diff options
Diffstat (limited to 'arch/arm/mm')
-rw-r--r-- | arch/arm/mm/copypage-fa.c | 35 | ||||
-rw-r--r-- | arch/arm/mm/copypage-feroceon.c | 98 | ||||
-rw-r--r-- | arch/arm/mm/copypage-v4mc.c | 19 | ||||
-rw-r--r-- | arch/arm/mm/copypage-v4wb.c | 41 | ||||
-rw-r--r-- | arch/arm/mm/copypage-v4wt.c | 37 | ||||
-rw-r--r-- | arch/arm/mm/copypage-xsc3.c | 79 | ||||
-rw-r--r-- | arch/arm/mm/copypage-xscale.c | 79 | ||||
-rw-r--r-- | arch/arm/mm/fault.c | 6 | ||||
-rw-r--r-- | arch/arm/mm/proc-macros.S | 10 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7-bugs.c | 17 | ||||
-rw-r--r-- | arch/arm/mm/proc-v7.S | 2 | ||||
-rw-r--r-- | arch/arm/mm/pv-fixup-asm.S | 16 |
12 files changed, 213 insertions, 226 deletions
diff --git a/arch/arm/mm/copypage-fa.c b/arch/arm/mm/copypage-fa.c index d130a5ece5d5..bf24690ec83a 100644 --- a/arch/arm/mm/copypage-fa.c +++ b/arch/arm/mm/copypage-fa.c @@ -17,26 +17,25 @@ /* * Faraday optimised copy_user_page */ -static void __naked -fa_copy_user_page(void *kto, const void *kfrom) +static void fa_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ -1: ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - subs r2, r2, #1 @ 1\n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + subs %2, %2, #1 @ 1\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "I" (PAGE_SIZE / 32)); + mcr p15, 0, %2, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 32) + : "r3", "r4", "ip", "lr"); } void fa_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c index 49ee0c1a7209..cc819732d9b8 100644 --- a/arch/arm/mm/copypage-feroceon.c +++ b/arch/arm/mm/copypage-feroceon.c @@ -13,58 +13,56 @@ #include <linux/init.h> #include <linux/highmem.h> -static void __naked -feroceon_copy_user_page(void *kto, const void *kfrom) +static void feroceon_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4-r9, lr} \n\ - mov ip, %2 \n\ -1: mov lr, r1 \n\ - ldmia r1!, {r2 - r9} \n\ - pld [lr, #32] \n\ - pld [lr, #64] \n\ - pld [lr, #96] \n\ - pld [lr, #128] \n\ - pld [lr, #160] \n\ - pld [lr, #192] \n\ - pld [lr, #224] \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - subs ip, ip, #(32 * 8) \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r2 - r7, ip, lr} \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ + pld [%1, #128] \n\ + pld [%1, #160] \n\ + pld [%1, #192] \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + subs %2, %2, #(32 * 8) \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ bne 1b \n\ - mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\ - ldmfd sp!, {r4-r9, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE)); + mcr p15, 0, %2, c7, c10, 4 @ drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE) + : "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr"); } void feroceon_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index 0224416cba3c..b03202cddddb 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -40,12 +40,11 @@ static DEFINE_RAW_SPINLOCK(minicache_lock); * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { - asm volatile( - "stmfd sp!, {r4, lr} @ 2\n\ - mov r4, %2 @ 1\n\ + int tmp; + + asm volatile ("\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ 1: mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ @@ -55,13 +54,13 @@ mc_copy_user_page(void *from, void *to) mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ - subs r4, r4, #1 @ 1\n\ + subs %2, %2, #1 @ 1\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmneia %0!, {r2, r3, ip, lr} @ 4\n\ - bne 1b @ 1\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64)); + bne 1b @ " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r2", "r3", "ip", "lr"); } void v4_mc_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c index 067d0fdd630c..cd3e165afeed 100644 --- a/arch/arm/mm/copypage-v4wb.c +++ b/arch/arm/mm/copypage-v4wb.c @@ -22,29 +22,28 @@ * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -v4wb_copy_user_page(void *kto, const void *kfrom) +static void v4wb_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %1, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); } void v4wb_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c index b85c5da2e510..8614572e1296 100644 --- a/arch/arm/mm/copypage-v4wt.c +++ b/arch/arm/mm/copypage-v4wt.c @@ -20,27 +20,26 @@ * dirty data in the cache. However, we do have to ensure that * subsequent reads are up to date. */ -static void __naked -v4wt_copy_user_page(void *kto, const void *kfrom) +static void v4wt_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c7, 0 @ flush ID cache\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %2, c7, c7, 0 @ flush ID cache" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); } void v4wt_copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c index 03a2042aced5..a08158241ad1 100644 --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -21,53 +21,46 @@ /* * XSC3 optimised copy_user_highpage - * r0 = destination - * r1 = source * * The source page may have some clean entries in the cache already, but we * can safely ignore them - break_cow() will flush them out of the cache * if we eventually end up using our copied page. * */ -static void __naked -xsc3_mc_copy_user_page(void *kto, const void *kfrom) +static void xsc3_mc_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r1, #64] \n\ - pld [r1, #96] \n\ + int tmp; + + asm volatile ("\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%1, #64] \n\ + pld [%1, #96] \n\ \n\ -2: ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - subs lr, lr, #1 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ +2: ldrd r2, r3, [%1], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, r3, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, r3, [%0], #8 \n\ + ldrd r2, r3, [%1], #8 \n\ + subs %2, %2, #1 \n\ + strd r4, r5, [%0], #8 \n\ + ldrd r4, r5, [%1], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r4, r5, [%0], #8 \n\ bgt 1b \n\ - beq 2b \n\ - \n\ - ldmfd sp!, {r4, r5, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5"); } void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, @@ -85,8 +78,6 @@ void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, /* * XScale optimised clear_user_page - * r0 = destination - * r1 = virtual user address of ultimate destination page */ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) { @@ -96,10 +87,10 @@ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) mov r2, #0 \n\ mov r3, #0 \n\ 1: mcr p15, 0, %0, c7, c6, 1 @ invalidate line\n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ subs r1, r1, #1 \n\ bne 1b" : "=r" (ptr) diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 97972379f4d6..63b921936754 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -36,52 +36,51 @@ static DEFINE_RAW_SPINLOCK(minicache_lock); * Dcache aliasing issue. The writes will be forwarded to the write buffer, * and merged as appropriate. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { + int tmp; + /* * Strangely enough, best performance is achieved * when prefetching destination as well. (NP) */ - asm volatile( - "stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - pld [r0, #0] \n\ - pld [r0, #32] \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r0, #64] \n\ - pld [r0, #96] \n\ - pld [r1, #64] \n\ - pld [r1, #96] \n\ -2: ldrd r2, [r0], #8 \n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + asm volatile ("\ + pld [%0, #0] \n\ + pld [%0, #32] \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%0, #64] \n\ + pld [%0, #96] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ +2: ldrd r2, r3, [%0], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, r3, [%1], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ + strd r4, r5, [%1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + strd r2, r3, [%1], #8 \n\ + strd r4, r5, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - ldrd r2, [r0], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, r3, [%1], #8 \n\ + ldrd r2, r3, [%0], #8 \n\ + strd r4, r5, [%1], #8 \n\ + ldrd r4, r5, [%0], #8 \n\ + strd r2, r3, [%1], #8 \n\ + strd r4, r5, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - subs lr, lr, #1 \n\ + subs %2, %2, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ bgt 1b \n\ - beq 2b \n\ - ldmfd sp!, {r4, r5, pc} " - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5", "ip"); } void xscale_mc_copy_user_highpage(struct page *to, struct page *from, @@ -115,10 +114,10 @@ xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr) mov r2, #0 \n\ mov r3, #0 \n\ 1: mov ip, %0 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ - strd r2, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ + strd r2, r3, [%0], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ subs r1, r1, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index f4ea4c62c613..58f69fa07df9 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -173,6 +173,12 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr, show_regs(regs); } #endif +#ifndef CONFIG_KUSER_HELPERS + if ((sig == SIGSEGV) && ((addr & PAGE_MASK) == 0xffff0000)) + printk_ratelimited(KERN_DEBUG + "%s: CONFIG_KUSER_HELPERS disabled at 0x%08lx\n", + tsk->comm, addr); +#endif tsk->thread.address = addr; tsk->thread.error_code = fsr; diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 81d0efb055c6..5461d589a1e2 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -274,6 +274,13 @@ .endm .macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0, bugs=0 +/* + * If we are building for big.Little with branch predictor hardening, + * we need the processor function tables to remain available after boot. + */ +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) + .section ".rodata" +#endif .type \name\()_processor_functions, #object .align 2 ENTRY(\name\()_processor_functions) @@ -309,6 +316,9 @@ ENTRY(\name\()_processor_functions) .endif .size \name\()_processor_functions, . - \name\()_processor_functions +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) + .previous +#endif .endm .macro define_cache_functions name:req diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 5544b82a2e7a..9a07916af8dd 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -52,8 +52,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - if (processor.switch_mm != cpu_v7_bpiall_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_bpiall; spectre_v2_method = "BPIALL"; @@ -61,8 +59,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - if (processor.switch_mm != cpu_v7_iciallu_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_iciallu; spectre_v2_method = "ICIALLU"; @@ -88,11 +84,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_hvc_arch_workaround_1; - processor.switch_mm = cpu_v7_hvc_switch_mm; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; spectre_v2_method = "hypervisor"; break; @@ -101,11 +95,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_smc_arch_workaround_1; - processor.switch_mm = cpu_v7_smc_switch_mm; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; spectre_v2_method = "firmware"; break; @@ -119,11 +111,6 @@ static void cpu_v7_spectre_init(void) if (spectre_v2_method) pr_info("CPU%u: Spectre v2: using %s workaround\n", smp_processor_id(), spectre_v2_method); - return; - -bl_error: - pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n", - cpu); } #else static void cpu_v7_spectre_init(void) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6fe52819e014..339eb17c9808 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -112,7 +112,7 @@ ENTRY(cpu_v7_hvc_switch_mm) hvc #0 ldmfd sp!, {r0 - r3} b cpu_v7_switch_mm -ENDPROC(cpu_v7_smc_switch_mm) +ENDPROC(cpu_v7_hvc_switch_mm) #endif ENTRY(cpu_v7_iciallu_switch_mm) mov r3, #0 diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S index 1867f3e43016..fd2ff9034d17 100644 --- a/arch/arm/mm/pv-fixup-asm.S +++ b/arch/arm/mm/pv-fixup-asm.S @@ -33,10 +33,10 @@ ENTRY(lpae_pgtables_remap_asm) add r7, r2, #0x1000 add r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER add r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER) -1: ldrd r4, [r7] +1: ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L2_ORDER + strd r4, r5, [r7], #1 << L2_ORDER cmp r7, r6 bls 1b @@ -44,22 +44,22 @@ ENTRY(lpae_pgtables_remap_asm) add r7, r2, #0x1000 add r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER bic r7, r7, #(1 << L2_ORDER) - 1 - ldrd r4, [r7] + ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L2_ORDER - ldrd r4, [r7] + strd r4, r5, [r7], #1 << L2_ORDER + ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7] + strd r4, r5, [r7] /* Update level 1 entries */ mov r6, #4 mov r7, r2 -2: ldrd r4, [r7] +2: ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 - strd r4, [r7], #1 << L1_ORDER + strd r4, r5, [r7], #1 << L1_ORDER subs r6, r6, #1 bne 2b |