--- /dev/null
+From 6a9af90a3bcde217a1c053e135f5f43e5d5fafbd Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Mon, 10 Jul 2017 15:52:40 -0700
+Subject: arm: move ELF_ET_DYN_BASE to 4MB
+
+From: Kees Cook <keescook@chromium.org>
+
+commit 6a9af90a3bcde217a1c053e135f5f43e5d5fafbd upstream.
+
+Now that explicitly executed loaders are loaded in the mmap region, we
+have more freedom to decide where we position PIE binaries in the
+address space to avoid possible collisions with mmap or stack regions.
+
+4MB is chosen here mainly to have parity with x86, where this is the
+traditional minimum load location, likely to avoid historically
+requiring a 4MB page table entry when only a portion of the first 4MB
+would be used (since the NULL address is avoided).
+
+For ARM the position could be 0x8000, the standard ET_EXEC load address,
+but that is needlessly close to the NULL address, and anyone running PIE
+on 32-bit ARM will have an MMU, so the tight mapping is not needed.
+
+Link: http://lkml.kernel.org/r/1498154792-49952-2-git-send-email-keescook@chromium.org
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Cc: Russell King <linux@armlinux.org.uk>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Will Deacon <will.deacon@arm.com>
+Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
+Cc: Paul Mackerras <paulus@samba.org>
+Cc: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
+Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
+Cc: James Hogan <james.hogan@imgtec.com>
+Cc: Pratyush Anand <panand@redhat.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: "H. Peter Anvin" <hpa@zytor.com>
+Cc: Alexander Viro <viro@zeniv.linux.org.uk>
+Cc: Andy Lutomirski <luto@amacapital.net>
+Cc: Daniel Micay <danielmicay@gmail.com>
+Cc: Dmitry Safonov <dsafonov@virtuozzo.com>
+Cc: Grzegorz Andrejczuk <grzegorz.andrejczuk@intel.com>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
+Cc: Qualys Security Advisory <qsa@qualys.com>
+Cc: Rik van Riel <riel@redhat.com>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/arm/include/asm/elf.h | 8 ++------
+ 1 file changed, 2 insertions(+), 6 deletions(-)
+
+--- a/arch/arm/include/asm/elf.h
++++ b/arch/arm/include/asm/elf.h
+@@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t
+ #define CORE_DUMP_USE_REGSET
+ #define ELF_EXEC_PAGESIZE 4096
+
+-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+- use of this is to invoke "./ld.so someprog" to test out a new version of
+- the loader. We need to make sure that it is out of the way of the program
+- that it will "exec", and that there is sufficient room for the brk. */
+-
+-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
++/* This is the base location for PIE (ET_DYN with INTERP) loads. */
++#define ELF_ET_DYN_BASE 0x400000UL
+
+ /* When the program starts, a1 contains a pointer to a function to be
+ registered with atexit, as per the SVR4 ABI. A value of 0 means we
--- /dev/null
+From 88cda00733f0731711c76e535d4972c296ac512e Mon Sep 17 00:00:00 2001
+From: Marc Zyngier <marc.zyngier@arm.com>
+Date: Wed, 21 Jun 2017 22:45:08 +0100
+Subject: ARM64: dts: marvell: armada37xx: Fix timer interrupt specifiers
+
+From: Marc Zyngier <marc.zyngier@arm.com>
+
+commit 88cda00733f0731711c76e535d4972c296ac512e upstream.
+
+Contrary to popular belief, PPIs connected to a GICv3 to not have
+an affinity field similar to that of GICv2. That is consistent
+with the fact that GICv3 is designed to accomodate thousands of
+CPUs, and fitting them as a bitmap in a byte is... difficult.
+
+Fixes: adbc3695d9e4 ("arm64: dts: add the Marvell Armada 3700 family and a development board")
+Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/arm64/boot/dts/marvell/armada-37xx.dtsi | 12 ++++--------
+ 1 file changed, 4 insertions(+), 8 deletions(-)
+
+--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
++++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+@@ -75,14 +75,10 @@
+
+ timer {
+ compatible = "arm,armv8-timer";
+- interrupts = <GIC_PPI 13
+- (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
+- <GIC_PPI 14
+- (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
+- <GIC_PPI 11
+- (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>,
+- <GIC_PPI 10
+- (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
++ interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>,
++ <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>,
++ <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>,
++ <GIC_PPI 10 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ soc {
--- /dev/null
+From 02445990a96e60a67526510d8b00f7e3d14101c3 Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Mon, 10 Jul 2017 15:52:44 -0700
+Subject: arm64: move ELF_ET_DYN_BASE to 4GB / 4MB
+
+From: Kees Cook <keescook@chromium.org>
+
+commit 02445990a96e60a67526510d8b00f7e3d14101c3 upstream.
+
+Now that explicitly executed loaders are loaded in the mmap region, we
+have more freedom to decide where we position PIE binaries in the
+address space to avoid possible collisions with mmap or stack regions.
+
+For 64-bit, align to 4GB to allow runtimes to use the entire 32-bit
+address space for 32-bit pointers. On 32-bit use 4MB, to match ARM.
+This could be 0x8000, the standard ET_EXEC load address, but that is
+needlessly close to the NULL address, and anyone running arm compat PIE
+will have an MMU, so the tight mapping is not needed.
+
+Link: http://lkml.kernel.org/r/1498251600-132458-4-git-send-email-keescook@chromium.org
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Mark Rutland <mark.rutland@arm.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/arm64/include/asm/elf.h | 12 ++++++------
+ 1 file changed, 6 insertions(+), 6 deletions(-)
+
+--- a/arch/arm64/include/asm/elf.h
++++ b/arch/arm64/include/asm/elf.h
+@@ -113,12 +113,11 @@
+ #define ELF_EXEC_PAGESIZE PAGE_SIZE
+
+ /*
+- * This is the location that an ET_DYN program is loaded if exec'ed. Typical
+- * use of this is to invoke "./ld.so someprog" to test out a new version of
+- * the loader. We need to make sure that it is out of the way of the program
+- * that it will "exec", and that there is sufficient room for the brk.
++ * This is the base location for PIE (ET_DYN with INTERP) loads. On
++ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
++ * space open for things that want to use the area for 32-bit pointers.
+ */
+-#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3)
++#define ELF_ET_DYN_BASE 0x100000000UL
+
+ #ifndef __ASSEMBLY__
+
+@@ -169,7 +168,8 @@ extern int arch_setup_additional_pages(s
+
+ #ifdef CONFIG_COMPAT
+
+-#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3)
++/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
++#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL
+
+ /* AArch32 registers. */
+ #define COMPAT_ELF_NGREG 18
--- /dev/null
+From eab09532d40090698b05a07c1c87f39fdbc5fab5 Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Mon, 10 Jul 2017 15:52:37 -0700
+Subject: binfmt_elf: use ELF_ET_DYN_BASE only for PIE
+
+From: Kees Cook <keescook@chromium.org>
+
+commit eab09532d40090698b05a07c1c87f39fdbc5fab5 upstream.
+
+The ELF_ET_DYN_BASE position was originally intended to keep loaders
+away from ET_EXEC binaries. (For example, running "/lib/ld-linux.so.2
+/bin/cat" might cause the subsequent load of /bin/cat into where the
+loader had been loaded.)
+
+With the advent of PIE (ET_DYN binaries with an INTERP Program Header),
+ELF_ET_DYN_BASE continued to be used since the kernel was only looking
+at ET_DYN. However, since ELF_ET_DYN_BASE is traditionally set at the
+top 1/3rd of the TASK_SIZE, a substantial portion of the address space
+is unused.
+
+For 32-bit tasks when RLIMIT_STACK is set to RLIM_INFINITY, programs are
+loaded above the mmap region. This means they can be made to collide
+(CVE-2017-1000370) or nearly collide (CVE-2017-1000371) with
+pathological stack regions.
+
+Lowering ELF_ET_DYN_BASE solves both by moving programs below the mmap
+region in all cases, and will now additionally avoid programs falling
+back to the mmap region by enforcing MAP_FIXED for program loads (i.e.
+if it would have collided with the stack, now it will fail to load
+instead of falling back to the mmap region).
+
+To allow for a lower ELF_ET_DYN_BASE, loaders (ET_DYN without INTERP)
+are loaded into the mmap region, leaving space available for either an
+ET_EXEC binary with a fixed location or PIE being loaded into mmap by
+the loader. Only PIE programs are loaded offset from ELF_ET_DYN_BASE,
+which means architectures can now safely lower their values without risk
+of loaders colliding with their subsequently loaded programs.
+
+For 64-bit, ELF_ET_DYN_BASE is best set to 4GB to allow runtimes to use
+the entire 32-bit address space for 32-bit pointers.
+
+Thanks to PaX Team, Daniel Micay, and Rik van Riel for inspiration and
+suggestions on how to implement this solution.
+
+Fixes: d1fd836dcf00 ("mm: split ET_DYN ASLR from mmap ASLR")
+Link: http://lkml.kernel.org/r/20170621173201.GA114489@beast
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Acked-by: Rik van Riel <riel@redhat.com>
+Cc: Daniel Micay <danielmicay@gmail.com>
+Cc: Qualys Security Advisory <qsa@qualys.com>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Cc: Ingo Molnar <mingo@redhat.com>
+Cc: "H. Peter Anvin" <hpa@zytor.com>
+Cc: Alexander Viro <viro@zeniv.linux.org.uk>
+Cc: Dmitry Safonov <dsafonov@virtuozzo.com>
+Cc: Andy Lutomirski <luto@amacapital.net>
+Cc: Grzegorz Andrejczuk <grzegorz.andrejczuk@intel.com>
+Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
+Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
+Cc: James Hogan <james.hogan@imgtec.com>
+Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
+Cc: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Paul Mackerras <paulus@samba.org>
+Cc: Pratyush Anand <panand@redhat.com>
+Cc: Russell King <linux@armlinux.org.uk>
+Cc: Will Deacon <will.deacon@arm.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/include/asm/elf.h | 13 +++++----
+ fs/binfmt_elf.c | 59 ++++++++++++++++++++++++++++++++++++++-------
+ 2 files changed, 58 insertions(+), 14 deletions(-)
+
+--- a/arch/x86/include/asm/elf.h
++++ b/arch/x86/include/asm/elf.h
+@@ -245,12 +245,13 @@ extern int force_personality32;
+ #define CORE_DUMP_USE_REGSET
+ #define ELF_EXEC_PAGESIZE 4096
+
+-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+- use of this is to invoke "./ld.so someprog" to test out a new version of
+- the loader. We need to make sure that it is out of the way of the program
+- that it will "exec", and that there is sufficient room for the brk. */
+-
+-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
++/*
++ * This is the base location for PIE (ET_DYN with INTERP) loads. On
++ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
++ * space open for things that want to use the area for 32-bit pointers.
++ */
++#define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \
++ 0x100000000UL)
+
+ /* This yields a mask that user programs can use to figure out what
+ instruction set this CPU supports. This could be done in user space,
+--- a/fs/binfmt_elf.c
++++ b/fs/binfmt_elf.c
+@@ -911,17 +911,60 @@ static int load_elf_binary(struct linux_
+ elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
+
+ vaddr = elf_ppnt->p_vaddr;
++ /*
++ * If we are loading ET_EXEC or we have already performed
++ * the ET_DYN load_addr calculations, proceed normally.
++ */
+ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
+ elf_flags |= MAP_FIXED;
+ } else if (loc->elf_ex.e_type == ET_DYN) {
+- /* Try and get dynamic programs out of the way of the
+- * default mmap base, as well as whatever program they
+- * might try to exec. This is because the brk will
+- * follow the loader, and is not movable. */
+- load_bias = ELF_ET_DYN_BASE - vaddr;
+- if (current->flags & PF_RANDOMIZE)
+- load_bias += arch_mmap_rnd();
+- load_bias = ELF_PAGESTART(load_bias);
++ /*
++ * This logic is run once for the first LOAD Program
++ * Header for ET_DYN binaries to calculate the
++ * randomization (load_bias) for all the LOAD
++ * Program Headers, and to calculate the entire
++ * size of the ELF mapping (total_size). (Note that
++ * load_addr_set is set to true later once the
++ * initial mapping is performed.)
++ *
++ * There are effectively two types of ET_DYN
++ * binaries: programs (i.e. PIE: ET_DYN with INTERP)
++ * and loaders (ET_DYN without INTERP, since they
++ * _are_ the ELF interpreter). The loaders must
++ * be loaded away from programs since the program
++ * may otherwise collide with the loader (especially
++ * for ET_EXEC which does not have a randomized
++ * position). For example to handle invocations of
++ * "./ld.so someprog" to test out a new version of
++ * the loader, the subsequent program that the
++ * loader loads must avoid the loader itself, so
++ * they cannot share the same load range. Sufficient
++ * room for the brk must be allocated with the
++ * loader as well, since brk must be available with
++ * the loader.
++ *
++ * Therefore, programs are loaded offset from
++ * ELF_ET_DYN_BASE and loaders are loaded into the
++ * independently randomized mmap region (0 load_bias
++ * without MAP_FIXED).
++ */
++ if (elf_interpreter) {
++ load_bias = ELF_ET_DYN_BASE;
++ if (current->flags & PF_RANDOMIZE)
++ load_bias += arch_mmap_rnd();
++ elf_flags |= MAP_FIXED;
++ } else
++ load_bias = 0;
++
++ /*
++ * Since load_bias is used for all subsequent loading
++ * calculations, we must lower it by the first vaddr
++ * so that the remaining calculations based on the
++ * ELF vaddrs will be correctly offset. The result
++ * is then page aligned.
++ */
++ load_bias = ELF_PAGESTART(load_bias - vaddr);
++
+ total_size = total_mapping_size(elf_phdata,
+ loc->elf_ex.e_phnum);
+ if (!total_size) {
--- /dev/null
+From 0a27844ce86d039d74221dd56cd8c0349b146b63 Mon Sep 17 00:00:00 2001
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Date: Fri, 7 Jul 2017 01:43:40 +0300
+Subject: cfg80211: Check if NAN service ID is of expected size
+
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+
+commit 0a27844ce86d039d74221dd56cd8c0349b146b63 upstream.
+
+nla policy checks for only maximum length of the attribute data when the
+attribute type is NLA_BINARY. If userspace sends less data than
+specified, cfg80211 may access illegal memory. When type is NLA_UNSPEC,
+nla policy check ensures that userspace sends minimum specified length
+number of bytes.
+
+Remove type assignment to NLA_BINARY from nla_policy of
+NL80211_NAN_FUNC_SERVICE_ID to make these NLA_UNSPEC and to make sure
+minimum NL80211_NAN_FUNC_SERVICE_ID_LEN bytes are received from
+userspace with NL80211_NAN_FUNC_SERVICE_ID.
+
+Fixes: a442b761b24 ("cfg80211: add add_nan_func / del_nan_func")
+Signed-off-by: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ net/wireless/nl80211.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -512,7 +512,7 @@ nl80211_bss_select_policy[NL80211_BSS_SE
+ static const struct nla_policy
+ nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = {
+ [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 },
+- [NL80211_NAN_FUNC_SERVICE_ID] = { .type = NLA_BINARY,
++ [NL80211_NAN_FUNC_SERVICE_ID] = {
+ .len = NL80211_NAN_FUNC_SERVICE_ID_LEN },
+ [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 },
+ [NL80211_NAN_FUNC_PUBLISH_BCAST] = { .type = NLA_FLAG },
--- /dev/null
+From 9361df14d1cbf966409d5d6f48bb334384fbe138 Mon Sep 17 00:00:00 2001
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Date: Fri, 7 Jul 2017 01:43:39 +0300
+Subject: cfg80211: Check if PMKID attribute is of expected size
+
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+
+commit 9361df14d1cbf966409d5d6f48bb334384fbe138 upstream.
+
+nla policy checks for only maximum length of the attribute data
+when the attribute type is NLA_BINARY. If userspace sends less
+data than specified, the wireless drivers may access illegal
+memory. When type is NLA_UNSPEC, nla policy check ensures that
+userspace sends minimum specified length number of bytes.
+
+Remove type assignment to NLA_BINARY from nla_policy of
+NL80211_ATTR_PMKID to make this NLA_UNSPEC and to make sure minimum
+WLAN_PMKID_LEN bytes are received from userspace with
+NL80211_ATTR_PMKID.
+
+Fixes: 67fbb16be69d ("nl80211: PMKSA caching support")
+Signed-off-by: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ net/wireless/nl80211.c | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -305,8 +305,7 @@ static const struct nla_policy nl80211_p
+ [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
+ [NL80211_ATTR_PID] = { .type = NLA_U32 },
+ [NL80211_ATTR_4ADDR] = { .type = NLA_U8 },
+- [NL80211_ATTR_PMKID] = { .type = NLA_BINARY,
+- .len = WLAN_PMKID_LEN },
++ [NL80211_ATTR_PMKID] = { .len = WLAN_PMKID_LEN },
+ [NL80211_ATTR_DURATION] = { .type = NLA_U32 },
+ [NL80211_ATTR_COOKIE] = { .type = NLA_U64 },
+ [NL80211_ATTR_TX_RATES] = { .type = NLA_NESTED },
--- /dev/null
+From 8feb69c7bd89513be80eb19198d48f154b254021 Mon Sep 17 00:00:00 2001
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Date: Fri, 7 Jul 2017 01:43:41 +0300
+Subject: cfg80211: Define nla_policy for NL80211_ATTR_LOCAL_MESH_POWER_MODE
+
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+
+commit 8feb69c7bd89513be80eb19198d48f154b254021 upstream.
+
+Buffer overread may happen as nl80211_set_station() reads 4 bytes
+from the attribute NL80211_ATTR_LOCAL_MESH_POWER_MODE without
+validating the size of data received when userspace sends less
+than 4 bytes of data with NL80211_ATTR_LOCAL_MESH_POWER_MODE.
+Define nla_policy for NL80211_ATTR_LOCAL_MESH_POWER_MODE to avoid
+the buffer overread.
+
+Fixes: 3b1c5a5307f ("{cfg,nl}80211: mesh power mode primitives and userspace access")
+Signed-off-by: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ net/wireless/nl80211.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -362,6 +362,7 @@ static const struct nla_policy nl80211_p
+ [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
+ [NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 },
+ [NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 },
++ [NL80211_ATTR_LOCAL_MESH_POWER_MODE] = {. type = NLA_U32 },
+ [NL80211_ATTR_ACL_POLICY] = {. type = NLA_U32 },
+ [NL80211_ATTR_MAC_ADDRS] = { .type = NLA_NESTED },
+ [NL80211_ATTR_STA_CAPABILITY] = { .type = NLA_U16 },
--- /dev/null
+From d7f13f7450369281a5d0ea463cc69890a15923ae Mon Sep 17 00:00:00 2001
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Date: Fri, 7 Jul 2017 01:43:42 +0300
+Subject: cfg80211: Validate frequencies nested in NL80211_ATTR_SCAN_FREQUENCIES
+
+From: Srinivas Dasari <dasaris@qti.qualcomm.com>
+
+commit d7f13f7450369281a5d0ea463cc69890a15923ae upstream.
+
+validate_scan_freqs() retrieves frequencies from attributes
+nested in the attribute NL80211_ATTR_SCAN_FREQUENCIES with
+nla_get_u32(), which reads 4 bytes from each attribute
+without validating the size of data received. Attributes
+nested in NL80211_ATTR_SCAN_FREQUENCIES don't have an nla policy.
+
+Validate size of each attribute before parsing to avoid potential buffer
+overread.
+
+Fixes: 2a519311926 ("cfg80211/nl80211: scanning (and mac80211 update to use it)")
+Signed-off-by: Srinivas Dasari <dasaris@qti.qualcomm.com>
+Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ net/wireless/nl80211.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -6327,6 +6327,10 @@ static int validate_scan_freqs(struct nl
+ struct nlattr *attr1, *attr2;
+ int n_channels = 0, tmp1, tmp2;
+
++ nla_for_each_nested(attr1, freqs, tmp1)
++ if (nla_len(attr1) != sizeof(u32))
++ return 0;
++
+ nla_for_each_nested(attr1, freqs, tmp1) {
+ n_channels++;
+ /*
--- /dev/null
+From 8d81ae05d0176da1c54aeaed697fa34be5c5575e Mon Sep 17 00:00:00 2001
+From: Cyril Bur <cyrilbur@gmail.com>
+Date: Mon, 10 Jul 2017 15:52:21 -0700
+Subject: checkpatch: silence perl 5.26.0 unescaped left brace warnings
+
+From: Cyril Bur <cyrilbur@gmail.com>
+
+commit 8d81ae05d0176da1c54aeaed697fa34be5c5575e upstream.
+
+As of perl 5, version 26, subversion 0 (v5.26.0) some new warnings have
+occurred when running checkpatch.
+
+Unescaped left brace in regex is deprecated here (and will be fatal in
+Perl 5.30), passed through in regex; marked by <-- HERE in m/^(.\s*){
+<-- HERE \s*/ at scripts/checkpatch.pl line 3544.
+
+Unescaped left brace in regex is deprecated here (and will be fatal in
+Perl 5.30), passed through in regex; marked by <-- HERE in m/^(.\s*){
+<-- HERE \s*/ at scripts/checkpatch.pl line 3885.
+
+Unescaped left brace in regex is deprecated here (and will be fatal in
+Perl 5.30), passed through in regex; marked by <-- HERE in
+m/^(\+.*(?:do|\))){ <-- HERE / at scripts/checkpatch.pl line 4374.
+
+It seems perfectly reasonable to do as the warning suggests and simply
+escape the left brace in these three locations.
+
+Link: http://lkml.kernel.org/r/20170607060135.17384-1-cyrilbur@gmail.com
+Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
+Acked-by: Joe Perches <joe@perches.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ scripts/checkpatch.pl | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+--- a/scripts/checkpatch.pl
++++ b/scripts/checkpatch.pl
+@@ -3499,7 +3499,7 @@ sub process {
+ $fixedline =~ s/\s*=\s*$/ = {/;
+ fix_insert_line($fixlinenr, $fixedline);
+ $fixedline = $line;
+- $fixedline =~ s/^(.\s*){\s*/$1/;
++ $fixedline =~ s/^(.\s*)\{\s*/$1/;
+ fix_insert_line($fixlinenr, $fixedline);
+ }
+ }
+@@ -3840,7 +3840,7 @@ sub process {
+ my $fixedline = rtrim($prevrawline) . " {";
+ fix_insert_line($fixlinenr, $fixedline);
+ $fixedline = $rawline;
+- $fixedline =~ s/^(.\s*){\s*/$1\t/;
++ $fixedline =~ s/^(.\s*)\{\s*/$1\t/;
+ if ($fixedline !~ /^\+\s*$/) {
+ fix_insert_line($fixlinenr, $fixedline);
+ }
+@@ -4329,7 +4329,7 @@ sub process {
+ if (ERROR("SPACING",
+ "space required before the open brace '{'\n" . $herecurr) &&
+ $fix) {
+- $fixed[$fixlinenr] =~ s/^(\+.*(?:do|\))){/$1 {/;
++ $fixed[$fixlinenr] =~ s/^(\+.*(?:do|\)))\{/$1 {/;
+ }
+ }
+
--- /dev/null
+From da029c11e6b12f321f36dac8771e833b65cec962 Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Fri, 7 Jul 2017 11:57:29 -0700
+Subject: exec: Limit arg stack to at most 75% of _STK_LIM
+
+From: Kees Cook <keescook@chromium.org>
+
+commit da029c11e6b12f321f36dac8771e833b65cec962 upstream.
+
+To avoid pathological stack usage or the need to special-case setuid
+execs, just limit all arg stack usage to at most 75% of _STK_LIM (6MB).
+
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/exec.c | 11 ++++++-----
+ 1 file changed, 6 insertions(+), 5 deletions(-)
+
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -215,8 +215,7 @@ static struct page *get_arg_page(struct
+
+ if (write) {
+ unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
+- unsigned long ptr_size;
+- struct rlimit *rlim;
++ unsigned long ptr_size, limit;
+
+ /*
+ * Since the stack will hold pointers to the strings, we
+@@ -245,14 +244,16 @@ static struct page *get_arg_page(struct
+ return page;
+
+ /*
+- * Limit to 1/4-th the stack size for the argv+env strings.
++ * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
++ * (whichever is smaller) for the argv+env strings.
+ * This ensures that:
+ * - the remaining binfmt code will not run out of stack space,
+ * - the program will have a reasonable amount of stack left
+ * to work from.
+ */
+- rlim = current->signal->rlim;
+- if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
++ limit = _STK_LIM / 4 * 3;
++ limit = min(limit, rlimit(RLIMIT_STACK) / 4);
++ if (size > limit)
+ goto fail;
+ }
+
--- /dev/null
+From b17c070fb624cf10162cf92ea5e1ec25cd8ac176 Mon Sep 17 00:00:00 2001
+From: Sahitya Tummala <stummala@codeaurora.org>
+Date: Mon, 10 Jul 2017 15:50:00 -0700
+Subject: fs/dcache.c: fix spin lockup issue on nlru->lock
+
+From: Sahitya Tummala <stummala@codeaurora.org>
+
+commit b17c070fb624cf10162cf92ea5e1ec25cd8ac176 upstream.
+
+__list_lru_walk_one() acquires nlru spin lock (nlru->lock) for longer
+duration if there are more number of items in the lru list. As per the
+current code, it can hold the spin lock for upto maximum UINT_MAX
+entries at a time. So if there are more number of items in the lru
+list, then "BUG: spinlock lockup suspected" is observed in the below
+path:
+
+ spin_bug+0x90
+ do_raw_spin_lock+0xfc
+ _raw_spin_lock+0x28
+ list_lru_add+0x28
+ dput+0x1c8
+ path_put+0x20
+ terminate_walk+0x3c
+ path_lookupat+0x100
+ filename_lookup+0x6c
+ user_path_at_empty+0x54
+ SyS_faccessat+0xd0
+ el0_svc_naked+0x24
+
+This nlru->lock is acquired by another CPU in this path -
+
+ d_lru_shrink_move+0x34
+ dentry_lru_isolate_shrink+0x48
+ __list_lru_walk_one.isra.10+0x94
+ list_lru_walk_node+0x40
+ shrink_dcache_sb+0x60
+ do_remount_sb+0xbc
+ do_emergency_remount+0xb0
+ process_one_work+0x228
+ worker_thread+0x2e0
+ kthread+0xf4
+ ret_from_fork+0x10
+
+Fix this lockup by reducing the number of entries to be shrinked from
+the lru list to 1024 at once. Also, add cond_resched() before
+processing the lru list again.
+
+Link: http://marc.info/?t=149722864900001&r=1&w=2
+Link: http://lkml.kernel.org/r/1498707575-2472-1-git-send-email-stummala@codeaurora.org
+Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
+Suggested-by: Jan Kara <jack@suse.cz>
+Suggested-by: Vladimir Davydov <vdavydov.dev@gmail.com>
+Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
+Cc: Alexander Polakov <apolyakov@beget.ru>
+Cc: Al Viro <viro@zeniv.linux.org.uk>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/dcache.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1133,11 +1133,12 @@ void shrink_dcache_sb(struct super_block
+ LIST_HEAD(dispose);
+
+ freed = list_lru_walk(&sb->s_dentry_lru,
+- dentry_lru_isolate_shrink, &dispose, UINT_MAX);
++ dentry_lru_isolate_shrink, &dispose, 1024);
+
+ this_cpu_sub(nr_dentry_unused, freed);
+ shrink_dentry_list(&dispose);
+- } while (freed > 0);
++ cond_resched();
++ } while (list_lru_count(&sb->s_dentry_lru) > 0);
+ }
+ EXPORT_SYMBOL(shrink_dcache_sb);
+
--- /dev/null
+From 866d7c1b0a3c70387646c4e455e727a58c5d465a Mon Sep 17 00:00:00 2001
+From: Suzuki K Poulose <suzuki.poulose@arm.com>
+Date: Fri, 30 Jun 2017 10:58:28 +0100
+Subject: irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity
+
+From: Suzuki K Poulose <suzuki.poulose@arm.com>
+
+commit 866d7c1b0a3c70387646c4e455e727a58c5d465a upstream.
+
+The GICv3 driver doesn't check if the target CPU for gic_set_affinity
+is valid before going ahead and making the changes. This triggers the
+following splat with KASAN:
+
+[ 141.189434] BUG: KASAN: global-out-of-bounds in gic_set_affinity+0x8c/0x140
+[ 141.189704] Read of size 8 at addr ffff200009741d20 by task swapper/1/0
+[ 141.189958]
+[ 141.190158] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.12.0-rc7
+[ 141.190458] Hardware name: Foundation-v8A (DT)
+[ 141.190658] Call trace:
+[ 141.190908] [<ffff200008089d70>] dump_backtrace+0x0/0x328
+[ 141.191224] [<ffff20000808a1b4>] show_stack+0x14/0x20
+[ 141.191507] [<ffff200008504c3c>] dump_stack+0xa4/0xc8
+[ 141.191858] [<ffff20000826c19c>] print_address_description+0x13c/0x250
+[ 141.192219] [<ffff20000826c5c8>] kasan_report+0x210/0x300
+[ 141.192547] [<ffff20000826ad54>] __asan_load8+0x84/0x98
+[ 141.192874] [<ffff20000854eeec>] gic_set_affinity+0x8c/0x140
+[ 141.193158] [<ffff200008148b14>] irq_do_set_affinity+0x54/0xb8
+[ 141.193473] [<ffff200008148d2c>] irq_set_affinity_locked+0x64/0xf0
+[ 141.193828] [<ffff200008148e00>] __irq_set_affinity+0x48/0x78
+[ 141.194158] [<ffff200008bc48a4>] arm_perf_starting_cpu+0x104/0x150
+[ 141.194513] [<ffff2000080d73bc>] cpuhp_invoke_callback+0x17c/0x1f8
+[ 141.194783] [<ffff2000080d94ec>] notify_cpu_starting+0x8c/0xb8
+[ 141.195130] [<ffff2000080911ec>] secondary_start_kernel+0x15c/0x200
+[ 141.195390] [<0000000080db81b4>] 0x80db81b4
+[ 141.195603]
+[ 141.195685] The buggy address belongs to the variable:
+[ 141.196012] __cpu_logical_map+0x200/0x220
+[ 141.196176]
+[ 141.196315] Memory state around the buggy address:
+[ 141.196586] ffff200009741c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 141.196913] ffff200009741c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 141.197158] >ffff200009741d00: 00 00 00 00 fa fa fa fa 00 00 00 00 00 00 00 00
+[ 141.197487] ^
+[ 141.197758] ffff200009741d80: 00 00 00 00 00 00 00 00 fa fa fa fa 00 00 00 00
+[ 141.198060] ffff200009741e00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 141.198358] ==================================================================
+[ 141.198609] Disabling lock debugging due to kernel taint
+[ 141.198961] CPU1: Booted secondary processor [410fd051]
+
+This patch adds the check to make sure the cpu is valid.
+
+Fixes: commit 021f653791ad17e03f98 ("irqchip: gic-v3: Initial support for GICv3")
+Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
+Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/irqchip/irq-gic-v3.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+--- a/drivers/irqchip/irq-gic-v3.c
++++ b/drivers/irqchip/irq-gic-v3.c
+@@ -646,6 +646,9 @@ static int gic_set_affinity(struct irq_d
+ int enabled;
+ u64 val;
+
++ if (cpu >= nr_cpu_ids)
++ return -EINVAL;
++
+ if (gic_irq_in_rdist(d))
+ return -EINVAL;
+
--- /dev/null
+From c0d80ddab89916273cb97114889d3f337bc370ae Mon Sep 17 00:00:00 2001
+From: Marcin Nowakowski <marcin.nowakowski@imgtec.com>
+Date: Thu, 6 Jul 2017 15:35:31 -0700
+Subject: kernel/extable.c: mark core_kernel_text notrace
+
+From: Marcin Nowakowski <marcin.nowakowski@imgtec.com>
+
+commit c0d80ddab89916273cb97114889d3f337bc370ae upstream.
+
+core_kernel_text is used by MIPS in its function graph trace processing,
+so having this method traced leads to an infinite set of recursive calls
+such as:
+
+ Call Trace:
+ ftrace_return_to_handler+0x50/0x128
+ core_kernel_text+0x10/0x1b8
+ prepare_ftrace_return+0x6c/0x114
+ ftrace_graph_caller+0x20/0x44
+ return_to_handler+0x10/0x30
+ return_to_handler+0x0/0x30
+ return_to_handler+0x0/0x30
+ ftrace_ops_no_ops+0x114/0x1bc
+ core_kernel_text+0x10/0x1b8
+ core_kernel_text+0x10/0x1b8
+ core_kernel_text+0x10/0x1b8
+ ftrace_ops_no_ops+0x114/0x1bc
+ core_kernel_text+0x10/0x1b8
+ prepare_ftrace_return+0x6c/0x114
+ ftrace_graph_caller+0x20/0x44
+ (...)
+
+Mark the function notrace to avoid it being traced.
+
+Link: http://lkml.kernel.org/r/1498028607-6765-1-git-send-email-marcin.nowakowski@imgtec.com
+Signed-off-by: Marcin Nowakowski <marcin.nowakowski@imgtec.com>
+Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Thomas Meyer <thomas@m3y3r.de>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: Steven Rostedt <rostedt@goodmis.org>
+Cc: Daniel Borkmann <daniel@iogearbox.net>
+Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/extable.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/kernel/extable.c
++++ b/kernel/extable.c
+@@ -66,7 +66,7 @@ static inline int init_kernel_text(unsig
+ return 0;
+ }
+
+-int core_kernel_text(unsigned long addr)
++int notrace core_kernel_text(unsigned long addr)
+ {
+ if (addr >= (unsigned long)_stext &&
+ addr < (unsigned long)_etext)
--- /dev/null
+From 37511fb5c91db93d8bd6e3f52f86e5a7ff7cfcdf Mon Sep 17 00:00:00 2001
+From: Helge Deller <deller@gmx.de>
+Date: Fri, 14 Jul 2017 14:49:38 -0700
+Subject: mm: fix overflow check in expand_upwards()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Helge Deller <deller@gmx.de>
+
+commit 37511fb5c91db93d8bd6e3f52f86e5a7ff7cfcdf upstream.
+
+Jörn Engel noticed that the expand_upwards() function might not return
+-ENOMEM in case the requested address is (unsigned long)-PAGE_SIZE and
+if the architecture didn't defined TASK_SIZE as multiple of PAGE_SIZE.
+
+Affected architectures are arm, frv, m68k, blackfin, h8300 and xtensa
+which all define TASK_SIZE as 0xffffffff, but since none of those have
+an upwards-growing stack we currently have no actual issue.
+
+Nevertheless let's fix this just in case any of the architectures with
+an upward-growing stack (currently parisc, metag and partly ia64) define
+TASK_SIZE similar.
+
+Link: http://lkml.kernel.org/r/20170702192452.GA11868@p100.box
+Fixes: bd726c90b6b8 ("Allow stack to grow up to address space limit")
+Signed-off-by: Helge Deller <deller@gmx.de>
+Reported-by: Jörn Engel <joern@purestorage.com>
+Cc: Hugh Dickins <hughd@google.com>
+Cc: Oleg Nesterov <oleg@redhat.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/mmap.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -2228,7 +2228,7 @@ int expand_upwards(struct vm_area_struct
+
+ /* Guard against exceeding limits of the address space. */
+ address &= PAGE_MASK;
+- if (address >= TASK_SIZE)
++ if (address >= (TASK_SIZE & PAGE_MASK))
+ return -ENOMEM;
+ address += PAGE_SIZE;
+
--- /dev/null
+From 2c80cd57c74339889a8752b20862a16c28929c3a Mon Sep 17 00:00:00 2001
+From: Sahitya Tummala <stummala@codeaurora.org>
+Date: Mon, 10 Jul 2017 15:49:57 -0700
+Subject: mm/list_lru.c: fix list_lru_count_node() to be race free
+
+From: Sahitya Tummala <stummala@codeaurora.org>
+
+commit 2c80cd57c74339889a8752b20862a16c28929c3a upstream.
+
+list_lru_count_node() iterates over all memcgs to get the total number of
+entries on the node but it can race with memcg_drain_all_list_lrus(),
+which migrates the entries from a dead cgroup to another. This can return
+incorrect number of entries from list_lru_count_node().
+
+Fix this by keeping track of entries per node and simply return it in
+list_lru_count_node().
+
+Link: http://lkml.kernel.org/r/1498707555-30525-1-git-send-email-stummala@codeaurora.org
+Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
+Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Alexander Polakov <apolyakov@beget.ru>
+Cc: Al Viro <viro@zeniv.linux.org.uk>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ include/linux/list_lru.h | 1 +
+ mm/list_lru.c | 14 ++++++--------
+ 2 files changed, 7 insertions(+), 8 deletions(-)
+
+--- a/include/linux/list_lru.h
++++ b/include/linux/list_lru.h
+@@ -44,6 +44,7 @@ struct list_lru_node {
+ /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+ struct list_lru_memcg *memcg_lrus;
+ #endif
++ long nr_items;
+ } ____cacheline_aligned_in_smp;
+
+ struct list_lru {
+--- a/mm/list_lru.c
++++ b/mm/list_lru.c
+@@ -117,6 +117,7 @@ bool list_lru_add(struct list_lru *lru,
+ l = list_lru_from_kmem(nlru, item);
+ list_add_tail(item, &l->list);
+ l->nr_items++;
++ nlru->nr_items++;
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+@@ -136,6 +137,7 @@ bool list_lru_del(struct list_lru *lru,
+ l = list_lru_from_kmem(nlru, item);
+ list_del_init(item);
+ l->nr_items--;
++ nlru->nr_items--;
+ spin_unlock(&nlru->lock);
+ return true;
+ }
+@@ -183,15 +185,10 @@ EXPORT_SYMBOL_GPL(list_lru_count_one);
+
+ unsigned long list_lru_count_node(struct list_lru *lru, int nid)
+ {
+- long count = 0;
+- int memcg_idx;
++ struct list_lru_node *nlru;
+
+- count += __list_lru_count_one(lru, nid, -1);
+- if (list_lru_memcg_aware(lru)) {
+- for_each_memcg_cache_index(memcg_idx)
+- count += __list_lru_count_one(lru, nid, memcg_idx);
+- }
+- return count;
++ nlru = &lru->node[nid];
++ return nlru->nr_items;
+ }
+ EXPORT_SYMBOL_GPL(list_lru_count_node);
+
+@@ -226,6 +223,7 @@ restart:
+ assert_spin_locked(&nlru->lock);
+ case LRU_REMOVED:
+ isolated++;
++ nlru->nr_items--;
+ /*
+ * If the lru lock has been dropped, our list
+ * traversal is now invalid and so we have to
--- /dev/null
+From 99b19d16471e9c3faa85cad38abc9cbbe04c6d55 Mon Sep 17 00:00:00 2001
+From: "Eric W. Biederman" <ebiederm@xmission.com>
+Date: Mon, 24 Oct 2016 16:16:13 -0500
+Subject: mnt: In propgate_umount handle visiting mounts in any order
+
+From: Eric W. Biederman <ebiederm@xmission.com>
+
+commit 99b19d16471e9c3faa85cad38abc9cbbe04c6d55 upstream.
+
+While investigating some poor umount performance I realized that in
+the case of overlapping mount trees where some of the mounts are locked
+the code has been failing to unmount all of the mounts it should
+have been unmounting.
+
+This failure to unmount all of the necessary
+mounts can be reproduced with:
+
+$ cat locked_mounts_test.sh
+
+mount -t tmpfs test-base /mnt
+mount --make-shared /mnt
+mkdir -p /mnt/b
+
+mount -t tmpfs test1 /mnt/b
+mount --make-shared /mnt/b
+mkdir -p /mnt/b/10
+
+mount -t tmpfs test2 /mnt/b/10
+mount --make-shared /mnt/b/10
+mkdir -p /mnt/b/10/20
+
+mount --rbind /mnt/b /mnt/b/10/20
+
+unshare -Urm --propagation unchaged /bin/sh -c 'sleep 5; if [ $(grep test /proc/self/mountinfo | wc -l) -eq 1 ] ; then echo SUCCESS ; else echo FAILURE ; fi'
+sleep 1
+umount -l /mnt/b
+wait %%
+
+$ unshare -Urm ./locked_mounts_test.sh
+
+This failure is corrected by removing the prepass that marks mounts
+that may be umounted.
+
+A first pass is added that umounts mounts if possible and if not sets
+mount mark if they could be unmounted if they weren't locked and adds
+them to a list to umount possibilities. This first pass reconsiders
+the mounts parent if it is on the list of umount possibilities, ensuring
+that information of umoutability will pass from child to mount parent.
+
+A second pass then walks through all mounts that are umounted and processes
+their children unmounting them or marking them for reparenting.
+
+A last pass cleans up the state on the mounts that could not be umounted
+and if applicable reparents them to their first parent that remained
+mounted.
+
+While a bit longer than the old code this code is much more robust
+as it allows information to flow up from the leaves and down
+from the trunk making the order in which mounts are encountered
+in the umount propgation tree irrelevant.
+
+Fixes: 0c56fe31420c ("mnt: Don't propagate unmounts to locked mounts")
+Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
+Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/mount.h | 2
+ fs/namespace.c | 2
+ fs/pnode.c | 150 +++++++++++++++++++++++++++++++++------------------------
+ 3 files changed, 91 insertions(+), 63 deletions(-)
+
+--- a/fs/mount.h
++++ b/fs/mount.h
+@@ -58,7 +58,7 @@ struct mount {
+ struct mnt_namespace *mnt_ns; /* containing namespace */
+ struct mountpoint *mnt_mp; /* where is it mounted */
+ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
+- struct list_head mnt_reparent; /* reparent list entry */
++ struct list_head mnt_umounting; /* list entry for umount propagation */
+ #ifdef CONFIG_FSNOTIFY
+ struct hlist_head mnt_fsnotify_marks;
+ __u32 mnt_fsnotify_mask;
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -237,7 +237,7 @@ static struct mount *alloc_vfsmnt(const
+ INIT_LIST_HEAD(&mnt->mnt_slave_list);
+ INIT_LIST_HEAD(&mnt->mnt_slave);
+ INIT_HLIST_NODE(&mnt->mnt_mp_list);
+- INIT_LIST_HEAD(&mnt->mnt_reparent);
++ INIT_LIST_HEAD(&mnt->mnt_umounting);
+ #ifdef CONFIG_FSNOTIFY
+ INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
+ #endif
+--- a/fs/pnode.c
++++ b/fs/pnode.c
+@@ -415,86 +415,95 @@ void propagate_mount_unlock(struct mount
+ }
+ }
+
+-/*
+- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
+- */
+-static void mark_umount_candidates(struct mount *mnt)
++static void umount_one(struct mount *mnt, struct list_head *to_umount)
+ {
+- struct mount *parent = mnt->mnt_parent;
+- struct mount *m;
+-
+- BUG_ON(parent == mnt);
+-
+- for (m = propagation_next(parent, parent); m;
+- m = propagation_next(m, parent)) {
+- struct mount *child = __lookup_mnt(&m->mnt,
+- mnt->mnt_mountpoint);
+- if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
+- continue;
+- if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
+- SET_MNT_MARK(child);
+- }
+- }
++ CLEAR_MNT_MARK(mnt);
++ mnt->mnt.mnt_flags |= MNT_UMOUNT;
++ list_del_init(&mnt->mnt_child);
++ list_del_init(&mnt->mnt_umounting);
++ list_move_tail(&mnt->mnt_list, to_umount);
+ }
+
+ /*
+ * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
+ * parent propagates to.
+ */
+-static void __propagate_umount(struct mount *mnt, struct list_head *to_reparent)
++static bool __propagate_umount(struct mount *mnt,
++ struct list_head *to_umount,
++ struct list_head *to_restore)
+ {
+- struct mount *parent = mnt->mnt_parent;
+- struct mount *m;
++ bool progress = false;
++ struct mount *child;
+
+- BUG_ON(parent == mnt);
+-
+- for (m = propagation_next(parent, parent); m;
+- m = propagation_next(m, parent)) {
+- struct mount *topper;
+- struct mount *child = __lookup_mnt(&m->mnt,
+- mnt->mnt_mountpoint);
+- /*
+- * umount the child only if the child has no children
+- * and the child is marked safe to unmount.
+- */
+- if (!child || !IS_MNT_MARKED(child))
++ /*
++ * The state of the parent won't change if this mount is
++ * already unmounted or marked as without children.
++ */
++ if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
++ goto out;
++
++ /* Verify topper is the only grandchild that has not been
++ * speculatively unmounted.
++ */
++ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
++ if (child->mnt_mountpoint == mnt->mnt.mnt_root)
++ continue;
++ if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
+ continue;
+- CLEAR_MNT_MARK(child);
++ /* Found a mounted child */
++ goto children;
++ }
+
+- /* If there is exactly one mount covering all of child
+- * replace child with that mount.
+- */
+- topper = find_topper(child);
+- if (topper)
+- list_add_tail(&topper->mnt_reparent, to_reparent);
+-
+- if (topper || list_empty(&child->mnt_mounts)) {
+- list_del_init(&child->mnt_child);
+- list_del_init(&child->mnt_reparent);
+- child->mnt.mnt_flags |= MNT_UMOUNT;
+- list_move_tail(&child->mnt_list, &mnt->mnt_list);
++ /* Mark mounts that can be unmounted if not locked */
++ SET_MNT_MARK(mnt);
++ progress = true;
++
++ /* If a mount is without children and not locked umount it. */
++ if (!IS_MNT_LOCKED(mnt)) {
++ umount_one(mnt, to_umount);
++ } else {
++children:
++ list_move_tail(&mnt->mnt_umounting, to_restore);
++ }
++out:
++ return progress;
++}
++
++static void umount_list(struct list_head *to_umount,
++ struct list_head *to_restore)
++{
++ struct mount *mnt, *child, *tmp;
++ list_for_each_entry(mnt, to_umount, mnt_list) {
++ list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
++ /* topper? */
++ if (child->mnt_mountpoint == mnt->mnt.mnt_root)
++ list_move_tail(&child->mnt_umounting, to_restore);
++ else
++ umount_one(child, to_umount);
+ }
+ }
+ }
+
+-static void reparent_mounts(struct list_head *to_reparent)
++static void restore_mounts(struct list_head *to_restore)
+ {
+- while (!list_empty(to_reparent)) {
++ /* Restore mounts to a clean working state */
++ while (!list_empty(to_restore)) {
+ struct mount *mnt, *parent;
+ struct mountpoint *mp;
+
+- mnt = list_first_entry(to_reparent, struct mount, mnt_reparent);
+- list_del_init(&mnt->mnt_reparent);
++ mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
++ CLEAR_MNT_MARK(mnt);
++ list_del_init(&mnt->mnt_umounting);
+
+- /* Where should this mount be reparented to? */
++ /* Should this mount be reparented? */
+ mp = mnt->mnt_mp;
+ parent = mnt->mnt_parent;
+ while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+ mp = parent->mnt_mp;
+ parent = parent->mnt_parent;
+ }
+-
+- mnt_change_mountpoint(parent, mp, mnt);
++ if (parent != mnt->mnt_parent)
++ mnt_change_mountpoint(parent, mp, mnt);
+ }
+ }
+
+@@ -508,15 +517,34 @@ static void reparent_mounts(struct list_
+ int propagate_umount(struct list_head *list)
+ {
+ struct mount *mnt;
+- LIST_HEAD(to_reparent);
+-
+- list_for_each_entry_reverse(mnt, list, mnt_list)
+- mark_umount_candidates(mnt);
++ LIST_HEAD(to_restore);
++ LIST_HEAD(to_umount);
+
+- list_for_each_entry(mnt, list, mnt_list)
+- __propagate_umount(mnt, &to_reparent);
++ list_for_each_entry(mnt, list, mnt_list) {
++ struct mount *parent = mnt->mnt_parent;
++ struct mount *m;
++
++ for (m = propagation_next(parent, parent); m;
++ m = propagation_next(m, parent)) {
++ struct mount *child = __lookup_mnt(&m->mnt,
++ mnt->mnt_mountpoint);
++ if (!child)
++ continue;
++
++ /* Check the child and parents while progress is made */
++ while (__propagate_umount(child,
++ &to_umount, &to_restore)) {
++ /* Is the parent a umount candidate? */
++ child = child->mnt_parent;
++ if (list_empty(&child->mnt_umounting))
++ break;
++ }
++ }
++ }
+
+- reparent_mounts(&to_reparent);
++ umount_list(&to_umount, &to_restore);
++ restore_mounts(&to_restore);
++ list_splice_tail(&to_umount, list);
+
+ return 0;
+ }
--- /dev/null
+From 570487d3faf2a1d8a220e6ee10f472163123d7da Mon Sep 17 00:00:00 2001
+From: "Eric W. Biederman" <ebiederm@xmission.com>
+Date: Mon, 15 May 2017 14:42:07 -0500
+Subject: mnt: In umount propagation reparent in a separate pass
+
+From: Eric W. Biederman <ebiederm@xmission.com>
+
+commit 570487d3faf2a1d8a220e6ee10f472163123d7da upstream.
+
+It was observed that in some pathlogical cases that the current code
+does not unmount everything it should. After investigation it
+was determined that the issue is that mnt_change_mntpoint can
+can change which mounts are available to be unmounted during mount
+propagation which is wrong.
+
+The trivial reproducer is:
+$ cat ./pathological.sh
+
+mount -t tmpfs test-base /mnt
+cd /mnt
+mkdir 1 2 1/1
+mount --bind 1 1
+mount --make-shared 1
+mount --bind 1 2
+mount --bind 1/1 1/1
+mount --bind 1/1 1/1
+echo
+grep test-base /proc/self/mountinfo
+umount 1/1
+echo
+grep test-base /proc/self/mountinfo
+
+$ unshare -Urm ./pathological.sh
+
+The expected output looks like:
+46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
+47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+
+46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
+47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+
+The output without the fix looks like:
+46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
+47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+
+46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
+47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+52 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
+
+That last mount in the output was in the propgation tree to be unmounted but
+was missed because the mnt_change_mountpoint changed it's parent before the walk
+through the mount propagation tree observed it.
+
+Fixes: 1064f874abc0 ("mnt: Tuck mounts under others instead of creating shadow/side mounts.")
+Acked-by: Andrei Vagin <avagin@virtuozzo.com>
+Reviewed-by: Ram Pai <linuxram@us.ibm.com>
+Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/mount.h | 1 +
+ fs/namespace.c | 1 +
+ fs/pnode.c | 35 ++++++++++++++++++++++++++++++-----
+ 3 files changed, 32 insertions(+), 5 deletions(-)
+
+--- a/fs/mount.h
++++ b/fs/mount.h
+@@ -58,6 +58,7 @@ struct mount {
+ struct mnt_namespace *mnt_ns; /* containing namespace */
+ struct mountpoint *mnt_mp; /* where is it mounted */
+ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
++ struct list_head mnt_reparent; /* reparent list entry */
+ #ifdef CONFIG_FSNOTIFY
+ struct hlist_head mnt_fsnotify_marks;
+ __u32 mnt_fsnotify_mask;
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -237,6 +237,7 @@ static struct mount *alloc_vfsmnt(const
+ INIT_LIST_HEAD(&mnt->mnt_slave_list);
+ INIT_LIST_HEAD(&mnt->mnt_slave);
+ INIT_HLIST_NODE(&mnt->mnt_mp_list);
++ INIT_LIST_HEAD(&mnt->mnt_reparent);
+ #ifdef CONFIG_FSNOTIFY
+ INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
+ #endif
+--- a/fs/pnode.c
++++ b/fs/pnode.c
+@@ -441,7 +441,7 @@ static void mark_umount_candidates(struc
+ * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
+ * parent propagates to.
+ */
+-static void __propagate_umount(struct mount *mnt)
++static void __propagate_umount(struct mount *mnt, struct list_head *to_reparent)
+ {
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *m;
+@@ -466,17 +466,38 @@ static void __propagate_umount(struct mo
+ */
+ topper = find_topper(child);
+ if (topper)
+- mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
+- topper);
++ list_add_tail(&topper->mnt_reparent, to_reparent);
+
+- if (list_empty(&child->mnt_mounts)) {
++ if (topper || list_empty(&child->mnt_mounts)) {
+ list_del_init(&child->mnt_child);
++ list_del_init(&child->mnt_reparent);
+ child->mnt.mnt_flags |= MNT_UMOUNT;
+ list_move_tail(&child->mnt_list, &mnt->mnt_list);
+ }
+ }
+ }
+
++static void reparent_mounts(struct list_head *to_reparent)
++{
++ while (!list_empty(to_reparent)) {
++ struct mount *mnt, *parent;
++ struct mountpoint *mp;
++
++ mnt = list_first_entry(to_reparent, struct mount, mnt_reparent);
++ list_del_init(&mnt->mnt_reparent);
++
++ /* Where should this mount be reparented to? */
++ mp = mnt->mnt_mp;
++ parent = mnt->mnt_parent;
++ while (parent->mnt.mnt_flags & MNT_UMOUNT) {
++ mp = parent->mnt_mp;
++ parent = parent->mnt_parent;
++ }
++
++ mnt_change_mountpoint(parent, mp, mnt);
++ }
++}
++
+ /*
+ * collect all mounts that receive propagation from the mount in @list,
+ * and return these additional mounts in the same list.
+@@ -487,11 +508,15 @@ static void __propagate_umount(struct mo
+ int propagate_umount(struct list_head *list)
+ {
+ struct mount *mnt;
++ LIST_HEAD(to_reparent);
+
+ list_for_each_entry_reverse(mnt, list, mnt_list)
+ mark_umount_candidates(mnt);
+
+ list_for_each_entry(mnt, list, mnt_list)
+- __propagate_umount(mnt);
++ __propagate_umount(mnt, &to_reparent);
++
++ reparent_mounts(&to_reparent);
++
+ return 0;
+ }
--- /dev/null
+From 296990deb389c7da21c78030376ba244dc1badf5 Mon Sep 17 00:00:00 2001
+From: "Eric W. Biederman" <ebiederm@xmission.com>
+Date: Mon, 24 Oct 2016 17:25:19 -0500
+Subject: mnt: Make propagate_umount less slow for overlapping mount propagation trees
+
+From: Eric W. Biederman <ebiederm@xmission.com>
+
+commit 296990deb389c7da21c78030376ba244dc1badf5 upstream.
+
+Andrei Vagin pointed out that time to executue propagate_umount can go
+non-linear (and take a ludicrious amount of time) when the mount
+propogation trees of the mounts to be unmunted by a lazy unmount
+overlap.
+
+Make the walk of the mount propagation trees nearly linear by
+remembering which mounts have already been visited, allowing
+subsequent walks to detect when walking a mount propgation tree or a
+subtree of a mount propgation tree would be duplicate work and to skip
+them entirely.
+
+Walk the list of mounts whose propgatation trees need to be traversed
+from the mount highest in the mount tree to mounts lower in the mount
+tree so that odds are higher that the code will walk the largest trees
+first, allowing later tree walks to be skipped entirely.
+
+Add cleanup_umount_visitation to remover the code's memory of which
+mounts have been visited.
+
+Add the functions last_slave and skip_propagation_subtree to allow
+skipping appropriate parts of the mount propagation tree without
+needing to change the logic of the rest of the code.
+
+A script to generate overlapping mount propagation trees:
+
+$ cat runs.h
+set -e
+mount -t tmpfs zdtm /mnt
+mkdir -p /mnt/1 /mnt/2
+mount -t tmpfs zdtm /mnt/1
+mount --make-shared /mnt/1
+mkdir /mnt/1/1
+
+iteration=10
+if [ -n "$1" ] ; then
+ iteration=$1
+fi
+
+for i in $(seq $iteration); do
+ mount --bind /mnt/1/1 /mnt/1/1
+done
+
+mount --rbind /mnt/1 /mnt/2
+
+TIMEFORMAT='%Rs'
+nr=$(( ( 2 ** ( $iteration + 1 ) ) + 1 ))
+echo -n "umount -l /mnt/1 -> $nr "
+time umount -l /mnt/1
+
+nr=$(cat /proc/self/mountinfo | grep zdtm | wc -l )
+time umount -l /mnt/2
+
+$ for i in $(seq 9 19); do echo $i; unshare -Urm bash ./run.sh $i; done
+
+Here are the performance numbers with and without the patch:
+
+ mhash | 8192 | 8192 | 1048576 | 1048576
+ mounts | before | after | before | after
+ ------------------------------------------------
+ 1025 | 0.040s | 0.016s | 0.038s | 0.019s
+ 2049 | 0.094s | 0.017s | 0.080s | 0.018s
+ 4097 | 0.243s | 0.019s | 0.206s | 0.023s
+ 8193 | 1.202s | 0.028s | 1.562s | 0.032s
+ 16385 | 9.635s | 0.036s | 9.952s | 0.041s
+ 32769 | 60.928s | 0.063s | 44.321s | 0.064s
+ 65537 | | 0.097s | | 0.097s
+ 131073 | | 0.233s | | 0.176s
+ 262145 | | 0.653s | | 0.344s
+ 524289 | | 2.305s | | 0.735s
+ 1048577 | | 7.107s | | 2.603s
+
+Andrei Vagin reports fixing the performance problem is part of the
+work to fix CVE-2016-6213.
+
+Fixes: a05964f3917c ("[PATCH] shared mounts handling: umount")
+Reported-by: Andrei Vagin <avagin@openvz.org>
+Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
+Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/pnode.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
+ 1 file changed, 62 insertions(+), 1 deletion(-)
+
+--- a/fs/pnode.c
++++ b/fs/pnode.c
+@@ -24,6 +24,11 @@ static inline struct mount *first_slave(
+ return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
+ }
+
++static inline struct mount *last_slave(struct mount *p)
++{
++ return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
++}
++
+ static inline struct mount *next_slave(struct mount *p)
+ {
+ return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
+@@ -164,6 +169,19 @@ static struct mount *propagation_next(st
+ }
+ }
+
++static struct mount *skip_propagation_subtree(struct mount *m,
++ struct mount *origin)
++{
++ /*
++ * Advance m such that propagation_next will not return
++ * the slaves of m.
++ */
++ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
++ m = last_slave(m);
++
++ return m;
++}
++
+ static struct mount *next_group(struct mount *m, struct mount *origin)
+ {
+ while (1) {
+@@ -507,6 +525,15 @@ static void restore_mounts(struct list_h
+ }
+ }
+
++static void cleanup_umount_visitations(struct list_head *visited)
++{
++ while (!list_empty(visited)) {
++ struct mount *mnt =
++ list_first_entry(visited, struct mount, mnt_umounting);
++ list_del_init(&mnt->mnt_umounting);
++ }
++}
++
+ /*
+ * collect all mounts that receive propagation from the mount in @list,
+ * and return these additional mounts in the same list.
+@@ -519,11 +546,23 @@ int propagate_umount(struct list_head *l
+ struct mount *mnt;
+ LIST_HEAD(to_restore);
+ LIST_HEAD(to_umount);
++ LIST_HEAD(visited);
+
+- list_for_each_entry(mnt, list, mnt_list) {
++ /* Find candidates for unmounting */
++ list_for_each_entry_reverse(mnt, list, mnt_list) {
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *m;
+
++ /*
++ * If this mount has already been visited it is known that it's
++ * entire peer group and all of their slaves in the propagation
++ * tree for the mountpoint has already been visited and there is
++ * no need to visit them again.
++ */
++ if (!list_empty(&mnt->mnt_umounting))
++ continue;
++
++ list_add_tail(&mnt->mnt_umounting, &visited);
+ for (m = propagation_next(parent, parent); m;
+ m = propagation_next(m, parent)) {
+ struct mount *child = __lookup_mnt(&m->mnt,
+@@ -531,6 +570,27 @@ int propagate_umount(struct list_head *l
+ if (!child)
+ continue;
+
++ if (!list_empty(&child->mnt_umounting)) {
++ /*
++ * If the child has already been visited it is
++ * know that it's entire peer group and all of
++ * their slaves in the propgation tree for the
++ * mountpoint has already been visited and there
++ * is no need to visit this subtree again.
++ */
++ m = skip_propagation_subtree(m, parent);
++ continue;
++ } else if (child->mnt.mnt_flags & MNT_UMOUNT) {
++ /*
++ * We have come accross an partially unmounted
++ * mount in list that has not been visited yet.
++ * Remember it has been visited and continue
++ * about our merry way.
++ */
++ list_add_tail(&child->mnt_umounting, &visited);
++ continue;
++ }
++
+ /* Check the child and parents while progress is made */
+ while (__propagate_umount(child,
+ &to_umount, &to_restore)) {
+@@ -544,6 +604,7 @@ int propagate_umount(struct list_head *l
+
+ umount_list(&to_umount, &to_restore);
+ restore_mounts(&to_restore);
++ cleanup_umount_visitations(&visited);
+ list_splice_tail(&to_umount, list);
+
+ return 0;
--- /dev/null
+From 3360acdf839170b612f5b212539694c20e3f16d0 Mon Sep 17 00:00:00 2001
+From: Johan Hovold <johan@kernel.org>
+Date: Fri, 9 Jun 2017 10:59:07 +0100
+Subject: nvmem: core: fix leaks on registration errors
+
+From: Johan Hovold <johan@kernel.org>
+
+commit 3360acdf839170b612f5b212539694c20e3f16d0 upstream.
+
+Make sure to deregister and release the nvmem device and underlying
+memory on registration errors.
+
+Note that the private data must be freed using put_device() once the
+struct device has been initialised.
+
+Also note that there's a related reference leak in the deregistration
+function as reported by Mika Westerberg which is being fixed separately.
+
+Fixes: b6c217ab9be6 ("nvmem: Add backwards compatibility support for older EEPROM drivers.")
+Fixes: eace75cfdcf7 ("nvmem: Add a simple NVMEM framework for nvmem providers")
+Cc: Andrew Lunn <andrew@lunn.ch>
+Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
+Signed-off-by: Johan Hovold <johan@kernel.org>
+Acked-by: Andrey Smirnov <andrew.smirnov@gmail.com>
+Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/nvmem/core.c | 13 ++++++++-----
+ 1 file changed, 8 insertions(+), 5 deletions(-)
+
+--- a/drivers/nvmem/core.c
++++ b/drivers/nvmem/core.c
+@@ -488,21 +488,24 @@ struct nvmem_device *nvmem_register(cons
+
+ rval = device_add(&nvmem->dev);
+ if (rval)
+- goto out;
++ goto err_put_device;
+
+ if (config->compat) {
+ rval = nvmem_setup_compat(nvmem, config);
+ if (rval)
+- goto out;
++ goto err_device_del;
+ }
+
+ if (config->cells)
+ nvmem_add_cells(nvmem, config);
+
+ return nvmem;
+-out:
+- ida_simple_remove(&nvmem_ida, nvmem->id);
+- kfree(nvmem);
++
++err_device_del:
++ device_del(&nvmem->dev);
++err_put_device:
++ put_device(&nvmem->dev);
++
+ return ERR_PTR(rval);
+ }
+ EXPORT_SYMBOL_GPL(nvmem_register);
--- /dev/null
+From 33f9e02495d15a061f0c94ef46f5103a2d0c20f3 Mon Sep 17 00:00:00 2001
+From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+Date: Mon, 3 Jul 2017 10:38:05 +0200
+Subject: parisc: DMA API: return error instead of BUG_ON for dma ops on non dma devs
+
+From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+
+commit 33f9e02495d15a061f0c94ef46f5103a2d0c20f3 upstream.
+
+Enabling parport pc driver on a B2600 (and probably other 64bit PARISC
+systems) produced following BUG:
+
+CPU: 0 PID: 1 Comm: swapper Not tainted 4.12.0-rc5-30198-g1132d5e #156
+task: 000000009e050000 task.stack: 000000009e04c000
+
+ YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI
+PSW: 00001000000001101111111100001111 Not tainted
+r00-03 000000ff0806ff0f 000000009e04c990 0000000040871b78 000000009e04cac0
+r04-07 0000000040c14de0 ffffffffffffffff 000000009e07f098 000000009d82d200
+r08-11 000000009d82d210 0000000000000378 0000000000000000 0000000040c345e0
+r12-15 0000000000000005 0000000040c345e0 0000000000000000 0000000040c9d5e0
+r16-19 0000000040c345e0 00000000f00001c4 00000000f00001bc 0000000000000061
+r20-23 000000009e04ce28 0000000000000010 0000000000000010 0000000040b89e40
+r24-27 0000000000000003 0000000000ffffff 000000009d82d210 0000000040c14de0
+r28-31 0000000000000000 000000009e04ca90 000000009e04cb40 0000000000000000
+sr00-03 0000000000000000 0000000000000000 0000000000000000 0000000000000000
+sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000
+
+IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000404aece0 00000000404aece4
+ IIR: 03ffe01f ISR: 0000000010340000 IOR: 000001781304cac8
+ CPU: 0 CR30: 000000009e04c000 CR31: 00000000e2976de2
+ ORIG_R28: 0000000000000200
+ IAOQ[0]: sba_dma_supported+0x80/0xd0
+ IAOQ[1]: sba_dma_supported+0x84/0xd0
+ RP(r2): parport_pc_probe_port+0x178/0x1200
+
+Cause is a call to dma_coerce_mask_and_coherenet in parport_pc_probe_port,
+which PARISC DMA API doesn't handle very nicely. This commit gives back
+DMA_ERROR_CODE for DMA API calls, if device isn't capable of DMA
+transaction.
+
+Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/parisc/include/asm/dma-mapping.h | 11 +++++++----
+ drivers/parisc/ccio-dma.c | 12 ++++++++++++
+ drivers/parisc/dino.c | 5 ++++-
+ drivers/parisc/lba_pci.c | 6 ++++--
+ drivers/parisc/sba_iommu.c | 14 ++++++++++++++
+ 5 files changed, 41 insertions(+), 7 deletions(-)
+
+--- a/arch/parisc/include/asm/dma-mapping.h
++++ b/arch/parisc/include/asm/dma-mapping.h
+@@ -20,6 +20,8 @@
+ ** flush/purge and allocate "regular" cacheable pages for everything.
+ */
+
++#define DMA_ERROR_CODE (~(dma_addr_t)0)
++
+ #ifdef CONFIG_PA11
+ extern struct dma_map_ops pcxl_dma_ops;
+ extern struct dma_map_ops pcx_dma_ops;
+@@ -54,12 +56,13 @@ parisc_walk_tree(struct device *dev)
+ break;
+ }
+ }
+- BUG_ON(!dev->platform_data);
+ return dev->platform_data;
+ }
+-
+-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu)
+-
++
++#define GET_IOC(dev) ({ \
++ void *__pdata = parisc_walk_tree(dev); \
++ __pdata ? HBA_DATA(__pdata)->iommu : NULL; \
++})
+
+ #ifdef CONFIG_IOMMU_CCIO
+ struct parisc_device;
+--- a/drivers/parisc/ccio-dma.c
++++ b/drivers/parisc/ccio-dma.c
+@@ -741,6 +741,8 @@ ccio_map_single(struct device *dev, void
+
+ BUG_ON(!dev);
+ ioc = GET_IOC(dev);
++ if (!ioc)
++ return DMA_ERROR_CODE;
+
+ BUG_ON(size <= 0);
+
+@@ -814,6 +816,10 @@ ccio_unmap_page(struct device *dev, dma_
+
+ BUG_ON(!dev);
+ ioc = GET_IOC(dev);
++ if (!ioc) {
++ WARN_ON(!ioc);
++ return;
++ }
+
+ DBG_RUN("%s() iovp 0x%lx/%x\n",
+ __func__, (long)iova, size);
+@@ -918,6 +924,8 @@ ccio_map_sg(struct device *dev, struct s
+
+ BUG_ON(!dev);
+ ioc = GET_IOC(dev);
++ if (!ioc)
++ return 0;
+
+ DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
+
+@@ -990,6 +998,10 @@ ccio_unmap_sg(struct device *dev, struct
+
+ BUG_ON(!dev);
+ ioc = GET_IOC(dev);
++ if (!ioc) {
++ WARN_ON(!ioc);
++ return;
++ }
+
+ DBG_RUN_SG("%s() START %d entries, %p,%x\n",
+ __func__, nents, sg_virt(sglist), sglist->length);
+--- a/drivers/parisc/dino.c
++++ b/drivers/parisc/dino.c
+@@ -154,7 +154,10 @@ struct dino_device
+ };
+
+ /* Looks nice and keeps the compiler happy */
+-#define DINO_DEV(d) ((struct dino_device *) d)
++#define DINO_DEV(d) ({ \
++ void *__pdata = d; \
++ BUG_ON(!__pdata); \
++ (struct dino_device *)__pdata; })
+
+
+ /*
+--- a/drivers/parisc/lba_pci.c
++++ b/drivers/parisc/lba_pci.c
+@@ -111,8 +111,10 @@ static u32 lba_t32;
+
+
+ /* Looks nice and keeps the compiler happy */
+-#define LBA_DEV(d) ((struct lba_device *) (d))
+-
++#define LBA_DEV(d) ({ \
++ void *__pdata = d; \
++ BUG_ON(!__pdata); \
++ (struct lba_device *)__pdata; })
+
+ /*
+ ** Only allow 8 subsidiary busses per LBA
+--- a/drivers/parisc/sba_iommu.c
++++ b/drivers/parisc/sba_iommu.c
+@@ -691,6 +691,8 @@ static int sba_dma_supported( struct dev
+ return 0;
+
+ ioc = GET_IOC(dev);
++ if (!ioc)
++ return 0;
+
+ /*
+ * check if mask is >= than the current max IO Virt Address
+@@ -722,6 +724,8 @@ sba_map_single(struct device *dev, void
+ int pide;
+
+ ioc = GET_IOC(dev);
++ if (!ioc)
++ return DMA_ERROR_CODE;
+
+ /* save offset bits */
+ offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK;
+@@ -813,6 +817,10 @@ sba_unmap_page(struct device *dev, dma_a
+ DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long) iova, size);
+
+ ioc = GET_IOC(dev);
++ if (!ioc) {
++ WARN_ON(!ioc);
++ return;
++ }
+ offset = iova & ~IOVP_MASK;
+ iova ^= offset; /* clear offset bits */
+ size += offset;
+@@ -952,6 +960,8 @@ sba_map_sg(struct device *dev, struct sc
+ DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
+
+ ioc = GET_IOC(dev);
++ if (!ioc)
++ return 0;
+
+ /* Fast path single entry scatterlists. */
+ if (nents == 1) {
+@@ -1037,6 +1047,10 @@ sba_unmap_sg(struct device *dev, struct
+ __func__, nents, sg_virt(sglist), sglist->length);
+
+ ioc = GET_IOC(dev);
++ if (!ioc) {
++ WARN_ON(!ioc);
++ return;
++ }
+
+ #ifdef SBA_COLLECT_STATS
+ ioc->usg_calls++;
--- /dev/null
+From 649aa24254e85bf6bd7807dd372d083707852b1f Mon Sep 17 00:00:00 2001
+From: Helge Deller <deller@gmx.de>
+Date: Mon, 29 May 2017 17:14:16 +0200
+Subject: parisc/mm: Ensure IRQs are off in switch_mm()
+
+From: Helge Deller <deller@gmx.de>
+
+commit 649aa24254e85bf6bd7807dd372d083707852b1f upstream.
+
+This is because of commit f98db6013c55 ("sched/core: Add switch_mm_irqs_off()
+and use it in the scheduler") in which switch_mm_irqs_off() is called by the
+scheduler, vs switch_mm() which is used by use_mm().
+
+This patch lets the parisc code mirror the x86 and powerpc code, ie. it
+disables interrupts in switch_mm(), and optimises the scheduler case by
+defining switch_mm_irqs_off().
+
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/parisc/include/asm/mmu_context.h | 15 +++++++++++++--
+ 1 file changed, 13 insertions(+), 2 deletions(-)
+
+--- a/arch/parisc/include/asm/mmu_context.h
++++ b/arch/parisc/include/asm/mmu_context.h
+@@ -49,15 +49,26 @@ static inline void load_context(mm_conte
+ mtctl(__space_to_prot(context), 8);
+ }
+
+-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
++static inline void switch_mm_irqs_off(struct mm_struct *prev,
++ struct mm_struct *next, struct task_struct *tsk)
+ {
+-
+ if (prev != next) {
+ mtctl(__pa(next->pgd), 25);
+ load_context(next->context);
+ }
+ }
+
++static inline void switch_mm(struct mm_struct *prev,
++ struct mm_struct *next, struct task_struct *tsk)
++{
++ unsigned long flags;
++
++ local_irq_save(flags);
++ switch_mm_irqs_off(prev, next, tsk);
++ local_irq_restore(flags);
++}
++#define switch_mm_irqs_off switch_mm_irqs_off
++
+ #define deactivate_mm(tsk,mm) do { } while (0)
+
+ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
--- /dev/null
+From 247462316f85a9e0479445c1a4223950b68ffac1 Mon Sep 17 00:00:00 2001
+From: Helge Deller <deller@gmx.de>
+Date: Sun, 2 Jul 2017 22:00:41 +0200
+Subject: parisc: Report SIGSEGV instead of SIGBUS when running out of stack
+
+From: Helge Deller <deller@gmx.de>
+
+commit 247462316f85a9e0479445c1a4223950b68ffac1 upstream.
+
+When a process runs out of stack the parisc kernel wrongly faults with SIGBUS
+instead of the expected SIGSEGV signal.
+
+This example shows how the kernel faults:
+do_page_fault() command='a.out' type=15 address=0xfaac2000 in libc-2.24.so[f8308000+16c000]
+trap #15: Data TLB miss fault, vm_start = 0xfa2c2000, vm_end = 0xfaac2000
+
+The vma->vm_end value is the first address which does not belong to the vma, so
+adjust the check to include vma->vm_end to the range for which to send the
+SIGSEGV signal.
+
+This patch unbreaks building the debian libsigsegv package.
+
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/parisc/mm/fault.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/arch/parisc/mm/fault.c
++++ b/arch/parisc/mm/fault.c
+@@ -366,7 +366,7 @@ bad_area:
+ case 15: /* Data TLB miss fault/Data page fault */
+ /* send SIGSEGV when outside of vma */
+ if (!vma ||
+- address < vma->vm_start || address > vma->vm_end) {
++ address < vma->vm_start || address >= vma->vm_end) {
+ si.si_signo = SIGSEGV;
+ si.si_code = SEGV_MAPERR;
+ break;
--- /dev/null
+From b0f94efd5aa8daa8a07d7601714c2573266cd4c9 Mon Sep 17 00:00:00 2001
+From: Eric Biggers <ebiggers@google.com>
+Date: Mon, 12 Jun 2017 23:18:30 -0700
+Subject: parisc: use compat_sys_keyctl()
+
+From: Eric Biggers <ebiggers@google.com>
+
+commit b0f94efd5aa8daa8a07d7601714c2573266cd4c9 upstream.
+
+Architectures with a compat syscall table must put compat_sys_keyctl()
+in it, not sys_keyctl(). The parisc architecture was not doing this;
+fix it.
+
+Signed-off-by: Eric Biggers <ebiggers@google.com>
+Acked-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/parisc/kernel/syscall_table.S | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/arch/parisc/kernel/syscall_table.S
++++ b/arch/parisc/kernel/syscall_table.S
+@@ -361,7 +361,7 @@
+ ENTRY_SAME(ni_syscall) /* 263: reserved for vserver */
+ ENTRY_SAME(add_key)
+ ENTRY_SAME(request_key) /* 265 */
+- ENTRY_SAME(keyctl)
++ ENTRY_COMP(keyctl)
+ ENTRY_SAME(ioprio_set)
+ ENTRY_SAME(ioprio_get)
+ ENTRY_SAME(inotify_init)
--- /dev/null
+From 47ebb09d54856500c5a5e14824781902b3bb738e Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Mon, 10 Jul 2017 15:52:47 -0700
+Subject: powerpc: move ELF_ET_DYN_BASE to 4GB / 4MB
+
+From: Kees Cook <keescook@chromium.org>
+
+commit 47ebb09d54856500c5a5e14824781902b3bb738e upstream.
+
+Now that explicitly executed loaders are loaded in the mmap region, we
+have more freedom to decide where we position PIE binaries in the
+address space to avoid possible collisions with mmap or stack regions.
+
+For 64-bit, align to 4GB to allow runtimes to use the entire 32-bit
+address space for 32-bit pointers. On 32-bit use 4MB, which is the
+traditional x86 minimum load location, likely to avoid historically
+requiring a 4MB page table entry when only a portion of the first 4MB
+would be used (since the NULL address is avoided).
+
+Link: http://lkml.kernel.org/r/1498154792-49952-4-git-send-email-keescook@chromium.org
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Tested-by: Michael Ellerman <mpe@ellerman.id.au>
+Acked-by: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Russell King <linux@armlinux.org.uk>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Will Deacon <will.deacon@arm.com>
+Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
+Cc: Paul Mackerras <paulus@samba.org>
+Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
+Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
+Cc: James Hogan <james.hogan@imgtec.com>
+Cc: Pratyush Anand <panand@redhat.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/powerpc/include/asm/elf.h | 13 +++++++------
+ 1 file changed, 7 insertions(+), 6 deletions(-)
+
+--- a/arch/powerpc/include/asm/elf.h
++++ b/arch/powerpc/include/asm/elf.h
+@@ -23,12 +23,13 @@
+ #define CORE_DUMP_USE_REGSET
+ #define ELF_EXEC_PAGESIZE PAGE_SIZE
+
+-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+- use of this is to invoke "./ld.so someprog" to test out a new version of
+- the loader. We need to make sure that it is out of the way of the program
+- that it will "exec", and that there is sufficient room for the brk. */
+-
+-#define ELF_ET_DYN_BASE 0x20000000
++/*
++ * This is the base location for PIE (ET_DYN with INTERP) loads. On
++ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
++ * space open for things that want to use the area for 32-bit pointers.
++ */
++#define ELF_ET_DYN_BASE (is_32bit_task() ? 0x000400000UL : \
++ 0x100000000UL)
+
+ #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
+
--- /dev/null
+From 6b5fc3a1331810db407c9e0e673dc1837afdc9d0 Mon Sep 17 00:00:00 2001
+From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+Date: Fri, 28 Apr 2017 20:11:09 -0700
+Subject: rcu: Add memory barriers for NOCB leader wakeup
+
+From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+commit 6b5fc3a1331810db407c9e0e673dc1837afdc9d0 upstream.
+
+Wait/wakeup operations do not guarantee ordering on their own. Instead,
+either locking or memory barriers are required. This commit therefore
+adds memory barriers to wake_nocb_leader() and nocb_leader_wait().
+
+Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+Tested-by: Krister Johansen <kjlx@templeofstupid.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/rcu/tree_plugin.h | 2 ++
+ 1 file changed, 2 insertions(+)
+
+--- a/kernel/rcu/tree_plugin.h
++++ b/kernel/rcu/tree_plugin.h
+@@ -1767,6 +1767,7 @@ static void wake_nocb_leader(struct rcu_
+ if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+ /* Prior smp_mb__after_atomic() orders against prior enqueue. */
+ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
++ smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
+ swake_up(&rdp_leader->nocb_wq);
+ }
+ }
+@@ -2021,6 +2022,7 @@ wait_again:
+ * nocb_gp_head, where they await a grace period.
+ */
+ gotcbs = false;
++ smp_mb(); /* wakeup before ->nocb_head reads. */
+ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
+ rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
+ if (!rdp->nocb_gp_head)
--- /dev/null
+From a73dc5370e153ac63718d850bddf0c9aa9d871e6 Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Mon, 10 Jul 2017 15:52:51 -0700
+Subject: s390: reduce ELF_ET_DYN_BASE
+
+From: Kees Cook <keescook@chromium.org>
+
+commit a73dc5370e153ac63718d850bddf0c9aa9d871e6 upstream.
+
+Now that explicitly executed loaders are loaded in the mmap region, we
+have more freedom to decide where we position PIE binaries in the
+address space to avoid possible collisions with mmap or stack regions.
+
+For 64-bit, align to 4GB to allow runtimes to use the entire 32-bit
+address space for 32-bit pointers. On 32-bit use 4MB, which is the
+traditional x86 minimum load location, likely to avoid historically
+requiring a 4MB page table entry when only a portion of the first 4MB
+would be used (since the NULL address is avoided). For s390 the
+position could be 0x10000, but that is needlessly close to the NULL
+address.
+
+Link: http://lkml.kernel.org/r/1498154792-49952-5-git-send-email-keescook@chromium.org
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Cc: Russell King <linux@armlinux.org.uk>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Will Deacon <will.deacon@arm.com>
+Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
+Cc: Paul Mackerras <paulus@samba.org>
+Cc: Michael Ellerman <mpe@ellerman.id.au>
+Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
+Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
+Cc: James Hogan <james.hogan@imgtec.com>
+Cc: Pratyush Anand <panand@redhat.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/s390/include/asm/elf.h | 15 +++++++--------
+ 1 file changed, 7 insertions(+), 8 deletions(-)
+
+--- a/arch/s390/include/asm/elf.h
++++ b/arch/s390/include/asm/elf.h
+@@ -158,14 +158,13 @@ extern unsigned int vdso_enabled;
+ #define CORE_DUMP_USE_REGSET
+ #define ELF_EXEC_PAGESIZE 4096
+
+-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
+- use of this is to invoke "./ld.so someprog" to test out a new version of
+- the loader. We need to make sure that it is out of the way of the program
+- that it will "exec", and that there is sufficient room for the brk. 64-bit
+- tasks are aligned to 4GB. */
+-#define ELF_ET_DYN_BASE (is_compat_task() ? \
+- (STACK_TOP / 3 * 2) : \
+- (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
++/*
++ * This is the base location for PIE (ET_DYN with INTERP) loads. On
++ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
++ * space open for things that want to use the area for 32-bit pointers.
++ */
++#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \
++ 0x100000000UL)
+
+ /* This yields a mask that user programs can use to figure out what
+ instruction set this CPU supports. */
--- /dev/null
+From 796a3bae2fba6810427efdb314a1c126c9490fb3 Mon Sep 17 00:00:00 2001
+From: Andy Lutomirski <luto@kernel.org>
+Date: Thu, 29 Jun 2017 08:46:12 -0700
+Subject: selftests/capabilities: Fix the test_execve test
+
+From: Andy Lutomirski <luto@kernel.org>
+
+commit 796a3bae2fba6810427efdb314a1c126c9490fb3 upstream.
+
+test_execve does rather odd mount manipulations to safely create
+temporary setuid and setgid executables that aren't visible to the
+rest of the system. Those executables end up in the test's cwd, but
+that cwd is MNT_DETACHed.
+
+The core namespace code considers MNT_DETACHed trees to belong to no
+mount namespace at all and, in general, MNT_DETACHed trees are only
+barely function. This interacted with commit 380cf5ba6b0a ("fs:
+Treat foreign mounts as nosuid") to cause all MNT_DETACHed trees to
+act as though they're nosuid, breaking the test.
+
+Fix it by just not detaching the tree. It's still in a private
+mount namespace and is therefore still invisible to the rest of the
+system (except via /proc, and the same nosuid logic will protect all
+other programs on the system from believing in test_execve's setuid
+bits).
+
+While we're at it, fix some blatant whitespace problems.
+
+Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
+Fixes: 380cf5ba6b0a ("fs: Treat foreign mounts as nosuid")
+Cc: "Eric W. Biederman" <ebiederm@xmission.com>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Shuah Khan <shuahkh@osg.samsung.com>
+Cc: Greg KH <greg@kroah.com>
+Cc: linux-kselftest@vger.kernel.org
+Signed-off-by: Andy Lutomirski <luto@kernel.org>
+Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ tools/testing/selftests/capabilities/test_execve.c | 7 ++-----
+ 1 file changed, 2 insertions(+), 5 deletions(-)
+
+--- a/tools/testing/selftests/capabilities/test_execve.c
++++ b/tools/testing/selftests/capabilities/test_execve.c
+@@ -138,9 +138,6 @@ static void chdir_to_tmpfs(void)
+
+ if (chdir(cwd) != 0)
+ err(1, "chdir to private tmpfs");
+-
+- if (umount2(".", MNT_DETACH) != 0)
+- err(1, "detach private tmpfs");
+ }
+
+ static void copy_fromat_to(int fromfd, const char *fromname, const char *toname)
+@@ -248,7 +245,7 @@ static int do_tests(int uid, const char
+ err(1, "chown");
+ if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0)
+ err(1, "chmod");
+-}
++ }
+
+ capng_get_caps_process();
+
+@@ -384,7 +381,7 @@ static int do_tests(int uid, const char
+ } else {
+ printf("[RUN]\tNon-root +ia, sgidnonroot => i\n");
+ exec_other_validate_cap("./validate_cap_sgidnonroot",
+- false, false, true, false);
++ false, false, true, false);
+
+ if (fork_wait()) {
+ printf("[RUN]\tNon-root +ia, sgidroot => i\n");
brcmfmac-fix-a-memory-leak-in-error-handling-path-in-brcmf_cfg80211_attach.patch
brcmfmac-fix-glom_skb-leak-in-brcmf_sdiod_recv_chain.patch
sfc-don-t-read-beyond-unicast-address-list.patch
+cfg80211-define-nla_policy-for-nl80211_attr_local_mesh_power_mode.patch
+cfg80211-validate-frequencies-nested-in-nl80211_attr_scan_frequencies.patch
+cfg80211-check-if-pmkid-attribute-is-of-expected-size.patch
+cfg80211-check-if-nan-service-id-is-of-expected-size.patch
+irqchip-gic-v3-fix-out-of-bound-access-in-gic_set_affinity.patch
+parisc-report-sigsegv-instead-of-sigbus-when-running-out-of-stack.patch
+parisc-use-compat_sys_keyctl.patch
+parisc-dma-api-return-error-instead-of-bug_on-for-dma-ops-on-non-dma-devs.patch
+parisc-mm-ensure-irqs-are-off-in-switch_mm.patch
+tools-lib-lockdep-reduce-max_lock_depth-to-avoid-overflowing-lock_chain-depth.patch
+thp-mm-fix-crash-due-race-in-madv_free-handling.patch
+kernel-extable.c-mark-core_kernel_text-notrace.patch
+mm-list_lru.c-fix-list_lru_count_node-to-be-race-free.patch
+fs-dcache.c-fix-spin-lockup-issue-on-nlru-lock.patch
+checkpatch-silence-perl-5.26.0-unescaped-left-brace-warnings.patch
+binfmt_elf-use-elf_et_dyn_base-only-for-pie.patch
+arm-move-elf_et_dyn_base-to-4mb.patch
+arm64-move-elf_et_dyn_base-to-4gb-4mb.patch
+powerpc-move-elf_et_dyn_base-to-4gb-4mb.patch
+s390-reduce-elf_et_dyn_base.patch
+exec-limit-arg-stack-to-at-most-75-of-_stk_lim.patch
+arm64-dts-marvell-armada37xx-fix-timer-interrupt-specifiers.patch
+vt-fix-unchecked-__put_user-in-tioclinux-ioctls.patch
+rcu-add-memory-barriers-for-nocb-leader-wakeup.patch
+nvmem-core-fix-leaks-on-registration-errors.patch
+mnt-in-umount-propagation-reparent-in-a-separate-pass.patch
+mnt-in-propgate_umount-handle-visiting-mounts-in-any-order.patch
+mnt-make-propagate_umount-less-slow-for-overlapping-mount-propagation-trees.patch
+selftests-capabilities-fix-the-test_execve-test.patch
+mm-fix-overflow-check-in-expand_upwards.patch
--- /dev/null
+From bbf29ffc7f963bb894f84f0580c70cfea01c3892 Mon Sep 17 00:00:00 2001
+From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
+Date: Thu, 6 Jul 2017 15:35:28 -0700
+Subject: thp, mm: fix crash due race in MADV_FREE handling
+
+From: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+
+commit bbf29ffc7f963bb894f84f0580c70cfea01c3892 upstream.
+
+Reinette reported the following crash:
+
+ BUG: Bad page state in process log2exe pfn:57600
+ page:ffffea00015d8000 count:0 mapcount:0 mapping: (null) index:0x20200
+ flags: 0x4000000000040019(locked|uptodate|dirty|swapbacked)
+ raw: 4000000000040019 0000000000000000 0000000000020200 00000000ffffffff
+ raw: ffffea00015d8020 ffffea00015d8020 0000000000000000 0000000000000000
+ page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set
+ bad because of flags: 0x1(locked)
+ Modules linked in: rfcomm 8021q bnep intel_rapl x86_pkg_temp_thermal coretemp efivars btusb btrtl btbcm pwm_lpss_pci snd_hda_codec_hdmi btintel pwm_lpss snd_hda_codec_realtek snd_soc_skl snd_hda_codec_generic snd_soc_skl_ipc spi_pxa2xx_platform snd_soc_sst_ipc snd_soc_sst_dsp i2c_designware_platform i2c_designware_core snd_hda_ext_core snd_soc_sst_match snd_hda_intel snd_hda_codec mei_me snd_hda_core mei snd_soc_rt286 snd_soc_rl6347a snd_soc_core efivarfs
+ CPU: 1 PID: 354 Comm: log2exe Not tainted 4.12.0-rc7-test-test #19
+ Hardware name: Intel corporation NUC6CAYS/NUC6CAYB, BIOS AYAPLCEL.86A.0027.2016.1108.1529 11/08/2016
+ Call Trace:
+ bad_page+0x16a/0x1f0
+ free_pages_check_bad+0x117/0x190
+ free_hot_cold_page+0x7b1/0xad0
+ __put_page+0x70/0xa0
+ madvise_free_huge_pmd+0x627/0x7b0
+ madvise_free_pte_range+0x6f8/0x1150
+ __walk_page_range+0x6b5/0xe30
+ walk_page_range+0x13b/0x310
+ madvise_free_page_range.isra.16+0xad/0xd0
+ madvise_free_single_vma+0x2e4/0x470
+ SyS_madvise+0x8ce/0x1450
+
+If somebody frees the page under us and we hold the last reference to
+it, put_page() would attempt to free the page before unlocking it.
+
+The fix is trivial reorder of operations.
+
+Dave said:
+ "I came up with the exact same patch. For posterity, here's the test
+ case, generated by syzkaller and trimmed down by Reinette:
+
+ https://www.sr71.net/~dave/intel/log2.c
+
+ And the config that helps detect this:
+
+ https://www.sr71.net/~dave/intel/config-log2"
+
+Fixes: b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called")
+Link: http://lkml.kernel.org/r/20170628101249.17879-1-kirill.shutemov@linux.intel.com
+Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Reported-by: Reinette Chatre <reinette.chatre@intel.com>
+Acked-by: Dave Hansen <dave.hansen@intel.com>
+Acked-by: Michal Hocko <mhocko@suse.com>
+Acked-by: Minchan Kim <minchan@kernel.org>
+Cc: Huang Ying <ying.huang@intel.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/huge_memory.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -1373,8 +1373,8 @@ bool madvise_free_huge_pmd(struct mmu_ga
+ get_page(page);
+ spin_unlock(ptl);
+ split_huge_page(page);
+- put_page(page);
+ unlock_page(page);
++ put_page(page);
+ goto out_unlocked;
+ }
+
--- /dev/null
+From 98dcea0cfd04e083ac74137ceb9a632604740e2d Mon Sep 17 00:00:00 2001
+From: Ben Hutchings <ben@decadent.org.uk>
+Date: Thu, 25 May 2017 12:58:33 +0000
+Subject: tools/lib/lockdep: Reduce MAX_LOCK_DEPTH to avoid overflowing lock_chain/: Depth
+
+From: Ben Hutchings <ben@decadent.org.uk>
+
+commit 98dcea0cfd04e083ac74137ceb9a632604740e2d upstream.
+
+liblockdep has been broken since commit 75dd602a5198 ("lockdep: Fix
+lock_chain::base size"), as that adds a check that MAX_LOCK_DEPTH is
+within the range of lock_chain::depth and in liblockdep it is much
+too large.
+
+That should have resulted in a compiler error, but didn't because:
+
+- the check uses ARRAY_SIZE(), which isn't yet defined in liblockdep
+ so is assumed to be an (undeclared) function
+- putting a function call inside a BUILD_BUG_ON() expression quietly
+ turns it into some nonsense involving a variable-length array
+
+It did produce a compiler warning, but I didn't notice because
+liblockdep already produces too many warnings if -Wall is enabled
+(which I'll fix shortly).
+
+Even before that commit, which reduced lock_chain::depth from 8 bits
+to 6, MAX_LOCK_DEPTH was too large.
+
+Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
+Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Cc: a.p.zijlstra@chello.nl
+Link: http://lkml.kernel.org/r/20170525130005.5947-3-alexander.levin@verizon.com
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ tools/lib/lockdep/uinclude/linux/lockdep.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/tools/lib/lockdep/uinclude/linux/lockdep.h
++++ b/tools/lib/lockdep/uinclude/linux/lockdep.h
+@@ -8,7 +8,7 @@
+ #include <linux/utsname.h>
+ #include <linux/compiler.h>
+
+-#define MAX_LOCK_DEPTH 2000UL
++#define MAX_LOCK_DEPTH 63UL
+
+ #define asmlinkage
+ #define __visible
--- /dev/null
+From 6987dc8a70976561d22450b5858fc9767788cc1c Mon Sep 17 00:00:00 2001
+From: Adam Borowski <kilobyte@angband.pl>
+Date: Sat, 3 Jun 2017 09:35:06 +0200
+Subject: vt: fix unchecked __put_user() in tioclinux ioctls
+
+From: Adam Borowski <kilobyte@angband.pl>
+
+commit 6987dc8a70976561d22450b5858fc9767788cc1c upstream.
+
+Only read access is checked before this call.
+
+Actually, at the moment this is not an issue, as every in-tree arch does
+the same manual checks for VERIFY_READ vs VERIFY_WRITE, relying on the MMU
+to tell them apart, but this wasn't the case in the past and may happen
+again on some odd arch in the future.
+
+If anyone cares about 3.7 and earlier, this is a security hole (untested)
+on real 80386 CPUs.
+
+Signed-off-by: Adam Borowski <kilobyte@angband.pl>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/tty/vt/vt.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+--- a/drivers/tty/vt/vt.c
++++ b/drivers/tty/vt/vt.c
+@@ -2711,13 +2711,13 @@ int tioclinux(struct tty_struct *tty, un
+ * related to the kernel should not use this.
+ */
+ data = vt_get_shift_state();
+- ret = __put_user(data, p);
++ ret = put_user(data, p);
+ break;
+ case TIOCL_GETMOUSEREPORTING:
+ console_lock(); /* May be overkill */
+ data = mouse_reporting();
+ console_unlock();
+- ret = __put_user(data, p);
++ ret = put_user(data, p);
+ break;
+ case TIOCL_SETVESABLANK:
+ console_lock();
+@@ -2726,7 +2726,7 @@ int tioclinux(struct tty_struct *tty, un
+ break;
+ case TIOCL_GETKMSGREDIRECT:
+ data = vt_get_kmsg_redirect();
+- ret = __put_user(data, p);
++ ret = put_user(data, p);
+ break;
+ case TIOCL_SETKMSGREDIRECT:
+ if (!capable(CAP_SYS_ADMIN)) {
projects / thirdparty / kernel / stable-queue.git / commitdiff
