flat: fix data sections alignment

The flat loader uses an architecture's flat_stack_align() to align the
stack but assumes word-alignment is enough for the data sections.

However, on the Xtensa S6000 we have registers up to 128bit width
which can be used from userspace and therefor need userspace stack and
data-section alignment of at least this size.

This patch drops flat_stack_align() and uses the same alignment that
is required for slab caches, ARCH_SLAB_MINALIGN, or wordsize if it's
not defined by the architecture.

It also fixes m32r which was obviously kaput, aligning an
uninitialized stack entry instead of the stack pointer.

[[e-mail]: coding-style fixes]
Signed-off-by: Oskar Schirmer <[e-mail]>
Cc: David Howells <[e-mail]>
Cc: Russell King <[e-mail]>
Cc: Bryan Wu <[e-mail]>
Cc: Geert Uytterhoeven <[e-mail]>
Acked-by: Paul Mundt <[e-mail]>
Cc: Greg Ungerer <[e-mail]>
Signed-off-by: Johannes Weiner <[e-mail]>
Acked-by: Mike Frysinger <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/arm/include/asm/flat.h

···
 #ifndef __ARM_FLAT_H__
 #define __ARM_FLAT_H__
 
-/* An odd number of words will be pushed after this alignment, so
-   deliberately misalign the value.  */
-#define	flat_stack_align(sp)	sp = (void *)(((unsigned long)(sp) - 4) | 4)
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))

arch/blackfin/include/asm/flat.h

···
 
 #include <asm/unaligned.h>
 
-#define	flat_stack_align(sp)	/* nothing needed */
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 

arch/h8300/include/asm/flat.h

···
 #ifndef __H8300_FLAT_H__
 #define __H8300_FLAT_H__
 
-#define	flat_stack_align(sp)			/* nothing needed */
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		1
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))

arch/m32r/include/asm/flat.h

···
 #ifndef __ASM_M32R_FLAT_H
 #define __ASM_M32R_FLAT_H
 
-#define	flat_stack_align(sp)		(*sp += (*sp & 3 ? (4 - (*sp & 3)): 0))
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_set_persistent(relval, p)		0

arch/m68k/include/asm/flat.h

···
 #ifndef __M68KNOMMU_FLAT_H__
 #define __M68KNOMMU_FLAT_H__
 
-#define	flat_stack_align(sp)			/* nothing needed */
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))

arch/sh/include/asm/flat.h

···
 #ifndef __ASM_SH_FLAT_H
 #define __ASM_SH_FLAT_H
 
-#define	flat_stack_align(sp)			/* nothing needed */
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))

fs/binfmt_flat.c

···
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <asm/cacheflush.h>
+#include <asm/page.h>
 
 /****************************************************************************/
 
···
 #define	DBG_FLT(a...)	printk(a)
 #else
 #define	DBG_FLT(a...)
+#endif
+
+/*
+ * User data (stack, data section and bss) needs to be aligned
+ * for the same reasons as SLAB memory is, and to the same amount.
+ * Avoid duplicating architecture specific code by using the same
+ * macro as with SLAB allocation:
+ */
+#ifdef ARCH_SLAB_MINALIGN
+#define FLAT_DATA_ALIGN	(ARCH_SLAB_MINALIGN)
+#else
+#define FLAT_DATA_ALIGN	(sizeof(void *))
 #endif
 
 #define RELOC_FAILED 0xff00ff01		/* Relocation incorrect somewhere */
···
 	int envc = bprm->envc;
 	char uninitialized_var(dummy);
 
-	sp = (unsigned long *) ((-(unsigned long)sizeof(char *))&(unsigned long) p);
+	sp = (unsigned long *)p;
+	sp -= (envc + argc + 2) + 1 + (flat_argvp_envp_on_stack() ? 2 : 0);
+	sp = (unsigned long *) ((unsigned long)sp & -FLAT_DATA_ALIGN);
+	argv = sp + 1 + (flat_argvp_envp_on_stack() ? 2 : 0);
+	envp = argv + (argc + 1);
 
-	sp -= envc+1;
-	envp = sp;
-	sp -= argc+1;
-	argv = sp;
-
-	flat_stack_align(sp);
 	if (flat_argvp_envp_on_stack()) {
-		--sp; put_user((unsigned long) envp, sp);
-		--sp; put_user((unsigned long) argv, sp);
+		put_user((unsigned long) envp, sp + 2);
+		put_user((unsigned long) argv, sp + 1);
 	}
 
-	put_user(argc,--sp);
+	put_user(argc, sp);
 	current->mm->arg_start = (unsigned long) p;
 	while (argc-->0) {
 		put_user((unsigned long) p, argv++);
···
 			ret = realdatastart;
 			goto err;
 		}
-		datapos = realdatastart + MAX_SHARED_LIBS * sizeof(unsigned long);
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(unsigned long),
+				FLAT_DATA_ALIGN);
 
 		DBG_FLT("BINFMT_FLAT: Allocated data+bss+stack (%d bytes): %x\n",
 				(int)(data_len + bss_len + stack_len), (int)datapos);
···
 		}
 
 		realdatastart = textpos + ntohl(hdr->data_start);
-		datapos = realdatastart + MAX_SHARED_LIBS * sizeof(unsigned long);
-		reloc = (unsigned long *) (textpos + ntohl(hdr->reloc_start) +
-				MAX_SHARED_LIBS * sizeof(unsigned long));
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(unsigned long),
+				FLAT_DATA_ALIGN);
+
+		reloc = (unsigned long *)
+			(datapos + (ntohl(hdr->reloc_start) - text_len));
 		memp = textpos;
 		memp_size = len;
 #ifdef CONFIG_BINFMT_ZFLAT
···
 	stack_len = TOP_OF_ARGS - bprm->p;             /* the strings */
 	stack_len += (bprm->argc + 1) * sizeof(char *); /* the argv array */
 	stack_len += (bprm->envc + 1) * sizeof(char *); /* the envp array */
-
+	stack_len += FLAT_DATA_ALIGN - 1;  /* reserve for upcoming alignment */
 	
 	res = load_flat_file(bprm, &libinfo, 0, &stack_len);
 	if (res > (unsigned long)-4096)