Merge android-4.4@4b8fc9f (v4.4.82) into msm-4.4

* refs/heads/tmp-4b8fc9f
  UPSTREAM: locking: avoid passing around 'thread_info' in mutex debugging code
  ANDROID: arm64: fix undeclared 'init_thread_info' error
  UPSTREAM: kdb: use task_cpu() instead of task_thread_info()->cpu
  Linux 4.4.82
  net: account for current skb length when deciding about UFO
  ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output
  mm/mempool: avoid KASAN marking mempool poison checks as use-after-free
  KVM: arm/arm64: Handle hva aging while destroying the vm
  sparc64: Prevent perf from running during super critical sections
  udp: consistently apply ufo or fragmentation
  revert "ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output"
  revert "net: account for current skb length when deciding about UFO"
  packet: fix tp_reserve race in packet_set_ring
  net: avoid skb_warn_bad_offload false positives on UFO
  tcp: fastopen: tcp_connect() must refresh the route
  net: sched: set xt_tgchk_param par.nft_compat as 0 in ipt_init_target
  bpf, s390: fix jit branch offset related to ldimm64
  net: fix keepalive code vs TCP_FASTOPEN_CONNECT
  tcp: avoid setting cwnd to invalid ssthresh after cwnd reduction states
  ANDROID: keychord: Fix for a memory leak in keychord.
  ANDROID: keychord: Fix races in keychord_write.
  Use %zu to print resid (size_t).
  ANDROID: keychord: Fix a slab out-of-bounds read.
  Linux 4.4.81
  workqueue: implicit ordered attribute should be overridable
  net: account for current skb length when deciding about UFO
  ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output
  mm: don't dereference struct page fields of invalid pages
  signal: protect SIGNAL_UNKILLABLE from unintentional clearing.
  lib/Kconfig.debug: fix frv build failure
  mm, slab: make sure that KMALLOC_MAX_SIZE will fit into MAX_ORDER
  ARM: 8632/1: ftrace: fix syscall name matching
  virtio_blk: fix panic in initialization error path
  drm/virtio: fix framebuffer sparse warning
  scsi: qla2xxx: Get mutex lock before checking optrom_state
  phy state machine: failsafe leave invalid RUNNING state
  x86/boot: Add missing declaration of string functions
  tg3: Fix race condition in tg3_get_stats64().
  net: phy: dp83867: fix irq generation
  sh_eth: R8A7740 supports packet shecksumming
  wext: handle NULL extra data in iwe_stream_add_point better
  sparc64: Measure receiver forward progress to avoid send mondo timeout
  xen-netback: correctly schedule rate-limited queues
  net: phy: Fix PHY unbind crash
  net: phy: Correctly process PHY_HALTED in phy_stop_machine()
  net/mlx5: Fix command bad flow on command entry allocation failure
  sctp: fix the check for _sctp_walk_params and _sctp_walk_errors
  sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}()
  dccp: fix a memleak for dccp_feat_init err process
  dccp: fix a memleak that dccp_ipv4 doesn't put reqsk properly
  dccp: fix a memleak that dccp_ipv6 doesn't put reqsk properly
  net: ethernet: nb8800: Handle all 4 RGMII modes identically
  ipv6: Don't increase IPSTATS_MIB_FRAGFAILS twice in ip6_fragment()
  packet: fix use-after-free in prb_retire_rx_blk_timer_expired()
  openvswitch: fix potential out of bound access in parse_ct
  mcs7780: Fix initialization when CONFIG_VMAP_STACK is enabled
  rtnetlink: allocate more memory for dev_set_mac_address()
  ipv4: initialize fib_trie prior to register_netdev_notifier call.
  ipv6: avoid overflow of offset in ip6_find_1stfragopt
  net: Zero terminate ifr_name in dev_ifname().
  ipv4: ipv6: initialize treq->txhash in cookie_v[46]_check()
  saa7164: fix double fetch PCIe access condition
  drm: rcar-du: fix backport bug
  f2fs: sanity check checkpoint segno and blkoff
  media: lirc: LIRC_GET_REC_RESOLUTION should return microseconds
  mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries
  iser-target: Avoid isert_conn->cm_id dereference in isert_login_recv_done
  iscsi-target: Fix delayed logout processing greater than SECONDS_FOR_LOGOUT_COMP
  iscsi-target: Fix initial login PDU asynchronous socket close OOPs
  iscsi-target: Fix early sk_data_ready LOGIN_FLAGS_READY race
  iscsi-target: Always wait for kthread_should_stop() before kthread exit
  target: Avoid mappedlun symlink creation during lun shutdown
  media: platform: davinci: return -EINVAL for VPFE_CMD_S_CCDC_RAW_PARAMS ioctl
  ARM: dts: armada-38x: Fix irq type for pca955
  ext4: fix overflow caused by missing cast in ext4_resize_fs()
  ext4: fix SEEK_HOLE/SEEK_DATA for blocksize < pagesize
  mm/page_alloc: Remove kernel address exposure in free_reserved_area()
  KVM: async_pf: make rcu irq exit if not triggered from idle task
  ASoC: do not close shared backend dailink
  ALSA: hda - Fix speaker output from VAIO VPCL14M1R
  workqueue: restore WQ_UNBOUND/max_active==1 to be ordered
  libata: array underflow in ata_find_dev()
  ANDROID: binder: don't queue async transactions to thread.
  ANDROID: binder: don't enqueue death notifications to thread todo.
  ANDROID: binder: call poll_wait() unconditionally.
  android: configs: move quota-related configs to recommended
  BACKPORT: arm64: split thread_info from task stack
  UPSTREAM: arm64: assembler: introduce ldr_this_cpu
  UPSTREAM: arm64: make cpu number a percpu variable
  UPSTREAM: arm64: smp: prepare for smp_processor_id() rework
  BACKPORT: arm64: move sp_el0 and tpidr_el1 into cpu_suspend_ctx
  UPSTREAM: arm64: prep stack walkers for THREAD_INFO_IN_TASK
  UPSTREAM: arm64: unexport walk_stackframe
  UPSTREAM: arm64: traps: simplify die() and __die()
  UPSTREAM: arm64: factor out current_stack_pointer
  BACKPORT: arm64: asm-offsets: remove unused definitions
  UPSTREAM: arm64: thread_info remove stale items
  UPSTREAM: thread_info: include <current.h> for THREAD_INFO_IN_TASK
  UPSTREAM: thread_info: factor out restart_block
  UPSTREAM: kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
  UPSTREAM: sched/core: Add try_get_task_stack() and put_task_stack()
  UPSTREAM: sched/core: Allow putting thread_info into task_struct
  UPSTREAM: printk: when dumping regs, show the stack, not thread_info
  UPSTREAM: fix up initial thread stack pointer vs thread_info confusion
  UPSTREAM: Clarify naming of thread info/stack allocators
  ANDROID: sdcardfs: override credential for ioctl to lower fs

Conflicts:
	android/configs/android-base.cfg
	arch/arm64/Kconfig
	arch/arm64/include/asm/suspend.h
	arch/arm64/kernel/head.S
	arch/arm64/kernel/smp.c
	arch/arm64/kernel/suspend.c
	arch/arm64/kernel/traps.c
	arch/arm64/mm/proc.S
	kernel/fork.c
	sound/soc/soc-pcm.c

Change-Id: I273e216c94899a838bbd208391c6cbe20b2bf683
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

7 files changed, 154 insertions, 77 deletions

diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 349dd23e2876..0cdeb2b483a0 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -25,9 +25,11 @@ void destroy_context(struct mm_struct *mm);
 void __tsb_context_switch(unsigned long pgd_pa,
 			  struct tsb_config *tsb_base,
 			  struct tsb_config *tsb_huge,
-			  unsigned long tsb_descr_pa);
+			  unsigned long tsb_descr_pa,
+			  unsigned long secondary_ctx);
 
-static inline void tsb_context_switch(struct mm_struct *mm)
+static inline void tsb_context_switch_ctx(struct mm_struct *mm,
+					  unsigned long ctx)
 {
 	__tsb_context_switch(__pa(mm->pgd),
 			     &mm->context.tsb_block[0],
@@ -38,9 +40,12 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[0]));
+			     , __pa(&mm->context.tsb_descr[0]),
+			     ctx);
 }
 
+#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0)
+
 void tsb_grow(struct mm_struct *mm,
 	      unsigned long tsb_index,
 	      unsigned long mm_rss);
@@ -110,8 +115,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * cpu0 to update it's TSB because at that point the cpu_vm_mask
 	 * only had cpu1 set in it.
 	 */
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 
 	/* Any time a processor runs a context on an address space
 	 * for the first time, we must flush that context out of the
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ec9c04de3664..ff05992dae7a 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS];
 void init_cur_cpu_trap(struct thread_info *);
 void setup_tba(void);
 extern int ncpus_probed;
+extern u64 cpu_mondo_counter[NR_CPUS];
 
 unsigned long real_hard_smp_processor_id(void);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 95a9fa0d2195..4511caa3b7e9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -617,22 +617,48 @@ retry:
 	}
 }
 
-/* Multi-cpu list version.  */
+#define	CPU_MONDO_COUNTER(cpuid)	(cpu_mondo_counter[cpuid])
+#define	MONDO_USEC_WAIT_MIN		2
+#define	MONDO_USEC_WAIT_MAX		100
+#define	MONDO_RETRY_LIMIT		500000
+
+/* Multi-cpu list version.
+ *
+ * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'.
+ * Sometimes not all cpus receive the mondo, requiring us to re-send
+ * the mondo until all cpus have received, or cpus are truly stuck
+ * unable to receive mondo, and we timeout.
+ * Occasionally a target cpu strand is borrowed briefly by hypervisor to
+ * perform guest service, such as PCIe error handling. Consider the
+ * service time, 1 second overall wait is reasonable for 1 cpu.
+ * Here two in-between mondo check wait time are defined: 2 usec for
+ * single cpu quick turn around and up to 100usec for large cpu count.
+ * Deliver mondo to large number of cpus could take longer, we adjusts
+ * the retry count as long as target cpus are making forward progress.
+ */
 static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 {
-	int retries, this_cpu, prev_sent, i, saw_cpu_error;
+	int this_cpu, tot_cpus, prev_sent, i, rem;
+	int usec_wait, retries, tot_retries;
+	u16 first_cpu = 0xffff;
+	unsigned long xc_rcvd = 0;
 	unsigned long status;
+	int ecpuerror_id = 0;
+	int enocpu_id = 0;
 	u16 *cpu_list;
+	u16 cpu;
 
 	this_cpu = smp_processor_id();
-
 	cpu_list = __va(tb->cpu_list_pa);
-
-	saw_cpu_error = 0;
-	retries = 0;
+	usec_wait = cnt * MONDO_USEC_WAIT_MIN;
+	if (usec_wait > MONDO_USEC_WAIT_MAX)
+		usec_wait = MONDO_USEC_WAIT_MAX;
+	retries = tot_retries = 0;
+	tot_cpus = cnt;
 	prev_sent = 0;
+
 	do {
-		int forward_progress, n_sent;
+		int n_sent, mondo_delivered, target_cpu_busy;
 
 		status = sun4v_cpu_mondo_send(cnt,
 					      tb->cpu_list_pa,
@@ -640,94 +666,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 
 		/* HV_EOK means all cpus received the xcall, we're done.  */
 		if (likely(status == HV_EOK))
-			break;
+			goto xcall_done;
+
+		/* If not these non-fatal errors, panic */
+		if (unlikely((status != HV_EWOULDBLOCK) &&
+			(status != HV_ECPUERROR) &&
+			(status != HV_ENOCPU)))
+			goto fatal_errors;
 
 		/* First, see if we made any forward progress.
 		 *
+		 * Go through the cpu_list, count the target cpus that have
+		 * received our mondo (n_sent), and those that did not (rem).
+		 * Re-pack cpu_list with the cpus remain to be retried in the
+		 * front - this simplifies tracking the truly stalled cpus.
+		 *
 		 * The hypervisor indicates successful sends by setting
 		 * cpu list entries to the value 0xffff.
+		 *
+		 * EWOULDBLOCK means some target cpus did not receive the
+		 * mondo and retry usually helps.
+		 *
+		 * ECPUERROR means at least one target cpu is in error state,
+		 * it's usually safe to skip the faulty cpu and retry.
+		 *
+		 * ENOCPU means one of the target cpu doesn't belong to the
+		 * domain, perhaps offlined which is unexpected, but not
+		 * fatal and it's okay to skip the offlined cpu.
 		 */
+		rem = 0;
 		n_sent = 0;
 		for (i = 0; i < cnt; i++) {
-			if (likely(cpu_list[i] == 0xffff))
+			cpu = cpu_list[i];
+			if (likely(cpu == 0xffff)) {
 				n_sent++;
+			} else if ((status == HV_ECPUERROR) &&
+				(sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) {
+				ecpuerror_id = cpu + 1;
+			} else if (status == HV_ENOCPU && !cpu_online(cpu)) {
+				enocpu_id = cpu + 1;
+			} else {
+				cpu_list[rem++] = cpu;
+			}
 		}
 
-		forward_progress = 0;
-		if (n_sent > prev_sent)
-			forward_progress = 1;
+		/* No cpu remained, we're done. */
+		if (rem == 0)
+			break;
 
-		prev_sent = n_sent;
+		/* Otherwise, update the cpu count for retry. */
+		cnt = rem;
 
-		/* If we get a HV_ECPUERROR, then one or more of the cpus
-		 * in the list are in error state.  Use the cpu_state()
-		 * hypervisor call to find out which cpus are in error state.
+		/* Record the overall number of mondos received by the
+		 * first of the remaining cpus.
 		 */
-		if (unlikely(status == HV_ECPUERROR)) {
-			for (i = 0; i < cnt; i++) {
-				long err;
-				u16 cpu;
+		if (first_cpu != cpu_list[0]) {
+			first_cpu = cpu_list[0];
+			xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
+		}
 
-				cpu = cpu_list[i];
-				if (cpu == 0xffff)
-					continue;
+		/* Was any mondo delivered successfully? */
+		mondo_delivered = (n_sent > prev_sent);
+		prev_sent = n_sent;
 
-				err = sun4v_cpu_state(cpu);
-				if (err == HV_CPU_STATE_ERROR) {
-					saw_cpu_error = (cpu + 1);
-					cpu_list[i] = 0xffff;
-				}
-			}
-		} else if (unlikely(status != HV_EWOULDBLOCK))
-			goto fatal_mondo_error;
+		/* or, was any target cpu busy processing other mondos? */
+		target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu));
+		xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
 
-		/* Don't bother rewriting the CPU list, just leave the
-		 * 0xffff and non-0xffff entries in there and the
-		 * hypervisor will do the right thing.
-		 *
-		 * Only advance timeout state if we didn't make any
-		 * forward progress.
+		/* Retry count is for no progress. If we're making progress,
+		 * reset the retry count.
 		 */
-		if (unlikely(!forward_progress)) {
-			if (unlikely(++retries > 10000))
-				goto fatal_mondo_timeout;
-
-			/* Delay a little bit to let other cpus catch up
-			 * on their cpu mondo queue work.
-			 */
-			udelay(2 * cnt);
+		if (likely(mondo_delivered || target_cpu_busy)) {
+			tot_retries += retries;
+			retries = 0;
+		} else if (unlikely(retries > MONDO_RETRY_LIMIT)) {
+			goto fatal_mondo_timeout;
 		}
-	} while (1);
 
-	if (unlikely(saw_cpu_error))
-		goto fatal_mondo_cpu_error;
+		/* Delay a little bit to let other cpus catch up on
+		 * their cpu mondo queue work.
+		 */
+		if (!mondo_delivered)
+			udelay(usec_wait);
 
-	return;
+		retries++;
+	} while (1);
 
-fatal_mondo_cpu_error:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus "
-	       "(including %d) were in error state\n",
-	       this_cpu, saw_cpu_error - 1);
+xcall_done:
+	if (unlikely(ecpuerror_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n",
+		       this_cpu, ecpuerror_id - 1);
+	} else if (unlikely(enocpu_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n",
+		       this_cpu, enocpu_id - 1);
+	}
 	return;
 
+fatal_errors:
+	/* fatal errors include bad alignment, etc */
+	pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n",
+	       this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
+	panic("Unexpected SUN4V mondo error %lu\n", status);
+
 fatal_mondo_timeout:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward "
-	       " progress after %d retries.\n",
-	       this_cpu, retries);
-	goto dump_cpu_list_and_out;
-
-fatal_mondo_error:
-	printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n",
-	       this_cpu, status);
-	printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) "
-	       "mondo_block_pa(%lx)\n",
-	       this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
-
-dump_cpu_list_and_out:
-	printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu);
-	for (i = 0; i < cnt; i++)
-		printk("%u ", cpu_list[i]);
-	printk("]\n");
+	/* some cpus being non-responsive to the cpu mondo */
+	pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n",
+	       this_cpu, first_cpu, (tot_retries + retries), tot_cpus);
+	panic("SUN4V mondo timeout panic\n");
 }
 
 static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index 559bc5e9c199..34631995859a 100644
--- a/arch/sparc/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -26,6 +26,21 @@ sun4v_cpu_mondo:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g4
 	sub	%g4, TRAP_PER_CPU_FAULT_INFO, %g4
 
+	/* Get smp_processor_id() into %g3 */
+	sethi	%hi(trap_block), %g5
+	or	%g5, %lo(trap_block), %g5
+	sub	%g4, %g5, %g3
+	srlx	%g3, TRAP_BLOCK_SZ_SHIFT, %g3
+
+	/* Increment cpu_mondo_counter[smp_processor_id()] */
+	sethi	%hi(cpu_mondo_counter), %g5
+	or	%g5, %lo(cpu_mondo_counter), %g5
+	sllx	%g3, 3, %g3
+	add	%g5, %g3, %g5
+	ldx	[%g5], %g3
+	add	%g3, 1, %g3
+	stx	%g3, [%g5]
+
 	/* Get CPU mondo queue base phys address into %g7.  */
 	ldx	[%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7
 
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index cc97a43268ee..d883c5951e8b 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2659,6 +2659,7 @@ void do_getpsr(struct pt_regs *regs)
 	}
 }
 
+u64 cpu_mondo_counter[NR_CPUS] = {0};
 struct trap_per_cpu trap_block[NR_CPUS];
 EXPORT_SYMBOL(trap_block);
 
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 395ec1800530..7d961f6e3907 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -375,6 +375,7 @@ tsb_flush:
 	 * %o1:	TSB base config pointer
 	 * %o2:	TSB huge config pointer, or NULL if none
 	 * %o3:	Hypervisor TSB descriptor physical address
+	 * %o4: Secondary context to load, if non-zero
 	 *
 	 * We have to run this whole thing with interrupts
 	 * disabled so that the current cpu doesn't change
@@ -387,6 +388,17 @@ __tsb_context_switch:
 	rdpr	%pstate, %g1
 	wrpr	%g1, PSTATE_IE, %pstate
 
+	brz,pn	%o4, 1f
+	 mov	SECONDARY_CONTEXT, %o5
+
+661:	stxa	%o4, [%o5] ASI_DMMU
+	.section .sun4v_1insn_patch, "ax"
+	.word	661b
+	stxa	%o4, [%o5] ASI_MMU
+	.previous
+	flush	%g6
+
+1:
 	TRAP_LOAD_TRAP_BLOCK(%g2, %g3)
 
 	stx	%o0, [%g2 + TRAP_PER_CPU_PGD_PADDR]
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 17bd2e167e07..df707a8ad311 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -35,6 +35,5 @@ void restore_processor_state(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 }