summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMike Pagano <mpagano@gentoo.org>2015-01-09 13:28:20 -0500
committerMike Pagano <mpagano@gentoo.org>2015-01-09 13:28:20 -0500
commit7f750c59142fd88befd49a9cabb85dbcd421fb46 (patch)
treec96c9410815188f4f672e98da463fed4070a3908
parentBFQ upgrade to v7r7 (diff)
downloadlinux-patches-3.14-33.tar.gz
linux-patches-3.14-33.tar.bz2
linux-patches-3.14-33.zip
Linux patch 3.14.283.14-33
-rw-r--r--0000_README4
-rw-r--r--1027_linux-3.14.28.patch1961
2 files changed, 1965 insertions, 0 deletions
diff --git a/0000_README b/0000_README
index 0f5f3a09..62e39ea3 100644
--- a/0000_README
+++ b/0000_README
@@ -150,6 +150,10 @@ Patch: 1026_linux-3.14.27.patch
From: http://www.kernel.org
Desc: Linux 3.14.27
+Patch: 1027_linux-3.14.28.patch
+From: http://www.kernel.org
+Desc: Linux 3.14.28
+
Patch: 1500_XATTR_USER_PREFIX.patch
From: https://bugs.gentoo.org/show_bug.cgi?id=470644
Desc: Support for namespace user.pax.* on tmpfs.
diff --git a/1027_linux-3.14.28.patch b/1027_linux-3.14.28.patch
new file mode 100644
index 00000000..ac6bcbc2
--- /dev/null
+++ b/1027_linux-3.14.28.patch
@@ -0,0 +1,1961 @@
+diff --git a/Makefile b/Makefile
+index 944db2356a7c..a2e572bfff7d 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,6 +1,6 @@
+ VERSION = 3
+ PATCHLEVEL = 14
+-SUBLEVEL = 27
++SUBLEVEL = 28
+ EXTRAVERSION =
+ NAME = Remembering Coco
+
+diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
+index 0d8530c98cf5..34841fc1a977 100644
+--- a/arch/arm/boot/dts/armada-370.dtsi
++++ b/arch/arm/boot/dts/armada-370.dtsi
+@@ -106,11 +106,6 @@
+ reg = <0x11100 0x20>;
+ };
+
+- system-controller@18200 {
+- compatible = "marvell,armada-370-xp-system-controller";
+- reg = <0x18200 0x100>;
+- };
+-
+ pinctrl {
+ compatible = "marvell,mv88f6710-pinctrl";
+ reg = <0x18000 0x38>;
+@@ -167,6 +162,11 @@
+ interrupts = <91>;
+ };
+
++ system-controller@18200 {
++ compatible = "marvell,armada-370-xp-system-controller";
++ reg = <0x18200 0x100>;
++ };
++
+ gateclk: clock-gating-control@18220 {
+ compatible = "marvell,armada-370-gating-clock";
+ reg = <0x18220 0x4>;
+diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
+index 8c1ba4fea384..350579961e78 100644
+--- a/arch/arm/mach-tegra/reset-handler.S
++++ b/arch/arm/mach-tegra/reset-handler.S
+@@ -51,6 +51,7 @@ ENTRY(tegra_resume)
+ THUMB( it ne )
+ bne cpu_resume @ no
+
++ tegra_get_soc_id TEGRA_APB_MISC_BASE, r6
+ /* Are we on Tegra20? */
+ cmp r6, #TEGRA20
+ beq 1f @ Yes
+diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
+index 6cddbb0c9f54..e0ec201eaf56 100644
+--- a/arch/arm64/include/asm/hwcap.h
++++ b/arch/arm64/include/asm/hwcap.h
+@@ -30,6 +30,7 @@
+ #define COMPAT_HWCAP_IDIVA (1 << 17)
+ #define COMPAT_HWCAP_IDIVT (1 << 18)
+ #define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
++#define COMPAT_HWCAP_LPAE (1 << 20)
+ #define COMPAT_HWCAP_EVTSTRM (1 << 21)
+
+ #ifndef __ASSEMBLY__
+diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
+index c8e9effe52e1..071c3822442b 100644
+--- a/arch/arm64/kernel/setup.c
++++ b/arch/arm64/kernel/setup.c
+@@ -67,7 +67,8 @@ EXPORT_SYMBOL_GPL(elf_hwcap);
+ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
+ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
+ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
+- COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
++ COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
++ COMPAT_HWCAP_LPAE)
+ unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+ #endif
+
+diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
+index db02052bd137..5426c9eb5114 100644
+--- a/arch/s390/kernel/compat_linux.c
++++ b/arch/s390/kernel/compat_linux.c
+@@ -245,7 +245,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
+ struct group_info *group_info;
+ int retval;
+
+- if (!capable(CAP_SETGID))
++ if (!may_setgroups())
+ return -EPERM;
+ if ((unsigned)gidsetsize > NGROUPS_MAX)
+ return -EINVAL;
+diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
+index 46727eb37bfe..6e1aaf73852a 100644
+--- a/arch/x86/include/uapi/asm/ldt.h
++++ b/arch/x86/include/uapi/asm/ldt.h
+@@ -28,6 +28,13 @@ struct user_desc {
+ unsigned int seg_not_present:1;
+ unsigned int useable:1;
+ #ifdef __x86_64__
++ /*
++ * Because this bit is not present in 32-bit user code, user
++ * programs can pass uninitialized values here. Therefore, in
++ * any context in which a user_desc comes from a 32-bit program,
++ * the kernel must act as though lm == 0, regardless of the
++ * actual value.
++ */
+ unsigned int lm:1;
+ #endif
+ };
+diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
+index 713f1b3bad52..0b1e1d5dbc5b 100644
+--- a/arch/x86/kernel/kvm.c
++++ b/arch/x86/kernel/kvm.c
+@@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
+ static void __init paravirt_ops_setup(void)
+ {
+ pv_info.name = "KVM";
+- pv_info.paravirt_enabled = 1;
++
++ /*
++ * KVM isn't paravirt in the sense of paravirt_enabled. A KVM
++ * guest kernel works like a bare metal kernel with additional
++ * features, and paravirt_enabled is about features that are
++ * missing.
++ */
++ pv_info.paravirt_enabled = 0;
+
+ if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
+ pv_cpu_ops.io_delay = kvm_io_delay;
+diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
+index e6041094ff26..c8e98cdc84c2 100644
+--- a/arch/x86/kernel/kvmclock.c
++++ b/arch/x86/kernel/kvmclock.c
+@@ -263,7 +263,6 @@ void __init kvmclock_init(void)
+ #endif
+ kvm_get_preset_lpj();
+ clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
+- pv_info.paravirt_enabled = 1;
+ pv_info.name = "KVM";
+
+ if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
+index 9c0280f93d05..e2d26ce9b854 100644
+--- a/arch/x86/kernel/process_64.c
++++ b/arch/x86/kernel/process_64.c
+@@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+
+ fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+
+- /*
+- * Reload esp0, LDT and the page table pointer:
+- */
++ /* Reload esp0 and ss1. */
+ load_sp0(tss, next);
+
+- /*
+- * Switch DS and ES.
+- * This won't pick up thread selector changes, but I guess that is ok.
+- */
+- savesegment(es, prev->es);
+- if (unlikely(next->es | prev->es))
+- loadsegment(es, next->es);
+-
+- savesegment(ds, prev->ds);
+- if (unlikely(next->ds | prev->ds))
+- loadsegment(ds, next->ds);
+-
+-
+ /* We must save %fs and %gs before load_TLS() because
+ * %fs and %gs may be cleared by load_TLS().
+ *
+@@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
+ savesegment(fs, fsindex);
+ savesegment(gs, gsindex);
+
++ /*
++ * Load TLS before restoring any segments so that segment loads
++ * reference the correct GDT entries.
++ */
+ load_TLS(next, cpu);
+
+ /*
+- * Leave lazy mode, flushing any hypercalls made here.
+- * This must be done before restoring TLS segments so
+- * the GDT and LDT are properly updated, and must be
+- * done before math_state_restore, so the TS bit is up
+- * to date.
++ * Leave lazy mode, flushing any hypercalls made here. This
++ * must be done after loading TLS entries in the GDT but before
++ * loading segments that might reference them, and and it must
++ * be done before math_state_restore, so the TS bit is up to
++ * date.
+ */
+ arch_end_context_switch(next_p);
+
++ /* Switch DS and ES.
++ *
++ * Reading them only returns the selectors, but writing them (if
++ * nonzero) loads the full descriptor from the GDT or LDT. The
++ * LDT for next is loaded in switch_mm, and the GDT is loaded
++ * above.
++ *
++ * We therefore need to write new values to the segment
++ * registers on every context switch unless both the new and old
++ * values are zero.
++ *
++ * Note that we don't need to do anything for CS and SS, as
++ * those are saved and restored as part of pt_regs.
++ */
++ savesegment(es, prev->es);
++ if (unlikely(next->es | prev->es))
++ loadsegment(es, next->es);
++
++ savesegment(ds, prev->ds);
++ if (unlikely(next->ds | prev->ds))
++ loadsegment(ds, next->ds);
++
+ /*
+ * Switch FS and GS.
+ *
+- * Segment register != 0 always requires a reload. Also
+- * reload when it has changed. When prev process used 64bit
+- * base always reload to avoid an information leak.
++ * These are even more complicated than FS and GS: they have
++ * 64-bit bases are that controlled by arch_prctl. Those bases
++ * only differ from the values in the GDT or LDT if the selector
++ * is 0.
++ *
++ * Loading the segment register resets the hidden base part of
++ * the register to 0 or the value from the GDT / LDT. If the
++ * next base address zero, writing 0 to the segment register is
++ * much faster than using wrmsr to explicitly zero the base.
++ *
++ * The thread_struct.fs and thread_struct.gs values are 0
++ * if the fs and gs bases respectively are not overridden
++ * from the values implied by fsindex and gsindex. They
++ * are nonzero, and store the nonzero base addresses, if
++ * the bases are overridden.
++ *
++ * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
++ * be impossible.
++ *
++ * Therefore we need to reload the segment registers if either
++ * the old or new selector is nonzero, and we need to override
++ * the base address if next thread expects it to be overridden.
++ *
++ * This code is unnecessarily slow in the case where the old and
++ * new indexes are zero and the new base is nonzero -- it will
++ * unnecessarily write 0 to the selector before writing the new
++ * base address.
++ *
++ * Note: This all depends on arch_prctl being the only way that
++ * user code can override the segment base. Once wrfsbase and
++ * wrgsbase are enabled, most of this code will need to change.
+ */
+ if (unlikely(fsindex | next->fsindex | prev->fs)) {
+ loadsegment(fs, next->fsindex);
++
+ /*
+- * Check if the user used a selector != 0; if yes
+- * clear 64bit base, since overloaded base is always
+- * mapped to the Null selector
++ * If user code wrote a nonzero value to FS, then it also
++ * cleared the overridden base address.
++ *
++ * XXX: if user code wrote 0 to FS and cleared the base
++ * address itself, we won't notice and we'll incorrectly
++ * restore the prior base address next time we reschdule
++ * the process.
+ */
+ if (fsindex)
+ prev->fs = 0;
+ }
+- /* when next process has a 64bit base use it */
+ if (next->fs)
+ wrmsrl(MSR_FS_BASE, next->fs);
+ prev->fsindex = fsindex;
+
+ if (unlikely(gsindex | next->gsindex | prev->gs)) {
+ load_gs_index(next->gsindex);
++
++ /* This works (and fails) the same way as fsindex above. */
+ if (gsindex)
+ prev->gs = 0;
+ }
+diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
+index f7fec09e3e3a..4e942f31b1a7 100644
+--- a/arch/x86/kernel/tls.c
++++ b/arch/x86/kernel/tls.c
+@@ -27,6 +27,37 @@ static int get_free_idx(void)
+ return -ESRCH;
+ }
+
++static bool tls_desc_okay(const struct user_desc *info)
++{
++ if (LDT_empty(info))
++ return true;
++
++ /*
++ * espfix is required for 16-bit data segments, but espfix
++ * only works for LDT segments.
++ */
++ if (!info->seg_32bit)
++ return false;
++
++ /* Only allow data segments in the TLS array. */
++ if (info->contents > 1)
++ return false;
++
++ /*
++ * Non-present segments with DPL 3 present an interesting attack
++ * surface. The kernel should handle such segments correctly,
++ * but TLS is very difficult to protect in a sandbox, so prevent
++ * such segments from being created.
++ *
++ * If userspace needs to remove a TLS entry, it can still delete
++ * it outright.
++ */
++ if (info->seg_not_present)
++ return false;
++
++ return true;
++}
++
+ static void set_tls_desc(struct task_struct *p, int idx,
+ const struct user_desc *info, int n)
+ {
+@@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
+ if (copy_from_user(&info, u_info, sizeof(info)))
+ return -EFAULT;
+
++ if (!tls_desc_okay(&info))
++ return -EINVAL;
++
+ if (idx == -1)
+ idx = info.entry_number;
+
+@@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
+ {
+ struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
+ const struct user_desc *info;
++ int i;
+
+ if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+ (pos % sizeof(struct user_desc)) != 0 ||
+@@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
+ else
+ info = infobuf;
+
++ for (i = 0; i < count / sizeof(struct user_desc); i++)
++ if (!tls_desc_okay(info + i))
++ return -EINVAL;
++
+ set_tls_desc(target,
+ GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
+ info, count / sizeof(struct user_desc));
+diff --git a/crypto/af_alg.c b/crypto/af_alg.c
+index 6a3ad8011585..1de4beeb25f8 100644
+--- a/crypto/af_alg.c
++++ b/crypto/af_alg.c
+@@ -449,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err)
+ {
+ struct af_alg_completion *completion = req->data;
+
++ if (err == -EINPROGRESS)
++ return;
++
+ completion->err = err;
+ complete(&completion->completion);
+ }
+diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
+index 4195a01b1535..8e51b3a3e7b9 100644
+--- a/drivers/md/bitmap.c
++++ b/drivers/md/bitmap.c
+@@ -883,7 +883,6 @@ void bitmap_unplug(struct bitmap *bitmap)
+ {
+ unsigned long i;
+ int dirty, need_write;
+- int wait = 0;
+
+ if (!bitmap || !bitmap->storage.filemap ||
+ test_bit(BITMAP_STALE, &bitmap->flags))
+@@ -901,16 +900,13 @@ void bitmap_unplug(struct bitmap *bitmap)
+ clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
+ write_page(bitmap, bitmap->storage.filemap[i], 0);
+ }
+- if (dirty)
+- wait = 1;
+- }
+- if (wait) { /* if any writes were performed, we need to wait on them */
+- if (bitmap->storage.file)
+- wait_event(bitmap->write_wait,
+- atomic_read(&bitmap->pending_writes)==0);
+- else
+- md_super_wait(bitmap->mddev);
+ }
++ if (bitmap->storage.file)
++ wait_event(bitmap->write_wait,
++ atomic_read(&bitmap->pending_writes)==0);
++ else
++ md_super_wait(bitmap->mddev);
++
+ if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
+ bitmap_file_kick(bitmap);
+ }
+diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
+index a1cebf745b22..03c872fd5d5c 100644
+--- a/drivers/md/dm-bufio.c
++++ b/drivers/md/dm-bufio.c
+@@ -532,6 +532,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
+ end_io(&b->bio, r);
+ }
+
++static void inline_endio(struct bio *bio, int error)
++{
++ bio_end_io_t *end_fn = bio->bi_private;
++
++ /*
++ * Reset the bio to free any attached resources
++ * (e.g. bio integrity profiles).
++ */
++ bio_reset(bio);
++
++ end_fn(bio, error);
++}
++
+ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
+ bio_end_io_t *end_io)
+ {
+@@ -543,7 +556,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
+ b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
+ b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits;
+ b->bio.bi_bdev = b->c->bdev;
+- b->bio.bi_end_io = end_io;
++ b->bio.bi_end_io = inline_endio;
++ /*
++ * Use of .bi_private isn't a problem here because
++ * the dm_buffer's inline bio is local to bufio.
++ */
++ b->bio.bi_private = end_io;
+
+ /*
+ * We assume that if len >= PAGE_SIZE ptr is page-aligned.
+diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
+index 2331543005b2..ff284b7a17bd 100644
+--- a/drivers/md/dm-cache-target.c
++++ b/drivers/md/dm-cache-target.c
+@@ -946,10 +946,14 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
+ }
+
+ } else {
+- clear_dirty(cache, mg->new_oblock, mg->cblock);
+- if (mg->requeue_holder)
++ if (mg->requeue_holder) {
++ clear_dirty(cache, mg->new_oblock, mg->cblock);
+ cell_defer(cache, mg->new_ocell, true);
+- else {
++ } else {
++ /*
++ * The block was promoted via an overwrite, so it's dirty.
++ */
++ set_dirty(cache, mg->new_oblock, mg->cblock);
+ bio_endio(mg->new_ocell->holder, 0);
+ cell_defer(cache, mg->new_ocell, false);
+ }
+@@ -1060,7 +1064,8 @@ static void issue_copy(struct dm_cache_migration *mg)
+
+ avoid = is_discarded_oblock(cache, mg->new_oblock);
+
+- if (!avoid && bio_writes_complete_block(cache, bio)) {
++ if (writeback_mode(&cache->features) &&
++ !avoid && bio_writes_complete_block(cache, bio)) {
+ issue_overwrite(mg, bio);
+ return;
+ }
+diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
+index 9533f835ce07..4a8d19d0a5a4 100644
+--- a/drivers/md/dm-crypt.c
++++ b/drivers/md/dm-crypt.c
+@@ -709,7 +709,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
+ for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++)
+ crypto_xor(data + i * 8, buf, 8);
+ out:
+- memset(buf, 0, sizeof(buf));
++ memzero_explicit(buf, sizeof(buf));
+ return r;
+ }
+
+diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
+index 37f2648c112b..f7e052c7ab5f 100644
+--- a/drivers/md/dm-thin.c
++++ b/drivers/md/dm-thin.c
+@@ -916,6 +916,24 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
+ }
+ }
+
++static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
++
++static void check_for_space(struct pool *pool)
++{
++ int r;
++ dm_block_t nr_free;
++
++ if (get_pool_mode(pool) != PM_OUT_OF_DATA_SPACE)
++ return;
++
++ r = dm_pool_get_free_block_count(pool->pmd, &nr_free);
++ if (r)
++ return;
++
++ if (nr_free)
++ set_pool_mode(pool, PM_WRITE);
++}
++
+ /*
+ * A non-zero return indicates read_only or fail_io mode.
+ * Many callers don't care about the return value.
+@@ -930,6 +948,8 @@ static int commit(struct pool *pool)
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r)
+ metadata_operation_failed(pool, "dm_pool_commit_metadata", r);
++ else
++ check_for_space(pool);
+
+ return r;
+ }
+@@ -948,8 +968,6 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks)
+ }
+ }
+
+-static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+-
+ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
+ {
+ int r;
+@@ -1592,7 +1610,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
+ pool->process_bio = process_bio_read_only;
+ pool->process_discard = process_discard;
+ pool->process_prepared_mapping = process_prepared_mapping;
+- pool->process_prepared_discard = process_prepared_discard_passdown;
++ pool->process_prepared_discard = process_prepared_discard;
+
+ if (!pool->pf.error_if_no_space && no_space_timeout)
+ queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout);
+diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
+index 786b689bdfc7..f4e22bcc7fb8 100644
+--- a/drivers/md/persistent-data/dm-space-map-metadata.c
++++ b/drivers/md/persistent-data/dm-space-map-metadata.c
+@@ -564,7 +564,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count
+ {
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+- return smm->ll.nr_blocks;
++ *count = smm->ll.nr_blocks;
++
++ return 0;
+ }
+
+ static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
+index 11c19e538551..48579e5ef02c 100644
+--- a/drivers/mfd/tc6393xb.c
++++ b/drivers/mfd/tc6393xb.c
+@@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
+ return 0;
+ }
+
++static int tc6393xb_ohci_suspend(struct platform_device *dev)
++{
++ struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
++
++ /* We can't properly store/restore OHCI state, so fail here */
++ if (tcpd->resume_restore)
++ return -EBUSY;
++
++ return tc6393xb_ohci_disable(dev);
++}
++
+ static int tc6393xb_fb_enable(struct platform_device *dev)
+ {
+ struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
+@@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = {
+ .num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
+ .resources = tc6393xb_ohci_resources,
+ .enable = tc6393xb_ohci_enable,
+- .suspend = tc6393xb_ohci_disable,
++ .suspend = tc6393xb_ohci_suspend,
+ .resume = tc6393xb_ohci_enable,
+ .disable = tc6393xb_ohci_disable,
+ },
+diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
+index 7b5424f398ac..df72c478c5a2 100644
+--- a/drivers/mmc/card/block.c
++++ b/drivers/mmc/card/block.c
+@@ -260,7 +260,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr,
+ int ret;
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+
+- ret = snprintf(buf, PAGE_SIZE, "%d",
++ ret = snprintf(buf, PAGE_SIZE, "%d\n",
+ get_disk_ro(dev_to_disk(dev)) ^
+ md->read_only);
+ mmc_blk_put(md);
+diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
+index 55cd110a49c4..caed9d53e8fa 100644
+--- a/drivers/mmc/host/dw_mmc.c
++++ b/drivers/mmc/host/dw_mmc.c
+@@ -632,6 +632,13 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
+
+ WARN_ON(!(data->flags & MMC_DATA_READ));
+
++ /*
++ * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is
++ * in the FIFO region, so we really shouldn't access it).
++ */
++ if (host->verid < DW_MMC_240A)
++ return;
++
+ if (host->timing != MMC_TIMING_MMC_HS200 &&
+ host->timing != MMC_TIMING_UHS_SDR104)
+ goto disable;
+diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
+index f49666bcc52a..257e9ca30166 100644
+--- a/drivers/mmc/host/sdhci-pci-o2micro.c
++++ b/drivers/mmc/host/sdhci-pci-o2micro.c
+@@ -88,8 +88,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
+ return;
+ scratch_32 &= ~((1 << 21) | (1 << 30));
+
+- /* Set RTD3 function disabled */
+- scratch_32 |= ((1 << 29) | (1 << 28));
+ pci_write_config_dword(chip->pdev, O2_SD_FUNC_REG3, scratch_32);
+
+ /* Set L1 Entrance Timer */
+diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
+index 1e9d6ad9302b..7563b3d9cc76 100644
+--- a/drivers/scsi/NCR5380.c
++++ b/drivers/scsi/NCR5380.c
+@@ -2655,14 +2655,14 @@ static void NCR5380_dma_complete(NCR5380_instance * instance) {
+ *
+ * Purpose : abort a command
+ *
+- * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the
+- * host byte of the result field to, if zero DID_ABORTED is
++ * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the
++ * host byte of the result field to, if zero DID_ABORTED is
+ * used.
+ *
+- * Returns : 0 - success, -1 on failure.
++ * Returns : SUCCESS - success, FAILED on failure.
+ *
+- * XXX - there is no way to abort the command that is currently
+- * connected, you have to wait for it to complete. If this is
++ * XXX - there is no way to abort the command that is currently
++ * connected, you have to wait for it to complete. If this is
+ * a problem, we could implement longjmp() / setjmp(), setjmp()
+ * called where the loop started in NCR5380_main().
+ *
+@@ -2712,7 +2712,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
+ * aborted flag and get back into our main loop.
+ */
+
+- return 0;
++ return SUCCESS;
+ }
+ #endif
+
+diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
+index 5f3101797c93..31ace4bef8fe 100644
+--- a/drivers/scsi/aha1740.c
++++ b/drivers/scsi/aha1740.c
+@@ -531,7 +531,7 @@ static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy)
+ * quiet as possible...
+ */
+
+- return 0;
++ return SUCCESS;
+ }
+
+ static struct scsi_host_template aha1740_template = {
+diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
+index 0f3cdbc80ba6..30073d43d87b 100644
+--- a/drivers/scsi/atari_NCR5380.c
++++ b/drivers/scsi/atari_NCR5380.c
+@@ -2613,7 +2613,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
+ * host byte of the result field to, if zero DID_ABORTED is
+ * used.
+ *
+- * Returns : 0 - success, -1 on failure.
++ * Returns : SUCCESS - success, FAILED on failure.
+ *
+ * XXX - there is no way to abort the command that is currently
+ * connected, you have to wait for it to complete. If this is
+diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
+index f37f3e3dd5d5..28fe6feae44c 100644
+--- a/drivers/scsi/esas2r/esas2r_main.c
++++ b/drivers/scsi/esas2r/esas2r_main.c
+@@ -1057,7 +1057,7 @@ int esas2r_eh_abort(struct scsi_cmnd *cmd)
+
+ cmd->scsi_done(cmd);
+
+- return 0;
++ return SUCCESS;
+ }
+
+ spin_lock_irqsave(&a->queue_lock, flags);
+diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
+index 816db12ef5d5..52587ceac099 100644
+--- a/drivers/scsi/megaraid.c
++++ b/drivers/scsi/megaraid.c
+@@ -1967,7 +1967,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
+ cmd->device->id, cmd->device->lun);
+
+ if(list_empty(&adapter->pending_list))
+- return FALSE;
++ return FAILED;
+
+ list_for_each_safe(pos, next, &adapter->pending_list) {
+
+@@ -1990,7 +1990,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
+ (aor==SCB_ABORT) ? "ABORTING":"RESET",
+ scb->idx);
+
+- return FALSE;
++ return FAILED;
+ }
+ else {
+
+@@ -2015,12 +2015,12 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
+ list_add_tail(SCSI_LIST(cmd),
+ &adapter->completed_list);
+
+- return TRUE;
++ return SUCCESS;
+ }
+ }
+ }
+
+- return FALSE;
++ return FAILED;
+ }
+
+ static inline int
+diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
+index 3b7ad10497fe..c80afde97e96 100644
+--- a/drivers/scsi/megaraid/megaraid_sas_base.c
++++ b/drivers/scsi/megaraid/megaraid_sas_base.c
+@@ -953,7 +953,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
+ cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr));
+
+ cmd->sync_cmd = 1;
+- cmd->cmd_status = 0xFF;
++ cmd->cmd_status = ENODATA;
+
+ instance->instancet->issue_dcmd(instance, cmd);
+
+diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c
+index 636bbe0ea84c..fc57c8aec2b3 100644
+--- a/drivers/scsi/sun3_NCR5380.c
++++ b/drivers/scsi/sun3_NCR5380.c
+@@ -2597,15 +2597,15 @@ static void NCR5380_reselect (struct Scsi_Host *instance)
+ * Purpose : abort a command
+ *
+ * Inputs : cmd - the struct scsi_cmnd to abort, code - code to set the
+- * host byte of the result field to, if zero DID_ABORTED is
++ * host byte of the result field to, if zero DID_ABORTED is
+ * used.
+ *
+- * Returns : 0 - success, -1 on failure.
++ * Returns : SUCCESS - success, FAILED on failure.
+ *
+- * XXX - there is no way to abort the command that is currently
+- * connected, you have to wait for it to complete. If this is
++ * XXX - there is no way to abort the command that is currently
++ * connected, you have to wait for it to complete. If this is
+ * a problem, we could implement longjmp() / setjmp(), setjmp()
+- * called where the loop started in NCR5380_main().
++ * called where the loop started in NCR5380_main().
+ */
+
+ static int NCR5380_abort(struct scsi_cmnd *cmd)
+diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
+index 71b0ec0c370d..284733e1fb6f 100644
+--- a/drivers/thermal/thermal_core.c
++++ b/drivers/thermal/thermal_core.c
+@@ -1824,10 +1824,10 @@ static int __init thermal_init(void)
+
+ exit_netlink:
+ genetlink_exit();
+-unregister_governors:
+- thermal_unregister_governors();
+ unregister_class:
+ class_unregister(&thermal_class);
++unregister_governors:
++ thermal_unregister_governors();
+ error:
+ idr_destroy(&thermal_tz_idr);
+ idr_destroy(&thermal_cdev_idr);
+diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
+index 370ef7450157..0db8ded65923 100644
+--- a/fs/btrfs/disk-io.c
++++ b/fs/btrfs/disk-io.c
+@@ -3978,12 +3978,6 @@ again:
+ if (ret)
+ break;
+
+- /* opt_discard */
+- if (btrfs_test_opt(root, DISCARD))
+- ret = btrfs_error_discard_extent(root, start,
+- end + 1 - start,
+- NULL);
+-
+ clear_extent_dirty(unpin, start, end, GFP_NOFS);
+ btrfs_error_unpin_extent_range(root, start, end);
+ cond_resched();
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 3ff98e23f651..d2f1c011d73a 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -5503,7 +5503,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
+ update_global_block_rsv(fs_info);
+ }
+
+-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
++static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
++ const bool return_free_space)
+ {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_block_group_cache *cache = NULL;
+@@ -5527,7 +5528,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+
+ if (start < cache->last_byte_to_unpin) {
+ len = min(len, cache->last_byte_to_unpin - start);
+- btrfs_add_free_space(cache, start, len);
++ if (return_free_space)
++ btrfs_add_free_space(cache, start, len);
+ }
+
+ start += len;
+@@ -5590,7 +5592,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
+ end + 1 - start, NULL);
+
+ clear_extent_dirty(unpin, start, end, GFP_NOFS);
+- unpin_extent_range(root, start, end);
++ unpin_extent_range(root, start, end, true);
+ cond_resched();
+ }
+
+@@ -8886,7 +8888,7 @@ out:
+
+ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+ {
+- return unpin_extent_range(root, start, end);
++ return unpin_extent_range(root, start, end, false);
+ }
+
+ int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
+index 996ad56b57db..82845a6c63c2 100644
+--- a/fs/btrfs/extent_map.c
++++ b/fs/btrfs/extent_map.c
+@@ -290,8 +290,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
+ if (!em)
+ goto out;
+
+- if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+- list_move(&em->list, &tree->modified_extents);
+ em->generation = gen;
+ clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ em->mod_start = em->start;
+diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
+index 2f6735dbf1a9..31b148f3e772 100644
+--- a/fs/ecryptfs/crypto.c
++++ b/fs/ecryptfs/crypto.c
+@@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
+ break;
+ case 2:
+ dst[dst_byte_offset++] |= (src_byte);
+- dst[dst_byte_offset] = 0;
+ current_bit_offset = 0;
+ break;
+ }
+diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
+index b1eaa7a1f82c..03df50211c48 100644
+--- a/fs/ecryptfs/file.c
++++ b/fs/ecryptfs/file.c
+@@ -191,23 +191,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
+ {
+ int rc = 0;
+ struct ecryptfs_crypt_stat *crypt_stat = NULL;
+- struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+ struct dentry *ecryptfs_dentry = file->f_path.dentry;
+ /* Private value of ecryptfs_dentry allocated in
+ * ecryptfs_lookup() */
+ struct ecryptfs_file_info *file_info;
+
+- mount_crypt_stat = &ecryptfs_superblock_to_private(
+- ecryptfs_dentry->d_sb)->mount_crypt_stat;
+- if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+- && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
+- || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
+- || (file->f_flags & O_APPEND))) {
+- printk(KERN_WARNING "Mount has encrypted view enabled; "
+- "files may only be read\n");
+- rc = -EPERM;
+- goto out;
+- }
+ /* Released in ecryptfs_release or end of function if failure */
+ file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
+ ecryptfs_set_file_private(file, file_info);
+diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
+index 1b119d3bf924..34eb8433d93f 100644
+--- a/fs/ecryptfs/main.c
++++ b/fs/ecryptfs/main.c
+@@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
+ {
+ struct super_block *s;
+ struct ecryptfs_sb_info *sbi;
++ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+ struct ecryptfs_dentry_info *root_info;
+ const char *err = "Getting sb failed";
+ struct inode *inode;
+@@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
+ err = "Error parsing options";
+ goto out;
+ }
++ mount_crypt_stat = &sbi->mount_crypt_stat;
+
+ s = sget(fs_type, NULL, set_anon_super, flags, NULL);
+ if (IS_ERR(s)) {
+@@ -557,11 +559,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
+
+ /**
+ * Set the POSIX ACL flag based on whether they're enabled in the lower
+- * mount. Force a read-only eCryptfs mount if the lower mount is ro.
+- * Allow a ro eCryptfs mount even when the lower mount is rw.
++ * mount.
+ */
+ s->s_flags = flags & ~MS_POSIXACL;
+- s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
++ s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
++
++ /**
++ * Force a read-only eCryptfs mount when:
++ * 1) The lower mount is ro
++ * 2) The ecryptfs_encrypted_view mount option is specified
++ */
++ if (path.dentry->d_sb->s_flags & MS_RDONLY ||
++ mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
++ s->s_flags |= MS_RDONLY;
+
+ s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
+ s->s_blocksize = path.dentry->d_sb->s_blocksize;
+diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
+index f488bbae541a..735d7522a3a9 100644
+--- a/fs/isofs/rock.c
++++ b/fs/isofs/rock.c
+@@ -30,6 +30,7 @@ struct rock_state {
+ int cont_size;
+ int cont_extent;
+ int cont_offset;
++ int cont_loops;
+ struct inode *inode;
+ };
+
+@@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode)
+ rs->inode = inode;
+ }
+
++/* Maximum number of Rock Ridge continuation entries */
++#define RR_MAX_CE_ENTRIES 32
++
+ /*
+ * Returns 0 if the caller should continue scanning, 1 if the scan must end
+ * and -ve on error.
+@@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs)
+ goto out;
+ }
+ ret = -EIO;
++ if (++rs->cont_loops >= RR_MAX_CE_ENTRIES)
++ goto out;
+ bh = sb_bread(rs->inode->i_sb, rs->cont_extent);
+ if (bh) {
+ memcpy(rs->buffer, bh->b_data + rs->cont_offset,
+@@ -356,6 +362,9 @@ repeat:
+ rs.cont_size = isonum_733(rr->u.CE.size);
+ break;
+ case SIG('E', 'R'):
++ /* Invalid length of ER tag id? */
++ if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len)
++ goto out;
+ ISOFS_SB(inode->i_sb)->s_rock = 1;
+ printk(KERN_DEBUG "ISO 9660 Extensions: ");
+ {
+diff --git a/fs/namespace.c b/fs/namespace.c
+index d9bf3efbf040..039f3802d70e 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -1295,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how)
+ }
+ if (last) {
+ last->mnt_hash.next = unmounted.first;
++ if (unmounted.first)
++ unmounted.first->pprev = &last->mnt_hash.next;
+ unmounted.first = tmp_list.first;
+ unmounted.first->pprev = &unmounted.first;
+ }
+@@ -1439,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
+ goto dput_and_out;
+ if (mnt->mnt.mnt_flags & MNT_LOCKED)
+ goto dput_and_out;
++ retval = -EPERM;
++ if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
++ goto dput_and_out;
+
+ retval = do_umount(mnt, flags);
+ dput_and_out:
+@@ -1964,7 +1969,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+ !(mnt_flags & MNT_NODEV)) {
+- return -EPERM;
++ /* Was the nodev implicitly added in mount? */
++ if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
++ !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
++ mnt_flags |= MNT_NODEV;
++ } else {
++ return -EPERM;
++ }
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+ !(mnt_flags & MNT_NOSUID)) {
+diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
+index 60426ccb3b65..2f970de02b16 100644
+--- a/fs/ncpfs/ioctl.c
++++ b/fs/ncpfs/ioctl.c
+@@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
+ result = -EIO;
+ }
+ }
+- result = 0;
+ }
+ mutex_unlock(&server->root_setup_lock);
+
+diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
+index bd01803d0656..58258ad50d5f 100644
+--- a/fs/nfs/nfs4proc.c
++++ b/fs/nfs/nfs4proc.c
+@@ -7589,6 +7589,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+
+ dprintk("--> %s\n", __func__);
+
++ /* nfs4_layoutget_release calls pnfs_put_layout_hdr */
++ pnfs_get_layout_hdr(NFS_I(inode)->layout);
++
+ lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
+ if (!lgp->args.layout.pages) {
+ nfs4_layoutget_release(lgp);
+@@ -7601,9 +7604,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+ lgp->res.seq_res.sr_slot = NULL;
+ nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
+
+- /* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+- pnfs_get_layout_hdr(NFS_I(inode)->layout);
+-
+ task = rpc_run_task(&task_setup_data);
+ if (IS_ERR(task))
+ return ERR_CAST(task);
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+index b9760628e1fd..489ba8caafc0 100644
+--- a/fs/proc/base.c
++++ b/fs/proc/base.c
+@@ -2555,6 +2555,57 @@ static const struct file_operations proc_projid_map_operations = {
+ .llseek = seq_lseek,
+ .release = proc_id_map_release,
+ };
++
++static int proc_setgroups_open(struct inode *inode, struct file *file)
++{
++ struct user_namespace *ns = NULL;
++ struct task_struct *task;
++ int ret;
++
++ ret = -ESRCH;
++ task = get_proc_task(inode);
++ if (task) {
++ rcu_read_lock();
++ ns = get_user_ns(task_cred_xxx(task, user_ns));
++ rcu_read_unlock();
++ put_task_struct(task);
++ }
++ if (!ns)
++ goto err;
++
++ if (file->f_mode & FMODE_WRITE) {
++ ret = -EACCES;
++ if (!ns_capable(ns, CAP_SYS_ADMIN))
++ goto err_put_ns;
++ }
++
++ ret = single_open(file, &proc_setgroups_show, ns);
++ if (ret)
++ goto err_put_ns;
++
++ return 0;
++err_put_ns:
++ put_user_ns(ns);
++err:
++ return ret;
++}
++
++static int proc_setgroups_release(struct inode *inode, struct file *file)
++{
++ struct seq_file *seq = file->private_data;
++ struct user_namespace *ns = seq->private;
++ int ret = single_release(inode, file);
++ put_user_ns(ns);
++ return ret;
++}
++
++static const struct file_operations proc_setgroups_operations = {
++ .open = proc_setgroups_open,
++ .write = proc_setgroups_write,
++ .read = seq_read,
++ .llseek = seq_lseek,
++ .release = proc_setgroups_release,
++};
+ #endif /* CONFIG_USER_NS */
+
+ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+@@ -2663,6 +2714,7 @@ static const struct pid_entry tgid_base_stuff[] = {
+ REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
+ REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations),
+ REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
++ REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
+ #endif
+ #ifdef CONFIG_CHECKPOINT_RESTORE
+ REG("timers", S_IRUGO, proc_timers_operations),
+@@ -2998,6 +3050,7 @@ static const struct pid_entry tid_base_stuff[] = {
+ REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
+ REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations),
+ REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
++ REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
+ #endif
+ };
+
+diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
+index d7c6dbe4194b..d89f324bc387 100644
+--- a/fs/udf/symlink.c
++++ b/fs/udf/symlink.c
+@@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page)
+ struct inode *inode = page->mapping->host;
+ struct buffer_head *bh = NULL;
+ unsigned char *symlink;
+- int err = -EIO;
++ int err;
+ unsigned char *p = kmap(page);
+ struct udf_inode_info *iinfo;
+ uint32_t pos;
+
++ /* We don't support symlinks longer than one block */
++ if (inode->i_size > inode->i_sb->s_blocksize) {
++ err = -ENAMETOOLONG;
++ goto out_unmap;
++ }
++
+ iinfo = UDF_I(inode);
+ pos = udf_block_map(inode, 0);
+
+@@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
+ } else {
+ bh = sb_bread(inode->i_sb, pos);
+
+- if (!bh)
+- goto out;
++ if (!bh) {
++ err = -EIO;
++ goto out_unlock_inode;
++ }
+
+ symlink = bh->b_data;
+ }
+@@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
+ unlock_page(page);
+ return 0;
+
+-out:
++out_unlock_inode:
+ up_read(&iinfo->i_data_sem);
+ SetPageError(page);
++out_unmap:
+ kunmap(page);
+ unlock_page(page);
+ return err;
+diff --git a/include/linux/audit.h b/include/linux/audit.h
+index ec1464df4c60..419b7d7d7a7f 100644
+--- a/include/linux/audit.h
++++ b/include/linux/audit.h
+@@ -47,6 +47,7 @@ struct sk_buff;
+
+ struct audit_krule {
+ int vers_ops;
++ u32 pflags;
+ u32 flags;
+ u32 listnr;
+ u32 action;
+@@ -64,6 +65,9 @@ struct audit_krule {
+ u64 prio;
+ };
+
++/* Flag to indicate legacy AUDIT_LOGINUID unset usage */
++#define AUDIT_LOGINUID_LEGACY 0x1
++
+ struct audit_field {
+ u32 type;
+ u32 val;
+diff --git a/include/linux/cred.h b/include/linux/cred.h
+index 04421e825365..6c58dd7cb9ac 100644
+--- a/include/linux/cred.h
++++ b/include/linux/cred.h
+@@ -68,6 +68,7 @@ extern void groups_free(struct group_info *);
+ extern int set_current_groups(struct group_info *);
+ extern int set_groups(struct cred *, struct group_info *);
+ extern int groups_search(const struct group_info *, kgid_t);
++extern bool may_setgroups(void);
+
+ /* access the groups "array" with this macro */
+ #define GROUP_AT(gi, i) \
+diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
+index 4836ba3c1cd8..e92abf9e796f 100644
+--- a/include/linux/user_namespace.h
++++ b/include/linux/user_namespace.h
+@@ -17,6 +17,10 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */
+ } extent[UID_GID_MAP_MAX_EXTENTS];
+ };
+
++#define USERNS_SETGROUPS_ALLOWED 1UL
++
++#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
++
+ struct user_namespace {
+ struct uid_gid_map uid_map;
+ struct uid_gid_map gid_map;
+@@ -27,6 +31,7 @@ struct user_namespace {
+ kuid_t owner;
+ kgid_t group;
+ unsigned int proc_inum;
++ unsigned long flags;
+
+ /* Register of per-UID persistent keyrings for this namespace */
+ #ifdef CONFIG_PERSISTENT_KEYRINGS
+@@ -63,6 +68,9 @@ extern struct seq_operations proc_projid_seq_operations;
+ extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
+ extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
+ extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
++extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
++extern int proc_setgroups_show(struct seq_file *m, void *v);
++extern bool userns_may_setgroups(const struct user_namespace *ns);
+ #else
+
+ static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
+@@ -87,6 +95,10 @@ static inline void put_user_ns(struct user_namespace *ns)
+ {
+ }
+
++static inline bool userns_may_setgroups(const struct user_namespace *ns)
++{
++ return true;
++}
+ #endif
+
+ #endif /* _LINUX_USER_H */
+diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
+index 92062fd6cc8c..598c1dcf26dd 100644
+--- a/kernel/auditfilter.c
++++ b/kernel/auditfilter.c
+@@ -429,6 +429,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
+ if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
+ f->type = AUDIT_LOGINUID_SET;
+ f->val = 0;
++ entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
+ }
+
+ err = audit_field_valid(entry, f);
+@@ -604,6 +605,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
+ data->buflen += data->values[i] =
+ audit_pack_string(&bufp, krule->filterkey);
+ break;
++ case AUDIT_LOGINUID_SET:
++ if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
++ data->fields[i] = AUDIT_LOGINUID;
++ data->values[i] = AUDIT_UID_UNSET;
++ break;
++ }
++ /* fallthrough if set */
+ default:
+ data->values[i] = f->val;
+ }
+@@ -620,6 +628,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
+ int i;
+
+ if (a->flags != b->flags ||
++ a->pflags != b->pflags ||
+ a->listnr != b->listnr ||
+ a->action != b->action ||
+ a->field_count != b->field_count)
+@@ -738,6 +747,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old)
+ new = &entry->rule;
+ new->vers_ops = old->vers_ops;
+ new->flags = old->flags;
++ new->pflags = old->pflags;
+ new->listnr = old->listnr;
+ new->action = old->action;
+ for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
+diff --git a/kernel/groups.c b/kernel/groups.c
+index 90cf1c38c8ea..67b4ba30475f 100644
+--- a/kernel/groups.c
++++ b/kernel/groups.c
+@@ -6,6 +6,7 @@
+ #include <linux/slab.h>
+ #include <linux/security.h>
+ #include <linux/syscalls.h>
++#include <linux/user_namespace.h>
+ #include <asm/uaccess.h>
+
+ /* init to 2 - one for init_task, one to ensure it is never freed */
+@@ -223,6 +224,14 @@ out:
+ return i;
+ }
+
++bool may_setgroups(void)
++{
++ struct user_namespace *user_ns = current_user_ns();
++
++ return ns_capable(user_ns, CAP_SETGID) &&
++ userns_may_setgroups(user_ns);
++}
++
+ /*
+ * SMP: Our groups are copy-on-write. We can set them safely
+ * without another task interfering.
+@@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
+ struct group_info *group_info;
+ int retval;
+
+- if (!ns_capable(current_user_ns(), CAP_SETGID))
++ if (!may_setgroups())
+ return -EPERM;
+ if ((unsigned)gidsetsize > NGROUPS_MAX)
+ return -EINVAL;
+diff --git a/kernel/pid.c b/kernel/pid.c
+index 9b9a26698144..82430c858d69 100644
+--- a/kernel/pid.c
++++ b/kernel/pid.c
+@@ -341,6 +341,8 @@ out:
+
+ out_unlock:
+ spin_unlock_irq(&pidmap_lock);
++ put_pid_ns(ns);
++
+ out_free:
+ while (++i <= ns->level)
+ free_pidmap(pid->numbers + i);
+diff --git a/kernel/uid16.c b/kernel/uid16.c
+index 602e5bbbceff..d58cc4d8f0d1 100644
+--- a/kernel/uid16.c
++++ b/kernel/uid16.c
+@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
+ struct group_info *group_info;
+ int retval;
+
+- if (!ns_capable(current_user_ns(), CAP_SETGID))
++ if (!may_setgroups())
+ return -EPERM;
+ if ((unsigned)gidsetsize > NGROUPS_MAX)
+ return -EINVAL;
+diff --git a/kernel/user.c b/kernel/user.c
+index c006131beb77..c2bbb50f5a90 100644
+--- a/kernel/user.c
++++ b/kernel/user.c
+@@ -51,6 +51,7 @@ struct user_namespace init_user_ns = {
+ .owner = GLOBAL_ROOT_UID,
+ .group = GLOBAL_ROOT_GID,
+ .proc_inum = PROC_USER_INIT_INO,
++ .flags = USERNS_INIT_FLAGS,
+ #ifdef CONFIG_PERSISTENT_KEYRINGS
+ .persistent_keyring_register_sem =
+ __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
+diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
+index 80a57afd8647..153971e4798a 100644
+--- a/kernel/user_namespace.c
++++ b/kernel/user_namespace.c
+@@ -24,6 +24,7 @@
+ #include <linux/fs_struct.h>
+
+ static struct kmem_cache *user_ns_cachep __read_mostly;
++static DEFINE_MUTEX(userns_state_mutex);
+
+ static bool new_idmap_permitted(const struct file *file,
+ struct user_namespace *ns, int cap_setid,
+@@ -99,6 +100,11 @@ int create_user_ns(struct cred *new)
+ ns->owner = owner;
+ ns->group = group;
+
++ /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
++ mutex_lock(&userns_state_mutex);
++ ns->flags = parent_ns->flags;
++ mutex_unlock(&userns_state_mutex);
++
+ set_cred_user_ns(new, ns);
+
+ #ifdef CONFIG_PERSISTENT_KEYRINGS
+@@ -581,9 +587,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent
+ return false;
+ }
+
+-
+-static DEFINE_MUTEX(id_map_mutex);
+-
+ static ssize_t map_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos,
+ int cap_setid,
+@@ -600,7 +603,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
+ ssize_t ret = -EINVAL;
+
+ /*
+- * The id_map_mutex serializes all writes to any given map.
++ * The userns_state_mutex serializes all writes to any given map.
+ *
+ * Any map is only ever written once.
+ *
+@@ -618,7 +621,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
+ * order and smp_rmb() is guaranteed that we don't have crazy
+ * architectures returning stale data.
+ */
+- mutex_lock(&id_map_mutex);
++ mutex_lock(&userns_state_mutex);
+
+ ret = -EPERM;
+ /* Only allow one successful write to the map */
+@@ -745,7 +748,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
+ *ppos = count;
+ ret = count;
+ out:
+- mutex_unlock(&id_map_mutex);
++ mutex_unlock(&userns_state_mutex);
+ if (page)
+ free_page(page);
+ return ret;
+@@ -804,17 +807,21 @@ static bool new_idmap_permitted(const struct file *file,
+ struct user_namespace *ns, int cap_setid,
+ struct uid_gid_map *new_map)
+ {
+- /* Allow mapping to your own filesystem ids */
+- if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
++ const struct cred *cred = file->f_cred;
++ /* Don't allow mappings that would allow anything that wouldn't
++ * be allowed without the establishment of unprivileged mappings.
++ */
++ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
++ uid_eq(ns->owner, cred->euid)) {
+ u32 id = new_map->extent[0].lower_first;
+ if (cap_setid == CAP_SETUID) {
+ kuid_t uid = make_kuid(ns->parent, id);
+- if (uid_eq(uid, file->f_cred->fsuid))
++ if (uid_eq(uid, cred->euid))
+ return true;
+- }
+- else if (cap_setid == CAP_SETGID) {
++ } else if (cap_setid == CAP_SETGID) {
+ kgid_t gid = make_kgid(ns->parent, id);
+- if (gid_eq(gid, file->f_cred->fsgid))
++ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
++ gid_eq(gid, cred->egid))
+ return true;
+ }
+ }
+@@ -834,6 +841,100 @@ static bool new_idmap_permitted(const struct file *file,
+ return false;
+ }
+
++int proc_setgroups_show(struct seq_file *seq, void *v)
++{
++ struct user_namespace *ns = seq->private;
++ unsigned long userns_flags = ACCESS_ONCE(ns->flags);
++
++ seq_printf(seq, "%s\n",
++ (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
++ "allow" : "deny");
++ return 0;
++}
++
++ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
++ size_t count, loff_t *ppos)
++{
++ struct seq_file *seq = file->private_data;
++ struct user_namespace *ns = seq->private;
++ char kbuf[8], *pos;
++ bool setgroups_allowed;
++ ssize_t ret;
++
++ /* Only allow a very narrow range of strings to be written */
++ ret = -EINVAL;
++ if ((*ppos != 0) || (count >= sizeof(kbuf)))
++ goto out;
++
++ /* What was written? */
++ ret = -EFAULT;
++ if (copy_from_user(kbuf, buf, count))
++ goto out;
++ kbuf[count] = '\0';
++ pos = kbuf;
++
++ /* What is being requested? */
++ ret = -EINVAL;
++ if (strncmp(pos, "allow", 5) == 0) {
++ pos += 5;
++ setgroups_allowed = true;
++ }
++ else if (strncmp(pos, "deny", 4) == 0) {
++ pos += 4;
++ setgroups_allowed = false;
++ }
++ else
++ goto out;
++
++ /* Verify there is not trailing junk on the line */
++ pos = skip_spaces(pos);
++ if (*pos != '\0')
++ goto out;
++
++ ret = -EPERM;
++ mutex_lock(&userns_state_mutex);
++ if (setgroups_allowed) {
++ /* Enabling setgroups after setgroups has been disabled
++ * is not allowed.
++ */
++ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
++ goto out_unlock;
++ } else {
++ /* Permanently disabling setgroups after setgroups has
++ * been enabled by writing the gid_map is not allowed.
++ */
++ if (ns->gid_map.nr_extents != 0)
++ goto out_unlock;
++ ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
++ }
++ mutex_unlock(&userns_state_mutex);
++
++ /* Report a successful write */
++ *ppos = count;
++ ret = count;
++out:
++ return ret;
++out_unlock:
++ mutex_unlock(&userns_state_mutex);
++ goto out;
++}
++
++bool userns_may_setgroups(const struct user_namespace *ns)
++{
++ bool allowed;
++
++ mutex_lock(&userns_state_mutex);
++ /* It is not safe to use setgroups until a gid mapping in
++ * the user namespace has been established.
++ */
++ allowed = ns->gid_map.nr_extents != 0;
++ /* Is setgroups allowed? */
++ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
++ mutex_unlock(&userns_state_mutex);
++
++ return allowed;
++}
++
+ static void *userns_get(struct task_struct *task)
+ {
+ struct user_namespace *user_ns;
+diff --git a/net/mac80211/key.c b/net/mac80211/key.c
+index 6ff65a1ebaa9..d78b37a5d951 100644
+--- a/net/mac80211/key.c
++++ b/net/mac80211/key.c
+@@ -652,7 +652,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
+ int i;
+
+ mutex_lock(&local->key_mtx);
+- for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
++ for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
+ key = key_mtx_dereference(local, sta->gtk[i]);
+ if (!key)
+ continue;
+diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
+index 095c16037bc5..1e4dc4ed5e0d 100644
+--- a/net/mac80211/rx.c
++++ b/net/mac80211/rx.c
+@@ -1679,14 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
+ sc = le16_to_cpu(hdr->seq_ctrl);
+ frag = sc & IEEE80211_SCTL_FRAG;
+
+- if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+- goto out;
+-
+ if (is_multicast_ether_addr(hdr->addr1)) {
+ rx->local->dot11MulticastReceivedFrameCount++;
+- goto out;
++ goto out_no_led;
+ }
+
++ if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
++ goto out;
++
+ I802_DEBUG_INC(rx->local->rx_handlers_fragments);
+
+ if (skb_linearize(rx->skb))
+@@ -1777,9 +1777,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
+ status->rx_flags |= IEEE80211_RX_FRAGMENTED;
+
+ out:
++ ieee80211_led_rx(rx->local);
++ out_no_led:
+ if (rx->sta)
+ rx->sta->rx_packets++;
+- ieee80211_led_rx(rx->local);
+ return RX_CONTINUE;
+ }
+
+diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
+index 9e1e005c7596..c4c8df4b214d 100644
+--- a/security/keys/encrypted-keys/encrypted.c
++++ b/security/keys/encrypted-keys/encrypted.c
+@@ -1018,10 +1018,13 @@ static int __init init_encrypted(void)
+ ret = encrypted_shash_alloc();
+ if (ret < 0)
+ return ret;
++ ret = aes_get_sizes();
++ if (ret < 0)
++ goto out;
+ ret = register_key_type(&key_type_encrypted);
+ if (ret < 0)
+ goto out;
+- return aes_get_sizes();
++ return 0;
+ out:
+ encrypted_shash_release();
+ return ret;
+diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
+index 1b3ff2fda4d0..517785052f1c 100644
+--- a/tools/testing/selftests/mount/unprivileged-remount-test.c
++++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
+@@ -6,6 +6,8 @@
+ #include <sys/types.h>
+ #include <sys/mount.h>
+ #include <sys/wait.h>
++#include <sys/vfs.h>
++#include <sys/statvfs.h>
+ #include <stdlib.h>
+ #include <unistd.h>
+ #include <fcntl.h>
+@@ -32,11 +34,14 @@
+ # define CLONE_NEWPID 0x20000000
+ #endif
+
++#ifndef MS_REC
++# define MS_REC 16384
++#endif
+ #ifndef MS_RELATIME
+-#define MS_RELATIME (1 << 21)
++# define MS_RELATIME (1 << 21)
+ #endif
+ #ifndef MS_STRICTATIME
+-#define MS_STRICTATIME (1 << 24)
++# define MS_STRICTATIME (1 << 24)
+ #endif
+
+ static void die(char *fmt, ...)
+@@ -48,17 +53,14 @@ static void die(char *fmt, ...)
+ exit(EXIT_FAILURE);
+ }
+
+-static void write_file(char *filename, char *fmt, ...)
++static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
+ {
+ char buf[4096];
+ int fd;
+ ssize_t written;
+ int buf_len;
+- va_list ap;
+
+- va_start(ap, fmt);
+ buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+- va_end(ap);
+ if (buf_len < 0) {
+ die("vsnprintf failed: %s\n",
+ strerror(errno));
+@@ -69,6 +71,8 @@ static void write_file(char *filename, char *fmt, ...)
+
+ fd = open(filename, O_WRONLY);
+ if (fd < 0) {
++ if ((errno == ENOENT) && enoent_ok)
++ return;
+ die("open of %s failed: %s\n",
+ filename, strerror(errno));
+ }
+@@ -87,6 +91,65 @@ static void write_file(char *filename, char *fmt, ...)
+ }
+ }
+
++static void maybe_write_file(char *filename, char *fmt, ...)
++{
++ va_list ap;
++
++ va_start(ap, fmt);
++ vmaybe_write_file(true, filename, fmt, ap);
++ va_end(ap);
++
++}
++
++static void write_file(char *filename, char *fmt, ...)
++{
++ va_list ap;
++
++ va_start(ap, fmt);
++ vmaybe_write_file(false, filename, fmt, ap);
++ va_end(ap);
++
++}
++
++static int read_mnt_flags(const char *path)
++{
++ int ret;
++ struct statvfs stat;
++ int mnt_flags;
++
++ ret = statvfs(path, &stat);
++ if (ret != 0) {
++ die("statvfs of %s failed: %s\n",
++ path, strerror(errno));
++ }
++ if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
++ ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
++ ST_SYNCHRONOUS | ST_MANDLOCK)) {
++ die("Unrecognized mount flags\n");
++ }
++ mnt_flags = 0;
++ if (stat.f_flag & ST_RDONLY)
++ mnt_flags |= MS_RDONLY;
++ if (stat.f_flag & ST_NOSUID)
++ mnt_flags |= MS_NOSUID;
++ if (stat.f_flag & ST_NODEV)
++ mnt_flags |= MS_NODEV;
++ if (stat.f_flag & ST_NOEXEC)
++ mnt_flags |= MS_NOEXEC;
++ if (stat.f_flag & ST_NOATIME)
++ mnt_flags |= MS_NOATIME;
++ if (stat.f_flag & ST_NODIRATIME)
++ mnt_flags |= MS_NODIRATIME;
++ if (stat.f_flag & ST_RELATIME)
++ mnt_flags |= MS_RELATIME;
++ if (stat.f_flag & ST_SYNCHRONOUS)
++ mnt_flags |= MS_SYNCHRONOUS;
++ if (stat.f_flag & ST_MANDLOCK)
++ mnt_flags |= ST_MANDLOCK;
++
++ return mnt_flags;
++}
++
+ static void create_and_enter_userns(void)
+ {
+ uid_t uid;
+@@ -100,13 +163,10 @@ static void create_and_enter_userns(void)
+ strerror(errno));
+ }
+
++ maybe_write_file("/proc/self/setgroups", "deny");
+ write_file("/proc/self/uid_map", "0 %d 1", uid);
+ write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+- if (setgroups(0, NULL) != 0) {
+- die("setgroups failed: %s\n",
+- strerror(errno));
+- }
+ if (setgid(0) != 0) {
+ die ("setgid(0) failed %s\n",
+ strerror(errno));
+@@ -118,7 +178,8 @@ static void create_and_enter_userns(void)
+ }
+
+ static
+-bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
++bool test_unpriv_remount(const char *fstype, const char *mount_options,
++ int mount_flags, int remount_flags, int invalid_flags)
+ {
+ pid_t child;
+
+@@ -151,9 +212,11 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+ strerror(errno));
+ }
+
+- if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) {
+- die("mount of /tmp failed: %s\n",
+- strerror(errno));
++ if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
++ die("mount of %s with options '%s' on /tmp failed: %s\n",
++ fstype,
++ mount_options? mount_options : "",
++ strerror(errno));
+ }
+
+ create_and_enter_userns();
+@@ -181,62 +244,127 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+
+ static bool test_unpriv_remount_simple(int mount_flags)
+ {
+- return test_unpriv_remount(mount_flags, mount_flags, 0);
++ return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
+ }
+
+ static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+ {
+- return test_unpriv_remount(mount_flags, mount_flags, invalid_flags);
++ return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
++ invalid_flags);
++}
++
++static bool test_priv_mount_unpriv_remount(void)
++{
++ pid_t child;
++ int ret;
++ const char *orig_path = "/dev";
++ const char *dest_path = "/tmp";
++ int orig_mnt_flags, remount_mnt_flags;
++
++ child = fork();
++ if (child == -1) {
++ die("fork failed: %s\n",
++ strerror(errno));
++ }
++ if (child != 0) { /* parent */
++ pid_t pid;
++ int status;
++ pid = waitpid(child, &status, 0);
++ if (pid == -1) {
++ die("waitpid failed: %s\n",
++ strerror(errno));
++ }
++ if (pid != child) {
++ die("waited for %d got %d\n",
++ child, pid);
++ }
++ if (!WIFEXITED(status)) {
++ die("child did not terminate cleanly\n");
++ }
++ return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
++ }
++
++ orig_mnt_flags = read_mnt_flags(orig_path);
++
++ create_and_enter_userns();
++ ret = unshare(CLONE_NEWNS);
++ if (ret != 0) {
++ die("unshare(CLONE_NEWNS) failed: %s\n",
++ strerror(errno));
++ }
++
++ ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
++ if (ret != 0) {
++ die("recursive bind mount of %s onto %s failed: %s\n",
++ orig_path, dest_path, strerror(errno));
++ }
++
++ ret = mount(dest_path, dest_path, "none",
++ MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
++ if (ret != 0) {
++ /* system("cat /proc/self/mounts"); */
++ die("remount of /tmp failed: %s\n",
++ strerror(errno));
++ }
++
++ remount_mnt_flags = read_mnt_flags(dest_path);
++ if (orig_mnt_flags != remount_mnt_flags) {
++ die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
++ dest_path, orig_path);
++ }
++ exit(EXIT_SUCCESS);
+ }
+
+ int main(int argc, char **argv)
+ {
+- if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) {
++ if (!test_unpriv_remount_simple(MS_RDONLY)) {
+ die("MS_RDONLY malfunctions\n");
+ }
+- if (!test_unpriv_remount_simple(MS_NODEV)) {
++ if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
+ die("MS_NODEV malfunctions\n");
+ }
+- if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) {
++ if (!test_unpriv_remount_simple(MS_NOSUID)) {
+ die("MS_NOSUID malfunctions\n");
+ }
+- if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) {
++ if (!test_unpriv_remount_simple(MS_NOEXEC)) {
+ die("MS_NOEXEC malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV,
+- MS_NOATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_RELATIME,
++ MS_NOATIME))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV,
+- MS_NOATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_STRICTATIME,
++ MS_NOATIME))
+ {
+ die("MS_STRICTATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV,
+- MS_STRICTATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_NOATIME,
++ MS_STRICTATIME))
+ {
+- die("MS_RELATIME malfunctions\n");
++ die("MS_NOATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV,
+- MS_NOATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
++ MS_NOATIME))
+ {
+- die("MS_RELATIME malfunctions\n");
++ die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV,
+- MS_NOATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
++ MS_NOATIME))
+ {
+- die("MS_RELATIME malfunctions\n");
++ die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV,
+- MS_STRICTATIME|MS_NODEV))
++ if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
++ MS_STRICTATIME))
+ {
+- die("MS_RELATIME malfunctions\n");
++ die("MS_NOATIME|MS_DIRATIME malfunctions\n");
+ }
+- if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV,
+- MS_NOATIME|MS_NODEV))
++ if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
+ {
+ die("Default atime malfunctions\n");
+ }
++ if (!test_priv_mount_unpriv_remount()) {
++ die("Mount flags unexpectedly changed after remount\n");
++ }
+ return EXIT_SUCCESS;
+ }