File 5d4d850a-introduce-bss-percpu-page-aligned.patch of Package xen.26345

# Commit 6c9639a72f0ca3a9430ef75f375877182281fdef
# Date 2019-08-09 16:36:58 +0200
# Author Andrew Cooper <andrew.cooper3@citrix.com>
# Committer Jan Beulich <jbeulich@suse.com>
xen/link: Introduce .bss.percpu.page_aligned

Future changes are going to need to page align some percpu data.

Shuffle the exact link order of items within the BSS to give
.bss.percpu.page_aligned appropriate alignment, even on CPU0, which uses
.bss.percpu itself.

Insert explicit alignment such that there won't be a gap between
__per_cpu_start and the first actual per-CPU object.  The POINTER_ALIGN
for __bss_end is to cover the lack of SMP_CACHE_BYTES alignment, as the
loops which zero the BSS use pointer-sized stores on all architectures.

Rework __DEFINE_PER_CPU() so the caller passes in all attributes, and
adjust DEFINE_PER_CPU{,_READ_MOSTLY}() to match.  This has the added bonus
that it is now possible to grep for .bss.percpu and find all the users.

Finally, introduce DEFINE_PER_CPU_PAGE_ALIGNED() which specifies the
section attribute and verifies the type's alignment.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>

Make DEFINE_PER_CPU_PAGE_ALIGNED() verify the alignment rather than
specifying it. It is the underlying type which should be suitably aligned.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Julien Grall <julien.grall@arm.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>

--- a/xen/arch/arm/xen.lds.S
+++ b/xen/arch/arm/xen.lds.S
@@ -183,14 +183,16 @@ SECTIONS
        *(.bss.stack_aligned)
        . = ALIGN(PAGE_SIZE);
        *(.bss.page_aligned)
-       *(.bss)
-       . = ALIGN(SMP_CACHE_BYTES);
+       . = ALIGN(PAGE_SIZE);
        __per_cpu_start = .;
+       *(.bss.percpu.page_aligned)
        *(.bss.percpu)
        . = ALIGN(SMP_CACHE_BYTES);
        *(.bss.percpu.read_mostly)
        . = ALIGN(SMP_CACHE_BYTES);
        __per_cpu_data_end = .;
+       *(.bss)
+       . = ALIGN(POINTER_ALIGN);
        __bss_end = .;
   } :text
   _end = . ;
--- a/xen/arch/x86/xen.lds.S
+++ b/xen/arch/x86/xen.lds.S
@@ -254,14 +254,16 @@ SECTIONS
        __bss_start = .;
        *(.bss.stack_aligned)
        *(.bss.page_aligned*)
-       *(.bss)
-       . = ALIGN(SMP_CACHE_BYTES);
+       . = ALIGN(PAGE_SIZE);
        __per_cpu_start = .;
+       *(.bss.percpu.page_aligned)
        *(.bss.percpu)
        . = ALIGN(SMP_CACHE_BYTES);
        *(.bss.percpu.read_mostly)
        . = ALIGN(SMP_CACHE_BYTES);
        __per_cpu_data_end = .;
+       *(.bss)
+       . = ALIGN(POINTER_ALIGN);
        __bss_end = .;
   } :text
   _end = . ;
--- a/xen/include/asm-arm/percpu.h
+++ b/xen/include/asm-arm/percpu.h
@@ -16,10 +16,8 @@ extern char __per_cpu_start[], __per_cpu
 extern unsigned long __per_cpu_offset[NR_CPUS];
 void percpu_init_areas(void);
 
-/* Separate out the type, so (int[3], foo) works. */
-#define __DEFINE_PER_CPU(type, name, suffix)                    \
-    __section(".bss.percpu" #suffix)                            \
-    __typeof__(type) per_cpu_##name
+#define __DEFINE_PER_CPU(attr, type, name) \
+    attr __typeof__(type) per_cpu_ ## name
 
 #define per_cpu(var, cpu)  \
     (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
--- a/xen/include/asm-x86/percpu.h
+++ b/xen/include/asm-x86/percpu.h
@@ -7,10 +7,8 @@ extern unsigned long __per_cpu_offset[NR
 void percpu_init_areas(void);
 #endif
 
-/* Separate out the type, so (int[3], foo) works. */
-#define __DEFINE_PER_CPU(type, name, suffix)                    \
-    __section(".bss.percpu" #suffix)                            \
-    __typeof__(type) per_cpu_##name
+#define __DEFINE_PER_CPU(attr, type, name) \
+    attr __typeof__(type) per_cpu_ ## name
 
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu)  \
--- a/xen/include/xen/percpu.h
+++ b/xen/include/xen/percpu.h
@@ -9,9 +9,17 @@
  * The _##name concatenation is being used here to prevent 'name' from getting
  * macro expanded, while still allowing a per-architecture symbol name prefix.
  */
-#define DEFINE_PER_CPU(type, name) __DEFINE_PER_CPU(type, _##name, )
+#define DEFINE_PER_CPU(type, name) \
+    __DEFINE_PER_CPU(__section(".bss.percpu"), type, _ ## name)
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
+    typedef char name ## _chk_t \
+        [BUILD_BUG_ON_ZERO(__alignof(type) & (PAGE_SIZE - 1))]; \
+    __DEFINE_PER_CPU(__section(".bss.percpu.page_aligned"), \
+                     type, _ ## name)
+
 #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \
-	__DEFINE_PER_CPU(type, _##name, .read_mostly)
+    __DEFINE_PER_CPU(__section(".bss.percpu.read_mostly"), type, _ ## name)
 
 /* Preferred on Xen. Also see arch-defined per_cpu(). */
 #define this_cpu(var)    __get_cpu_var(var)