x86: allow extend_brk users to reserve brk space

Impact: new interface; remove hard-coded limit

Add RESERVE_BRK(name, size) macro to reserve space in the brk
area.  This should be a conservative (ie, larger) estimate of
how much space might possibly be required from the brk area.
Any unused space will be freed, so there's no real downside
on making the reservation too large (within limits).

The name should be unique within a given file, and somewhat
descriptive.

The C definition of RESERVE_BRK() ends up being more complex than
one would expect to work around a cluster of gcc infelicities:

  The first attempt was to simply try putting __section(.brk_reservation)
  on a variable.  This doesn't work because it ends up making it a
  @progbits section, which gets actual space allocated in the vmlinux
  executable.

  The second attempt was to emit the space into a section using asm,
  but gcc doesn't allow arguments to be passed to file-level asm()
  statements, making it hard to pass in the size.

  The final attempt is to wrap the asm() in a function to allow
  it to have arguments, and put the function itself into the
  .discard section, which vmlinux*.lds drops entirely from the
  emitted vmlinux.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/include/asm/setup.h

@@ -104,6 +104,29 @@ extern struct boot_params boot_params;
 extern unsigned long _brk_end;
 void *extend_brk(size_t size, size_t align);
 
+/*
+ * Reserve space in the brk section.  The name must be unique within
+ * the file, and somewhat descriptive.  The size is in bytes.  Must be
+ * used at file scope.
+ *
+ * (This uses a temp function to wrap the asm so we can pass it the
+ * size parameter; otherwise we wouldn't be able to.  We can't use a
+ * "section" attribute on a normal variable because it always ends up
+ * being @progbits, which ends up allocating space in the vmlinux
+ * executable.)
+ */
+#define RESERVE_BRK(name,sz)						\
+	static void __section(.discard) __used			\
+	__brk_reservation_fn_##name##__(void) {				\
+		asm volatile (						\
+			".pushsection .brk_reservation,\"aw\",@nobits;" \
+			"__brk_reservation_" #name "__:"		\
+			" 1:.skip %c0;"					\
+			" .size __brk_reservation_" #name "__, . - 1b;"	\
+			" .popsection"					\
+			: : "i" (sz));					\
+	}
+
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
@@ -115,6 +138,13 @@ void __init x86_64_start_reservations(char *real_mode_data);
 
 #endif /* __i386__ */
 #endif /* _SETUP */
+#else
+#define RESERVE_BRK(name,sz)				\
+	.pushsection .brk_reservation,"aw",@nobits;	\
+__brk_reservation_##name##__:				\
+1:	.skip sz;					\
+	.size __brk_reservation_##name##__,.-1b;	\
+	.popsection
 #endif /* __ASSEMBLY__ */
 #endif  /*  __KERNEL__  */
 

arch/x86/kernel/head_32.S

@@ -75,6 +75,8 @@ ALLOCATOR_SLOP = 4
 
 INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_SIZE_asm
 
+RESERVE_BRK(pagetables, PAGE_TABLE_SIZE * PAGE_SIZE)
+
 /*
  * 32-bit kernel entrypoint; only used by the boot CPU.  On entry,
  * %esi points to the real-mode code as a 32-bit pointer.

arch/x86/kernel/setup.c

@@ -112,6 +112,8 @@
 #define ARCH_SETUP
 #endif
 
+RESERVE_BRK(dmi_alloc, 65536);
+
 unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;

arch/x86/kernel/vmlinux_32.lds.S

@@ -192,7 +192,8 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	__brk_base = . ;
-	. += 1024 * 1024 ;
+	. += 64 * 1024 ;	/* 64k slop space */
+	*(.brk_reservation)	/* areas brk users have reserved */
 	__brk_limit = . ;
 
   	_end = . ;
@@ -201,6 +202,7 @@ SECTIONS
   /* Sections to be discarded */
   /DISCARD/ : {
 	*(.exitcall.exit)
+	*(.discard)
 	}
 
   STABS_DEBUG

arch/x86/kernel/vmlinux_64.lds.S

@@ -250,7 +250,8 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	__brk_base = . ;
-	. += 1024 * 1024 ;
+	. += 64 * 1024;		/* 64k slop space */
+	*(.brk_reservation)	/* areas brk users have reserved */
 	__brk_limit = . ;
   }
 
@@ -260,6 +261,7 @@ SECTIONS
   /DISCARD/ : {
 	*(.exitcall.exit)
 	*(.eh_frame)
+	*(.discard)
 	}
 
   STABS_DEBUG