powerpc: Replace __get_cpu_var uses

This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.

V2->V2
  - Fix up to work against 3.18-rc1

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
      assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 12 insertions, 12 deletions

diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 1062f71f5a85..39049e4884fb 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -75,7 +75,7 @@ static atomic_t dtl_count;
  */
 static void consume_dtle(struct dtl_entry *dtle, u64 index)
 {
-        struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings);
+        struct dtl_ring *dtlr = this_cpu_ptr(&dtl_rings);
         struct dtl_entry *wp = dtlr->write_ptr;
         struct lppaca *vpa = local_paca->lppaca_ptr;
 
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index 4575f0c9e521..f02ec3ab428c 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -110,7 +110,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long
         if (opcode > MAX_HCALL_OPCODE)
                 return;
 
-        h = &__get_cpu_var(hcall_stats)[opcode / 4];
+        h = this_cpu_ptr(&hcall_stats[opcode / 4]);
         h->tb_start = mftb();
         h->purr_start = mfspr(SPRN_PURR);
 }
@@ -123,7 +123,7 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long
         if (opcode > MAX_HCALL_OPCODE)
                 return;
 
-        h = &__get_cpu_var(hcall_stats)[opcode / 4];
+        h = this_cpu_ptr(&hcall_stats[opcode / 4]);
         h->num_calls++;
         h->tb_total += mftb() - h->tb_start;
         h->purr_total += mfspr(SPRN_PURR) - h->purr_start;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e32e00976a94..49bcf7c09c49 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -199,7 +199,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 
         local_irq_save(flags);  /* to protect tcep and the page behind it */
 
-        tcep = __get_cpu_var(tce_page);
+        tcep = __this_cpu_read(tce_page);
 
         /* This is safe to do since interrupts are off when we're called
          * from iommu_alloc{,_sg}()
@@ -212,7 +212,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
                         return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
                                             direction, attrs);
                 }
-                __get_cpu_var(tce_page) = tcep;
+                __this_cpu_write(tce_page, tcep);
         }
 
         rpn = __pa(uaddr) >> TCE_SHIFT;
@@ -398,7 +398,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
         long l, limit;
 
         local_irq_disable();    /* to protect tcep and the page behind it */
-        tcep = __get_cpu_var(tce_page);
+        tcep = __this_cpu_read(tce_page);
 
         if (!tcep) {
                 tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
@@ -406,7 +406,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
                         local_irq_enable();
                         return -ENOMEM;
                 }
-                __get_cpu_var(tce_page) = tcep;
+                __this_cpu_write(tce_page, tcep);
         }
 
         proto_tce = TCE_PCI_READ | TCE_PCI_WRITE;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8c509d5397c6..87d8792f906c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -505,7 +505,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
         unsigned long vpn;
         unsigned long i, pix, rc;
         unsigned long flags = 0;
-        struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
         int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
         unsigned long param[9];
         unsigned long hash, index, shift, hidx, slot;
@@ -695,7 +695,7 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 
         local_irq_save(flags);
 
-        depth = &__get_cpu_var(hcall_trace_depth);
+        depth = this_cpu_ptr(&hcall_trace_depth);
 
         if (*depth)
                 goto out;
@@ -720,7 +720,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval,
 
         local_irq_save(flags);
 
-        depth = &__get_cpu_var(hcall_trace_depth);
+        depth = this_cpu_ptr(&hcall_trace_depth);
 
         if (*depth)
                 goto out;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 5a4d0fc03b03..c3b2a7e81ddb 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -302,8 +302,8 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
         /* If it isn't an extended log we can use the per cpu 64bit buffer */
         h = (struct rtas_error_log *)&savep[1];
         if (!rtas_error_extended(h)) {
-                memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64));
-                errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf);
+                memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64));
+                errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf);
         } else {
                 int len, error_log_length;