
|
if (result)
|
|
return result;
|
|
continue;
|
|
}
|
|
|
|
p4d = (p4d_t *)info->alloc_pgt_page(info->context);
|
|
if (!p4d)
|
|
return -ENOMEM;
|
|
result = ident_p4d_init(info, p4d, addr, next);
|
|
if (result)
|
|
return result;
|
|
if (pgtable_l5_enabled()) {
|
|
set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
|
|
} else {
|
|
/*
|
|
* With p4d folded, pgd is equal to p4d.
|
|
* The pgd entry has to point to the pud page table in this case.
|
|
*/
|
|
pud_t *pud = pud_offset(p4d, 0);
|
|
set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|