linux/lib/ioremap.c
Linus Torvalds b39ab98e2f Mark 'ioremap_page_range()' as possibly sleeping
It turns out that some drivers seem to think it's ok to remap page
ranges from within interrupts and even NMI's.  That is definitely not
the case, since the page table build-up is simply not interrupt-safe.

This showed up in the zero-day robot that reported it for the ACPI APEI
GHES ("Generic Hardware Error Source") driver.  Normally it had been
hidden by the fact that no page table operations had been needed because
the vmalloc area had been set up by other things.

Apparently due to a recent change to the GHEI driver: commit
77b246b32b ("acpi: apei: check for pending errors when probing GHES
entries") 0day actually caught a case during bootup whenthe ioremap
called down to page allocation.  But that recent change only showed the
symptom, it wasn't the root cause of the problem.

Hopefully it is limited to just that one driver.

If you need to access random physical memory, you either need to ioremap
in process context, or you need to use the FIXMAP facility to set one
particular fixmap entry to the required mapping - that can be done safely.

Cc: Borislav Petkov <bp@suse.de>
Cc: Len Brown <lenb@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Tyler Baicar <tbaicar@codeaurora.org>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-10-30 10:09:56 -07:00

181 lines
4.1 KiB
C

/*
* Re-map IO memory to kernel address space so that we can access it.
* This is needed for high PCI addresses that aren't mapped in the
* 640k-1MB IO memory area on PC's
*
* (C) Copyright 1995 1996 Linus Torvalds
*/
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/io.h>
#include <linux/export.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static int __read_mostly ioremap_p4d_capable;
static int __read_mostly ioremap_pud_capable;
static int __read_mostly ioremap_pmd_capable;
static int __read_mostly ioremap_huge_disabled;
static int __init set_nohugeiomap(char *str)
{
ioremap_huge_disabled = 1;
return 0;
}
early_param("nohugeiomap", set_nohugeiomap);
void __init ioremap_huge_init(void)
{
if (!ioremap_huge_disabled) {
if (arch_ioremap_pud_supported())
ioremap_pud_capable = 1;
if (arch_ioremap_pmd_supported())
ioremap_pmd_capable = 1;
}
}
static inline int ioremap_p4d_enabled(void)
{
return ioremap_p4d_capable;
}
static inline int ioremap_pud_enabled(void)
{
return ioremap_pud_capable;
}
static inline int ioremap_pmd_enabled(void)
{
return ioremap_pmd_capable;
}
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int ioremap_p4d_enabled(void) { return 0; }
static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pte_t *pte;
u64 pfn;
pfn = phys_addr >> PAGE_SHIFT;
pte = pte_alloc_kernel(pmd, addr);
if (!pte)
return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
return 0;
}
static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
phys_addr -= addr;
pmd = pmd_alloc(&init_mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (ioremap_pmd_enabled() &&
((next - addr) == PMD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PMD_SIZE)) {
if (pmd_set_huge(pmd, phys_addr + addr, prot))
continue;
}
if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
phys_addr -= addr;
pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (ioremap_pud_enabled() &&
((next - addr) == PUD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PUD_SIZE)) {
if (pud_set_huge(pud, phys_addr + addr, prot))
continue;
}
if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
p4d_t *p4d;
unsigned long next;
phys_addr -= addr;
p4d = p4d_alloc(&init_mm, pgd, addr);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
if (ioremap_p4d_enabled() &&
((next - addr) == P4D_SIZE) &&
IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
if (p4d_set_huge(p4d, phys_addr + addr, prot))
continue;
}
if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
}
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pgd_t *pgd;
unsigned long start;
unsigned long next;
int err;
might_sleep();
BUG_ON(addr >= end);
start = addr;
phys_addr -= addr;
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
flush_cache_vmap(start, end);
return err;
}