--- /dev/null
+From b6e238dceed36891cc633167afe7151f1f3d83c5 Mon Sep 17 00:00:00 2001
+From: Oleg Nesterov <oleg@redhat.com>
+Date: Mon, 19 Mar 2012 17:03:41 +0100
+Subject: exit_signal: fix the "parent has changed security domain" logic
+
+From: Oleg Nesterov <oleg@redhat.com>
+
+commit b6e238dceed36891cc633167afe7151f1f3d83c5 upstream.
+
+exit_notify() changes ->exit_signal if the parent already did exec.
+This doesn't really work, we are not going to send the signal now
+if there is another live thread or the exiting task is traced. The
+parent can exec before the last dies or the tracer detaches.
+
+Move this check into do_notify_parent() which actually sends the
+signal.
+
+The user-visible change is that we do not change ->exit_signal,
+and thus the exiting task is still "clone children" for
+do_wait()->eligible_child(__WCLONE). Hopefully this is fine, the
+current logic is racy anyway.
+
+Signed-off-by: Oleg Nesterov <oleg@redhat.com>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/exit.c | 14 --------------
+ kernel/signal.c | 9 +++++++++
+ 2 files changed, 9 insertions(+), 14 deletions(-)
+
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -818,20 +818,6 @@ static void exit_notify(struct task_stru
+ if (group_dead)
+ kill_orphaned_pgrp(tsk->group_leader, NULL);
+
+- /* Let father know we died
+- *
+- * Thread signals are configurable, but you aren't going to use
+- * that to send signals to arbitrary processes.
+- * That stops right now.
+- *
+- * If the parent exec id doesn't match the exec id we saved
+- * when we started then we know the parent has changed security
+- * domain.
+- */
+- if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
+- tsk->parent_exec_id != tsk->real_parent->self_exec_id)
+- tsk->exit_signal = SIGCHLD;
+-
+ if (unlikely(tsk->ptrace)) {
+ int sig = thread_group_leader(tsk) &&
+ thread_group_empty(tsk) &&
+--- a/kernel/signal.c
++++ b/kernel/signal.c
+@@ -1642,6 +1642,15 @@ bool do_notify_parent(struct task_struct
+ BUG_ON(!tsk->ptrace &&
+ (tsk->group_leader != tsk || !thread_group_empty(tsk)));
+
++ if (sig != SIGCHLD) {
++ /*
++ * This is only possible if parent == real_parent.
++ * Check if it has changed security domain.
++ */
++ if (tsk->parent_exec_id != tsk->parent->self_exec_id)
++ sig = SIGCHLD;
++ }
++
+ info.si_signo = sig;
+ info.si_errno = 0;
+ /*
--- /dev/null
+From e636825346b36a07ccfc8e30946d52855e21f681 Mon Sep 17 00:00:00 2001
+From: Oleg Nesterov <oleg@redhat.com>
+Date: Mon, 19 Mar 2012 17:03:22 +0100
+Subject: exit_signal: simplify the "we have changed execution domain" logic
+
+From: Oleg Nesterov <oleg@redhat.com>
+
+commit e636825346b36a07ccfc8e30946d52855e21f681 upstream.
+
+exit_notify() checks "tsk->self_exec_id != tsk->parent_exec_id"
+to handle the "we have changed execution domain" case.
+
+We can change do_thread() to always set ->exit_signal = SIGCHLD
+and remove this check to simplify the code.
+
+We could change setup_new_exec() instead, this looks more logical
+because it increments ->self_exec_id. But note that de_thread()
+already resets ->exit_signal if it changes the leader, let's keep
+both changes close to each other.
+
+Note that we change ->exit_signal lockless, this changes the rules.
+Thereafter ->exit_signal is not stable under tasklist but this is
+fine, the only possible change is OLDSIG -> SIGCHLD. This can race
+with eligible_child() but the race is harmless. We can race with
+reparent_leader() which changes our ->exit_signal in parallel, but
+it does the same change to SIGCHLD.
+
+The noticeable user-visible change is that the execing task is not
+"visible" to do_wait()->eligible_child(__WCLONE) right after exec.
+To me this looks more logical, and this is consistent with mt case.
+
+Signed-off-by: Oleg Nesterov <oleg@redhat.com>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/exec.c | 3 +++
+ kernel/exit.c | 7 +------
+ 2 files changed, 4 insertions(+), 6 deletions(-)
+
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -975,6 +975,9 @@ static int de_thread(struct task_struct
+ sig->notify_count = 0;
+
+ no_thread_group:
++ /* we have changed execution domain */
++ tsk->exit_signal = SIGCHLD;
++
+ if (current->mm)
+ setmax_mm_hiwater_rss(&sig->maxrss, current->mm);
+
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -827,14 +827,9 @@ static void exit_notify(struct task_stru
+ * If the parent exec id doesn't match the exec id we saved
+ * when we started then we know the parent has changed security
+ * domain.
+- *
+- * If our self_exec id doesn't match our parent_exec_id then
+- * we have changed execution domain as these two values started
+- * the same after a fork.
+ */
+ if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
+- (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
+- tsk->self_exec_id != tsk->parent_exec_id))
++ tsk->parent_exec_id != tsk->real_parent->self_exec_id)
+ tsk->exit_signal = SIGCHLD;
+
+ if (unlikely(tsk->ptrace)) {
--- /dev/null
+From f8262d476823a7ea1eb497ff9676d1eab2393c75 Mon Sep 17 00:00:00 2001
+From: Bojan Smojver <bojan@rexursive.com>
+Date: Tue, 24 Apr 2012 23:53:28 +0200
+Subject: PM / Hibernate: fix the number of pages used for hibernate/thaw buffering
+
+From: Bojan Smojver <bojan@rexursive.com>
+
+commit f8262d476823a7ea1eb497ff9676d1eab2393c75 upstream.
+
+Hibernation regression fix, since 3.2.
+
+Calculate the number of required free pages based on non-high memory
+pages only, because that is where the buffers will come from.
+
+Commit 081a9d043c983f161b78fdc4671324d1342b86bc introduced a new buffer
+page allocation logic during hibernation, in order to improve the
+performance. The amount of pages allocated was calculated based on total
+amount of pages available, although only non-high memory pages are
+usable for this purpose. This caused hibernation code to attempt to over
+allocate pages on platforms that have high memory, which led to hangs.
+
+Signed-off-by: Bojan Smojver <bojan@rexursive.com>
+Signed-off-by: Rafael J. Wysocki <rjw@suse.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/power/swap.c | 28 ++++++++++++++++++++++------
+ 1 file changed, 22 insertions(+), 6 deletions(-)
+
+--- a/kernel/power/swap.c
++++ b/kernel/power/swap.c
+@@ -51,6 +51,23 @@
+
+ #define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
+
++/*
++ * Number of free pages that are not high.
++ */
++static inline unsigned long low_free_pages(void)
++{
++ return nr_free_pages() - nr_free_highpages();
++}
++
++/*
++ * Number of pages required to be kept free while writing the image. Always
++ * half of all available low pages before the writing starts.
++ */
++static inline unsigned long reqd_free_pages(void)
++{
++ return low_free_pages() / 2;
++}
++
+ struct swap_map_page {
+ sector_t entries[MAP_PAGE_ENTRIES];
+ sector_t next_swap;
+@@ -72,7 +89,7 @@ struct swap_map_handle {
+ sector_t cur_swap;
+ sector_t first_sector;
+ unsigned int k;
+- unsigned long nr_free_pages, written;
++ unsigned long reqd_free_pages;
+ u32 crc32;
+ };
+
+@@ -316,8 +333,7 @@ static int get_swap_writer(struct swap_m
+ goto err_rel;
+ }
+ handle->k = 0;
+- handle->nr_free_pages = nr_free_pages() >> 1;
+- handle->written = 0;
++ handle->reqd_free_pages = reqd_free_pages();
+ handle->first_sector = handle->cur_swap;
+ return 0;
+ err_rel:
+@@ -352,11 +368,11 @@ static int swap_write_page(struct swap_m
+ handle->cur_swap = offset;
+ handle->k = 0;
+ }
+- if (bio_chain && ++handle->written > handle->nr_free_pages) {
++ if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+ error = hib_wait_on_bio_chain(bio_chain);
+ if (error)
+ goto out;
+- handle->written = 0;
++ handle->reqd_free_pages = reqd_free_pages();
+ }
+ out:
+ return error;
+@@ -618,7 +634,7 @@ static int save_image_lzo(struct swap_ma
+ * Adjust number of free pages after all allocations have been done.
+ * We don't want to run out of pages when writing.
+ */
+- handle->nr_free_pages = nr_free_pages() >> 1;
++ handle->reqd_free_pages = reqd_free_pages();
+
+ /*
+ * Start the CRC32 thread.
--- /dev/null
+From 8a95bc8dfe06982fc2b8a0a2adda7baa2346a17b Mon Sep 17 00:00:00 2001
+From: Timur Tabi <timur@freescale.com>
+Date: Wed, 30 Nov 2011 10:19:17 -0600
+Subject: powerpc/85xx: don't call of_platform_bus_probe() twice
+
+From: Timur Tabi <timur@freescale.com>
+
+commit 8a95bc8dfe06982fc2b8a0a2adda7baa2346a17b upstream.
+
+Commit 46d026ac ("powerpc/85xx: consolidate of_platform_bus_probe calls")
+replaced platform-specific of_device_id tables with a single function
+that probes the most of the busses in 85xx device trees. If a specific
+platform needed additional busses probed, then it could call
+of_platform_bus_probe() again. Typically, the additional platform-specific
+busses are children of existing busses that have already been probed.
+of_platform_bus_probe() does not handle those child busses automatically.
+
+Unfortunately, this doesn't actually work. The second (platform-specific)
+call to of_platform_bus_probe() never finds any of the busses it's asked
+to find.
+
+To remedy this, the platform-specific of_device_id tables are eliminated,
+and their entries are merged into mpc85xx_common_ids[], so that all busses
+are probed at once.
+
+Signed-off-by: Timur Tabi <timur@freescale.com>
+Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/powerpc/platforms/85xx/common.c | 6 ++++++
+ arch/powerpc/platforms/85xx/mpc85xx_mds.c | 11 +----------
+ arch/powerpc/platforms/85xx/p1022_ds.c | 13 +------------
+ 3 files changed, 8 insertions(+), 22 deletions(-)
+
+--- a/arch/powerpc/platforms/85xx/common.c
++++ b/arch/powerpc/platforms/85xx/common.c
+@@ -21,6 +21,12 @@ static struct of_device_id __initdata mp
+ { .compatible = "fsl,qe", },
+ { .compatible = "fsl,cpm2", },
+ { .compatible = "fsl,srio", },
++ /* So that the DMA channel nodes can be probed individually: */
++ { .compatible = "fsl,eloplus-dma", },
++ /* For the PMC driver */
++ { .compatible = "fsl,mpc8548-guts", },
++ /* Probably unnecessary? */
++ { .compatible = "gpio-leds", },
+ {},
+ };
+
+--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
++++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+@@ -405,12 +405,6 @@ static int __init board_fixups(void)
+ machine_arch_initcall(mpc8568_mds, board_fixups);
+ machine_arch_initcall(mpc8569_mds, board_fixups);
+
+-static struct of_device_id mpc85xx_ids[] = {
+- { .compatible = "fsl,mpc8548-guts", },
+- { .compatible = "gpio-leds", },
+- {},
+-};
+-
+ static int __init mpc85xx_publish_devices(void)
+ {
+ if (machine_is(mpc8568_mds))
+@@ -418,10 +412,7 @@ static int __init mpc85xx_publish_device
+ if (machine_is(mpc8569_mds))
+ simple_gpiochip_init("fsl,mpc8569mds-bcsr-gpio");
+
+- mpc85xx_common_publish_devices();
+- of_platform_bus_probe(NULL, mpc85xx_ids, NULL);
+-
+- return 0;
++ return mpc85xx_common_publish_devices();
+ }
+
+ machine_device_initcall(mpc8568_mds, mpc85xx_publish_devices);
+--- a/arch/powerpc/platforms/85xx/p1022_ds.c
++++ b/arch/powerpc/platforms/85xx/p1022_ds.c
+@@ -303,18 +303,7 @@ static void __init p1022_ds_setup_arch(v
+ pr_info("Freescale P1022 DS reference board\n");
+ }
+
+-static struct of_device_id __initdata p1022_ds_ids[] = {
+- /* So that the DMA channel nodes can be probed individually: */
+- { .compatible = "fsl,eloplus-dma", },
+- {},
+-};
+-
+-static int __init p1022_ds_publish_devices(void)
+-{
+- mpc85xx_common_publish_devices();
+- return of_platform_bus_probe(NULL, p1022_ds_ids, NULL);
+-}
+-machine_device_initcall(p1022_ds, p1022_ds_publish_devices);
++machine_device_initcall(p1022_ds, mpc85xx_common_publish_devices);
+
+ machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
+
--- /dev/null
+From c308b56b5398779cd3da0f62ab26b0453494c3d4 Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Thu, 1 Mar 2012 15:04:46 +0100
+Subject: sched: Fix nohz load accounting -- again!
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Peter Zijlstra <peterz@infradead.org>
+
+commit c308b56b5398779cd3da0f62ab26b0453494c3d4 upstream.
+
+Various people reported nohz load tracking still being wrecked, but Doug
+spotted the actual problem. We fold the nohz remainder in too soon,
+causing us to loose samples and under-account.
+
+So instead of playing catch-up up-front, always do a single load-fold
+with whatever state we encounter and only then fold the nohz remainder
+and play catch-up.
+
+Reported-by: Doug Smythies <dsmythies@telus.net>
+Reported-by: LesÅ=82aw Kope=C4=87 <leslaw.kopec@nasza-klasa.pl>
+Reported-by: Aman Gupta <aman@tmm1.net>
+Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
+Link: http://lkml.kernel.org/n/tip-4v31etnhgg9kwd6ocgx3rxl8@git.kernel.org
+Signed-off-by: Ingo Molnar <mingo@elte.hu>
+Cc: Kerin Millar <kerframil@gmail.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/sched/core.c | 53 +++++++++++++++++++++++++---------------------------
+ 1 file changed, 26 insertions(+), 27 deletions(-)
+
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -2266,13 +2266,10 @@ calc_load_n(unsigned long load, unsigned
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+-static void calc_global_nohz(unsigned long ticks)
++static void calc_global_nohz(void)
+ {
+ long delta, active, n;
+
+- if (time_before(jiffies, calc_load_update))
+- return;
+-
+ /*
+ * If we crossed a calc_load_update boundary, make sure to fold
+ * any pending idle changes, the respective CPUs might have
+@@ -2284,31 +2281,25 @@ static void calc_global_nohz(unsigned lo
+ atomic_long_add(delta, &calc_load_tasks);
+
+ /*
+- * If we were idle for multiple load cycles, apply them.
++ * It could be the one fold was all it took, we done!
+ */
+- if (ticks >= LOAD_FREQ) {
+- n = ticks / LOAD_FREQ;
++ if (time_before(jiffies, calc_load_update + 10))
++ return;
+
+- active = atomic_long_read(&calc_load_tasks);
+- active = active > 0 ? active * FIXED_1 : 0;
++ /*
++ * Catch-up, fold however many we are behind still
++ */
++ delta = jiffies - calc_load_update - 10;
++ n = 1 + (delta / LOAD_FREQ);
+
+- avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+- avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+- avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
++ active = atomic_long_read(&calc_load_tasks);
++ active = active > 0 ? active * FIXED_1 : 0;
+
+- calc_load_update += n * LOAD_FREQ;
+- }
++ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
++ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
++ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+- /*
+- * Its possible the remainder of the above division also crosses
+- * a LOAD_FREQ period, the regular check in calc_global_load()
+- * which comes after this will take care of that.
+- *
+- * Consider us being 11 ticks before a cycle completion, and us
+- * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+- * age us 4 cycles, and the test in calc_global_load() will
+- * pick up the final one.
+- */
++ calc_load_update += n * LOAD_FREQ;
+ }
+ #else
+ void calc_load_account_idle(struct rq *this_rq)
+@@ -2320,7 +2311,7 @@ static inline long calc_load_fold_idle(v
+ return 0;
+ }
+
+-static void calc_global_nohz(unsigned long ticks)
++static void calc_global_nohz(void)
+ {
+ }
+ #endif
+@@ -2348,8 +2339,6 @@ void calc_global_load(unsigned long tick
+ {
+ long active;
+
+- calc_global_nohz(ticks);
+-
+ if (time_before(jiffies, calc_load_update + 10))
+ return;
+
+@@ -2361,6 +2350,16 @@ void calc_global_load(unsigned long tick
+ avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+ calc_load_update += LOAD_FREQ;
++
++ /*
++ * Account one period with whatever state we found before
++ * folding in the nohz state and ageing the entire idle period.
++ *
++ * This avoids loosing a sample when we go idle between
++ * calc_load_account_active() (10 ticks ago) and now and thus
++ * under-accounting.
++ */
++ calc_global_nohz();
+ }
+
+ /*
x86-efi-fix-endian-issues-and-unaligned-accesses.patch
x86-boot-correct-cflags-for-hostprogs.patch
x86-efi-add-dedicated-efi-stub-entry-point.patch
+powerpc-85xx-don-t-call-of_platform_bus_probe-twice.patch
+pm-hibernate-fix-the-number-of-pages-used-for-hibernate-thaw-buffering.patch
+sched-fix-nohz-load-accounting-again.patch
+exit_signal-simplify-the-we-have-changed-execution-domain-logic.patch
+exit_signal-fix-the-parent-has-changed-security-domain-logic.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
