[PATCH 1/2] FRV: Fix the section attribute on UP DECLARE_PER_CPU()

[PATCH 1/2] FRV: Fix the section attribute on UP DECLARE_PER_CPU()

[David Howells]

In non-SMP mode, the variable section attribute specified by DECLARE_PER_CPU()
does not agree with that specified by DEFINE_PER_CPU().  This means that
architectures that have a small data section references relative to a base
register may throw up linkage errors due to too great a displacement between
where the base register points and the per-CPU variable.

On FRV, the .h declaration says that the variable is in the .sdata section, but
the .c definition says it's actually in the .data section.  The linker throws
up the following errors:

kernel/built-in.o: In function `release_task':
kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o
kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o

To fix this, DECLARE_PER_CPU() should simply apply the same section attribute
as does DEFINE_PER_CPU().  However, this is made slightly more complex by
virtue of the fact that there are several variants on DEFINE, so these need to
be matched by variants on DECLARE.

Signed-off-by: David Howells <dhowells@redhat.com>
---

 arch/alpha/include/asm/percpu.h  |    2 +-
 arch/ia64/include/asm/smp.h      |    2 +-
 arch/x86/include/asm/desc.h      |    2 +-
 arch/x86/include/asm/hardirq.h   |    2 +-
 arch/x86/include/asm/processor.h |    6 +++--
 arch/x86/include/asm/tlbflush.h  |    2 +-
 include/asm-generic/percpu.h     |   43 ++++++++++++++++++++++++++++++++++++--
 include/linux/percpu.h           |   24 ---------------------
 net/rds/rds.h                    |    2 +-
 9 files changed, 50 insertions(+), 35 deletions(-)


diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
index 3495e8e..e9e0bb5 100644
--- a/arch/alpha/include/asm/percpu.h
+++ b/arch/alpha/include/asm/percpu.h
@@ -73,6 +73,6 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 
 #endif /* SMP */
 
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu_var(name)
+#include <asm-generic/percpu.h>
 
 #endif /* __ALPHA_PERCPU_H */
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 5984083..d217d1d 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -58,7 +58,7 @@ extern struct smp_boot_data {
 extern char no_int_routing __devinitdata;
 
 extern cpumask_t cpu_core_map[NR_CPUS];
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
+DECLARE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map);
 extern int smp_num_siblings;
 extern void __iomem *ipi_base_addr;
 extern unsigned char smp_int_redirect;
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 5623c50..c45f415 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -37,7 +37,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 039db6a..37555e5 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -26,7 +26,7 @@ typedef struct {
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 /* We can have at most NR_VECTORS irqs routed to a cpu at a time */
 #define MAX_HARDIRQS_PER_CPU NR_VECTORS
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fcf4d92..c2cceae 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -138,7 +138,7 @@ extern struct tss_struct	doublefault_tss;
 extern __u32			cleared_cpu_caps[NCAPINTS];
 
 #ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)		per_cpu(cpu_info, cpu)
 #define current_cpu_data	__get_cpu_var(cpu_info)
 #else
@@ -270,7 +270,7 @@ struct tss_struct {
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU(struct tss_struct, init_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
 
 /*
  * Save the original ist values for checking stack pointers during debugging
@@ -393,7 +393,7 @@ union irq_stack_union {
 	};
 };
 
-DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union);
 DECLARE_INIT_PER_CPU(irq_stack_union);
 
 DECLARE_PER_CPU(char *, irq_stack_ptr);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d3539f9..16a5c84 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -152,7 +152,7 @@ struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
 };
-DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
 static inline void reset_lazy_tlbstate(void)
 {
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c6..af47b9e 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -73,11 +73,50 @@ extern void setup_per_cpu_areas(void);
 
 #endif	/* SMP */
 
+#ifndef PER_CPU_BASE_SECTION
+#ifdef CONFIG_SMP
+#define PER_CPU_BASE_SECTION ".data.percpu"
+#else
+#define PER_CPU_BASE_SECTION ".data"
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifdef MODULE
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#else
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
+#endif
+#define PER_CPU_FIRST_SECTION ".first"
+
+#else
+
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
 #ifndef PER_CPU_ATTRIBUTES
 #define PER_CPU_ATTRIBUTES
 #endif
 
-#define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
-					__typeof__(type) per_cpu_var(name)
+#define DECLARE_PER_CPU_SECTION(type, name, section)			\
+	extern \
+	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define DECLARE_PER_CPU(type, name)					\
+	DECLARE_PER_CPU_SECTION(type, name, "")
+
+#define DECLARE_PER_CPU_SHARED_ALIGNED(type, name)			\
+	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
+	____cacheline_aligned_in_smp
+
+#define DECLARE_PER_CPU_PAGE_ALIGNED(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, ".page_aligned")
+
+#define DECLARE_PER_CPU_FIRST(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index cfda2d5..f052d81 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -9,30 +9,6 @@
 
 #include <asm/percpu.h>
 
-#ifndef PER_CPU_BASE_SECTION
-#ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data.percpu"
-#else
-#define PER_CPU_BASE_SECTION ".data"
-#endif
-#endif
-
-#ifdef CONFIG_SMP
-
-#ifdef MODULE
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#else
-#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
-#endif
-#define PER_CPU_FIRST_SECTION ".first"
-
-#else
-
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_FIRST_SECTION ""
-
-#endif
-
 #define DEFINE_PER_CPU_SECTION(type, name, section)			\
 	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
 	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 619f0a3..7179444 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -638,7 +638,7 @@ struct rds_message *rds_send_get_message(struct rds_connection *,
 void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
 
 /* stats.c */
-DECLARE_PER_CPU(struct rds_statistics, rds_stats);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats);
 #define rds_stats_inc_which(which, member) do {		\
 	per_cpu(which, get_cpu()).member++;		\
 	put_cpu();					\

[PATCH 2/2] PERCPU: Collect the DECLARE/DEFINE declarations together

[David Howells]

Collect the DECLARE/DEFINE declarations together in linux/percpu-defs.h so
that they're in one place, and give them descriptive comments, particularly
the SHARED_ALIGNED variant.

It would be nice to collect these in linux/percpu.h, but that's not possible
without sorting out the severe #include recursion between the x86 arch headers
and the general headers (and possibly other arches too).

Signed-off-by: David Howells <dhowells@redhat.com>
---

 include/asm-generic/percpu.h |   26 +------------
 include/linux/percpu-defs.h  |   84 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/percpu.h       |   20 ----------
 3 files changed, 86 insertions(+), 44 deletions(-)
 create mode 100644 include/linux/percpu-defs.h


diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index af47b9e..d7d50d7 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -1,13 +1,9 @@
 #ifndef _ASM_GENERIC_PERCPU_H_
 #define _ASM_GENERIC_PERCPU_H_
+
 #include <linux/compiler.h>
 #include <linux/threads.h>
-
-/*
- * Determine the real variable name from the name visible in the
- * kernel sources.
- */
-#define per_cpu_var(var) per_cpu__##var
+#include <linux/percpu-defs.h>
 
 #ifdef CONFIG_SMP
 
@@ -101,22 +97,4 @@ extern void setup_per_cpu_areas(void);
 #define PER_CPU_ATTRIBUTES
 #endif
 
-#define DECLARE_PER_CPU_SECTION(type, name, section)			\
-	extern \
-	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-
-#define DECLARE_PER_CPU(type, name)					\
-	DECLARE_PER_CPU_SECTION(type, name, "")
-
-#define DECLARE_PER_CPU_SHARED_ALIGNED(type, name)			\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
-	____cacheline_aligned_in_smp
-
-#define DECLARE_PER_CPU_PAGE_ALIGNED(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, ".page_aligned")
-
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
new file mode 100644
index 0000000..8f921d7
--- /dev/null
+++ b/include/linux/percpu-defs.h
@@ -0,0 +1,84 @@
+#ifndef _LINUX_PERCPU_DEFS_H
+#define _LINUX_PERCPU_DEFS_H
+
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
+/*
+ * Base implementations of per-CPU variable declarations and definitions, where
+ * the section in which the variable is to be placed is provided by the
+ * 'section' argument.  This may be used to affect the parameters governing the
+ * variable's storage.
+ *
+ * NOTE!  The sections for the DECLARE and for the DEFINE must match, lest
+ * linkage errors occur due the compiler generating the wrong code to access
+ * that section.
+ */
+#define DECLARE_PER_CPU_SECTION(type, name, section)			\
+	extern								\
+	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU_SECTION(type, name, section)			\
+	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+/*
+ * Variant on the per-CPU variable declaration/definition theme used for
+ * ordinary per-CPU variables.
+ */
+#define DECLARE_PER_CPU(type, name)					\
+	DECLARE_PER_CPU_SECTION(type, name, "")
+
+#define DEFINE_PER_CPU(type, name)					\
+	DEFINE_PER_CPU_SECTION(type, name, "")
+
+/*
+ * Declaration/definition used for per-CPU variables that must come first in
+ * the set of variables.
+ */
+#define DECLARE_PER_CPU_FIRST(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+
+/*
+ * Declaration/definition used for per-CPU variables that must be cacheline
+ * aligned under SMP conditions so that, whilst a particular instance of the
+ * data corresponds to a particular CPU, inefficiencies due to direct access by
+ * other CPUs are reduced by preventing the data from unnecessarily spanning
+ * cachelines.
+ *
+ * An example of this would be statistical data, where each CPU's set of data
+ * is updated by that CPU alone, but the data from across all CPUs is collated
+ * by a CPU processing a read from a proc file.
+ */
+#define DECLARE_PER_CPU_SHARED_ALIGNED(type, name)			\
+	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
+	____cacheline_aligned_in_smp
+
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
+	____cacheline_aligned_in_smp
+
+/*
+ * Declaration/definition used for per-CPU variables that must be page aligned.
+ */
+#define DECLARE_PER_CPU_PAGE_ALIGNED(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, ".page_aligned")
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
+
+/*
+ * Intermodule exports for per-CPU variables.
+ */
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+
+
+#endif /* _LINUX_PERCPU_DEFS_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index f052d81..1581ff2 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -9,26 +9,6 @@
 
 #include <asm/percpu.h>
 
-#define DEFINE_PER_CPU_SECTION(type, name, section)			\
-	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU(type, name)					\
-	DEFINE_PER_CPU_SECTION(type, name, "")
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
-	____cacheline_aligned_in_smp
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
-
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
 /* enough to cover all DEFINE_PER_CPUs in modules */
 #ifdef CONFIG_MODULES
 #define PERCPU_MODULE_RESERVE		(8 << 10)