#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
+#include <linux/kmemleak.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
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;
/*
* (Un)populated page region iterators. Iterate over (un)populated
- * page regions betwen @start and @end in @chunk. @rs and @re should
+ * page regions between @start and @end in @chunk. @rs and @re should
* be integer variables and will be set to start and end page index of
* the current region.
*/
(rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
/**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used. The returned
+ * kzalloc() is used; otherwise, vzalloc() is used. The returned
* memory is always zeroed.
*
* CONTEXT:
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
{
if (WARN_ON_ONCE(!slab_is_available()))
return NULL;
if (size <= PAGE_SIZE)
return kzalloc(size, GFP_KERNEL);
- else {
- void *ptr = vmalloc(size);
- if (ptr)
- memset(ptr, 0, size);
- return ptr;
- }
+ else
+ return vzalloc(size);
}
/**
* @ptr: memory to free
* @size: size of the area
*
- * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc().
*/
static void pcpu_mem_free(void *ptr, size_t size)
{
* @chunk: chunk of interest
*
* Determine whether area map of @chunk needs to be extended to
- * accomodate a new allocation.
+ * accommodate a new allocation.
*
* CONTEXT:
* pcpu_lock.
size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
unsigned long flags;
- new = pcpu_mem_alloc(new_size);
+ new = pcpu_mem_zalloc(new_size);
if (!new)
return -ENOMEM;
* depending on @head, is reduced by @tail bytes and @tail byte block
* is inserted after the target block.
*
- * @chunk->map must have enough free slots to accomodate the split.
+ * @chunk->map must have enough free slots to accommodate the split.
*
* CONTEXT:
* pcpu_lock.
{
struct pcpu_chunk *chunk;
- chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+ chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
if (!chunk)
return NULL;
- chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+ chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+ sizeof(chunk->map[0]));
if (!chunk->map) {
kfree(chunk);
return NULL;
const char *err;
int slot, off, new_alloc;
unsigned long flags;
+ void __percpu *ptr;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
WARN(true, "illegal size (%zu) or align (%zu) for "
mutex_unlock(&pcpu_alloc_mutex);
/* return address relative to base address */
- return __addr_to_pcpu_ptr(chunk->base_addr + off);
+ ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
+ kmemleak_alloc_percpu(ptr, size);
+ return ptr;
fail_unlock:
spin_unlock_irqrestore(&pcpu_lock, flags);
if (!ptr)
return;
+ kmemleak_free_percpu(ptr);
+
addr = __pcpu_ptr_to_addr(ptr);
spin_lock_irqsave(&pcpu_lock, flags);
* 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.
*/
{
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);
}
if (in_first_chunk) {
- if ((unsigned long)addr < VMALLOC_START ||
- (unsigned long)addr >= VMALLOC_END)
+ 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);
}
/**
PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
#ifdef CONFIG_SMP
PCPU_SETUP_BUG_ON(!ai->static_size);
+ PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
#endif
PCPU_SETUP_BUG_ON(!base_addr);
+ PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
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];
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;
/* we're done parsing the input, undefine BUG macro and dump config */
#undef PCPU_SETUP_BUG_ON
- pcpu_dump_alloc_info(KERN_INFO, ai);
+ pcpu_dump_alloc_info(KERN_DEBUG, ai);
pcpu_nr_groups = ai->nr_groups;
pcpu_group_offsets = group_offsets;
/*
* Determine min_unit_size, alloc_size and max_upa such that
* alloc_size is multiple of atom_size and is the smallest
- * which can accomodate 4k aligned segments which are equal to
+ * which can accommodate 4k aligned segments which are equal to
* or larger than min_unit_size.
*/
min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
* @alloc_fn: function to allocate percpu page
- * @free_fn: funtion to free percpu page
+ * @free_fn: function to free percpu page
*
* This is a helper to ease setting up embedded first percpu chunk and
* can be called where pcpu_setup_first_chunk() is expected.
rc = -ENOMEM;
goto out_free_areas;
}
+ /* kmemleak tracks the percpu allocations separately */
+ kmemleak_free(ptr);
areas[group] = ptr;
base = min(ptr, base);
/* warn if maximum distance is further than 75% of vmalloc space */
if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
- "space 0x%lx\n",
- max_distance, VMALLOC_END - VMALLOC_START);
+ "space 0x%lx\n", max_distance,
+ (unsigned long)(VMALLOC_END - VMALLOC_START));
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
/* and fail if we have fallback */
rc = -EINVAL;
* pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
* @reserved_size: the size of reserved percpu area in bytes
* @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
- * @free_fn: funtion to free percpu page, always called with PAGE_SIZE
+ * @free_fn: function to free percpu page, always called with PAGE_SIZE
* @populate_pte_fn: function to populate pte
*
* This is a helper to ease setting up page-remapped first percpu
"for cpu%u\n", psize_str, cpu);
goto enomem;
}
+ /* kmemleak tracks the percpu allocations separately */
+ kmemleak_free(ptr);
pages[j++] = virt_to_page(ptr);
}
BUILD_BUG_ON(size > PAGE_SIZE);
- map = pcpu_mem_alloc(size);
+ map = pcpu_mem_zalloc(size);
BUG_ON(!map);
spin_lock_irqsave(&pcpu_lock, flags);