4.4.108-stable review

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vaibhav Jain <[email protected]>

commit 12841f87b7a8ceb3d54f171660f72a86941bfcb3 upstream.

During an eeh a kernel-oops is reported if no vPHB is allocated to the AFU. This happens as during AFU init, an error in creation of vPHB is a non-fatal error. Hence afu->phb should always be checked for NULL before iterating over it for the virtual AFU pci devices.

This patch fixes the kenel-oops by adding a NULL pointer check for afu->phb before it is dereferenced.

---
 drivers/misc/cxl/pci.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

@@ -1329,6 +1329,9 @@ static pci_ers_result_t cxl_vphb_error_d
 	/* There should only be one entry, but go through the list
 	 * anyway
 	 */
+	if (afu->phb == NULL)
+		return result;
+
 	list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
 		if (!afu_dev->driver)
 			continue;

@@ -1369,6 +1372,10 @@ static pci_ers_result_t cxl_pci_error_de
 		 */
 		for (i = 0; i < adapter->slices; i++) {
 			afu = adapter->afu[i];
+			/*
+			 * Tell the AFU drivers; but we don't care what they
+			 * say, we're going away.
+			 */
 			cxl_vphb_error_detected(afu, state);
 		}
 		return PCI_ERS_RESULT_DISCONNECT;

@@ -1492,6 +1499,9 @@ static pci_ers_result_t cxl_pci_slot_res
 		if (cxl_afu_select_best_mode(afu))
 			goto err;
 
+		if (afu->phb == NULL)
+			continue;
+
 		cxl_pci_vphb_reconfigure(afu);
 
 		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {

@@ -1556,6 +1566,9 @@ static void cxl_pci_resume(struct pci_de
 	for (i = 0; i < adapter->slices; i++) {
 		afu = adapter->afu[i];
 
+		if (afu->phb == NULL)
+			continue;
+
 		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
 			if (afu_dev->driver && afu_dev->driver->err_handler &&
 			    afu_dev->driver->err_handler->resume)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 060a402a1ddb551455ee410de2eadd3349f2801b upstream.

This adds helpers for each of the four currently-specified INVPCID modes.

---
 arch/x86/include/asm/tlbflush.h |   48 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

@@ -7,6 +7,54 @@
 #include <asm/processor.h>
 #include <asm/special_insns.h>
 
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	u64 desc[2] = { pcid, addr };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Borislav Petkov <[email protected]>

commit e2c7698cd61f11d4077fdb28148b2d31b82ac848 upstream.

So we want to specify the dependency on both @pcid and @addr so that the compiler doesn't reorder accesses to them *before* the TLB flush. But for that to work, we need to express this properly in the inline asm and deref the whole desc array, not the pointer to it. See clwb() for an example.

This fixes the build error on 32-bit:

arch/x86/include/asm/tlbflush.h: In function ‘__invpcid’:
arch/x86/include/asm/tlbflush.h:26:18: error: memory input 0 is not directly addressable

which gcc4.7 caught but 5.x didn't. Which is strange. :-\

---
 arch/x86/include/asm/tlbflush.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -10,7 +10,7 @@
 static inline void __invpcid(unsigned long pcid, unsigned long addr,
 			     unsigned long type)
 {
-	u64 desc[2] = { pcid, addr };
+	struct { u64 d[2]; } desc = { { pcid, addr } };
 
 	/*
 	 * The memory clobber is because the whole point is to invalidate

@@ -22,7 +22,7 @@ static inline void __invpcid(unsigned lo
 	 * invpcid (%rcx), %rax in long mode.
 	 */
 	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (desc) : "memory");
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
 }
 
 #define INVPCID_TYPE_INDIV_ADDR		0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit d12a72b844a49d4162f24cefdab30bed3f86730e upstream.

This adds a chicken bit to turn off INVPCID in case something goes wrong. It's an early_param() because we do TLB flushes before we parse __setup() parameters.

---
 Documentation/kernel-parameters.txt |    2 ++
 arch/x86/kernel/cpu/common.c        |   16 ++++++++++++++++
 2 files changed, 18 insertions(+)

@@ -2519,6 +2519,8 @@ bytes respectively. Such letter suffixes
 
 	nointroute	[IA-64]
 
+	noinvpcid	[X86] Disable the INVPCID cpu feature.
+
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver

@@ -162,6 +162,22 @@ static int __init x86_mpx_setup(char *s)
 }
 __setup("nompx", x86_mpx_setup);
 
+static int __init x86_noinvpcid_setup(char *s)
+{
+	/* noinvpcid doesn't accept parameters */
+	if (s)
+		return -EINVAL;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_INVPCID))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
+	pr_info("noinvpcid: INVPCID feature disabled\n");
+	return 0;
+}
+early_param("noinvpcid", x86_noinvpcid_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit d8bced79af1db6734f66b42064cc773cada2ce99 upstream.

On my Skylake laptop, INVPCID function 2 (flush absolutely everything) takes about 376ns, whereas saving flags, twiddling CR4.PGE to flush global mappings, and restoring flags takes about 539ns.

---
 arch/x86/include/asm/tlbflush.h |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -159,6 +159,15 @@ static inline void __native_flush_tlb_gl
 {
 	unsigned long flags;
 
+	if (static_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ingo Molnar <[email protected]>

commit 8efd755ac2fe262d4c8d5c9bbe054bb67dae93da upstream.

Some architectures (such as Alpha) rely on include/linux/sched.h definitions in their mmu_context.h files.

So include sched.h before mmu_context.h.

---
 mm/mmu_context.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -4,9 +4,9 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/mmu_context.h>
 #include <linux/export.h>
-#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit f98db6013c557c216da5038d9c52045be55cd039 upstream.

By default, this is the same thing as switch_mm().

x86 will override it as an optimization.

---
 include/linux/mmu_context.h |    7 +++++++
 kernel/sched/core.c         |    6 +++---
 2 files changed, 10 insertions(+), 3 deletions(-)

@@ -1,9 +1,16 @@
 #ifndef _LINUX_MMU_CONTEXT_H
 #define _LINUX_MMU_CONTEXT_H
 
+#include <asm/mmu_context.h>
+
 struct mm_struct;
 
 void use_mm(struct mm_struct *mm);
 void unuse_mm(struct mm_struct *mm);
 
+/* Architectures that care about IRQ state in switch_mm can override this. */
+#ifndef switch_mm_irqs_off
+# define switch_mm_irqs_off switch_mm
+#endif
+
 #endif

@@ -32,7 +32,7 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
-#include <asm/mmu_context.h>
+#include <linux/mmu_context.h>
 #include <linux/interrupt.h>
 #include <linux/capability.h>
 #include <linux/completion.h>

@@ -2708,7 +2708,7 @@ context_switch(struct rq *rq, struct tas
 		atomic_inc(&oldmm->mm_count);
 		enter_lazy_tlb(oldmm, next);
 	} else
-		switch_mm(oldmm, mm, next);
+		switch_mm_irqs_off(oldmm, mm, next);
 
 	if (!prev->mm) {
 		prev->active_mm = NULL;

@@ -5206,7 +5206,7 @@ void idle_task_exit(void)
 	BUG_ON(cpu_online(smp_processor_id()));
 
 	if (mm != &init_mm) {
-		switch_mm(mm, &init_mm, current);
+		switch_mm_irqs_off(mm, &init_mm, current);
 		finish_arch_post_lock_switch();
 	}
 	mmdrop(mm);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 078194f8e9fe3cf54c8fd8bded48a1db5bd8eb8a upstream.

Potential races between switch_mm() and TLB-flush or LDT-flush IPIs could be very messy. AFAICT the code is currently okay, whether by accident or by careful design, but enabling PCID will make it considerably more complicated and will no longer be obviously safe.

Fix it with a big hammer: run switch_mm() with IRQs off.

To avoid a performance hit in the scheduler, we take advantage of our knowledge that the scheduler already has IRQs disabled when it calls switch_mm().

---
 arch/x86/include/asm/mmu_context.h |    3 +++
 arch/x86/mm/tlb.c                  |   10 ++++++++++
 2 files changed, 13 insertions(+)

@@ -107,6 +107,9 @@ static inline void enter_lazy_tlb(struct
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		      struct task_struct *tsk);
 
+extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			       struct task_struct *tsk);
+#define switch_mm_irqs_off switch_mm_irqs_off
 
 #define activate_mm(prev, next)			\
 do {						\

@@ -64,6 +64,16 @@ EXPORT_SYMBOL_GPL(leave_mm);
 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);
+}
+
+void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			struct task_struct *tsk)
+{
 	unsigned cpu = smp_processor_id();
 
 	if (likely(prev != next)) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt <[email protected]>

commit ef0491ea17f8019821c7e9c8e801184ecf17f85a upstream.

The introduction of switch_mm_irqs_off() brought back an old bug regarding the use of preempt_enable_no_resched:

As part of:

62b94a08da1b ("sched/preempt: Take away preempt_enable_no_resched() from modules")

the definition of preempt_enable_no_resched() is only available in built-in code, not in loadable modules, so we can't generally use it from header files.

However, the ARM version of finish_arch_post_lock_switch() calls preempt_enable_no_resched() and is defined as a static inline function in asm/mmu_context.h. This in turn means we cannot include asm/mmu_context.h from modules.

With today's tip tree, asm/mmu_context.h gets included from linux/mmu_context.h, which is normally the exact pattern one would expect, but unfortunately, linux/mmu_context.h can be included from the vhost driver that is a loadable module, now causing this compile time error with modular configs:

In file included from ../include/linux/mmu_context.h:4:0,

                   from ../drivers/vhost/vhost.c:18:
  ../arch/arm/include/asm/mmu_context.h: In function 'finish_arch_post_lock_switch':
  ../arch/arm/include/asm/mmu_context.h:88:3: error: implicit declaration of function 'preempt_enable_no_resched' [-Werror=implicit-function-declaration]
     preempt_enable_no_resched();

Andy already tried to fix the bug by including linux/preempt.h from asm/mmu_context.h, but that didn't help. Arnd suggested reordering the header files, which wasn't popular, so let's use this workaround instead:

The finish_arch_post_lock_switch() definition is now also hidden inside of #ifdef MODULE, so we don't see anything referencing preempt_enable_no_resched() from a header file. I've built a few hundred randconfig kernels with this, and did not see any new problems.

---
 arch/arm/include/asm/mmu_context.h |    2 ++
 1 file changed, 2 insertions(+)

@@ -61,6 +61,7 @@ static inline void check_and_switch_cont
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+#ifndef MODULE
 #define finish_arch_post_lock_switch \
 	finish_arch_post_lock_switch
 static inline void finish_arch_post_lock_switch(void)

@@ -82,6 +83,7 @@ static inline void finish_arch_post_lock
 		preempt_enable_no_resched();
 	}
 }
+#endif /* !MODULE */
 
 #endif	/* CONFIG_MMU */
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 252d2a4117bc181b287eeddf848863788da733ae upstream.

idle_task_exit() can be called with IRQs on x86 on and therefore should use switch_mm(), not switch_mm_irqs_off().

This doesn't seem to cause any problems right now, but it will confuse my upcoming TLB flush changes. Nonetheless, I think it should be backported because it's trivial. There won't be any meaningful performance impact because idle_task_exit() is only used when offlining a CPU.

---
 kernel/sched/core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -5206,7 +5206,7 @@ void idle_task_exit(void)
 	BUG_ON(cpu_online(smp_processor_id()));
 
 	if (mm != &init_mm) {
-		switch_mm_irqs_off(mm, &init_mm, current);
+		switch_mm(mm, &init_mm, current);
 		finish_arch_post_lock_switch();
 	}
 	mmdrop(mm);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaroslav Kysela <[email protected]>

[ Upstream commit 04d5466a976b096364a39a63ac264c1b3a5f8fa1 ]

This tested patch adds missing initialization for Line-In/Out PINs for the docking station for HP 820 G2.

---
 sound/pci/hda/patch_realtek.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

@@ -4839,6 +4839,7 @@ enum {
 	ALC286_FIXUP_HP_GPIO_LED,
 	ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
 	ALC280_FIXUP_HP_DOCK_PINS,
+	ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED,
 	ALC280_FIXUP_HP_9480M,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,

@@ -5377,6 +5378,16 @@ static const struct hda_fixup alc269_fix
 		.chained = true,
 		.chain_id = ALC280_FIXUP_HP_GPIO4
 	},
+	[ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1b, 0x21011020 }, /* line-out */
+			{ 0x18, 0x2181103f }, /* line-in */
+			{ },
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HP_GPIO_MIC1_LED
+	},
 	[ALC280_FIXUP_HP_9480M] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc280_fixup_hp_9480m,

@@ -5629,7 +5640,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x2256, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2257, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2259, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
+	SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),

@@ -5794,6 +5805,7 @@ static const struct hda_model_fixup alc2
 	{.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"},
 	{.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"},
 	{.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
+	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
 	{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
 	{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Hiramatsu <[email protected]>

[ Upstream commit 06553175f585b52509c7df37d6f4a50aacb7b211 ]

This is arm port of commit 737480a0d525 ("kprobes/x86:
Fix the return address of multiple kretprobes").

Fix the return address of subsequent kretprobes when multiple kretprobes are set on the same function.

For example:

  # cd /sys/kernel/debug/tracing
  # echo "r:event1 sys_symlink" > kprobe_events
  # echo "r:event2 sys_symlink" >> kprobe_events
  # echo 1 > events/kprobes/enable
  # ln -s /tmp/foo /tmp/bar

(without this patch)

  # cat trace | grep -v ^#
              ln-82    [000] dn.2    68.446525: event1: (kretprobe_trampoline+0x0/0x18 <- SyS_symlink)
              ln-82    [000] dn.2    68.447831: event2: (ret_fast_syscall+0x0/0x1c <- SyS_symlink)

(with this patch)

  # cat trace | grep -v ^#
              ln-81    [000] dn.1    39.463469: event1: (ret_fast_syscall+0x0/0x1c <- SyS_symlink)
              ln-81    [000] dn.1    39.464701: event2: (ret_fast_syscall+0x0/0x1c <- SyS_symlink)

---
 arch/arm/probes/kprobes/core.c |   24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

@@ -433,6 +433,7 @@ static __used __kprobes void *trampoline
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);

@@ -455,14 +456,34 @@ static __used __kprobes void *trampoline
 			/* another task is sharing our hash bucket */
 			continue;
 
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__this_cpu_write(current_kprobe, NULL);
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)

@@ -474,7 +495,6 @@ static __used __kprobes void *trampoline
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: hayeswang <[email protected]>

[ Upstream commit 98d068ab52b4b11d403995ed14154660797e7136 ]

The list rx_done would be initialized when the linking on occurs. Therefore, if a napi is scheduled without any linking on before, the following kernel panic would happen.

	BUG: unable to handle kernel NULL pointer dereference at 000000000000008
	IP: [<ffffffffc085efde>] r8152_poll+0xe1e/0x1210 [r8152]
	PGD 0
	Oops: 0002 [#1] SMP

---
 drivers/net/usb/r8152.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1277,6 +1277,7 @@ static int alloc_all_mem(struct r8152 *t
 	spin_lock_init(&tp->rx_lock);
 	spin_lock_init(&tp->tx_lock);
 	INIT_LIST_HEAD(&tp->tx_free);
+	INIT_LIST_HEAD(&tp->rx_done);
 	skb_queue_head_init(&tp->tx_queue);
 	skb_queue_head_init(&tp->rx_queue);
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Gustavo A. R. Silva" <[email protected]>

[ Upstream commit 1f459262b0e1649a1e5ad12fa4c66eb76c2220ce ]

Remove pointer dereference after free.

Addresses-Coverity-ID: 1091173

---
 drivers/usb/gadget/udc/pch_udc.c |    1 -
 1 file changed, 1 deletion(-)

@@ -1534,7 +1534,6 @@ static void pch_udc_free_dma_chain(struc
 		td = phys_to_virt(addr);
 		addr2 = (dma_addr_t)td->next;
 		pci_pool_free(dev->data_requests, td, addr);
-		td->next = 0x00;
 		addr = addr2;
 	}
 	req->chain_len = 1;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 2c422257550f123049552b39f7af6e3428a60f43 ]

We only allow runtime updates of expectation policies for timeout and maximum number of expectations, otherwise reject the update.

---
 net/netfilter/nfnetlink_cthelper.c |   86 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 84 insertions(+), 2 deletions(-)

@@ -256,6 +256,89 @@ err:
 }
 
 static int
+nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
+				struct nf_conntrack_expect_policy *new_policy,
+				const struct nlattr *attr)
+{
+	struct nlattr *tb[NFCTH_POLICY_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+			       nfnl_cthelper_expect_pol);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFCTH_POLICY_NAME] ||
+	    !tb[NFCTH_POLICY_EXPECT_MAX] ||
+	    !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+		return -EINVAL;
+
+	if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name))
+		return -EBUSY;
+
+	new_policy->max_expected =
+		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+	new_policy->timeout =
+		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
+
+	return 0;
+}
+
+static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
+					   struct nf_conntrack_helper *helper)
+{
+	struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1];
+	struct nf_conntrack_expect_policy *policy;
+	int i, err;
+
+	/* Check first that all policy attributes are well-formed, so we don't
+	 * leave things in inconsistent state on errors.
+	 */
+	for (i = 0; i < helper->expect_class_max + 1; i++) {
+
+		if (!tb[NFCTH_POLICY_SET + i])
+			return -EINVAL;
+
+		err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i],
+						      &new_policy[i],
+						      tb[NFCTH_POLICY_SET + i]);
+		if (err < 0)
+			return err;
+	}
+	/* Now we can safely update them. */
+	for (i = 0; i < helper->expect_class_max + 1; i++) {
+		policy = (struct nf_conntrack_expect_policy *)
+				&helper->expect_policy[i];
+		policy->max_expected = new_policy->max_expected;
+		policy->timeout	= new_policy->timeout;
+	}
+
+	return 0;
+}
+
+static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
+				       const struct nlattr *attr)
+{
+	struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1];
+	unsigned int class_max;
+	int err;
+
+	err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+			       nfnl_cthelper_expect_policy_set);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFCTH_POLICY_SET_NUM])
+		return -EINVAL;
+
+	class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+	if (helper->expect_class_max + 1 != class_max)
+		return -EBUSY;
+
+	return nfnl_cthelper_update_policy_all(tb, helper);
+}
+
+static int
 nfnl_cthelper_update(const struct nlattr * const tb[],
 		     struct nf_conntrack_helper *helper)
 {

@@ -265,8 +348,7 @@ nfnl_cthelper_update(const struct nlattr
 		return -EBUSY;
 
 	if (tb[NFCTH_POLICY]) {
-		ret = nfnl_cthelper_parse_expect_policy(helper,
-							tb[NFCTH_POLICY]);
+		ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
 		if (ret < 0)
 			return ret;
 	}

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit ec4fbd64751de18729eaa816ec69e4b504b5a7a2 ]

Dmitry reported a lockdep splat [1] (false positive) that we can fix by releasing the spinlock before calling icmp_send() from ip_expire()

This is a false positive because sending an ICMP message can not possibly re-enter the IP frag engine.

[1]
[ INFO: possible circular locking dependency detected ] 4.10.0+ #29 Not tainted
-------------------------------------------------------
modprobe/12392 is trying to acquire lock:
(_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>] spin_lock
include/linux/spinlock.h:299 [inline]
(_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>] __netif_tx_lock
include/linux/netdevice.h:3486 [inline]
(_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>]
sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180

but task is already holding lock:
(&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>] spin_lock
include/linux/spinlock.h:299 [inline]
(&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>]
ip_expire+0x51/0x6c0 net/ipv4/ip_fragment.c:201

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&(&q->lock)->rlock){+.-...}:

       validate_chain kernel/locking/lockdep.c:2267 [inline]
       __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
       lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
       __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
       _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
       spin_lock include/linux/spinlock.h:299 [inline]
       ip_defrag+0x3a2/0x4130 net/ipv4/ip_fragment.c:669
       ip_check_defrag+0x4e3/0x8b0 net/ipv4/ip_fragment.c:713
       packet_rcv_fanout+0x282/0x800 net/packet/af_packet.c:1459
       deliver_skb net/core/dev.c:1834 [inline]
       dev_queue_xmit_nit+0x294/0xa90 net/core/dev.c:1890
       xmit_one net/core/dev.c:2903 [inline]
       dev_hard_start_xmit+0x16b/0xab0 net/core/dev.c:2923
       sch_direct_xmit+0x31f/0x6d0 net/sched/sch_generic.c:182
       __dev_xmit_skb net/core/dev.c:3092 [inline]
       __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
       dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
       neigh_resolve_output+0x6b9/0xb10 net/core/neighbour.c:1308
       neigh_output include/net/neighbour.h:478 [inline]
       ip_finish_output2+0x8b8/0x15a0 net/ipv4/ip_output.c:228
       ip_do_fragment+0x1d93/0x2720 net/ipv4/ip_output.c:672
       ip_fragment.constprop.54+0x145/0x200 net/ipv4/ip_output.c:545
       ip_finish_output+0x82d/0xe10 net/ipv4/ip_output.c:314
       NF_HOOK_COND include/linux/netfilter.h:246 [inline]
       ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
       dst_output include/net/dst.h:486 [inline]
       ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
       ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
       ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
       raw_sendmsg+0x26de/0x3a00 net/ipv4/raw.c:655
       inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761
       sock_sendmsg_nosec net/socket.c:633 [inline]
       sock_sendmsg+0xca/0x110 net/socket.c:643
       ___sys_sendmsg+0x4a3/0x9f0 net/socket.c:1985
       __sys_sendmmsg+0x25c/0x750 net/socket.c:2075
       SYSC_sendmmsg net/socket.c:2106 [inline]
       SyS_sendmmsg+0x35/0x60 net/socket.c:2101
       do_syscall_64+0x2e8/0x930 arch/x86/entry/common.c:281
       return_from_SYSCALL_64+0x0/0x7a

-> #0 (_xmit_ETHER#2){+.-...}:

       check_prev_add kernel/locking/lockdep.c:1830 [inline]
       check_prevs_add+0xa8f/0x19f0 kernel/locking/lockdep.c:1940
       validate_chain kernel/locking/lockdep.c:2267 [inline]
       __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
       lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
       __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
       _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
       spin_lock include/linux/spinlock.h:299 [inline]
       __netif_tx_lock include/linux/netdevice.h:3486 [inline]
       sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180
       __dev_xmit_skb net/core/dev.c:3092 [inline]
       __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
       dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
       neigh_hh_output include/net/neighbour.h:468 [inline]
       neigh_output include/net/neighbour.h:476 [inline]
       ip_finish_output2+0xf6c/0x15a0 net/ipv4/ip_output.c:228
       ip_finish_output+0xa29/0xe10 net/ipv4/ip_output.c:316
       NF_HOOK_COND include/linux/netfilter.h:246 [inline]
       ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
       dst_output include/net/dst.h:486 [inline]
       ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
       ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
       ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
       icmp_push_reply+0x372/0x4d0 net/ipv4/icmp.c:394
       icmp_send+0x156c/0x1c80 net/ipv4/icmp.c:754
       ip_expire+0x40e/0x6c0 net/ipv4/ip_fragment.c:239
       call_timer_fn+0x241/0x820 kernel/time/timer.c:1268
       expire_timers kernel/time/timer.c:1307 [inline]
       __run_timers+0x960/0xcf0 kernel/time/timer.c:1601
       run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
       __do_softirq+0x31f/0xbe7 kernel/softirq.c:284
       invoke_softirq kernel/softirq.c:364 [inline]
       irq_exit+0x1cc/0x200 kernel/softirq.c:405
       exiting_irq arch/x86/include/asm/apic.h:657 [inline]
       smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:962
       apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:707
       __read_once_size include/linux/compiler.h:254 [inline]
       atomic_read arch/x86/include/asm/atomic.h:26 [inline]
       rcu_dynticks_curr_cpu_in_eqs kernel/rcu/tree.c:350 [inline]
       __rcu_is_watching kernel/rcu/tree.c:1133 [inline]
       rcu_is_watching+0x83/0x110 kernel/rcu/tree.c:1147
       rcu_read_lock_held+0x87/0xc0 kernel/rcu/update.c:293
       radix_tree_deref_slot include/linux/radix-tree.h:238 [inline]
       filemap_map_pages+0x6d4/0x1570 mm/filemap.c:2335
       do_fault_around mm/memory.c:3231 [inline]
       do_read_fault mm/memory.c:3265 [inline]
       do_fault+0xbd5/0x2080 mm/memory.c:3370
       handle_pte_fault mm/memory.c:3600 [inline]
       __handle_mm_fault+0x1062/0x2cb0 mm/memory.c:3714
       handle_mm_fault+0x1e2/0x480 mm/memory.c:3751
       __do_page_fault+0x4f6/0xb60 arch/x86/mm/fault.c:1397
       do_page_fault+0x54/0x70 arch/x86/mm/fault.c:1460
       page_fault+0x28/0x30 arch/x86/entry/entry_64.S:1011

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&(&q->lock)->rlock);
                               lock(_xmit_ETHER#2);
                               lock(&(&q->lock)->rlock);

lock(_xmit_ETHER#2);

*** DEADLOCK ***

10 locks held by modprobe/12392:
#0: (&mm->mmap_sem){++++++}, at: [<ffffffff81329758>]

__do_page_fault+0x2b8/0xb60 arch/x86/mm/fault.c:1336
 #1:  (rcu_read_lock){......}, at: [<ffffffff8188cab6>]
filemap_map_pages+0x1e6/0x1570 mm/filemap.c:2324
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
spin_lock include/linux/spinlock.h:299 [inline]
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
pte_alloc_one_map mm/memory.c:2944 [inline]
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
alloc_set_pte+0x13b8/0x1b90 mm/memory.c:3072
 #3:  (((&q->timer))){+.-...}, at: [<ffffffff81627e72>]
lockdep_copy_map include/linux/lockdep.h:175 [inline]
 #3:  (((&q->timer))){+.-...}, at: [<ffffffff81627e72>]
call_timer_fn+0x1c2/0x820 kernel/time/timer.c:1258
 #4:  (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>] spin_lock
include/linux/spinlock.h:299 [inline]
 #4:  (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>]
ip_expire+0x51/0x6c0 net/ipv4/ip_fragment.c:201
 #5:  (rcu_read_lock){......}, at: [<ffffffff8389a633>]
ip_expire+0x1b3/0x6c0 net/ipv4/ip_fragment.c:216
 #6:  (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>] spin_trylock

include/linux/spinlock.h:309 [inline]
#6: (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>] icmp_xmit_lock
net/ipv4/icmp.c:219 [inline]
#6: (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>]

icmp_send+0x803/0x1c80 net/ipv4/icmp.c:681
 #7:  (rcu_read_lock_bh){......}, at: [<ffffffff838ab9a1>]
ip_finish_output2+0x2c1/0x15a0 net/ipv4/ip_output.c:198
 #8:  (rcu_read_lock_bh){......}, at: [<ffffffff836d1dee>]
__dev_queue_xmit+0x23e/0x1e60 net/core/dev.c:3324
 #9:  (dev->qdisc_running_key ?: &qdisc_running_key){+.....}, at:
[<ffffffff836d3a27>] dev_queue_xmit+0x17/0x20 net/core/dev.c:3423

stack backtrace:
CPU: 0 PID: 12392 Comm: modprobe Not tainted 4.10.0+ #29
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:52
 print_circular_bug+0x307/0x3b0 kernel/locking/lockdep.c:1204
 check_prev_add kernel/locking/lockdep.c:1830 [inline]
 check_prevs_add+0xa8f/0x19f0 kernel/locking/lockdep.c:1940
 validate_chain kernel/locking/lockdep.c:2267 [inline]
 __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
 lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 __netif_tx_lock include/linux/netdevice.h:3486 [inline]
 sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180
 __dev_xmit_skb net/core/dev.c:3092 [inline]
 __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
 neigh_hh_output include/net/neighbour.h:468 [inline]
 neigh_output include/net/neighbour.h:476 [inline]
 ip_finish_output2+0xf6c/0x15a0 net/ipv4/ip_output.c:228
 ip_finish_output+0xa29/0xe10 net/ipv4/ip_output.c:316
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
 dst_output include/net/dst.h:486 [inline]
 ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
 ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
 ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
 icmp_push_reply+0x372/0x4d0 net/ipv4/icmp.c:394
 icmp_send+0x156c/0x1c80 net/ipv4/icmp.c:754
 ip_expire+0x40e/0x6c0 net/ipv4/ip_fragment.c:239
 call_timer_fn+0x241/0x820 kernel/time/timer.c:1268
 expire_timers kernel/time/timer.c:1307 [inline]
 __run_timers+0x960/0xcf0 kernel/time/timer.c:1601
 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
 __do_softirq+0x31f/0xbe7 kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:657 [inline]
 smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:962
 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:707
RIP: 0010:__read_once_size include/linux/compiler.h:254 [inline]
RIP: 0010:atomic_read arch/x86/include/asm/atomic.h:26 [inline]
RIP: 0010:rcu_dynticks_curr_cpu_in_eqs kernel/rcu/tree.c:350 [inline]
RIP: 0010:__rcu_is_watching kernel/rcu/tree.c:1133 [inline]
RIP: 0010:rcu_is_watching+0x83/0x110 kernel/rcu/tree.c:1147
RSP: 0000:ffff8801c391f120 EFLAGS: 00000a03 ORIG_RAX: ffffffffffffff10
RAX: dffffc0000000000 RBX: ffff8801c391f148 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 000055edd4374000 RDI: ffff8801dbe1ae0c
RBP: ffff8801c391f1a0 R08: 0000000000000002 R09: 0000000000000000
R10: dffffc0000000000 R11: 0000000000000002 R12: 1ffff10038723e25
R13: ffff8801dbe1ae00 R14: ffff8801c391f680 R15: dffffc0000000000
 </IRQ>
 rcu_read_lock_held+0x87/0xc0 kernel/rcu/update.c:293
 radix_tree_deref_slot include/linux/radix-tree.h:238 [inline]
 filemap_map_pages+0x6d4/0x1570 mm/filemap.c:2335
 do_fault_around mm/memory.c:3231 [inline]
 do_read_fault mm/memory.c:3265 [inline]
 do_fault+0xbd5/0x2080 mm/memory.c:3370
 handle_pte_fault mm/memory.c:3600 [inline]
 __handle_mm_fault+0x1062/0x2cb0 mm/memory.c:3714
 handle_mm_fault+0x1e2/0x480 mm/memory.c:3751
 __do_page_fault+0x4f6/0xb60 arch/x86/mm/fault.c:1397
 do_page_fault+0x54/0x70 arch/x86/mm/fault.c:1460
 page_fault+0x28/0x30 arch/x86/entry/entry_64.S:1011
RIP: 0033:0x7f83172f2786
RSP: 002b:00007fffe859ae80 EFLAGS: 00010293
RAX: 000055edd4373040 RBX: 00007f83175111c8 RCX: 000055edd4373238
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00007f8317510970
RBP: 00007fffe859afd0 R08: 0000000000000009 R09: 0000000000000000
R10: 0000000000000064 R11: 0000000000000000 R12: 000055edd4373040
R13: 0000000000000000 R14: 00007fffe859afe8 R15: 0000000000000000

---
 net/ipv4/ip_fragment.c |   25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

@@ -200,6 +200,7 @@ static void ip_expire(unsigned long arg)
 	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
 
+	rcu_read_lock();
 	spin_lock(&qp->q.lock);
 
 	if (qp->q.flags & INET_FRAG_COMPLETE)

@@ -209,7 +210,7 @@ static void ip_expire(unsigned long arg)
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
 	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *head = qp->q.fragments;
+		struct sk_buff *clone, *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
 

@@ -218,32 +219,40 @@ static void ip_expire(unsigned long arg)
 		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
 			goto out;
 
-		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
 		if (!head->dev)
-			goto out_rcu_unlock;
+			goto out;
+
 
 		/* skb has no dst, perform route lookup again */
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
 		if (err)
-			goto out_rcu_unlock;
+			goto out;
 
 		/* Only an end host needs to send an ICMP
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (frag_expire_skip_icmp(qp->user) &&
 		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out_rcu_unlock;
+			goto out;
+
+		clone = skb_clone(head, GFP_ATOMIC);
 
 		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-out_rcu_unlock:
-		rcu_read_unlock();
+		if (clone) {
+			spin_unlock(&qp->q.lock);
+			icmp_send(clone, ICMP_TIME_EXCEEDED,
+				  ICMP_EXC_FRAGTIME, 0);
+			consume_skb(clone);
+			goto out_rcu_unlock;
+		}
 	}
 out:
 	spin_unlock(&qp->q.lock);
+out_rcu_unlock:
+	rcu_read_unlock();
 	ipq_put(qp);
 }
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dick Kennedy <[email protected]>

[ Upstream commit a71e3cdcfce4880a4578915e110e3eaed1659765 ]

lpfc cannot establish connection with targets that send PRLI in P2P configurations.

If lpfc rejects a PRLI that is sent from a target the target will not resend and will reject the PRLI send from the initiator.

[mkp: applied by hand]

---
 drivers/scsi/lpfc/lpfc_els.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -7491,7 +7491,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *p
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLI++;
-		if (vport->port_state < LPFC_DISC_AUTH) {
+		if ((vport->port_state < LPFC_DISC_AUTH) &&
+		    (vport->fc_flag & FC_FABRIC)) {
 			rjt_err = LSRJT_UNABLE_TPC;
 			rjt_exp = LSEXP_NOTHING_MORE;
 			break;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit a2125d02443e9a4e68bcfd9f8004fa23239e8329 ]

The latest gcc-7 snapshot adds a warning to point out that when atk_read_value_old or atk_read_value_new fails, we copy uninitialized data into sensor->cached_value:

drivers/hwmon/asus_atk0110.c: In function 'atk_input_show':
drivers/hwmon/asus_atk0110.c:651:26: error: 'value' may be used uninitialized in this function [-Werror=maybe-uninitialized]

Adding an error check avoids this. All versions of the driver are affected.

---
 drivers/hwmon/asus_atk0110.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -646,6 +646,9 @@ static int atk_read_value(struct atk_sen
 		else
 			err = atk_read_value_new(sensor, value);
 
+		if (err)
+			return err;
+
 		sensor->is_valid = true;
 		sensor->last_updated = jiffies;
 		sensor->cached_value = *value;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mike Looijmans <[email protected]>

[ Upstream commit dbe4d69d252e9e65c6c46826980b77b11a142065 ]

The spec for the pca9546 was missing. This chip is the same as the pca9545 except that it lacks interrupt lines. While the i2c_device_id table mapped the pca9546 to the pca9545 definition the compatible table did not.

---
 drivers/i2c/muxes/i2c-mux-pca954x.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -94,6 +94,10 @@ static const struct chip_desc chips[] =
 		.nchans = 4,
 		.muxtype = pca954x_isswi,
 	},
+	[pca_9546] = {
+		.nchans = 4,
+		.muxtype = pca954x_isswi,
+	},
 	[pca_9547] = {
 		.nchans = 8,
 		.enable = 0x8,

@@ -111,7 +115,7 @@ static const struct i2c_device_id pca954
 	{ "pca9543", pca_9543 },
 	{ "pca9544", pca_9544 },
 	{ "pca9545", pca_9545 },
-	{ "pca9546", pca_9545 },
+	{ "pca9546", pca_9546 },
 	{ "pca9547", pca_9547 },
 	{ "pca9548", pca_9548 },
 	{ }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Stein <[email protected]>

[ Upstream commit 9257821c5a1dc57ef3a37f7cbcebaf548395c964 ]

There is a new clone of the XIN MO arcade controller which has same issue with out of range like the original. This fix will solve the issue where 2 directions on the joystick are not recognized by the new THT 2P arcade controller with device ID 0x75e1. In details the new device ID is added the hid-id list and the hid-xinmo source code.

---
 drivers/hid/hid-core.c  |    1 +
 drivers/hid/hid-ids.h   |    1 +
 drivers/hid/hid-xinmo.c |    1 +
 3 files changed, 3 insertions(+)

@@ -2053,6 +2053,7 @@ static const struct hid_device_id hid_ha
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_X_TENSIONS, USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZYDACRON, USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL) },

@@ -1021,6 +1021,7 @@
 
 #define USB_VENDOR_ID_XIN_MO			0x16c0
 #define USB_DEVICE_ID_XIN_MO_DUAL_ARCADE	0x05e1
+#define USB_DEVICE_ID_THT_2P_ARCADE		0x75e1
 
 #define USB_VENDOR_ID_XIROKU		0x1477
 #define USB_DEVICE_ID_XIROKU_SPX	0x1006

@@ -46,6 +46,7 @@ static int xinmo_event(struct hid_device
 
 static const struct hid_device_id xinmo_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
 	{ }
 };
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Wiedmann <[email protected]>

[ Upstream commit acd9776b5c45ef02d1a210969a6fcc058afb76e3 ]

With AF_IUCV traffic, the skb passed to hard_start_xmit() has a 14 byte slot at skb->data, intended for an ETH header. qeth_l3_fill_af_iucv_hdr() fills this ETH header... and then immediately moves it to the skb's headroom, where it disappears and is never seen again.

But it's still possible for us to return NETDEV_TX_BUSY after the skb has been modified. Since we didn't get a private copy of the skb, the next time the skb is delivered to hard_start_xmit() it no longer has the expected layout (we moved the ETH header to the headroom, so skb->data now starts at the IUCV_TRANS header). So when qeth_l3_fill_af_iucv_hdr() does another round of rebuilding, the resulting qeth header ends up all wrong. On transmission, the buffer is then rejected by the HiperSockets device with SBALF15 = x'04'.
When this error is passed back to af_iucv as TX_NOTIFY_UNREACHABLE, it tears down the offending socket.

As the ETH header for AF_IUCV serves no purpose, just align the code to what we do for IP traffic on L3 HiperSockets: keep the ETH header at skb->data, and pass down data_offset = ETH_HLEN to qeth_fill_buffer(). When mapping the payload into the SBAL elements, the ETH header is then stripped off. This avoids the skb manipulations in qeth_l3_fill_af_iucv_hdr(), and any buffer re-entering hard_start_xmit() after NETDEV_TX_BUSY is now processed properly.

---
 drivers/s390/net/qeth_l3_main.c |   15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

@@ -2680,17 +2680,13 @@ static void qeth_l3_fill_af_iucv_hdr(str
 	char daddr[16];
 	struct af_iucv_trans_hdr *iucv_hdr;
 
-	skb_pull(skb, 14);
-	card->dev->header_ops->create(skb, card->dev, 0,
-				      card->dev->dev_addr, card->dev->dev_addr,
-				      card->dev->addr_len);
-	skb_pull(skb, 14);
-	iucv_hdr = (struct af_iucv_trans_hdr *)skb->data;
 	memset(hdr, 0, sizeof(struct qeth_hdr));
 	hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
 	hdr->hdr.l3.ext_flags = 0;
-	hdr->hdr.l3.length = skb->len;
+	hdr->hdr.l3.length = skb->len - ETH_HLEN;
 	hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+
+	iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
 	memset(daddr, 0, sizeof(daddr));
 	daddr[0] = 0xfe;
 	daddr[1] = 0x80;

@@ -2873,10 +2869,7 @@ static int qeth_l3_hard_start_xmit(struc
 	if ((card->info.type == QETH_CARD_TYPE_IQD) && (!large_send) &&
 	    (skb_shinfo(skb)->nr_frags == 0)) {
 		new_skb = skb;
-		if (new_skb->protocol == ETH_P_AF_IUCV)
-			data_offset = 0;
-		else
-			data_offset = ETH_HLEN;
+		data_offset = ETH_HLEN;
 		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 		if (!hdr)
 			goto tx_drop;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit a5af83925363eb85d467933e3d6ec5a87001eb7c ]

The latest gcc-7 snapshot warns about bfa_ioc_send_enable/bfa_ioc_send_disable writing undefined values into the hardware registers:

drivers/net/ethernet/brocade/bna/bfa_ioc.c: In function 'bfa_iocpf_sm_disabling_entry':
arch/arm/include/asm/io.h:109:22: error: '*((void *)&disable_req+4)' is used uninitialized in this function [-Werror=uninitialized] arch/arm/include/asm/io.h:109:22: error: '*((void *)&disable_req+8)' is used uninitialized in this function [-Werror=uninitialized]

The two functions look like they should do the same thing, but only one of them initializes the time stamp and clscode field. The fact that we only get a warning for one of the two functions seems to be arbitrary, based on the inlining decisions in the compiler.

To address this, I'm making both functions do the same thing:

- set the clscode from the ioc structure in both
- set the time stamp from ktime_get_real_seconds (which also avoids the signed-integer overflow in 2038 and extends the well-defined behavior until 2106).
- zero-fill the reserved field

---
 drivers/net/ethernet/brocade/bna/bfa_ioc.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

@@ -1930,13 +1930,13 @@ static void
 bfa_ioc_send_enable(struct bfa_ioc *ioc)
 {
 	struct bfi_ioc_ctrl_req enable_req;
-	struct timeval tv;
 
 	bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ,
 		    bfa_ioc_portid(ioc));
 	enable_req.clscode = htons(ioc->clscode);
-	do_gettimeofday(&tv);
-	enable_req.tv_sec = ntohl(tv.tv_sec);
+	enable_req.rsvd = htons(0);
+	/* overflow in 2106 */
+	enable_req.tv_sec = ntohl(ktime_get_real_seconds());
 	bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req));
 }
 

@@ -1947,6 +1947,10 @@ bfa_ioc_send_disable(struct bfa_ioc *ioc
 
 	bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ,
 		    bfa_ioc_portid(ioc));
+	disable_req.clscode = htons(ioc->clscode);
+	disable_req.rsvd = htons(0);
+	/* overflow in 2106 */
+	disable_req.tv_sec = ntohl(ktime_get_real_seconds());
 	bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req));
 }
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Duyck <[email protected]>

[ Upstream commit 95f255211396958c718aef8c45e3923b5211ea7b ]

This change basically codifies what I think was already the limitations on the busy_poll and busy_read sysctl interfaces. We weren't checking the lower bounds and as such could input negative values. The behavior when that was used was dependent on the architecture. In order to prevent any issues with that I am just disabling support for values less than 0 since this way we don't have to worry about any odd behaviors.

By limiting the sysctl values this way it also makes it consistent with how we handle the SO_BUSY_POLL socket option since the value appears to be reported as a signed integer value and negative values are rejected.

---
 net/core/sysctl_net_core.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -360,14 +360,16 @@ static struct ctl_table net_core_table[]
 		.data		= &sysctl_net_busy_poll,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 	{
 		.procname	= "busy_read",
 		.data		= &sysctl_net_busy_read,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 #endif
 #ifdef CONFIG_NET_SCHED

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Duyck <[email protected]>

[ Upstream commit 13a8cd191a2b470cfd435b3b57dbd21aa65ff78c ]

When testing the epoll w/ busy poll code I found that I could get into a state where the i40e driver had q_vectors w/ active NAPI that had no rings. This was resulting in a divide by zero error. To correct it I am updating the driver code so that we only support NAPI on q_vectors that have 1 or more rings allocated to them.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

@@ -4201,8 +4201,12 @@ static void i40e_napi_enable_all(struct
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_enable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_enable(&q_vector->napi);
+	}
 }
 
 /**

@@ -4216,8 +4220,12 @@ static void i40e_napi_disable_all(struct
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_disable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_disable(&q_vector->napi);
+	}
 }
 
 /**

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liping Zhang <[email protected]>

[ Upstream commit 83d90219a5df8d950855ce73229a97b63605c317 ]

The nf_ct_helper_hash table is protected by nf_ct_helper_mutex, while nfct_helper operation is protected by nfnl_lock(NFNL_SUBSYS_CTHELPER). So it's possible that one CPU is walking the nf_ct_helper_hash for cthelper add/get/del, another cpu is doing nf_conntrack_helpers_unregister at the same time. This is dangrous, and may cause use after free error.

Note, delete operation will flush all cthelpers added via nfnetlink, so using rcu to do protect is not easy.

Now introduce a dummy list to record all the cthelpers added via nfnetlink, then we can walk the dummy list instead of walking the nf_ct_helper_hash. Also, keep nfnl_cthelper_dump_table unchanged, it may be invoked without nfnl_lock(NFNL_SUBSYS_CTHELPER) held.

---
 net/netfilter/nfnetlink_cthelper.c |  185 +++++++++++++++++--------------------
 1 file changed, 85 insertions(+), 100 deletions(-)

@@ -32,6 +32,13 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <[email protected]>");
 MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
 
+struct nfnl_cthelper {
+	struct list_head		list;
+	struct nf_conntrack_helper	helper;
+};
+
+static LIST_HEAD(nfnl_cthelper_list);
+
 static int
 nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
 			struct nf_conn *ct, enum ip_conntrack_info ctinfo)

@@ -205,14 +212,16 @@ nfnl_cthelper_create(const struct nlattr
 		     struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_helper *helper;
+	struct nfnl_cthelper *nfcth;
 	int ret;
 
 	if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
 		return -EINVAL;
 
-	helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
-	if (helper == NULL)
+	nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL);
+	if (nfcth == NULL)
 		return -ENOMEM;
+	helper = &nfcth->helper;
 
 	ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
 	if (ret < 0)

@@ -249,11 +258,12 @@ nfnl_cthelper_create(const struct nlattr
 	if (ret < 0)
 		goto err2;
 
+	list_add_tail(&nfcth->list, &nfnl_cthelper_list);
 	return 0;
 err2:
 	kfree(helper->expect_policy);
 err1:
-	kfree(helper);
+	kfree(nfcth);
 	return ret;
 }
 

@@ -379,7 +389,8 @@ nfnl_cthelper_new(struct sock *nfnl, str
 	const char *helper_name;
 	struct nf_conntrack_helper *cur, *helper = NULL;
 	struct nf_conntrack_tuple tuple;
-	int ret = 0, i;
+	struct nfnl_cthelper *nlcth;
+	int ret = 0;
 
 	if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
 		return -EINVAL;

@@ -390,31 +401,22 @@ nfnl_cthelper_new(struct sock *nfnl, str
 	if (ret < 0)
 		return ret;
 
-	rcu_read_lock();
-	for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
-		hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
 
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+		if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
 
-			if (strncmp(cur->name, helper_name,
-					NF_CT_HELPER_NAME_LEN) != 0)
-				continue;
+		if ((tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
 
-			if ((tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
 
-			if (nlh->nlmsg_flags & NLM_F_EXCL) {
-				ret = -EEXIST;
-				goto err;
-			}
-			helper = cur;
-			break;
-		}
+		helper = cur;
+		break;
 	}
-	rcu_read_unlock();
 
 	if (helper == NULL)
 		ret = nfnl_cthelper_create(tb, &tuple);

@@ -422,9 +424,6 @@ nfnl_cthelper_new(struct sock *nfnl, str
 		ret = nfnl_cthelper_update(tb, helper);
 
 	return ret;
-err:
-	rcu_read_unlock();
-	return ret;
 }
 
 static int

@@ -588,11 +587,12 @@ static int
 nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb,
 		  const struct nlmsghdr *nlh, const struct nlattr * const tb[])
 {
-	int ret = -ENOENT, i;
+	int ret = -ENOENT;
 	struct nf_conntrack_helper *cur;
 	struct sk_buff *skb2;
 	char *helper_name = NULL;
 	struct nf_conntrack_tuple tuple;
+	struct nfnl_cthelper *nlcth;
 	bool tuple_set = false;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {

@@ -613,45 +613,39 @@ nfnl_cthelper_get(struct sock *nfnl, str
 		tuple_set = true;
 	}
 
-	for (i = 0; i < nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
-
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
-
-			if (helper_name && strncmp(cur->name, helper_name,
-						NF_CT_HELPER_NAME_LEN) != 0) {
-				continue;
-			}
-			if (tuple_set &&
-			    (tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
-
-			skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-			if (skb2 == NULL) {
-				ret = -ENOMEM;
-				break;
-			}
+	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
+		if (helper_name &&
+		    strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
+
+		if (tuple_set &&
+		    (tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
+
+		skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+		if (skb2 == NULL) {
+			ret = -ENOMEM;
+			break;
+		}
 
-			ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
-						nlh->nlmsg_seq,
-						NFNL_MSG_TYPE(nlh->nlmsg_type),
-						NFNL_MSG_CTHELPER_NEW, cur);
-			if (ret <= 0) {
-				kfree_skb(skb2);
-				break;
-			}
+		ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
+					      nlh->nlmsg_seq,
+					      NFNL_MSG_TYPE(nlh->nlmsg_type),
+					      NFNL_MSG_CTHELPER_NEW, cur);
+		if (ret <= 0) {
+			kfree_skb(skb2);
+			break;
+		}
 
-			ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
-						MSG_DONTWAIT);
-			if (ret > 0)
-				ret = 0;
+		ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+				      MSG_DONTWAIT);
+		if (ret > 0)
+			ret = 0;
 
-			/* this avoids a loop in nfnetlink. */
-			return ret == -EAGAIN ? -ENOBUFS : ret;
-		}
+		/* this avoids a loop in nfnetlink. */
+		return ret == -EAGAIN ? -ENOBUFS : ret;
 	}
 	return ret;
 }

@@ -662,10 +656,10 @@ nfnl_cthelper_del(struct sock *nfnl, str
 {
 	char *helper_name = NULL;
 	struct nf_conntrack_helper *cur;
-	struct hlist_node *tmp;
 	struct nf_conntrack_tuple tuple;
 	bool tuple_set = false, found = false;
-	int i, j = 0, ret;
+	struct nfnl_cthelper *nlcth, *n;
+	int j = 0, ret;
 
 	if (tb[NFCTH_NAME])
 		helper_name = nla_data(tb[NFCTH_NAME]);

@@ -678,30 +672,27 @@ nfnl_cthelper_del(struct sock *nfnl, str
 		tuple_set = true;
 	}
 
-	for (i = 0; i < nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
-								hnode) {
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
-
-			j++;
-
-			if (helper_name && strncmp(cur->name, helper_name,
-						NF_CT_HELPER_NAME_LEN) != 0) {
-				continue;
-			}
-			if (tuple_set &&
-			    (tuple.src.l3num != cur->tuple.src.l3num ||
-			     tuple.dst.protonum != cur->tuple.dst.protonum))
-				continue;
+	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
+		j++;
+
+		if (helper_name &&
+		    strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+			continue;
+
+		if (tuple_set &&
+		    (tuple.src.l3num != cur->tuple.src.l3num ||
+		     tuple.dst.protonum != cur->tuple.dst.protonum))
+			continue;
+
+		found = true;
+		nf_conntrack_helper_unregister(cur);
+		kfree(cur->expect_policy);
 
-			found = true;
-			nf_conntrack_helper_unregister(cur);
-			kfree(cur->expect_policy);
-			kfree(cur);
-		}
+		list_del(&nlcth->list);
+		kfree(nlcth);
 	}
+
 	/* Make sure we return success if we flush and there is no helpers */
 	return (found || j == 0) ? 0 : -ENOENT;
 }

@@ -750,22 +741,16 @@ err_out:
 static void __exit nfnl_cthelper_exit(void)
 {
 	struct nf_conntrack_helper *cur;
-	struct hlist_node *tmp;
-	int i;
+	struct nfnl_cthelper *nlcth, *n;
 
 	nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
 
-	for (i=0; i<nf_ct_helper_hsize; i++) {
-		hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
-									hnode) {
-			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
-				continue;
+	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+		cur = &nlcth->helper;
 
-			nf_conntrack_helper_unregister(cur);
-			kfree(cur->expect_policy);
-			kfree(cur);
-		}
+		nf_conntrack_helper_unregister(cur);
+		kfree(cur->expect_policy);
+		kfree(nlcth);
 	}
 }
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gao Feng <[email protected]>

[ Upstream commit 75c689dca98851d65ef5a27e5ce26b625b68751c ]

In the commit 93557f53e1fb ("netfilter: nf_conntrack: nf_conntrack snmp helper"), the snmp_helper is replaced by nf_nat_snmp_hook. So the snmp_helper is never registered. But it still tries to unregister the snmp_helper, it could cause the panic.

Now remove the useless snmp_helper and the unregister call in the error handler.

---
 net/ipv4/netfilter/nf_nat_snmp_basic.c |   19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

@@ -1260,16 +1260,6 @@ static const struct nf_conntrack_expect_
 	.timeout	= 180,
 };
 
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
-	.me			= THIS_MODULE,
-	.help			= help,
-	.expect_policy		= &snmp_exp_policy,
-	.name			= "snmp",
-	.tuple.src.l3num	= AF_INET,
-	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-};
-
 static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
 	.me			= THIS_MODULE,
 	.help			= help,

@@ -1288,17 +1278,10 @@ static struct nf_conntrack_helper snmp_t
 
 static int __init nf_nat_snmp_basic_init(void)
 {
-	int ret = 0;
-
 	BUG_ON(nf_nat_snmp_hook != NULL);
 	RCU_INIT_POINTER(nf_nat_snmp_hook, help);
 
-	ret = nf_conntrack_helper_register(&snmp_trap_helper);
-	if (ret < 0) {
-		nf_conntrack_helper_unregister(&snmp_helper);
-		return ret;
-	}
-	return ret;
+	return nf_conntrack_helper_register(&snmp_trap_helper);
 }
 
 static void __exit nf_nat_snmp_basic_fini(void)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit af109a2cf6a9a6271fa420ae2d64d72d86c92b7d ]

gcc-7 points out that the AVMB1_ADDCARD ioctl results in an unintialized value ending up in the cardnr parameter:

drivers/isdn/capi/kcapi.c: In function 'old_capi_manufacturer':
drivers/isdn/capi/kcapi.c:1042:24: error: 'cdef.cardnr' may be used uninitialized in this function [-Werror=maybe-uninitialized]
cparams.cardnr = cdef.cardnr;

This has been broken since before the start of the git history, so either the value is not used for anything important, or the ioctl command doesn't get called in practice.

Setting the cardnr to zero avoids the warning and makes sure we have consistent behavior.

---
 drivers/isdn/capi/kcapi.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1032,6 +1032,7 @@ static int old_capi_manufacturer(unsigne
 						     sizeof(avmb1_carddef))))
 				return -EFAULT;
 			cdef.cardtype = AVM_CARDTYPE_B1;
+			cdef.cardnr = 0;
 		} else {
 			if ((retval = copy_from_user(&cdef, data,
 						     sizeof(avmb1_extcarddef))))

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vaidyanathan Srinivasan <[email protected]>

[ Upstream commit 293d264f13cbde328d5477f49e3103edbc1dc191 ]

drv->cpumask defaults to cpu_possible_mask in __cpuidle_driver_init(). On PowerNV platform cpu_present could be less than cpu_possible in cases where firmware detects the cpu, but it is not available to the OS. When CONFIG_HOTPLUG_CPU=n, such cpus are not hotplugable at runtime and hence we skip creating cpu_device.

This breaks cpuidle on powernv where register_cpu() is not called for cpus in cpu_possible_mask that cannot be hot-added at runtime.

Trying cpuidle_register_device() on cpu without cpu_device will cause crash like this:

cpu 0xf: Vector: 380 (Data SLB Access) at [c000000ff1503490]

    pc: c00000000022c8bc: string+0x34/0x60
    lr: c00000000022ed78: vsnprintf+0x284/0x42c
    sp: c000000ff1503710

msr: 9000000000009033
dar: 6000000060000000
current = 0xc000000ff1480000
paca = 0xc00000000fe82d00 softe: 0 irq_happened: 0x01
pid = 1, comm = swapper/8
Linux version 4.11.0-rc2 (sv@sagarika) (gcc version 4.9.4 (Buildroot 2017.02-00004-gc28573e) ) #15 SMP Fri Mar 17 19:32:02 IST 2017 enter ? for help
[link register ] c00000000022ed78 vsnprintf+0x284/0x42c
[c000000ff1503710] c00000000022ebb8 vsnprintf+0xc4/0x42c (unreliable) [c000000ff1503800] c00000000022ef40 vscnprintf+0x20/0x44 [c000000ff1503830] c0000000000ab61c vprintk_emit+0x94/0x2cc [c000000ff15038a0] c0000000000acc9c vprintk_func+0x60/0x74 [c000000ff15038c0] c000000000619694 printk+0x38/0x4c [c000000ff15038e0] c000000000224950 kobject_get+0x40/0x60 [c000000ff1503950] c00000000022507c kobject_add_internal+0x60/0x2c4 [c000000ff15039e0] c000000000225350 kobject_init_and_add+0x70/0x78 [c000000ff1503a60] c00000000053c288 cpuidle_add_sysfs+0x9c/0xe0 [c000000ff1503ae0] c00000000053aeac cpuidle_register_device+0xd4/0x12c [c000000ff1503b30] c00000000053b108 cpuidle_register+0x98/0xcc [c000000ff1503bc0] c00000000085eaf0 powernv_processor_idle_init+0x140/0x1e0 [c000000ff1503c60] c00000000000cd60 do_one_initcall+0xc0/0x15c [c000000ff1503d20] c000000000833e84 kernel_init_freeable+0x1a0/0x25c [c000000ff1503dc0] c00000000000d478 kernel_init+0x24/0x12c [c000000ff1503e30] c00000000000b564 ret_from_kernel_thread+0x5c/0x78

This patch fixes the bug by passing correct cpumask from powernv-cpuidle driver.

---
 drivers/cpuidle/cpuidle-powernv.c |   18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

@@ -160,6 +160,24 @@ static int powernv_cpuidle_driver_init(v
 		drv->state_count += 1;
 	}
 
+	/*
+	 * On the PowerNV platform cpu_present may be less than cpu_possible in
+	 * cases when firmware detects the CPU, but it is not available to the
+	 * OS.  If CONFIG_HOTPLUG_CPU=n, then such CPUs are not hotplugable at
+	 * run time and hence cpu_devices are not created for those CPUs by the
+	 * generic topology_init().
+	 *
+	 * drv->cpumask defaults to cpu_possible_mask in
+	 * __cpuidle_driver_init().  This breaks cpuidle on PowerNV where
+	 * cpu_devices are not created for CPUs in cpu_possible_mask that
+	 * cannot be hot-added later at run time.
+	 *
+	 * Trying cpuidle_register_device() on a CPU without a cpu_device is
+	 * incorrect, so pass a correct CPU mask to the generic cpuidle driver.
+	 */
+
+	drv->cpumask = (struct cpumask *)cpu_present_mask;
+
 	return 0;
 }
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christian Lamparter <[email protected]>

[ Upstream commit 778f81d6cdb7d25360f082ac0384d5103f04eca5 ]

If crypto4xx is used in conjunction with dm-crypt, the available ring buffer elements are not enough to handle the load properly.

On an aes-cbc-essiv:sha256 encrypted swap partition the read performance is abyssal: (tested with hdparm -t)

/dev/mapper/swap_crypt:
Timing buffered disk reads: 14 MB in 3.68 seconds = 3.81 MB/sec

The patch increases both PPC4XX_NUM_SD and PPC4XX_NUM_PD to 256. This improves the performance considerably:

/dev/mapper/swap_crypt:
Timing buffered disk reads: 104 MB in 3.03 seconds = 34.31 MB/sec

Furthermore, PPC4XX_LAST_SD, PPC4XX_LAST_GD and PPC4XX_LAST_PD can be easily calculated from their respective PPC4XX_NUM_* constant.

---
 drivers/crypto/amcc/crypto4xx_core.h |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -32,12 +32,12 @@
 #define PPC405EX_CE_RESET                       0x00000008
 
 #define CRYPTO4XX_CRYPTO_PRIORITY		300
-#define PPC4XX_LAST_PD				63
-#define PPC4XX_NUM_PD				64
-#define PPC4XX_LAST_GD				1023
+#define PPC4XX_NUM_PD				256
+#define PPC4XX_LAST_PD				(PPC4XX_NUM_PD - 1)
 #define PPC4XX_NUM_GD				1024
-#define PPC4XX_LAST_SD				63
-#define PPC4XX_NUM_SD				64
+#define PPC4XX_LAST_GD				(PPC4XX_NUM_GD - 1)
+#define PPC4XX_NUM_SD				256
+#define PPC4XX_LAST_SD				(PPC4XX_NUM_SD - 1)
 #define PPC4XX_SD_BUFFER_SIZE			2048
 
 #define PD_ENTRY_INUSE				1

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Russell King <[email protected]>

[ Upstream commit 5b64a2965dfdfca8039e93303c64e2b15c19ff0c ]

On some platforms, the interrupt for the PL031 is optional. Avoid trying to claim the interrupt if it's not specified.

---
 drivers/rtc/rtc-pl031.c |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

@@ -308,7 +308,8 @@ static int pl031_remove(struct amba_devi
 
 	dev_pm_clear_wake_irq(&adev->dev);
 	device_init_wakeup(&adev->dev, false);
-	free_irq(adev->irq[0], ldata);
+	if (adev->irq[0])
+		free_irq(adev->irq[0], ldata);
 	rtc_device_unregister(ldata->rtc);
 	iounmap(ldata->base);
 	kfree(ldata);

@@ -381,12 +382,13 @@ static int pl031_probe(struct amba_devic
 		goto out_no_rtc;
 	}
 
-	if (request_irq(adev->irq[0], pl031_interrupt,
-			vendor->irqflags, "rtc-pl031", ldata)) {
-		ret = -EIO;
-		goto out_no_irq;
+	if (adev->irq[0]) {
+		ret = request_irq(adev->irq[0], pl031_interrupt,
+				  vendor->irqflags, "rtc-pl031", ldata);
+		if (ret)
+			goto out_no_irq;
+		dev_pm_set_wake_irq(&adev->dev, adev->irq[0]);
 	}
-	dev_pm_set_wake_irq(&adev->dev, adev->irq[0]);
 	return 0;
 
 out_no_irq:

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dan Murphy <[email protected]>

[ Upstream commit fc7556877d1748ac00958822a0a3bba1d4bd9e0d ]

Change the return error code to EINVAL if the MAC address is not valid in the set_wol function.

---
 drivers/net/phy/at803x.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -105,7 +105,7 @@ static int at803x_set_wol(struct phy_dev
 		mac = (const u8 *) ndev->dev_addr;
 
 		if (!is_valid_ether_addr(mac))
-			return -EFAULT;
+			return -EINVAL;
 
 		for (i = 0; i < 3; i++) {
 			phy_write(phydev, AT803X_MMD_ACCESS_CONTROL,

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Varun Prakash <[email protected]>

[ Upstream commit 9b3a081fb62158b50bcc90522ca2423017544367 ]

In case of connection reset Tx skb queue can have some skbs which are not transmitted so purge Tx skb queue in release_offload_resources() to avoid skb leak.

---
 drivers/scsi/cxgbi/cxgb4i/cxgb4i.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1339,6 +1339,7 @@ static void release_offload_resources(st
 		csk, csk->state, csk->flags, csk->tid);
 
 	cxgbi_sock_free_cpl_skbs(csk);
+	cxgbi_sock_purge_write_queue(csk);
 	if (csk->wr_cred != csk->wr_max_cred) {
 		cxgbi_sock_purge_wr_queue(csk);
 		cxgbi_sock_reset_wr_list(csk);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sreekanth Reddy <[email protected]>

[ Upstream commit 2ce9a3645299ba1752873d333d73f67620f4550b ]

Whenever an I/O for a RAID volume fails with IOCStatus MPI2_IOCSTATUS_SCSI_IOC_TERMINATED and SCSIStatus equal to (MPI2_SCSI_STATE_TERMINATED | MPI2_SCSI_STATE_NO_SCSI_STATUS) then return the I/O to SCSI midlayer with "DID_RESET" (i.e. retry the IO infinite times) set in the host byte.

Previously, the driver was completing the I/O with "DID_SOFT_ERROR" which causes the I/O to be quickly retried. However, firmware needed more time and hence I/Os were failing.

---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -4588,6 +4588,11 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *i
 		} else if (log_info == VIRTUAL_IO_FAILED_RETRY) {
 			scmd->result = DID_RESET << 16;
 			break;
+		} else if ((scmd->device->channel == RAID_CHANNEL) &&
+		   (scsi_state == (MPI2_SCSI_STATE_TERMINATED |
+		   MPI2_SCSI_STATE_NO_SCSI_STATUS))) {
+			scmd->result = DID_RESET << 16;
+			break;
 		}
 		scmd->result = DID_SOFT_ERROR << 16;
 		break;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit 18eb86362a52f0af933cc0fd5e37027317eb2d1c ]

Check memory allocation failures and return -ENOMEM in such cases, as already done for other memory allocations in this function.

This avoids NULL pointers dereference.

---
 drivers/net/ethernet/intel/igb/igb_main.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -3005,6 +3005,8 @@ static int igb_sw_init(struct igb_adapte
 	/* Setup and initialize a copy of the hw vlan table array */
 	adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32),
 				       GFP_ATOMIC);
+	if (!adapter->shadow_vfta)
+		return -ENOMEM;
 
 	/* This call may decrease the number of queues */
 	if (igb_init_interrupt_scheme(adapter, true)) {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gabriele Paoloni <[email protected]>

[ Upstream commit 86acc790717fb60fb51ea3095084e331d8711c74 ]

Previously, if an non-fatal error was reported by an endpoint, we called report_error_detected() for the endpoint, every sibling on the bus, and their descendents. If any of them did not implement the .error_detected() method, do_recovery() failed, leaving all these devices unrecovered.

For example, the system described in the bugzilla below has two devices:

0000:74:02.0 [19e5:a230] SAS controller, driver has .error_detected() 0000:74:03.0 [19e5:a235] SATA controller, driver lacks .error_detected()

When a device such as 74:02.0 reported a non-fatal error, do_recovery() failed because 74:03.0 lacked an .error_detected() method. But per PCIe r3.1, sec 6.2.2.2.2, such an error does not compromise the Link and does not affect 74:03.0:

Non-fatal errors are uncorrectable errors which cause a particular transaction to be unreliable but the Link is otherwise fully functional. Isolating Non-fatal from Fatal errors provides Requester/Receiver logic in a device or system management software the opportunity to recover from the error without resetting the components on the Link and disturbing other transactions in progress. Devices not associated with the transaction in error are not impacted by the error.

Report non-fatal errors only to the endpoint that reported them. We really want to check for AER_NONFATAL here, but the current code structure doesn't allow that. Looking for pci_channel_io_normal is the best we can do now.

---
 drivers/pci/pcie/aer/aerdrv_core.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -388,7 +388,14 @@ static pci_ers_result_t broadcast_error_
 		 * If the error is reported by an end point, we think this
 		 * error is related to the upstream link of the end point.
 		 */
-		pci_walk_bus(dev->bus, cb, &result_data);
+		if (state == pci_channel_io_normal)
+			/*
+			 * the error is non fatal so the bus is ok, just invoke
+			 * the callback for the function that logged the error.
+			 */
+			cb(dev, &result_data);
+		else
+			pci_walk_bus(dev->bus, cb, &result_data);
 	}
 
 	return result_data.result;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dick Kennedy <[email protected]>

[ Upstream commit e8bcf0ae4c0346fdc78ebefe0eefcaa6a6622d38 ]

Local Reject/Invalid RPI errors seen during discovery.

Temporary RPI cleanup was occurring regardless of SLI rev. It's only necessary on SLI-4.

Adjust the test for whether cleanup is necessary.

---
 drivers/scsi/lpfc/lpfc_hbadisc.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -4777,7 +4777,8 @@ lpfc_nlp_remove(struct lpfc_vport *vport
 	lpfc_cancel_retry_delay_tmo(vport, ndlp);
 	if ((ndlp->nlp_flag & NLP_DEFER_RM) &&
 	    !(ndlp->nlp_flag & NLP_REG_LOGIN_SEND) &&
-	    !(ndlp->nlp_flag & NLP_RPI_REGISTERED)) {
+	    !(ndlp->nlp_flag & NLP_RPI_REGISTERED) &&
+	    phba->sli_rev != LPFC_SLI_REV4) {
 		/* For this case we need to cleanup the default rpi
 		 * allocated by the firmware.
 		 */

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hoang Tran <[email protected]>

[ Upstream commit cf5d74b85ef40c202c76d90959db4d850f301b95 ]

With the commit 76174004a0f19785 (tcp: do not slow start when cwnd equals ssthresh), the comparison to the reduced cwnd in tcp_vegas_ssthresh() would under-evaluate the ssthresh.

---
 net/ipv4/tcp_vegas.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
 
 static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 {
-	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
+	return  min(tp->snd_ssthresh, tp->snd_cwnd);
 }
 
 static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Belloni <[email protected]>

[ Upstream commit 74717b28cb32e1ad3c1042cafd76b264c8c0f68d ]

If there is any non expired timer in the queue, the RTC alarm is never set. This is an issue when adding a timer that expires before the next non expired timer.

Ensure the RTC alarm is set in that case.

---
 drivers/rtc/interface.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -764,7 +764,7 @@ static int rtc_timer_enqueue(struct rtc_
 	}
 
 	timerqueue_add(&rtc->timerqueue, &timer->node);
-	if (!next) {
+	if (!next || ktime_before(timer->node.expires, next->expires)) {
 		struct rtc_wkalrm alarm;
 		int err;
 		alarm.time = rtc_ktime_to_tm(timer->node.expires);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksandar Markovic <[email protected]>

commit 409fcace9963c1e8d2cb0f7ac62e8b34d47ef979 upstream.

Fix final phase of <CLASS|MADDF|MSUBF|MAX|MIN|MAXA|MINA>.<D|S> emulation. Provide proper generation of SIGFPE signal and updating debugfs FP exception stats in cases of any exception flags set in preceding phases of emulation.

CLASS.<D|S> instruction may generate "Unimplemented Operation" FP exception. <MADDF|MSUBF>.<D|S> instructions may generate "Inexact", "Unimplemented Operation", "Invalid Operation", "Overflow", and "Underflow" FP exceptions. <MAX|MIN|MAXA|MINA>.<D|S> instructions can generate "Unimplemented Operation" and "Invalid Operation" FP exceptions.

The proper final processing of the cases when any FP exception flag is set is achieved by replacing "break" statement with "goto copcsr" statement. With such solution, this patch brings the final phase of emulation of the above instructions consistent with the one corresponding to the previously implemented emulation of other related FPU instructions (ADD, SUB, etc.).

Patchwork: https://patchwork.linux-mips.org/patch/17581/

---
 arch/mips/math-emu/cp1emu.c |   28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

@@ -1777,7 +1777,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			SPFROMREG(fd, MIPSInst_FD(ir));
 			rv.s = ieee754sp_maddf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmsubf_op: {

@@ -1790,7 +1790,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			SPFROMREG(fd, MIPSInst_FD(ir));
 			rv.s = ieee754sp_msubf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case frint_op: {

@@ -1814,7 +1814,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754sp_2008class(fs);
 			rfmt = w_fmt;
-			break;
+			goto copcsr;
 		}
 
 		case fmin_op: {

@@ -1826,7 +1826,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmin(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmina_op: {

@@ -1838,7 +1838,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmina(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmax_op: {

@@ -1850,7 +1850,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmax(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmaxa_op: {

@@ -1862,7 +1862,7 @@ static int fpu_emu(struct pt_regs *xcp,
 			SPFROMREG(ft, MIPSInst_FT(ir));
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fmaxa(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fabs_op:

@@ -2095,7 +2095,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			DPFROMREG(fd, MIPSInst_FD(ir));
 			rv.d = ieee754dp_maddf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmsubf_op: {

@@ -2108,7 +2108,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			DPFROMREG(fd, MIPSInst_FD(ir));
 			rv.d = ieee754dp_msubf(fd, fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case frint_op: {

@@ -2132,7 +2132,7 @@ copcsr:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754dp_2008class(fs);
 			rfmt = w_fmt;
-			break;
+			goto copcsr;
 		}
 
 		case fmin_op: {

@@ -2144,7 +2144,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmin(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmina_op: {

@@ -2156,7 +2156,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmina(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmax_op: {

@@ -2168,7 +2168,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmax(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fmaxa_op: {

@@ -2180,7 +2180,7 @@ copcsr:
 			DPFROMREG(ft, MIPSInst_FT(ir));
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fmaxa(fs, ft);
-			break;
+			goto copcsr;
 		}
 
 		case fabs_op:

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman <[email protected]>

This reverts commit ffc7565746bb2fc063fc0f484c55ef6d8951a6ee which is commit a0085f2510e8976614ad8f766b209448b385492f upstream.

It causes problems with working systems, as noted by a number of the ChromeOS developers.

---
 drivers/bluetooth/btusb.c |    5 -----
 1 file changed, 5 deletions(-)

@@ -1050,10 +1050,6 @@ static int btusb_open(struct hci_dev *hd
 		return err;
 
 	data->intf->needs_remote_wakeup = 1;
-	/* device specific wakeup source enabled and required for USB
-	 * remote wakeup while host is suspended
-	 */
-	device_wakeup_enable(&data->udev->dev);
 
 	if (test_and_set_bit(BTUSB_INTR_RUNNING, &data->flags))
 		goto done;

@@ -1117,7 +1113,6 @@ static int btusb_close(struct hci_dev *h
 		goto failed;
 
 	data->intf->needs_remote_wakeup = 0;
-	device_wakeup_disable(&data->udev->dev);
 	usb_autopm_put_interface(data->intf);
 
 failed:

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <[email protected]>

commit faafd03d23c913633d2ef7e6ffebdce01b164409 upstream.

The commit [d745f5e7b8b2: ALSA: hda - Add the pin / port mapping on Intel ILK and VLV] introduced a WARN_ON() to check the pointer for avoiding the double initializations. But hdac_acomp pointer wasn't cleared at snd_hdac_i915_exit(), thus after reloading the HD-audio driver, it may result in the false positive warning. This patch makes sure to clear the leftover pointer at exit.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94736

---
 sound/hda/hdac_i915.c |    1 +
 1 file changed, 1 insertion(+)

@@ -273,6 +273,7 @@ int snd_hdac_i915_exit(struct hdac_bus *
 
 	kfree(acomp);
 	bus->audio_component = NULL;
+	hdac_acomp = NULL;
 
 	return 0;
 }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve Capper <[email protected]>

commit f24e5834a2c3f6c5f814a417f858226f0a010ade upstream.

The high_memory global variable is used by
cma_declare_contiguous(.) before it is defined.

We don't notice this as we compute __pa(high_memory - 1), and it looks like we're processing a VA from the direct linear map.

This problem becomes apparent when we flip the kernel virtual address space and the linear map is moved to the bottom of the kernel VA space.

This patch moves the initialisation of high_memory before it used.

---
 arch/arm64/mm/init.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -178,6 +178,7 @@ void __init arm64_memblock_init(void)
 		arm64_dma_phys_limit = max_zone_dma_phys();
 	else
 		arm64_dma_phys_limit = PHYS_MASK + 1;
+	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();

@@ -202,7 +203,6 @@ void __init bootmem_init(void)
 	sparse_init();
 	zone_sizes_init(min, max);
 
-	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
 	max_pfn = max_low_pfn = max;
 }
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit e1074888c326038340a1ada9129d679e661f2ea6 upstream.

Currently all of the functions that live in tlb.c are inlined on !SMP builds. One can debate whether this is a good idea (in many respects the code in tlb.c is better than the inlined UP code).

Regardless, I want to add code that needs to be built on UP and SMP kernels and relates to tlb flushing, so arrange for tlb.c to be compiled unconditionally.

---
 arch/x86/mm/Makefile |    3 +--
 arch/x86/mm/tlb.c    |    4 ++++
 2 files changed, 5 insertions(+), 2 deletions(-)

@@ -1,5 +1,5 @@
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o gup.o setup_nx.o
+	    pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)

@@ -9,7 +9,6 @@ CFLAGS_setup_nx.o		:= $(nostackp)
 CFLAGS_fault.o := -I$(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
-obj-$(CONFIG_SMP)		+= tlb.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 

@@ -28,6 +28,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+#ifdef CONFIG_SMP
+
 struct flush_tlb_info {
 	struct mm_struct *flush_mm;
 	unsigned long flush_start;

@@ -351,3 +353,5 @@ static int __init create_tlb_single_page
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
+
+#endif /* CONFIG_SMP */

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 69c0319aabba45bcf33178916a2f06967b4adede upstream.

It's fairly large and it has quite a few callers. This may also help untangle some headers down the road.

---
 arch/x86/include/asm/mmu_context.h |   98 -----------------------------------
 arch/x86/mm/tlb.c                  |  102 +++++++++++++++++++++++++++++++++++++
 2 files changed, 104 insertions(+), 96 deletions(-)

@@ -104,103 +104,9 @@ static inline void enter_lazy_tlb(struct
 #endif
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
+extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+		      struct task_struct *tsk);
 
-	if (likely(prev != next)) {
-#ifdef CONFIG_SMP
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-
-		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
-		 */
-		load_cr3(next->pgd);
-
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
-
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
-
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		/*
-		 * Load the LDT, if the LDT is different.
-		 *
-		 * It's possible that prev->context.ldt doesn't match
-		 * the LDT register.  This can happen if leave_mm(prev)
-		 * was called and then modify_ldt changed
-		 * prev->context.ldt but suppressed an IPI to this CPU.
-		 * In this case, prev->context.ldt != NULL, because we
-		 * never set context.ldt to NULL while the mm still
-		 * exists.  That means that next->context.ldt !=
-		 * prev->context.ldt, because mms never share an LDT.
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-#endif
-	}
-#ifdef CONFIG_SMP
-	  else {
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * On established mms, the mm_cpumask is only changed
-			 * from irq context, from ptep_clear_flush() while in
-			 * lazy tlb mode, and here. Irqs are blocked during
-			 * schedule, protecting us from simultaneous changes.
-			 */
-			cpumask_set_cpu(cpu, mm_cpumask(next));
-
-			/*
-			 * We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_mm_cr4(next);
-			load_mm_ldt(next);
-		}
-	}
-#endif
-}
 
 #define activate_mm(prev, next)			\
 do {						\

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aaron Lu <[email protected]>

commit 82ba4faca1bffad429f15c90c980ffd010366c25 upstream.

Since commit:

52aec3308db8 ("x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR")

the TLB remote shootdown is done through call function vector. That commit didn't take care of irq_tlb_count, which a later commit:

fd0f5869724f ("x86: Distinguish TLB shootdown interrupts from other functions call interrupts")

... tried to fix.

The fix assumes every increase of irq_tlb_count has a corresponding increase of irq_call_count. So the irq_call_count is always bigger than irq_tlb_count and we could substract irq_tlb_count from irq_call_count.

Unfortunately this is not true for the smp_call_function_single() case. The IPI is only sent if the target CPU's call_single_queue is empty when adding a csd into it in generic_exec_single. That means if two threads are both adding flush tlb csds to the same CPU's call_single_queue, only one IPI is sent. In other words, the irq_call_count is incremented by 1 but irq_tlb_count is incremented by 2. Over time, irq_tlb_count will be bigger than irq_call_count and the substract will produce a very large irq_call_count value due to overflow.

Considering that:

1) it's not worth to send more IPIs for the sake of accurate counting of

     irq_call_count in generic_exec_single();

2) it's not easy to tell if the call function interrupt is for TLB shootdown in __smp_call_function_single_interrupt().

Not to exclude TLB shootdown from call function count seems to be the simplest fix and this patch just does that.

This bug was found by LKP's cyclic performance regression tracking recently with the vm-scalability test suite. I have bisected to commit:

3dec0ba0be6a ("mm/rmap: share the i_mmap_rwsem")

This commit didn't do anything wrong but revealed the irq_call_count problem. IIUC, the commit makes rwc->remap_one in rmap_walk_file concurrent with multiple threads. When remap_one is try_to_unmap_one(), then multiple threads could queue flush TLB to the same CPU but only one IPI will be sent.

Since the commit was added in Linux v3.19, the counting problem only shows up from v3.19 onwards.

---
 arch/x86/include/asm/hardirq.h |    4 ----
 arch/x86/kernel/irq.c          |    3 +--
 2 files changed, 1 insertion(+), 6 deletions(-)

@@ -22,10 +22,6 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	/*
-	 * irq_tlb_count is double-counted in irq_call_count, so it must be
-	 * subtracted from irq_call_count when displaying irq_call_count
-	 */
 	unsigned int irq_tlb_count;
 #endif
 #ifdef CONFIG_X86_THERMAL_VECTOR

@@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file
 	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
-					irq_stats(j)->irq_tlb_count);
+		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
 	seq_puts(p, "  Function call interrupts\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaroslav Kysela <[email protected]>

[ Upstream commit cc3a47a248d7791ef0d2c81a35c46769e55e4c6c ]

This tested patch adds missing initialization for Line-In/Out PINs for the docking station for HP 840 G3.

---
 sound/pci/hda/patch_conexant.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -261,6 +261,7 @@ enum {
 	CXT_FIXUP_HP_530,
 	CXT_FIXUP_CAP_MIX_AMP_5047,
 	CXT_FIXUP_MUTE_LED_EAPD,
+	CXT_FIXUP_HP_DOCK,
 	CXT_FIXUP_HP_SPECTRE,
 	CXT_FIXUP_HP_GATE_MIC,
 };

@@ -778,6 +779,14 @@ static const struct hda_fixup cxt_fixups
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_mute_led_eapd,
 	},
+	[CXT_FIXUP_HP_DOCK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x16, 0x21011020 }, /* line-out */
+			{ 0x18, 0x2181103f }, /* line-in */
+			{ }
+		}
+	},
 	[CXT_FIXUP_HP_SPECTRE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -839,6 +848,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
+	SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),

@@ -872,6 +882,7 @@ static const struct hda_model_fixup cxt5
 	{ .id = CXT_PINCFG_LEMOTE_A1205, .name = "lemote-a1205" },
 	{ .id = CXT_FIXUP_OLPC_XO, .name = "olpc-xo" },
 	{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
+	{ .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
 	{}
 };
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jon Medhurst <[email protected]>

[ Upstream commit 974310d047f3c7788a51d10c8d255eebdb1fa857 ]

kprobes test cases need to have a stack that is aligned to an 8-byte boundary because they call other functions (and the ARM ABI mandates that alignment) and because test cases include 64-bit accesses to the stack. Unfortunately, GCC doesn't ensure this alignment for inline assembler and for the code in question seems to always misalign it by pushing just the LR register onto the stack. We therefore need to explicitly perform stack alignment at the start of each test case.

Without this fix, some test cases will generate alignment faults on systems where alignment is enforced. Even if the kernel is configured to handle these faults in software, triggering them is ugly. It also exposes limitations in the fault handling code which doesn't cope with writes to the stack. E.g. when handling this instruction

strd r6, [sp, #-64]!

the fault handling code will write to a stack location below the SP value at the point the fault occurred, which coincides with where the exception handler has pushed the saved register context. This results in corruption of those registers.

---
 arch/arm/probes/kprobes/test-core.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -976,7 +976,10 @@ static void coverage_end(void)
 void __naked __kprobes_test_case_start(void)
 {
 	__asm__ __volatile__ (
-		"stmdb	sp!, {r4-r11}				\n\t"
+		"mov	r2, sp					\n\t"
+		"bic	r3, r2, #7				\n\t"
+		"mov	sp, r3					\n\t"
+		"stmdb	sp!, {r2-r11}				\n\t"
 		"sub	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
 		"bic	r0, lr, #1  @ r0 = inline data		\n\t"
 		"mov	r1, sp					\n\t"

@@ -996,7 +999,8 @@ void __naked __kprobes_test_case_end_32(
 		"movne	pc, r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"mov	pc, r0					\n\t"
 	);
 }

@@ -1012,7 +1016,8 @@ void __naked __kprobes_test_case_end_16(
 		"bxne	r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"bx	r0					\n\t"
 	);
 }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vaidyanathan Srinivasan <[email protected]>

[ Upstream commit ad0a45fd9c14feebd000b6e84189d0edff265170 ]

If a given cpu is not in cpu_present and cpu hotplug is disabled, arch can skip setting up the cpu_dev.

Arch cpuidle driver should pass correct cpu mask for registration, but failing to do so by the driver causes error to propagate and crash like this:

[   30.076045] Unable to handle kernel paging request for data at address 0x00000048
[   30.076100] Faulting instruction address: 0xc0000000007b2f30
cpu 0x4d: Vector: 300 (Data Access) at [c000003feb18b670]
    pc: c0000000007b2f30: kobject_get+0x20/0x70
    lr: c0000000007b3c94: kobject_add_internal+0x54/0x3f0
    sp: c000003feb18b8f0

msr: 9000000000009033
dar: 48
dsisr: 40000000
current = 0xc000003fd2ed8300
paca = 0xc00000000fbab500 softe: 0 irq_happened: 0x01
pid = 1, comm = swapper/0
Linux version 4.11.0-rc2-svaidy+ (sv@sagarika) (gcc version 6.2.0 20161005 (Ubuntu 6.2.0-5ubuntu12) ) #10 SMP Sun Mar 19 00:08:09 IST 2017 enter ? for help
[c000003feb18b960] c0000000007b3c94 kobject_add_internal+0x54/0x3f0 [c000003feb18b9f0] c0000000007b43a4 kobject_init_and_add+0x64/0xa0 [c000003feb18ba70] c000000000e284f4 cpuidle_add_sysfs+0xb4/0x130 [c000003feb18baf0] c000000000e26038 cpuidle_register_device+0x118/0x1c0 [c000003feb18bb30] c000000000e26c48 cpuidle_register+0x78/0x120 [c000003feb18bbc0] c00000000168fd9c powernv_processor_idle_init+0x110/0x1c4 [c000003feb18bc40] c00000000000cff8 do_one_initcall+0x68/0x1d0 [c000003feb18bd00] c0000000016242f4 kernel_init_freeable+0x280/0x360 [c000003feb18bdc0] c00000000000d864 kernel_init+0x24/0x160 [c000003feb18be30] c00000000000b4e8 ret_from_kernel_thread+0x5c/0x74

Validating cpu_dev fixes the crash and reports correct error message like:

[   30.163506] Failed to register cpuidle device for cpu136
[   30.173329] Registration of powernv driver failed.

---
 drivers/cpuidle/sysfs.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -613,6 +613,18 @@ int cpuidle_add_sysfs(struct cpuidle_dev
 	struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu);
 	int error;
 
+	/*
+	 * Return if cpu_device is not setup for this CPU.
+	 *
+	 * This could happen if the arch did not set up cpu_device
+	 * since this CPU is not in cpu_present mask and the
+	 * driver did not send a correct CPU mask during registration.
+	 * Without this check we would end up passing bogus
+	 * value for &cpu_dev->kobj in kobject_init_and_add()
+	 */
+	if (!cpu_dev)
+		return -ENODEV;
+
 	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
 	if (!kdev)
 		return -ENOMEM;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Herbert Xu <[email protected]>

[ Upstream commit 8a0f5ccfb33b0b8b51de65b7b3bf342ba10b4fb6 ]

Please try this patch.

---8<---
Subject: [PATCH 4.4 22/78] netlink: Annotate nlk cb_mutex by protocol

Currently all occurences of nlk->cb_mutex are annotated by lockdep as a single class. This causes a false lcokdep cycle involving genl and crypto_user.

This patch fixes it by dividing cb_mutex into individual classes based on the netlink protocol. As genl and crypto_user do not use the same netlink protocol this breaks the false dependency loop.

---
 net/netlink/af_netlink.c |   41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

@@ -96,6 +96,44 @@ EXPORT_SYMBOL_GPL(nl_table);
 
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
 
+static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS];
+
+static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
+	"nlk_cb_mutex-ROUTE",
+	"nlk_cb_mutex-1",
+	"nlk_cb_mutex-USERSOCK",
+	"nlk_cb_mutex-FIREWALL",
+	"nlk_cb_mutex-SOCK_DIAG",
+	"nlk_cb_mutex-NFLOG",
+	"nlk_cb_mutex-XFRM",
+	"nlk_cb_mutex-SELINUX",
+	"nlk_cb_mutex-ISCSI",
+	"nlk_cb_mutex-AUDIT",
+	"nlk_cb_mutex-FIB_LOOKUP",
+	"nlk_cb_mutex-CONNECTOR",
+	"nlk_cb_mutex-NETFILTER",
+	"nlk_cb_mutex-IP6_FW",
+	"nlk_cb_mutex-DNRTMSG",
+	"nlk_cb_mutex-KOBJECT_UEVENT",
+	"nlk_cb_mutex-GENERIC",
+	"nlk_cb_mutex-17",
+	"nlk_cb_mutex-SCSITRANSPORT",
+	"nlk_cb_mutex-ECRYPTFS",
+	"nlk_cb_mutex-RDMA",
+	"nlk_cb_mutex-CRYPTO",
+	"nlk_cb_mutex-SMC",
+	"nlk_cb_mutex-23",
+	"nlk_cb_mutex-24",
+	"nlk_cb_mutex-25",
+	"nlk_cb_mutex-26",
+	"nlk_cb_mutex-27",
+	"nlk_cb_mutex-28",
+	"nlk_cb_mutex-29",
+	"nlk_cb_mutex-30",
+	"nlk_cb_mutex-31",
+	"nlk_cb_mutex-MAX_LINKS"
+};
+
 static int netlink_dump(struct sock *sk);
 static void netlink_skb_destructor(struct sk_buff *skb);
 

@@ -585,6 +623,9 @@ static int __netlink_create(struct net *
 	} else {
 		nlk->cb_mutex = &nlk->cb_def_mutex;
 		mutex_init(nlk->cb_mutex);
+		lockdep_set_class_and_name(nlk->cb_mutex,
+					   nlk_cb_mutex_keys + protocol,
+					   nlk_cb_mutex_key_strings[protocol]);
 	}
 	init_waitqueue_head(&nlk->wait);
 

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit aea92fb2e09e29653b023d4254ac9fbf94221538 ]

skb_cow(skb, sizeof(ip header)) is not very helpful in this context.

First we need to use pskb_may_pull() to make sure the ip header is in skb linear part, then use skb_try_make_writable() to address clones issues.

---
 net/sched/sch_dsmark.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -199,9 +199,13 @@ static int dsmark_enqueue(struct sk_buff
 	pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
 
 	if (p->set_tc_index) {
+		int wlen = skb_network_offset(skb);
+
 		switch (tc_skb_protocol(skb)) {
 		case htons(ETH_P_IP):
-			if (skb_cow_head(skb, sizeof(struct iphdr)))
+			wlen += sizeof(struct iphdr);
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
 				goto drop;
 
 			skb->tc_index = ipv4_get_dsfield(ip_hdr(skb))

@@ -209,7 +213,9 @@ static int dsmark_enqueue(struct sk_buff
 			break;
 
 		case htons(ETH_P_IPV6):
-			if (skb_cow_head(skb, sizeof(struct ipv6hdr)))
+			wlen += sizeof(struct ipv6hdr);
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
 				goto drop;
 
 			skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb))

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dan Carpenter <[email protected]>

[ Upstream commit 13e2d5187f6b965ba3556caedb914baf81b98ed2 ]

We could allocate less memory than intended because we do:

	bnad->regdata = kzalloc(len << 2, GFP_KERNEL);

The shift can overflow leading to a crash. This is debugfs code so the impact is very small.

---
 drivers/net/ethernet/brocade/bna/bnad_debugfs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -324,7 +324,7 @@ bnad_debugfs_write_regrd(struct file *fi
 		return PTR_ERR(kern_buf);
 
 	rc = sscanf(kern_buf, "%x:%x", &addr, &len);
-	if (rc < 2) {
+	if (rc < 2 || len > UINT_MAX >> 2) {
 		netdev_warn(bnad->netdev, "failed to read user buffer\n");
 		kfree(kern_buf);
 		return -EINVAL;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Roger Quadros <[email protected]>

[ Upstream commit 16bb05d98c904a4f6c5ce7e2d992299f794acbf2 ]

As per USB3.0 Specification "Table 9-20. Standard Endpoint Descriptor", for interrupt and isochronous endpoints, wMaxPacketSize must be set to 1024 if the endpoint defines bMaxBurst to be greater than zero.

---
 drivers/usb/gadget/function/f_uvc.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -594,6 +594,14 @@ uvc_function_bind(struct usb_configurati
 	opts->streaming_maxpacket = clamp(opts->streaming_maxpacket, 1U, 3072U);
 	opts->streaming_maxburst = min(opts->streaming_maxburst, 15U);
 
+	/* For SS, wMaxPacketSize has to be 1024 if bMaxBurst is not 0 */
+	if (opts->streaming_maxburst &&
+	    (opts->streaming_maxpacket % 1024) != 0) {
+		opts->streaming_maxpacket = roundup(opts->streaming_maxpacket, 1024);
+		INFO(cdev, "overriding streaming_maxpacket to %d\n",
+		     opts->streaming_maxpacket);
+	}
+
 	/* Fill in the FS/HS/SS Video Streaming specific descriptors from the
 	 * module parameters.
 	 *

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nadav Amit <[email protected]>

commit 858eaaa711700ce4595e039441e239e56d7b9514 upstream.

The recently introduced batched invalidations mechanism uses its own mechanism for shootdown. However, it does wrong accounting of interrupts (e.g., inc_irq_stat is called for local invalidations), trace-points (e.g., TLB_REMOTE_SHOOTDOWN for local invalidations) and may break some platforms as it bypasses the invalidation mechanisms of Xen and SGI UV.

This patch reuses the existing TLB flushing mechnaisms instead. We use NULL as mm to indicate a global invalidation is required.

Fixes 72b252aed506b8 ("mm: send one IPI per CPU to TLB flush all entries after unmapping pages")

---
 arch/x86/include/asm/tlbflush.h |    6 ------
 arch/x86/mm/tlb.c               |    2 +-
 mm/rmap.c                       |   28 +++++++---------------------
 3 files changed, 8 insertions(+), 28 deletions(-)

@@ -325,12 +325,6 @@ static inline void reset_lazy_tlbstate(v
 
 #endif	/* SMP */
 
-/* Not inlined due to inc_irq_stat not being defined yet */
-#define flush_tlb_local() {		\
-	inc_irq_stat(irq_tlb_count);	\
-	local_flush_tlb();		\
-}
-
 #ifndef CONFIG_PARAVIRT
 #define flush_tlb_others(mask, mm, start, end)	\
 	native_flush_tlb_others(mask, mm, start, end)

@@ -104,7 +104,7 @@ static void flush_tlb_func(void *info)
 
 	inc_irq_stat(irq_tlb_count);
 
-	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+	if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);

@@ -587,19 +587,6 @@ vma_address(struct page *page, struct vm
 }
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-static void percpu_flush_tlb_batch_pages(void *data)
-{
-	/*
-	 * All TLB entries are flushed on the assumption that it is
-	 * cheaper to flush all TLBs and let them be refilled than
-	 * flushing individual PFNs. Note that we do not track mm's
-	 * to flush as that might simply be multiple full TLB flushes
-	 * for no gain.
-	 */
-	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
-	flush_tlb_local();
-}
-
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed

@@ -616,15 +603,14 @@ void try_to_unmap_flush(void)
 
 	cpu = get_cpu();
 
-	trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL);
-
-	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask))
-		percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask);
-
-	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) {
-		smp_call_function_many(&tlb_ubc->cpumask,
-			percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true);
+	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+		local_flush_tlb();
+		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
 	}
+
+	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
+		flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
 	cpumask_clear(&tlb_ubc->cpumask);
 	tlb_ubc->flush_required = false;
 	tlb_ubc->writable = false;

This is the start of the stable review cycle for the 4.4.108 release. There are 78 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sun Dec 24 08:45:30 UTC 2017. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.108-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y
and the diffstat can be found below.

thanks,

greg k-h