ALSA: pcm: potential uninitialized return values

[pandora-kernel.git] / mm / percpu.c

diff --git a/mm/percpu.c b/mm/percpu.c
index 28c37a2..e29a1c4 100644 (file)
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -116,9 +116,9 @@ static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
 
 /* the address of the first chunk which starts with the kernel static area */
 void *pcpu_base_addr __read_mostly;
@@ -978,6 +978,17 @@ bool is_kernel_percpu_address(unsigned long addr)
  * address.  The caller is responsible for ensuring @addr stays valid
  * until this function finishes.
  *
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
  * RETURNS:
  * The physical address for @addr.
  */
@@ -985,19 +996,19 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
 {
        void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
        bool in_first_chunk = false;
-       unsigned long first_start, first_end;
+       unsigned long first_low, first_high;
        unsigned int cpu;
 
        /*
-        * The following test on first_start/end isn't strictly
+        * The following test on unit_low/high isn't strictly
         * necessary but will speed up lookups of addresses which
         * aren't in the first chunk.
         */
-       first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
-       first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
-                                   pcpu_unit_pages);
-       if ((unsigned long)addr >= first_start &&
-           (unsigned long)addr < first_end) {
+       first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+       first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+                                    pcpu_unit_pages);
+       if ((unsigned long)addr >= first_low &&
+           (unsigned long)addr < first_high) {
                for_each_possible_cpu(cpu) {
                        void *start = per_cpu_ptr(base, cpu);
 
@@ -1012,9 +1023,11 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
                if (!is_vmalloc_addr(addr))
                        return __pa(addr);
                else
-                       return page_to_phys(vmalloc_to_page(addr));
+                       return page_to_phys(vmalloc_to_page(addr)) +
+                              offset_in_page(addr);
        } else
-               return page_to_phys(pcpu_addr_to_page(addr));
+               return page_to_phys(pcpu_addr_to_page(addr)) +
+                      offset_in_page(addr);
 }
 
 /**
@@ -1234,7 +1247,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
        for (cpu = 0; cpu < nr_cpu_ids; cpu++)
                unit_map[cpu] = UINT_MAX;
-       pcpu_first_unit_cpu = NR_CPUS;
+
+       pcpu_low_unit_cpu = NR_CPUS;
+       pcpu_high_unit_cpu = NR_CPUS;
 
        for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
                const struct pcpu_group_info *gi = &ai->groups[group];
@@ -1254,9 +1269,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
                        unit_map[cpu] = unit + i;
                        unit_off[cpu] = gi->base_offset + i * ai->unit_size;
 
-                       if (pcpu_first_unit_cpu == NR_CPUS)
-                               pcpu_first_unit_cpu = cpu;
-                       pcpu_last_unit_cpu = cpu;
+                       /* determine low/high unit_cpu */
+                       if (pcpu_low_unit_cpu == NR_CPUS ||
+                           unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+                               pcpu_low_unit_cpu = cpu;
+                       if (pcpu_high_unit_cpu == NR_CPUS ||
+                           unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+                               pcpu_high_unit_cpu = cpu;
                }
        }
        pcpu_nr_units = unit;
@@ -1623,6 +1642,16 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
                areas[group] = ptr;
 
                base = min(ptr, base);
+       }
+
+       /*
+        * Copy data and free unused parts.  This should happen after all
+        * allocations are complete; otherwise, we may end up with
+        * overlapping groups.
+        */
+       for (group = 0; group < ai->nr_groups; group++) {
+               struct pcpu_group_info *gi = &ai->groups[group];
+               void *ptr = areas[group];
 
                for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
                        if (gi->cpu_map[i] == NR_CPUS) {
@@ -1866,6 +1895,8 @@ void __init setup_per_cpu_areas(void)
 
        if (pcpu_setup_first_chunk(ai, fc) < 0)
                panic("Failed to initialize percpu areas.");
+
+       pcpu_free_alloc_info(ai);
 }
 
 #endif /* CONFIG_SMP */