sparc/mm: don't unconditionally set HW writable bit when setting PTE dirty on 64bit

On sparc64, there is no HW modified bit, therefore, SW tracks via a SW bit
if the PTE is dirty via pte_mkdirty().  However, pte_mkdirty() currently
also unconditionally sets the HW writable bit, which is wrong.

pte_mkdirty() is not supposed to make a PTE actually writable, unless the
SW writable bit -- pte_write() -- indicates that the PTE is not
write-protected.  Fortunately, sparc64 also defines a SW writable bit.

For example, this already turned into a problem in the context of THP
splitting as documented in commit 624a2c94f5 ("Partly revert "mm/thp:
carry over dirty bit when thp splits on pmd""), and for page migration, as
documented in commit 96a9c287e2 ("mm/migrate: fix wrongly apply write
bit after mkdirty on sparc64").

Also, we might want to use the dirty PTE bit in the context of KSM with
shared zeropage [1], whereby setting the page writable would be
problematic.

But more general, any code that might end up setting a PTE/PMD dirty
inside a VM without write permissions is possibly broken,

Before this commit (sun4u in QEMU):
	root@debian:~/linux/tools/testing/selftests/mm# ./mkdirty
	# [INFO] detected THP size: 8192 KiB
	TAP version 13
	1..6
	# [INFO] PTRACE write access
	not ok 1 SIGSEGV generated, page not modified
	# [INFO] PTRACE write access to THP
	not ok 2 SIGSEGV generated, page not modified
	# [INFO] Page migration
	ok 3 SIGSEGV generated, page not modified
	# [INFO] Page migration of THP
	ok 4 SIGSEGV generated, page not modified
	# [INFO] PTE-mapping a THP
	ok 5 SIGSEGV generated, page not modified
	# [INFO] UFFDIO_COPY
	not ok 6 SIGSEGV generated, page not modified
	Bail out! 3 out of 6 tests failed
	# Totals: pass:3 fail:3 xfail:0 xpass:0 skip:0 error:0

Test #3,#4,#5 pass ever since we added some MM workarounds, the
underlying issue remains.

Let's fix the remaining issues and prepare for reverting the workarounds
by setting the HW writable bit only if both, the SW dirty bit and the SW
writable bit are set.

We have to move pte_dirty() and pte_write() up. The code patching
mechanism and handling constants > 22bit is a bit special on sparc64.

The ASM logic in pte_mkdirty() and pte_mkwrite() match the logic in
pte_mkold() to create the mask depending on the machine type. The ASM
logic in __pte_mkhwwrite() matches the logic in pte_present(), just
using an "or" instead of an "and" instruction.

With this commit (sun4u in QEMU):
	root@debian:~/linux/tools/testing/selftests/mm# ./mkdirty
	# [INFO] detected THP size: 8192 KiB
	TAP version 13
	1..6
	# [INFO] PTRACE write access
	ok 1 SIGSEGV generated, page not modified
	# [INFO] PTRACE write access to THP
	ok 2 SIGSEGV generated, page not modified
	# [INFO] Page migration
	ok 3 SIGSEGV generated, page not modified
	# [INFO] Page migration of THP
	ok 4 SIGSEGV generated, page not modified
	# [INFO] PTE-mapping a THP
	ok 5 SIGSEGV generated, page not modified
	# [INFO] UFFDIO_COPY
	ok 6 SIGSEGV generated, page not modified
	# Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0

This handling seems to have been in place forever.

[1] https://lkml.kernel.org/r/533a7c3d-3a48-b16b-b421-6e8386e0b142@redhat.com

Link: https://lkml.kernel.org/r/20230411142512.438404-4-david@redhat.com
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
David Hildenbrand 2023-04-11 16:25:09 +02:00 committed by Andrew Morton
parent 9eac40fc0c
commit fa2e71a6fc

View File

@ -357,6 +357,42 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
*/
#define pgprot_noncached pgprot_noncached
static inline unsigned long pte_dirty(pte_t pte)
{
unsigned long mask;
__asm__ __volatile__(
"\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
" sethi %%uhi(%2), %0\n"
" sllx %0, 32, %0\n"
" .previous\n"
: "=r" (mask)
: "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
return (pte_val(pte) & mask);
}
static inline unsigned long pte_write(pte_t pte)
{
unsigned long mask;
__asm__ __volatile__(
"\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
" sethi %%uhi(%2), %0\n"
" sllx %0, 32, %0\n"
" .previous\n"
: "=r" (mask)
: "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
return (pte_val(pte) & mask);
}
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
@ -418,28 +454,43 @@ static inline bool is_hugetlb_pte(pte_t pte)
}
#endif
static inline pte_t __pte_mkhwwrite(pte_t pte)
{
unsigned long val = pte_val(pte);
/*
* Note: we only want to set the HW writable bit if the SW writable bit
* and the SW dirty bit are set.
*/
__asm__ __volatile__(
"\n661: or %0, %2, %0\n"
" .section .sun4v_1insn_patch, \"ax\"\n"
" .word 661b\n"
" or %0, %3, %0\n"
" .previous\n"
: "=r" (val)
: "0" (val), "i" (_PAGE_W_4U), "i" (_PAGE_W_4V));
return __pte(val);
}
static inline pte_t pte_mkdirty(pte_t pte)
{
unsigned long val = pte_val(pte), tmp;
unsigned long val = pte_val(pte), mask;
__asm__ __volatile__(
"\n661: or %0, %3, %0\n"
" nop\n"
"\n662: nop\n"
"\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
" sethi %%uhi(%4), %1\n"
" sllx %1, 32, %1\n"
" .word 662b\n"
" or %1, %%lo(%4), %1\n"
" or %0, %1, %0\n"
" sethi %%uhi(%2), %0\n"
" sllx %0, 32, %0\n"
" .previous\n"
: "=r" (val), "=r" (tmp)
: "0" (val), "i" (_PAGE_MODIFIED_4U | _PAGE_W_4U),
"i" (_PAGE_MODIFIED_4V | _PAGE_W_4V));
: "=r" (mask)
: "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
return __pte(val);
pte = __pte(val | mask);
return pte_write(pte) ? __pte_mkhwwrite(pte) : pte;
}
static inline pte_t pte_mkclean(pte_t pte)
@ -481,7 +532,8 @@ static inline pte_t pte_mkwrite(pte_t pte)
: "=r" (mask)
: "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
return __pte(val | mask);
pte = __pte(val | mask);
return pte_dirty(pte) ? __pte_mkhwwrite(pte) : pte;
}
static inline pte_t pte_wrprotect(pte_t pte)
@ -584,42 +636,6 @@ static inline unsigned long pte_young(pte_t pte)
return (pte_val(pte) & mask);
}
static inline unsigned long pte_dirty(pte_t pte)
{
unsigned long mask;
__asm__ __volatile__(
"\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
" sethi %%uhi(%2), %0\n"
" sllx %0, 32, %0\n"
" .previous\n"
: "=r" (mask)
: "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
return (pte_val(pte) & mask);
}
static inline unsigned long pte_write(pte_t pte)
{
unsigned long mask;
__asm__ __volatile__(
"\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
" sethi %%uhi(%2), %0\n"
" sllx %0, 32, %0\n"
" .previous\n"
: "=r" (mask)
: "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
return (pte_val(pte) & mask);
}
static inline unsigned long pte_exec(pte_t pte)
{
unsigned long mask;