sparc64: Store per-cpu offset in trap_block[]
Surprisingly this actually makes LOAD_PER_CPU_BASE() a little
more efficient.
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 91bf4c7..f8f2105 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -641,28 +641,6 @@
/* Not reached... */
1:
- /* If we boot on a non-zero cpu, all of the per-cpu
- * variable references we make before setting up the
- * per-cpu areas will use a bogus offset. Put a
- * compensating factor into __per_cpu_base to handle
- * this cleanly.
- *
- * What the per-cpu code calculates is:
- *
- * __per_cpu_base + (cpu << __per_cpu_shift)
- *
- * These two variables are zero initially, so to
- * make it all cancel out to zero we need to put
- * "0 - (cpu << 0)" into __per_cpu_base so that the
- * above formula evaluates to zero.
- *
- * We cannot even perform a printk() until this stuff
- * is setup as that calls cpu_clock() which uses
- * per-cpu variables.
- */
- sub %g0, %o0, %o1
- sethi %hi(__per_cpu_base), %o2
- stx %o1, [%o2 + %lo(__per_cpu_base)]
#else
mov 0, %o0
#endif
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 4226d0e..b20f253 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1371,23 +1371,17 @@
{
}
-unsigned long __per_cpu_base __read_mostly;
-unsigned long __per_cpu_shift __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_base);
-EXPORT_SYMBOL(__per_cpu_shift);
-
void __init real_setup_per_cpu_areas(void)
{
- unsigned long paddr, goal, size, i;
+ unsigned long base, shift, paddr, goal, size, i;
char *ptr;
/* Copy section for each CPU (we discard the original) */
goal = PERCPU_ENOUGH_ROOM;
- __per_cpu_shift = PAGE_SHIFT;
+ shift = PAGE_SHIFT;
for (size = PAGE_SIZE; size < goal; size <<= 1UL)
- __per_cpu_shift++;
+ shift++;
paddr = lmb_alloc(size * NR_CPUS, PAGE_SIZE);
if (!paddr) {
@@ -1396,10 +1390,12 @@
}
ptr = __va(paddr);
- __per_cpu_base = ptr - __per_cpu_start;
+ base = ptr - __per_cpu_start;
- for (i = 0; i < NR_CPUS; i++, ptr += size)
+ for (i = 0; i < NR_CPUS; i++, ptr += size) {
+ __per_cpu_offset(i) = base + (i * size);
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+ }
/* Setup %g5 for the boot cpu. */
__local_per_cpu_offset = __per_cpu_offset(smp_processor_id());
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index d809c4e..d073aab 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2509,6 +2509,7 @@
}
struct trap_per_cpu trap_block[NR_CPUS];
+EXPORT_SYMBOL(trap_block);
/* This can get invoked before sched_init() so play it super safe
* and use hard_smp_processor_id().
@@ -2592,7 +2593,9 @@
(TRAP_PER_CPU_RESUM_QMASK !=
offsetof(struct trap_per_cpu, resum_qmask)) ||
(TRAP_PER_CPU_NONRESUM_QMASK !=
- offsetof(struct trap_per_cpu, nonresum_qmask)))
+ offsetof(struct trap_per_cpu, nonresum_qmask)) ||
+ (TRAP_PER_CPU_PER_CPU_BASE !=
+ offsetof(struct trap_per_cpu, __per_cpu_base)))
trap_per_cpu_offsets_are_bolixed_dave();
if ((TSB_CONFIG_TSB !=