x86: alloc dyn_array all together

so could spare some memory with small alignment in bootmem

also tighten the alignment checking, and make print out less debug info.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 50 insertions, 15 deletions

diff --git a/init/main.c b/init/main.c
index 416bca4f734f..ab97d0877acc 100644
--- a/init/main.c
+++ b/init/main.c
@@ -394,10 +394,14 @@ static void __init setup_per_cpu_areas(void)
         unsigned long size, i, old_size;
         char *ptr;
         unsigned long nr_possible_cpus = num_possible_cpus();
+        unsigned long align = 1;
+        unsigned da_size;
 
         /* Copy section for each CPU (we discard the original) */
         old_size = PERCPU_ENOUGH_ROOM;
-        size = ALIGN(old_size + per_cpu_dyn_array_size(), PAGE_SIZE);
+        da_size = per_cpu_dyn_array_size(&align);
+        align = max_t(unsigned long, PAGE_SIZE, align);
+        size = ALIGN(old_size + da_size, align);
         ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
         for_each_possible_cpu(i) {
@@ -541,45 +545,78 @@ void __init __weak thread_info_cache_init(void)
 void pre_alloc_dyn_array(void)
 {
 #ifdef CONFIG_HAVE_DYN_ARRAY
-        unsigned long size, phys = 0;
+        unsigned long total_size = 0, size, phys;
+        unsigned long max_align = 1;
         struct dyn_array **daa;
+        char *ptr;
 
+        /* get the total size at first */
         for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
                 struct dyn_array *da = *daa;
 
                 size = da->size * (*da->nr);
-                print_fn_descriptor_symbol("dyna_array %s ", da->name);
-                printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+                print_fn_descriptor_symbol("dyn_array %s ", da->name);
+                printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
                         da->size, *da->nr, da->align);
-                *da->name = __alloc_bootmem(size, da->align, phys);
-                phys = virt_to_phys(*da->name);
+                total_size += roundup(size, da->align);
+                if (da->align > max_align)
+                        max_align = da->align;
+        }
+        if (total_size)
+                printk(KERN_DEBUG "dyn_array total_size: %#lx\n",
+                         total_size);
+        else
+                return;
+
+        /* allocate them all together */
+        max_align = max_t(unsigned long, max_align, PAGE_SIZE);
+        ptr = __alloc_bootmem_nopanic(total_size, max_align, 0);
+        if (!ptr)
+                panic("Can not alloc dyn_alloc\n");
+
+        phys = virt_to_phys(ptr);
+        for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
+                struct dyn_array *da = *daa;
+
+                size = da->size * (*da->nr);
+                print_fn_descriptor_symbol("dyn_array %s ", da->name);
+
+                phys = roundup(phys, da->align);
+                *da->name = phys_to_virt(phys);
                 printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
 
+                phys += size;
+
                 if (da->init_work)
                         da->init_work(da);
         }
 #endif
 }
 
-unsigned long per_cpu_dyn_array_size(void)
+unsigned long per_cpu_dyn_array_size(unsigned long *align)
 {
         unsigned long total_size = 0;
 #ifdef CONFIG_HAVE_DYN_ARRAY
         unsigned long size;
         struct dyn_array **daa;
+        unsigned max_align = 1;
 
         for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
                 struct dyn_array *da = *daa;
 
                 size = da->size * (*da->nr);
-                print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+                print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
                 printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
                         da->size, *da->nr, da->align);
                 total_size += roundup(size, da->align);
+                if (da->align > max_align)
+                        max_align = da->align;
         }
-        if (total_size)
-                printk(KERN_DEBUG "per_cpu_dyna_array total_size: %#lx\n",
+        if (total_size) {
+                printk(KERN_DEBUG "per_cpu_dyn_array total_size: %#lx\n",
                          total_size);
+                *align = max_align;
+        }
 #endif
         return total_size;
 }
@@ -593,14 +630,11 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
         void **array;
 
         phys = virt_to_phys(ptr);
-
         for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
                 struct dyn_array *da = *daa;
 
                 size = da->size * (*da->nr);
-                print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
-                printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
-                        da->size, *da->nr, da->align);
+                print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
 
                 phys = roundup(phys, da->align);
                 addr = (unsigned long)da->name;
@@ -608,7 +642,8 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
                 array = (void **)addr;
                 *array = phys_to_virt(phys);
                 *da->name = *array; /* so init_work could use it directly */
-                printk(KERN_CONT " %p ==> [%#lx - %#lx]\n", array, phys, phys + size);
+                printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
+
                 phys += size;
 
                 if (da->init_work) {