powerpc/32s: Fix BATs setting with CONFIG_STRICT_KERNEL_RWX

Serge reported some crashes with CONFIG_STRICT_KERNEL_RWX enabled
on a book3s32 machine.

Analysis shows two issues:
  - BATs addresses and sizes are not properly aligned.
  - There is a gap between the last address covered by BATs and the
    first address covered by pages.

Memory mapped with DBATs:
0: 0xc0000000-0xc07fffff 0x00000000 Kernel RO coherent
1: 0xc0800000-0xc0bfffff 0x00800000 Kernel RO coherent
2: 0xc0c00000-0xc13fffff 0x00c00000 Kernel RW coherent
3: 0xc1400000-0xc23fffff 0x01400000 Kernel RW coherent
4: 0xc2400000-0xc43fffff 0x02400000 Kernel RW coherent
5: 0xc4400000-0xc83fffff 0x04400000 Kernel RW coherent
6: 0xc8400000-0xd03fffff 0x08400000 Kernel RW coherent
7: 0xd0400000-0xe03fffff 0x10400000 Kernel RW coherent

Memory mapped with pages:
0xe1000000-0xefffffff  0x21000000       240M        rw       present           dirty  accessed

This patch fixes both issues. With the patch, we get the following
which is as expected:

Memory mapped with DBATs:
0: 0xc0000000-0xc07fffff 0x00000000 Kernel RO coherent
1: 0xc0800000-0xc0bfffff 0x00800000 Kernel RO coherent
2: 0xc0c00000-0xc0ffffff 0x00c00000 Kernel RW coherent
3: 0xc1000000-0xc1ffffff 0x01000000 Kernel RW coherent
4: 0xc2000000-0xc3ffffff 0x02000000 Kernel RW coherent
5: 0xc4000000-0xc7ffffff 0x04000000 Kernel RW coherent
6: 0xc8000000-0xcfffffff 0x08000000 Kernel RW coherent
7: 0xd0000000-0xdfffffff 0x10000000 Kernel RW coherent

Memory mapped with pages:
0xe0000000-0xefffffff  0x20000000       256M        rw       present           dirty  accessed

Fixes: 63b2bc61 ("powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX")
Reported-by: Serge Belyshev <belyshev@depni.sinp.msu.ru>
Acked-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/mm/ppc_mmu_32.c

@@ -98,10 +98,20 @@ static int find_free_bat(void)
 	return -1;
 }
 
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ *   is identified by the lowest bit set to 1 in the base address (for instance
+ *   if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ *   highest bit set to 1.
+ */
 static unsigned int block_size(unsigned long base, unsigned long top)
 {
 	unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
-	unsigned int base_shift = (fls(base) - 1) & 31;
+	unsigned int base_shift = (ffs(base) - 1) & 31;
 	unsigned int block_shift = (fls(top - base) - 1) & 31;
 
 	return min3(max_size, 1U << base_shift, 1U << block_shift);
@@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to
 
 unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
-	int done;
+	unsigned long done;
 	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
 
 	if (__map_without_bats) {
@@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 		return __mmu_mapin_ram(base, top);
 
 	done = __mmu_mapin_ram(base, border);
-	if (done != border - base)
+	if (done != border)
 		return done;
 
-	return done + __mmu_mapin_ram(border, top);
+	return __mmu_mapin_ram(border, top);
 }
 
 void mmu_mark_initmem_nx(void)