@@ -84,10 +84,12 @@ static inline void __dc_gzva(u64 p)
static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
bool init)
{
- u64 curr, mask, dczid_bs, end1, end2, end3;
+ u64 curr, mask, dczid, dczid_bs, dczid_dzp, end1, end2, end3;
/* Read DC G(Z)VA block size from the system register. */
- dczid_bs = 4ul << (read_cpuid(DCZID_EL0) & 0xf);
+ dczid = read_cpuid(DCZID_EL0);
+ dczid_bs = 4ul << (dczid & 0xf);
+ dczid_dzp = (dczid >> 4) & 1;
curr = (u64)__tag_set(addr, tag);
mask = dczid_bs - 1;
@@ -106,7 +108,7 @@ static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
*/
#define SET_MEMTAG_RANGE(stg_post, dc_gva) \
do { \
- if (size >= 2 * dczid_bs) { \
+ if (!dczid_dzp && size >= 2 * dczid_bs) {\
do { \
curr = stg_post(curr); \
} while (curr < end1); \
@@ -43,17 +43,23 @@ SYM_FUNC_END(mte_clear_page_tags)
* x0 - address to the beginning of the page
*/
SYM_FUNC_START(mte_zero_clear_page_tags)
+ and x0, x0, #(1 << MTE_TAG_SHIFT) - 1 // clear the tag
mrs x1, dczid_el0
+ tbnz x1, #4, 2f // Branch if DC GZVA is prohibited
and w1, w1, #0xf
mov x2, #4
lsl x1, x2, x1
- and x0, x0, #(1 << MTE_TAG_SHIFT) - 1 // clear the tag
1: dc gzva, x0
add x0, x0, x1
tst x0, #(PAGE_SIZE - 1)
b.ne 1b
ret
+
+2: stz2g x0, [x0], #(MTE_GRANULE_SIZE * 2)
+ tst x0, #(PAGE_SIZE - 1)
+ b.ne 2b
+ ret
SYM_FUNC_END(mte_zero_clear_page_tags)
/*
Currently, mte_set_mem_tag_range() and mte_zero_clear_page_tags() use DC {GVA,GZVA} unconditionally. But, they should make sure that DCZID_EL0.DZP, which indicates whether or not use of those instructions is prohibited, is zero when using those instructions. Use ST{G,ZG,Z2G} instead when DCZID_EL0.DZP == 1. Fixes: 013bb59dbb7c ("arm64: mte: handle tags zeroing at page allocation time") Fixes: 3d0cca0b02ac ("kasan: speed up mte_set_mem_tag_range") Signed-off-by: Reiji Watanabe <reijiw@google.com> --- arch/arm64/include/asm/mte-kasan.h | 8 +++++--- arch/arm64/lib/mte.S | 8 +++++++- 2 files changed, 12 insertions(+), 4 deletions(-)