Merge branch 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

Pull percpu consistent-ops changes from Tejun Heo:
 "Way back, before the current percpu allocator was implemented, static
  and dynamic percpu memory areas were allocated and handled separately
  and had their own accessors.  The distinction has been gone for many
  years now; however, the now duplicate two sets of accessors remained
  with the pointer based ones - this_cpu_*() - evolving various other
  operations over time.  During the process, we also accumulated other
  inconsistent operations.

  This pull request contains Christoph's patches to clean up the
  duplicate accessor situation.  __get_cpu_var() uses are replaced with
  with this_cpu_ptr() and __this_cpu_ptr() with raw_cpu_ptr().

  Unfortunately, the former sometimes is tricky thanks to C being a bit
  messy with the distinction between lvalues and pointers, which led to
  a rather ugly solution for cpumask_var_t involving the introduction of
  this_cpu_cpumask_var_ptr().

  This converts most of the uses but not all.  Christoph will follow up
  with the remaining conversions in this merge window and hopefully
  remove the obsolete accessors"

* 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (38 commits)
  irqchip: Properly fetch the per cpu offset
  percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t -fix
  ia64: sn_nodepda cannot be assigned to after this_cpu conversion. Use __this_cpu_write.
  percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t
  Revert "powerpc: Replace __get_cpu_var uses"
  percpu: Remove __this_cpu_ptr
  clocksource: Replace __this_cpu_ptr with raw_cpu_ptr
  sparc: Replace __get_cpu_var uses
  avr32: Replace __get_cpu_var with __this_cpu_write
  blackfin: Replace __get_cpu_var uses
  tile: Use this_cpu_ptr() for hardware counters
  tile: Replace __get_cpu_var uses
  powerpc: Replace __get_cpu_var uses
  alpha: Replace __get_cpu_var
  ia64: Replace __get_cpu_var uses
  s390: cio driver &__get_cpu_var replacements
  s390: Replace __get_cpu_var uses
  mips: Replace __get_cpu_var uses
  MIPS: Replace __get_cpu_var uses in FPU emulator.
  arm: Replace __this_cpu_ptr with raw_cpu_ptr
  ...

5 files changed, 17 insertions, 9 deletions

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2997af6d2ccd..0a9a6da21e74 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -666,10 +666,19 @@ static inline size_t cpumask_size(void)
  *
  * This code makes NR_CPUS length memcopy and brings to a memory corruption.
  * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
  */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
@@ -681,6 +690,8 @@ void free_bootmem_cpumask_var(cpumask_var_t mask);
 #else
 typedef struct cpumask cpumask_var_t[1];
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+
 static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ecbc52f9ff77..8422b4ed6882 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -44,8 +44,8 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu (&__get_cpu_var(kstat))
-#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_this_cpu this_cpu_ptr(&kstat)
+#define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index cfd56046ecec..420032d41d27 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -257,9 +257,6 @@ do {									\
 #define __raw_get_cpu_var(var)	(*raw_cpu_ptr(&(var)))
 #define __get_cpu_var(var)	(*this_cpu_ptr(&(var)))
 
-/* keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
-
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
  * we force a syntax error here if it isn't.
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37252f71a380..c8a7db605e03 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -242,7 +242,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
 static inline struct nf_conn *nf_ct_untracked_get(void)
 {
-	return &__raw_get_cpu_var(nf_conntrack_untracked);
+	return raw_cpu_ptr(&nf_conntrack_untracked);
 }
 void nf_ct_untracked_status_or(unsigned long bits);
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8fd2f498782e..35512ac6dcfb 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -164,7 +164,7 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS64_BH(mib, field, addend) 			\
 	do {								\
-		__typeof__(*mib) *ptr = __this_cpu_ptr(mib);		\
+		__typeof__(*mib) *ptr = raw_cpu_ptr(mib);		\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[field] += addend;				\
 		u64_stats_update_end(&ptr->syncp);			\
@@ -185,8 +185,8 @@ struct linux_xfrm_mib {
 #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
 	do {								\
-		__typeof__(*mib) *ptr;					\
-		ptr = __this_cpu_ptr(mib);				\
+		__typeof__(*mib) *ptr;				\
+		ptr = raw_cpu_ptr((mib));				\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[basefield##PKTS]++;				\
 		ptr->mibs[basefield##OCTETS] += addend;			\