Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 0d707a2f authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-4.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu 

Pull percpu fixes from Tejun Heo:
 "Late percpu pull request for v4.16-rc6.

   - percpu allocator pool replenishing no longer triggers OOM or
     warning messages.

     Also, the alloc interface now understands __GFP_NORETRY and
     __GFP_NOWARN. This is to allow avoiding OOMs from userland
     triggered actions like bpf map creation.

     Also added cond_resched() in alloc loop.

   - perpcu allocation now can be interrupted by kill sigs to avoid
     deadlocking OOM killer.

   - Added Dennis Zhou as a co-maintainer.

     He has rewritten the area map allocator, understands most of the
     code base and has been responsive for all bug reports"

* 'for-4.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
  percpu_ref: Update doc to dissuade users from depending on internal RCU grace periods
  mm: Allow to kill tasks doing pcpu_alloc() and waiting for pcpu_balance_workfn()
  percpu: include linux/sched.h for cond_resched()
  percpu: add a schedule point in pcpu_balance_workfn()
  percpu: allow select gfp to be passed to underlying allocators
  percpu: add __GFP_NORETRY semantics to the percpu balancing path
  percpu: match chunk allocator declarations with definitions
  percpu: add Dennis Zhou as a percpu co-maintainer
parents efac2483 b3a5d111

MAINTAINERS

+1 −0
Original line number Diff line number Diff line
@@ -10844,6 +10844,7 @@ F: drivers/platform/x86/peaq-wmi.c 
PER-CPU MEMORY ALLOCATOR

M:	Tejun Heo <tj@kernel.org>

M:	Christoph Lameter <cl@linux.com>

M:	Dennis Zhou <dennisszhou@gmail.com>

T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git

S:	Maintained

F:	include/linux/percpu*.h

include/linux/percpu-refcount.h

+12 −6
Original line number Diff line number Diff line
@@ -30,10 +30,14 @@ 
 * calls io_destroy() or the process exits.

 *

 * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it

 * calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove

 * the kioctx from the proccess's list of kioctxs - after that, there can't be

 * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop

 * the initial ref with percpu_ref_put().

 * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref.

 * After that, there can't be any new users of the kioctx (from lookup_ioctx())

 * and it's then safe to drop the initial ref with percpu_ref_put().

 *

 * Note that the free path, free_ioctx(), needs to go through explicit call_rcu()

 * to synchronize with RCU protected lookup_ioctx().  percpu_ref operations don't

 * imply RCU grace periods of any kind and if a user wants to combine percpu_ref

 * with RCU protection, it must be done explicitly.

 *

 * Code that does a two stage shutdown like this often needs some kind of

 * explicit synchronization to ensure the initial refcount can only be dropped
@@ -113,8 +117,10 @@ void percpu_ref_reinit(struct percpu_ref *ref); 
 * Must be used to drop the initial ref on a percpu refcount; must be called

 * precisely once before shutdown.

 *

 * Puts @ref in non percpu mode, then does a call_rcu() before gathering up the

 * percpu counters and dropping the initial ref.

 * Switches @ref into atomic mode before gathering up the percpu counters

 * and dropping the initial ref.

 *

 * There are no implied RCU grace periods between kill and release.

 */

static inline void percpu_ref_kill(struct percpu_ref *ref)

{

lib/percpu-refcount.c

+2 −0
Original line number Diff line number Diff line
@@ -322,6 +322,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); 
 * This function normally doesn't block and can be called from any context

 * but it may block if @confirm_kill is specified and @ref is in the

 * process of switching to atomic mode by percpu_ref_switch_to_atomic().

 *

 * There are no implied RCU grace periods between kill and release.

 */

void percpu_ref_kill_and_confirm(struct percpu_ref *ref,

				 percpu_ref_func_t *confirm_kill)

mm/percpu-km.c

+4 −4
Original line number Diff line number Diff line
@@ -34,7 +34,7 @@ 
#include <linux/log2.h>



static int pcpu_populate_chunk(struct pcpu_chunk *chunk,

			       int page_start, int page_end)

			       int page_start, int page_end, gfp_t gfp)

{

	return 0;

}
@@ -45,18 +45,18 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, 
	/* nada */

}



static struct pcpu_chunk *pcpu_create_chunk(void)

static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)

{

	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;

	struct pcpu_chunk *chunk;

	struct page *pages;

	int i;



	chunk = pcpu_alloc_chunk();

	chunk = pcpu_alloc_chunk(gfp);

	if (!chunk)

		return NULL;



	pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));

	pages = alloc_pages(gfp, order_base_2(nr_pages));

	if (!pages) {

		pcpu_free_chunk(chunk);

		return NULL;

mm/percpu-vm.c

+11 −7
Original line number Diff line number Diff line
@@ -37,7 +37,7 @@ static struct page **pcpu_get_pages(void) 
	lockdep_assert_held(&pcpu_alloc_mutex);



	if (!pages)

		pages = pcpu_mem_zalloc(pages_size);

		pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL);

	return pages;

}
@@ -73,18 +73,21 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk, 
 * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()

 * @page_start: page index of the first page to be allocated

 * @page_end: page index of the last page to be allocated + 1

 * @gfp: allocation flags passed to the underlying allocator

 *

 * Allocate pages [@page_start,@page_end) into @pages for all units.

 * The allocation is for @chunk.  Percpu core doesn't care about the

 * content of @pages and will pass it verbatim to pcpu_map_pages().

 */

static int pcpu_alloc_pages(struct pcpu_chunk *chunk,

			    struct page **pages, int page_start, int page_end)

			    struct page **pages, int page_start, int page_end,

			    gfp_t gfp)

{

	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM;

	unsigned int cpu, tcpu;

	int i;



	gfp |= __GFP_HIGHMEM;



	for_each_possible_cpu(cpu) {

		for (i = page_start; i < page_end; i++) {

			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
@@ -262,6 +265,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, 
 * @chunk: chunk of interest

 * @page_start: the start page

 * @page_end: the end page

 * @gfp: allocation flags passed to the underlying memory allocator

 *

 * For each cpu, populate and map pages [@page_start,@page_end) into

 * @chunk.
@@ -270,7 +274,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, 
 * pcpu_alloc_mutex, does GFP_KERNEL allocation.

 */

static int pcpu_populate_chunk(struct pcpu_chunk *chunk,

			       int page_start, int page_end)

			       int page_start, int page_end, gfp_t gfp)

{

	struct page **pages;
@@ -278,7 +282,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, 
	if (!pages)

		return -ENOMEM;



	if (pcpu_alloc_pages(chunk, pages, page_start, page_end))

	if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp))

		return -ENOMEM;



	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
@@ -325,12 +329,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, 
	pcpu_free_pages(chunk, pages, page_start, page_end);

}



static struct pcpu_chunk *pcpu_create_chunk(void)

static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)

{

	struct pcpu_chunk *chunk;

	struct vm_struct **vms;



	chunk = pcpu_alloc_chunk();

	chunk = pcpu_alloc_chunk(gfp);

	if (!chunk)

		return NULL;