Merge "Merge android-4.4@d68ba9f (v4.4.89) into msm-4.4"

Documentation/filesystems/f2fs.txt

@@ -102,14 +102,16 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        collection, triggered in background when I/O subsystem is
                        idle. If background_gc=on, it will turn on the garbage
                        collection and if background_gc=off, garbage collection
-                       will be truned off. If background_gc=sync, it will turn
+                       will be turned off. If background_gc=sync, it will turn
                        on synchronous garbage collection running in background.
                        Default value for this option is on. So garbage
                        collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
 norecovery             Disable the roll-forward recovery routine, mounted read-
                        only (i.e., -o ro,disable_roll_forward)
-discard                Issue discard/TRIM commands when a segment is cleaned.
+discard/nodiscard      Enable/disable real-time discard in f2fs, if discard is
+                       enabled, f2fs will issue discard/TRIM commands when a
+		       segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
 		       for node from the end of main area.
@@ -129,6 +131,7 @@ inline_dentry          Enable the inline dir feature: data in new created
                        directory entries can be written into inode block. The
                        space of inode block which is used to store inline
                        dentries is limited to ~3.4k.
+noinline_dentry        Diable the inline dentry feature.
 flush_merge	       Merge concurrent cache_flush commands as much as possible
                        to eliminate redundant command issues. If the underlying
 		       device handles the cache_flush command relatively slowly,
@@ -145,10 +148,15 @@ extent_cache           Enable an extent cache based on rb-tree, it can cache
                        as many as extent which map between contiguous logical
                        address and physical address per inode, resulting in
                        increasing the cache hit ratio. Set by default.
-noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+noextent_cache         Disable an extent cache based on rb-tree explicitly, see
                        the above extent_cache mount option.
 noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
+data_flush             Enable data flushing before checkpoint in order to
+                       persist data of regular and symlink.
+mode=%s                Control block allocation mode which supports "adaptive"
+                       and "lfs". In "lfs" mode, there should be no random
+                       writes towards main area.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -192,7 +200,7 @@ Files in /sys/fs/f2fs/<devname>
                               policy for garbage collection. Setting gc_idle = 0
                               (default) will disable this option. Setting
                               gc_idle = 1 will select the Cost Benefit approach
-                              & setting gc_idle = 2 will select the greedy aproach.
+                              & setting gc_idle = 2 will select the greedy approach.
 
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
@@ -298,7 +306,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
 file. Each file is dump_ssa and dump_sit.
 
 The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
-It shows on-disk inode information reconized by a given inode number, and is
+It shows on-disk inode information recognized by a given inode number, and is
 able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
 ./dump_sit respectively.
 

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 85
+SUBLEVEL = 89
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

android/configs/README

@@ -1,15 +0,0 @@
-The files in this directory are meant to be used as a base for an Android
-kernel config. All devices should have the options in android-base.cfg enabled.
-While not mandatory, the options in android-recommended.cfg enable advanced
-Android features.
-
-Assuming you already have a minimalist defconfig for your device, a possible
-way to enable these options would be:
-
-     ARCH=<arch> scripts/kconfig/merge_config.sh <path_to>/<device>_defconfig android/configs/android-base.cfg android/configs/android-recommended.cfg
-
-This will generate a .config that can then be used to save a new defconfig or
-compile a new kernel with Android features enabled.
-
-Because there is no tool to consistently generate these config fragments,
-lets keep them alphabetically sorted instead of random.

android/configs/android-base-arm64.cfg

@@ -1,5 +0,0 @@
-#  KEEP ALPHABETICALLY SORTED
-CONFIG_ARMV8_DEPRECATED=y
-CONFIG_CP15_BARRIER_EMULATION=y
-CONFIG_SETEND_EMULATION=y
-CONFIG_SWP_EMULATION=y

android/configs/android-base.cfg

@@ -1,164 +0,0 @@
-#  KEEP ALPHABETICALLY SORTED
-# CONFIG_DEVKMEM is not set
-# CONFIG_DEVMEM is not set
-# CONFIG_FHANDLE is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_NFSD is not set
-# CONFIG_NFS_FS is not set
-# CONFIG_OABI_COMPAT is not set
-# CONFIG_SYSVIPC is not set
-# CONFIG_USELIB is not set
-CONFIG_ANDROID=y
-CONFIG_ANDROID_BINDER_IPC=y
-CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder
-CONFIG_ANDROID_LOW_MEMORY_KILLER=y
-CONFIG_ASHMEM=y
-CONFIG_AUDIT=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_DEFAULT_SECURITY_SELINUX=y
-CONFIG_EMBEDDED=y
-CONFIG_FB=y
-CONFIG_HARDENED_USERCOPY=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_INET=y
-CONFIG_INET_DIAG_DESTROY=y
-CONFIG_INET_ESP=y
-CONFIG_INET_XFRM_MODE_TUNNEL=y
-CONFIG_IP6_NF_FILTER=y
-CONFIG_IP6_NF_IPTABLES=y
-CONFIG_IP6_NF_MANGLE=y
-CONFIG_IP6_NF_RAW=y
-CONFIG_IP6_NF_TARGET_REJECT=y
-CONFIG_IPV6=y
-CONFIG_IPV6_MIP6=y
-CONFIG_IPV6_MULTIPLE_TABLES=y
-CONFIG_IPV6_OPTIMISTIC_DAD=y
-CONFIG_IPV6_ROUTER_PREF=y
-CONFIG_IPV6_ROUTE_INFO=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_ARPFILTER=y
-CONFIG_IP_NF_ARPTABLES=y
-CONFIG_IP_NF_ARP_MANGLE=y
-CONFIG_IP_NF_FILTER=y
-CONFIG_IP_NF_IPTABLES=y
-CONFIG_IP_NF_MANGLE=y
-CONFIG_IP_NF_MATCH_AH=y
-CONFIG_IP_NF_MATCH_ECN=y
-CONFIG_IP_NF_MATCH_TTL=y
-CONFIG_IP_NF_NAT=y
-CONFIG_IP_NF_RAW=y
-CONFIG_IP_NF_SECURITY=y
-CONFIG_IP_NF_TARGET_MASQUERADE=y
-CONFIG_IP_NF_TARGET_NETMAP=y
-CONFIG_IP_NF_TARGET_REDIRECT=y
-CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_NET=y
-CONFIG_NETDEVICES=y
-CONFIG_NETFILTER=y
-CONFIG_NETFILTER_XT_MATCH_COMMENT=y
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
-CONFIG_NETFILTER_XT_MATCH_HELPER=y
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
-CONFIG_NETFILTER_XT_MATCH_LENGTH=y
-CONFIG_NETFILTER_XT_MATCH_LIMIT=y
-CONFIG_NETFILTER_XT_MATCH_MAC=y
-CONFIG_NETFILTER_XT_MATCH_MARK=y
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
-CONFIG_NETFILTER_XT_MATCH_POLICY=y
-CONFIG_NETFILTER_XT_MATCH_QTAGUID=y
-CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
-CONFIG_NETFILTER_XT_MATCH_QUOTA=y
-CONFIG_NETFILTER_XT_MATCH_SOCKET=y
-CONFIG_NETFILTER_XT_MATCH_STATE=y
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
-CONFIG_NETFILTER_XT_MATCH_STRING=y
-CONFIG_NETFILTER_XT_MATCH_TIME=y
-CONFIG_NETFILTER_XT_MATCH_U32=y
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
-CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
-CONFIG_NETFILTER_XT_TARGET_MARK=y
-CONFIG_NETFILTER_XT_TARGET_NFLOG=y
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
-CONFIG_NETFILTER_XT_TARGET_SECMARK=y
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
-CONFIG_NETFILTER_XT_TARGET_TPROXY=y
-CONFIG_NETFILTER_XT_TARGET_TRACE=y
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_CLS_U32=y
-CONFIG_NET_EMATCH=y
-CONFIG_NET_EMATCH_U32=y
-CONFIG_NET_KEY=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_HTB=y
-CONFIG_NF_CONNTRACK=y
-CONFIG_NF_CONNTRACK_AMANDA=y
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CONNTRACK_FTP=y
-CONFIG_NF_CONNTRACK_H323=y
-CONFIG_NF_CONNTRACK_IPV4=y
-CONFIG_NF_CONNTRACK_IPV6=y
-CONFIG_NF_CONNTRACK_IRC=y
-CONFIG_NF_CONNTRACK_NETBIOS_NS=y
-CONFIG_NF_CONNTRACK_PPTP=y
-CONFIG_NF_CONNTRACK_SANE=y
-CONFIG_NF_CONNTRACK_SECMARK=y
-CONFIG_NF_CONNTRACK_TFTP=y
-CONFIG_NF_CT_NETLINK=y
-CONFIG_NF_CT_PROTO_DCCP=y
-CONFIG_NF_CT_PROTO_SCTP=y
-CONFIG_NF_CT_PROTO_UDPLITE=y
-CONFIG_NF_NAT=y
-CONFIG_NO_HZ=y
-CONFIG_PACKET=y
-CONFIG_PM_AUTOSLEEP=y
-CONFIG_PM_WAKELOCKS=y
-CONFIG_PPP=y
-CONFIG_PPPOLAC=y
-CONFIG_PPPOPNS=y
-CONFIG_PPP_BSDCOMP=y
-CONFIG_PPP_DEFLATE=y
-CONFIG_PPP_MPPE=y
-CONFIG_PREEMPT=y
-CONFIG_PROFILING=y
-CONFIG_RANDOMIZE_BASE=y
-CONFIG_RTC_CLASS=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_SECCOMP=y
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_STAGING=y
-CONFIG_SYNC=y
-CONFIG_TUN=y
-CONFIG_UID_SYS_STATS=y
-CONFIG_UNIX=y
-CONFIG_USB_CONFIGFS=y
-CONFIG_USB_CONFIGFS_F_ACC=y
-CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y
-CONFIG_USB_CONFIGFS_F_FS=y
-CONFIG_USB_CONFIGFS_F_MIDI=y
-CONFIG_USB_CONFIGFS_F_MTP=y
-CONFIG_USB_CONFIGFS_F_PTP=y
-CONFIG_USB_CONFIGFS_UEVENT=y
-CONFIG_USB_GADGET=y
-CONFIG_XFRM_USER=y

android/configs/android-recommended.cfg

@@ -1,140 +0,0 @@
-#  KEEP ALPHABETICALLY SORTED
-# CONFIG_AIO is not set
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_NF_CONNTRACK_SIP is not set
-# CONFIG_PM_WAKELOCKS_GC is not set
-# CONFIG_VT is not set
-CONFIG_ANDROID_TIMED_GPIO=y
-CONFIG_ARM64_SW_TTBR0_PAN=y
-CONFIG_ARM_KERNMEM_PERMS=y
-CONFIG_ARM64_SW_TTBR0_PAN=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_CC_STACKPROTECTOR_STRONG=y
-CONFIG_COMPACTION=y
-CONFIG_CPU_SW_DOMAIN_PAN=y
-CONFIG_DEBUG_RODATA=y
-CONFIG_DM_CRYPT=y
-CONFIG_DM_UEVENT=y
-CONFIG_DM_VERITY=y
-CONFIG_DM_VERITY_FEC=y
-CONFIG_DRAGONRISE_FF=y
-CONFIG_ENABLE_DEFAULT_TRACERS=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_FUSE_FS=y
-CONFIG_GREENASIA_FF=y
-CONFIG_HIDRAW=y
-CONFIG_HID_A4TECH=y
-CONFIG_HID_ACRUX=y
-CONFIG_HID_ACRUX_FF=y
-CONFIG_HID_APPLE=y
-CONFIG_HID_BELKIN=y
-CONFIG_HID_CHERRY=y
-CONFIG_HID_CHICONY=y
-CONFIG_HID_CYPRESS=y
-CONFIG_HID_DRAGONRISE=y
-CONFIG_HID_ELECOM=y
-CONFIG_HID_EMS_FF=y
-CONFIG_HID_EZKEY=y
-CONFIG_HID_GREENASIA=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_HOLTEK=y
-CONFIG_HID_KENSINGTON=y
-CONFIG_HID_KEYTOUCH=y
-CONFIG_HID_KYE=y
-CONFIG_HID_LCPOWER=y
-CONFIG_HID_LOGITECH=y
-CONFIG_HID_LOGITECH_DJ=y
-CONFIG_HID_MAGICMOUSE=y
-CONFIG_HID_MICROSOFT=y
-CONFIG_HID_MONTEREY=y
-CONFIG_HID_MULTITOUCH=y
-CONFIG_HID_NTRIG=y
-CONFIG_HID_ORTEK=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_PICOLCD=y
-CONFIG_HID_PRIMAX=y
-CONFIG_HID_PRODIKEYS=y
-CONFIG_HID_ROCCAT=y
-CONFIG_HID_SAITEK=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SMARTJOYPLUS=y
-CONFIG_HID_SONY=y
-CONFIG_HID_SPEEDLINK=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_HID_THRUSTMASTER=y
-CONFIG_HID_TIVO=y
-CONFIG_HID_TOPSEED=y
-CONFIG_HID_TWINHAN=y
-CONFIG_HID_UCLOGIC=y
-CONFIG_HID_WACOM=y
-CONFIG_HID_WALTOP=y
-CONFIG_HID_WIIMOTE=y
-CONFIG_HID_ZEROPLUS=y
-CONFIG_HID_ZYDACRON=y
-CONFIG_INPUT_EVDEV=y
-CONFIG_INPUT_GPIO=y
-CONFIG_INPUT_JOYSTICK=y
-CONFIG_INPUT_KEYCHORD=y
-CONFIG_INPUT_KEYRESET=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_TABLET=y
-CONFIG_INPUT_UINPUT=y
-CONFIG_ION=y
-CONFIG_JOYSTICK_XPAD=y
-CONFIG_JOYSTICK_XPAD_FF=y
-CONFIG_JOYSTICK_XPAD_LEDS=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_KSM=y
-CONFIG_LOGIG940_FF=y
-CONFIG_LOGIRUMBLEPAD2_FF=y
-CONFIG_LOGITECH_FF=y
-CONFIG_MD=y
-CONFIG_MEDIA_SUPPORT=y
-CONFIG_MEMORY_STATE_TIME=y
-CONFIG_MSDOS_FS=y
-CONFIG_PANIC_TIMEOUT=5
-CONFIG_PANTHERLORD_FF=y
-CONFIG_PERF_EVENTS=y
-CONFIG_PM_DEBUG=y
-CONFIG_PM_RUNTIME=y
-CONFIG_PM_WAKELOCKS_LIMIT=0
-CONFIG_POWER_SUPPLY=y
-CONFIG_PSTORE=y
-CONFIG_PSTORE_CONSOLE=y
-CONFIG_PSTORE_RAM=y
-CONFIG_QFMT_V2=y
-CONFIG_QUOTA=y
-CONFIG_QUOTACTL=y
-CONFIG_QUOTA_NETLINK_INTERFACE=y
-CONFIG_QUOTA_TREE=y
-CONFIG_SCHEDSTATS=y
-CONFIG_SMARTJOYPLUS_FF=y
-CONFIG_SND=y
-CONFIG_SOUND=y
-CONFIG_SUSPEND_TIME=y
-CONFIG_TABLET_USB_ACECAD=y
-CONFIG_TABLET_USB_AIPTEK=y
-CONFIG_TABLET_USB_GTCO=y
-CONFIG_TABLET_USB_HANWANG=y
-CONFIG_TABLET_USB_KBTAB=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_TASK_XACCT=y
-CONFIG_TIMER_STATS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_UHID=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB_USBNET=y
-CONFIG_VFAT_FS=y

arch/alpha/include/asm/types.h

@@ -1,6 +1,6 @@
 #ifndef _ALPHA_TYPES_H
 #define _ALPHA_TYPES_H
 
-#include <asm-generic/int-ll64.h>
+#include <uapi/asm/types.h>
 
 #endif /* _ALPHA_TYPES_H */

arch/alpha/include/uapi/asm/types.h

@@ -9,8 +9,18 @@
  * need to be careful to avoid a name clashes.
  */
 
-#ifndef __KERNEL__
+/*
+ * This is here because we used to use l64 for alpha
+ * and we don't want to impact user mode with our change to ll64
+ * in the kernel.
+ *
+ * However, some user programs are fine with this.  They can
+ * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here.
+ */
+#if !defined(__SANE_USERSPACE_TYPES__) && !defined(__KERNEL__)
 #include <asm-generic/int-l64.h>
+#else
+#include <asm-generic/int-ll64.h>
 #endif
 
 #endif /* _UAPI_ALPHA_TYPES_H */

arch/arc/kernel/entry.S

@@ -104,6 +104,12 @@ ENTRY(EV_MachineCheck)
 	lr  r0, [efa]
 	mov r1, sp
 
+	; hardware auto-disables MMU, re-enable it to allow kernel vaddr
+	; access for say stack unwinding of modules for crash dumps
+	lr	r3, [ARC_REG_PID]
+	or	r3, r3, MMU_ENABLE
+	sr	r3, [ARC_REG_PID]
+
 	lsr  	r3, r2, 8
 	bmsk 	r3, r3, 7
 	brne    r3, ECR_C_MCHK_DUP_TLB, 1f

arch/arc/mm/tlb.c

@@ -885,9 +885,6 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
 
 	local_irq_save(flags);
 
-	/* re-enable the MMU */
-	write_aux_reg(ARC_REG_PID, MMU_ENABLE | read_aux_reg(ARC_REG_PID));
-
 	/* loop thru all sets of TLB */
 	for (set = 0; set < mmu->sets; set++) {
 

arch/arm/kvm/mmu.c

@@ -831,24 +831,25 @@ void stage2_unmap_vm(struct kvm *kvm)
  * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
  * underlying level-2 and level-3 tables before freeing the actual level-1 table
  * and setting the struct pointer to NULL.
- *
- * Note we don't need locking here as this is only called when the VM is
- * destroyed, which can only be done once.
  */
 void kvm_free_stage2_pgd(struct kvm *kvm)
 {
-	if (kvm->arch.pgd == NULL)
-		return;
+	void *pgd = NULL;
+	void *hwpgd = NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	if (kvm->arch.pgd) {
+		unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+		pgd = READ_ONCE(kvm->arch.pgd);
+		hwpgd = kvm_get_hwpgd(kvm);
+		kvm->arch.pgd = NULL;
+	}
 	spin_unlock(&kvm->mmu_lock);
 
-	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(kvm->arch.pgd);
-
-	kvm->arch.pgd = NULL;
+	if (hwpgd)
+		kvm_free_hwpgd(hwpgd);
+	if (KVM_PREALLOC_LEVEL > 0 && pgd)
+		kfree(pgd);
 }
 
 static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,

arch/arm/mm/fault.c

@@ -314,8 +314,11 @@ retry:
 	 * signal first. We do not need to release the mmap_sem because
 	 * it would already be released in __lock_page_or_retry in
 	 * mm/filemap.c. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return 0;
+	}
 
 	/*
 	 * Major/minor page fault accounting is only done on the

arch/arm64/kernel/fpsimd.c

@@ -202,9 +202,11 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 void fpsimd_flush_thread(void)
 {
+	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	preempt_enable();
 }
 
 /*

arch/arm64/mm/fault.c

@@ -370,8 +370,11 @@ retry:
 	 * signal first. We do not need to release the mmap_sem because it
 	 * would already be released in __lock_page_or_retry in mm/filemap.c.
 	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return 0;
+	}
 
 	/*
 	 * Major/minor page fault accounting is only done on the initial

arch/mips/math-emu/dp_fmax.c

@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 		return ys ? x : y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
 	else if (xs < ys)
 		return x;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return x;
-	else if (xe < ye)
-		return y;
+	/* Signs of inputs are equal, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return y;
+		return x;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return y;
-	return x;
+		return x;
+	return y;
 }
 
 union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754dp_inf(xs & ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 		return y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
 		return y;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
 		return y;
-	return x;
+	else if (xm > ym)
+		return x;
+	else if (xs == 0)
+		return x;
+	return y;
 }

arch/mips/math-emu/dp_fmin.c

@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 		return ys ? y : x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
 	else if (xs < ys)
 		return y;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return y;
-	else if (xe < ye)
-		return x;
+	/* Signs of inputs are the same, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return x;
+		return y;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return x;
-	return y;
+		return y;
+	return x;
 }
 
 union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754dp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754dp_inf(xs | ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		return x;
+		return y;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-		return y;
+		return x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754dp_zero(1);
+		return ieee754dp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
 		return x;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
+		return x;
+	else if (xm > ym)
+		return y;
+	else if (xs == 1)
 		return x;
 	return y;
 }

arch/mips/math-emu/sp_fmax.c

@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 		return ys ? x : y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
 	else if (xs < ys)
 		return x;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return x;
-	else if (xe < ye)
-		return y;
+	/* Signs of inputs are equal, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return y;
+		return x;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return y;
-	return x;
+		return x;
+	return y;
 }
 
 union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754sp_inf(xs & ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 		return y;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs & ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
 		return y;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
 		return y;
-	return x;
+	else if (xm > ym)
+		return x;
+	else if (xs == 0)
+		return x;
+	return y;
 }

arch/mips/math-emu/sp_fmin.c

@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 		return ys ? y : x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
 	else if (xs < ys)
 		return y;
 
-	/* Compare exponent */
-	if (xe > ye)
-		return y;
-	else if (xe < ye)
-		return x;
+	/* Signs of inputs are the same, let's compare exponents */
+	if (xs == 0) {
+		/* Inputs are both positive */
+		if (xe > ye)
+			return y;
+		else if (xe < ye)
+			return x;
+	} else {
+		/* Inputs are both negative */
+		if (xe > ye)
+			return x;
+		else if (xe < ye)
+			return y;
+	}
 
-	/* Compare mantissa */
+	/* Signs and exponents of inputs are equal, let's compare mantissas */
+	if (xs == 0) {
+		/* Inputs are both positive, with equal signs and exponents */
+		if (xm <= ym)
+			return x;
+		return y;
+	}
+	/* Inputs are both negative, with equal signs and exponents */
 	if (xm <= ym)
-		return x;
-	return y;
+		return y;
+	return x;
 }
 
 union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
 		return ieee754sp_nanxcpt(x);
 
-	/* numbers are preferred to NaNs */
+	/*
+	 * Quiet NaN handling
+	 */
+
+	/*
+	 *    The case of both inputs quiet NaNs
+	 */
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+		return x;
+
+	/*
+	 *    The cases of exactly one input quiet NaN (numbers
+	 *    are here preferred as returned values to NaNs)
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
 		return x;
 
-	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 	/*
 	 * Infinity and zero handling
 	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+		return ieee754sp_inf(xs | ys);
+
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		return x;
+		return y;
 
-	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
-		return y;
+		return x;
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		if (xs == ys)
-			return x;
-		return ieee754sp_zero(1);
+		return ieee754sp_zero(xs | ys);
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
 		return x;
 
 	/* Compare mantissa */
-	if (xm <= ym)
+	if (xm < ym)
+		return x;
+	else if (xm > ym)
+		return y;
+	else if (xs == 1)
 		return x;
 	return y;
 }

arch/powerpc/kernel/align.c

@@ -236,6 +236,28 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
 
 #define SWIZ_PTR(p)		((unsigned char __user *)((p) ^ swiz))
 
+#define __get_user_or_set_dar(_regs, _dest, _addr)		\
+	({							\
+		int rc = 0;					\
+		typeof(_addr) __addr = (_addr);			\
+		if (__get_user_inatomic(_dest, __addr)) {	\
+			_regs->dar = (unsigned long)__addr;	\
+			rc = -EFAULT;				\
+		}						\
+		rc;						\
+	})
+
+#define __put_user_or_set_dar(_regs, _src, _addr)		\
+	({							\
+		int rc = 0;					\
+		typeof(_addr) __addr = (_addr);			\
+		if (__put_user_inatomic(_src, __addr)) {	\
+			_regs->dar = (unsigned long)__addr;	\
+			rc = -EFAULT;				\
+		}						\
+		rc;						\
+	})
+
 static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 			    unsigned int reg, unsigned int nb,
 			    unsigned int flags, unsigned int instr,
@@ -264,9 +286,10 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 		} else {
 			unsigned long pc = regs->nip ^ (swiz & 4);
 
-			if (__get_user_inatomic(instr,
-						(unsigned int __user *)pc))
+			if (__get_user_or_set_dar(regs, instr,
+						  (unsigned int __user *)pc))
 				return -EFAULT;
+
 			if (swiz == 0 && (flags & SW))
 				instr = cpu_to_le32(instr);
 			nb = (instr >> 11) & 0x1f;
@@ -310,31 +333,31 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 			       ((nb0 + 3) / 4) * sizeof(unsigned long));
 
 		for (i = 0; i < nb; ++i, ++p)
-			if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
-						SWIZ_PTR(p)))
+			if (__get_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz),
+						  SWIZ_PTR(p)))
 				return -EFAULT;
 		if (nb0 > 0) {
 			rptr = &regs->gpr[0];
 			addr += nb;
 			for (i = 0; i < nb0; ++i, ++p)
-				if (__get_user_inatomic(REG_BYTE(rptr,
-								 i ^ bswiz),
-							SWIZ_PTR(p)))
+				if (__get_user_or_set_dar(regs,
+							  REG_BYTE(rptr, i ^ bswiz),
+							  SWIZ_PTR(p)))
 					return -EFAULT;
 		}
 
 	} else {
 		for (i = 0; i < nb; ++i, ++p)
-			if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
-						SWIZ_PTR(p)))
+			if (__put_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz),
+						  SWIZ_PTR(p)))
 				return -EFAULT;
 		if (nb0 > 0) {
 			rptr = &regs->gpr[0];
 			addr += nb;
 			for (i = 0; i < nb0; ++i, ++p)
-				if (__put_user_inatomic(REG_BYTE(rptr,
-								 i ^ bswiz),
-							SWIZ_PTR(p)))
+				if (__put_user_or_set_dar(regs,
+							  REG_BYTE(rptr, i ^ bswiz),
+							  SWIZ_PTR(p)))
 					return -EFAULT;
 		}
 	}
@@ -346,29 +369,32 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
  * Only POWER6 has these instructions, and it does true little-endian,
  * so we don't need the address swizzling.
  */
-static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg,
-			   unsigned int flags)
+static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
+			   unsigned int reg, unsigned int flags)
 {
 	char *ptr0 = (char *) &current->thread.TS_FPR(reg);
 	char *ptr1 = (char *) &current->thread.TS_FPR(reg+1);
-	int i, ret, sw = 0;
+	int i, sw = 0;
 
 	if (reg & 1)
 		return 0;	/* invalid form: FRS/FRT must be even */
 	if (flags & SW)
 		sw = 7;
-	ret = 0;
+
 	for (i = 0; i < 8; ++i) {
 		if (!(flags & ST)) {
-			ret |= __get_user(ptr0[i^sw], addr + i);
-			ret |= __get_user(ptr1[i^sw], addr + i + 8);
+			if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		} else {
-			ret |= __put_user(ptr0[i^sw], addr + i);
-			ret |= __put_user(ptr1[i^sw], addr + i + 8);
+			if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		}
 	}
-	if (ret)
-		return -EFAULT;
+
 	return 1;	/* exception handled and fixed up */
 }
 
@@ -378,24 +404,27 @@ static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr,
 {
 	char *ptr0 = (char *)&regs->gpr[reg];
 	char *ptr1 = (char *)&regs->gpr[reg+1];
-	int i, ret, sw = 0;
+	int i, sw = 0;
 
 	if (reg & 1)
 		return 0;	/* invalid form: GPR must be even */
 	if (flags & SW)
 		sw = 7;
-	ret = 0;
+
 	for (i = 0; i < 8; ++i) {
 		if (!(flags & ST)) {
-			ret |= __get_user(ptr0[i^sw], addr + i);
-			ret |= __get_user(ptr1[i^sw], addr + i + 8);
+			if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		} else {
-			ret |= __put_user(ptr0[i^sw], addr + i);
-			ret |= __put_user(ptr1[i^sw], addr + i + 8);
+			if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i))
+				return -EFAULT;
+			if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8))
+				return -EFAULT;
 		}
 	}
-	if (ret)
-		return -EFAULT;
+
 	return 1;	/* exception handled and fixed up */
 }
 #endif /* CONFIG_PPC64 */
@@ -688,9 +717,14 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	for (j = 0; j < length; j += elsize) {
 		for (i = 0; i < elsize; ++i) {
 			if (flags & ST)
-				ret |= __put_user(ptr[i^sw], addr + i);
+				ret = __put_user_or_set_dar(regs, ptr[i^sw],
+							    addr + i);
 			else
-				ret |= __get_user(ptr[i^sw], addr + i);
+				ret = __get_user_or_set_dar(regs, ptr[i^sw],
+							    addr + i);
+
+			if (ret)
+				return ret;
 		}
 		ptr  += elsize;
 #ifdef __LITTLE_ENDIAN__
@@ -740,7 +774,7 @@ int fix_alignment(struct pt_regs *regs)
 	unsigned int dsisr;
 	unsigned char __user *addr;
 	unsigned long p, swiz;
-	int ret, i;
+	int i;
 	union data {
 		u64 ll;
 		double dd;
@@ -923,7 +957,7 @@ int fix_alignment(struct pt_regs *regs)
 		if (flags & F) {
 			/* Special case for 16-byte FP loads and stores */
 			PPC_WARN_ALIGNMENT(fp_pair, regs);
-			return emulate_fp_pair(addr, reg, flags);
+			return emulate_fp_pair(regs, addr, reg, flags);
 		} else {
 #ifdef CONFIG_PPC64
 			/* Special case for 16-byte loads and stores */
@@ -953,15 +987,12 @@ int fix_alignment(struct pt_regs *regs)
 		}
 
 		data.ll = 0;
-		ret = 0;
 		p = (unsigned long)addr;
 
 		for (i = 0; i < nb; i++)
-			ret |= __get_user_inatomic(data.v[start + i],
-						   SWIZ_PTR(p++));
-
-		if (unlikely(ret))
-			return -EFAULT;
+			if (__get_user_or_set_dar(regs, data.v[start + i],
+						  SWIZ_PTR(p++)))
+				return -EFAULT;
 
 	} else if (flags & F) {
 		data.ll = current->thread.TS_FPR(reg);
@@ -1031,15 +1062,13 @@ int fix_alignment(struct pt_regs *regs)
 			break;
 		}
 
-		ret = 0;
 		p = (unsigned long)addr;
 
 		for (i = 0; i < nb; i++)
-			ret |= __put_user_inatomic(data.v[start + i],
-						   SWIZ_PTR(p++));
+			if (__put_user_or_set_dar(regs, data.v[start + i],
+						  SWIZ_PTR(p++)))
+				return -EFAULT;
 
-		if (unlikely(ret))
-			return -EFAULT;
 	} else if (flags & F)
 		current->thread.TS_FPR(reg) = data.ll;
 	else

arch/x86/include/asm/elf.h

@@ -204,6 +204,7 @@ void set_personality_ia32(bool);
 
 #define ELF_CORE_COPY_REGS(pr_reg, regs)			\
 do {								\
+	unsigned long base;					\
 	unsigned v;						\
 	(pr_reg)[0] = (regs)->r15;				\
 	(pr_reg)[1] = (regs)->r14;				\
@@ -226,8 +227,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fs;			\
-	(pr_reg)[22] = current->thread.gs;			\
+	rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base;		\
+	rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base;	\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\

arch/x86/include/asm/io.h

@@ -304,13 +304,13 @@ static inline unsigned type in##bwl##_p(int port)			\
 static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 {									\
 	asm volatile("rep; outs" #bwl					\
-		     : "+S"(addr), "+c"(count) : "d"(port));		\
+		     : "+S"(addr), "+c"(count) : "d"(port) : "memory");	\
 }									\
 									\
 static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 {									\
 	asm volatile("rep; ins" #bwl					\
-		     : "+D"(addr), "+c"(count) : "d"(port));		\
+		     : "+D"(addr), "+c"(count) : "d"(port) : "memory");	\
 }
 
 BUILDIO(b, b, char)

block/blk-core.c

@@ -247,7 +247,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
  **/
 void blk_start_queue(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
+	WARN_ON(!in_interrupt() && !irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);

crypto/algif_skcipher.c

@@ -86,8 +86,13 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq)
 	}
 	sgl = sreq->tsg;
 	n = sg_nents(sgl);
-	for_each_sg(sgl, sg, n, i)
-		put_page(sg_page(sg));
+	for_each_sg(sgl, sg, n, i) {
+		struct page *page = sg_page(sg);
+
+		/* some SGs may not have a page mapped */
+		if (page && atomic_read(&page->_count))
+			put_page(page);
+	}
 
 	kfree(sreq->tsg);
 }
@@ -138,8 +143,10 @@ static int skcipher_alloc_sgl(struct sock *sk)
 		sg_init_table(sgl->sg, MAX_SGL_ENTS + 1);
 		sgl->cur = 0;
 
-		if (sg)
+		if (sg) {
 			sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
+			sg_unmark_end(sg + (MAX_SGL_ENTS - 1));
+		}
 
 		list_add_tail(&sgl->list, &ctx->tsgl);
 	}

drivers/android/Kconfig

@@ -44,6 +44,16 @@ config ANDROID_BINDER_IPC_32BIT
 
 	  Note that enabling this will break newer Android user-space.
 
+config ANDROID_BINDER_IPC_SELFTEST
+	bool "Android Binder IPC Driver Selftest"
+	depends on ANDROID_BINDER_IPC
+	---help---
+	  This feature allows binder selftest to run.
+
+	  Binder selftest checks the allocation and free of binder buffers
+	  exhaustively with combinations of various buffer sizes and
+	  alignments.
+
 endif # if ANDROID
 
 endmenu

drivers/android/Makefile

@@ -1,3 +1,4 @@
 ccflags-y += -I$(src)			# needed for trace events
 
 obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o binder_alloc.o
+obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o

drivers/android/binder.c

@@ -2481,7 +2481,6 @@ static int binder_translate_handle(struct flat_binder_object *fp,
 			     (u64)node->ptr);
 		binder_node_unlock(node);
 	} else {
-		int ret;
 		struct binder_ref_data dest_rdata;
 
 		binder_node_unlock(node);
@@ -4581,6 +4580,8 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	/*pr_info("binder_ioctl: %d:%d %x %lx\n",
 			proc->pid, current->pid, cmd, arg);*/
 
+	binder_selftest_alloc(&proc->alloc);
+
 	trace_binder_ioctl(cmd, arg);
 
 	ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
@@ -5426,6 +5427,8 @@ static void print_binder_proc_stats(struct seq_file *m,
 	count = binder_alloc_get_allocated_count(&proc->alloc);
 	seq_printf(m, "  buffers: %d\n", count);
 
+	binder_alloc_print_pages(m, &proc->alloc);
+
 	count = 0;
 	binder_inner_proc_lock(proc);
 	list_for_each_entry(w, &proc->todo, entry) {
@@ -5622,6 +5625,8 @@ static int __init binder_init(void)
 	struct binder_device *device;
 	struct hlist_node *tmp;
 
+	binder_alloc_shrinker_init();
+
 	atomic_set(&binder_transaction_log.cur, ~0U);
 	atomic_set(&binder_transaction_log_failed.cur, ~0U);
 	binder_deferred_workqueue = create_singlethread_workqueue("binder");

drivers/android/binder_alloc.c

@@ -27,9 +27,12 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/list_lru.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
+struct list_lru binder_alloc_lru;
+
 static DEFINE_MUTEX(binder_alloc_mmap_lock);
 
 enum {
@@ -48,14 +51,23 @@ module_param_named(debug_mask, binder_alloc_debug_mask,
 			pr_info(x); \
 	} while (0)
 
+static struct binder_buffer *binder_buffer_next(struct binder_buffer *buffer)
+{
+	return list_entry(buffer->entry.next, struct binder_buffer, entry);
+}
+
+static struct binder_buffer *binder_buffer_prev(struct binder_buffer *buffer)
+{
+	return list_entry(buffer->entry.prev, struct binder_buffer, entry);
+}
+
 static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
 				       struct binder_buffer *buffer)
 {
 	if (list_is_last(&buffer->entry, &alloc->buffers))
-		return alloc->buffer +
-		       alloc->buffer_size - (void *)buffer->data;
-	return (size_t)list_entry(buffer->entry.next,
-			  struct binder_buffer, entry) - (size_t)buffer->data;
+		return (u8 *)alloc->buffer +
+			alloc->buffer_size - (u8 *)buffer->data;
+	return (u8 *)binder_buffer_next(buffer)->data - (u8 *)buffer->data;
 }
 
 static void binder_insert_free_buffer(struct binder_alloc *alloc,
@@ -105,9 +117,9 @@ static void binder_insert_allocated_buffer_locked(
 		buffer = rb_entry(parent, struct binder_buffer, rb_node);
 		BUG_ON(buffer->free);
 
-		if (new_buffer < buffer)
+		if (new_buffer->data < buffer->data)
 			p = &parent->rb_left;
-		else if (new_buffer > buffer)
+		else if (new_buffer->data > buffer->data)
 			p = &parent->rb_right;
 		else
 			BUG();
@@ -122,18 +134,17 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked(
 {
 	struct rb_node *n = alloc->allocated_buffers.rb_node;
 	struct binder_buffer *buffer;
-	struct binder_buffer *kern_ptr;
+	void *kern_ptr;
 
-	kern_ptr = (struct binder_buffer *)(user_ptr - alloc->user_buffer_offset
-		- offsetof(struct binder_buffer, data));
+	kern_ptr = (void *)(user_ptr - alloc->user_buffer_offset);
 
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(buffer->free);
 
-		if (kern_ptr < buffer)
+		if (kern_ptr < buffer->data)
 			n = n->rb_left;
-		else if (kern_ptr > buffer)
+		else if (kern_ptr > buffer->data)
 			n = n->rb_right;
 		else {
 			/*
@@ -175,13 +186,14 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 }
 
 static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
-				    void *start, void *end,
-				    struct vm_area_struct *vma)
+				    void *start, void *end)
 {
 	void *page_addr;
 	unsigned long user_page_addr;
-	struct page **page;
-	struct mm_struct *mm;
+	struct binder_lru_page *page;
+	struct vm_area_struct *vma = NULL;
+	struct mm_struct *mm = NULL;
+	bool need_mm = false;
 
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: %s pages %pK-%pK\n", alloc->pid,
@@ -192,25 +204,27 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 
 	trace_binder_update_page_range(alloc, allocate, start, end);
 
-	if (vma)
-		mm = NULL;
-	else
-		mm = get_task_mm(alloc->tsk);
+	if (allocate == 0)
+		goto free_range;
+
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
+		if (!page->page_ptr) {
+			need_mm = true;
+			break;
+		}
+	}
+
+	/* Same as mmget_not_zero() in later kernel versions */
+	if (need_mm && atomic_inc_not_zero(&alloc->vma_vm_mm->mm_users))
+		mm = alloc->vma_vm_mm;
 
 	if (mm) {
 		down_write(&mm->mmap_sem);
 		vma = alloc->vma;
-		if (vma && mm != alloc->vma_vm_mm) {
-			pr_err("%d: vma mm and task mm mismatch\n",
-				alloc->pid);
-			vma = NULL;
-		}
 	}
 
-	if (allocate == 0)
-		goto free_range;
-
-	if (vma == NULL) {
+	if (!vma && need_mm) {
 		pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
 			alloc->pid);
 		goto err_no_vma;
@@ -218,18 +232,40 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
 		int ret;
+		bool on_lru;
+		size_t index;
 
-		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
+		index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		page = &alloc->pages[index];
 
-		BUG_ON(*page);
-		*page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
-		if (*page == NULL) {
+		if (page->page_ptr) {
+			trace_binder_alloc_lru_start(alloc, index);
+
+			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
+			WARN_ON(!on_lru);
+
+			trace_binder_alloc_lru_end(alloc, index);
+			continue;
+		}
+
+		if (WARN_ON(!vma))
+			goto err_page_ptr_cleared;
+
+		trace_binder_alloc_page_start(alloc, index);
+		page->page_ptr = alloc_page(GFP_KERNEL |
+					    __GFP_HIGHMEM |
+					    __GFP_ZERO);
+		if (!page->page_ptr) {
 			pr_err("%d: binder_alloc_buf failed for page at %pK\n",
 				alloc->pid, page_addr);
 			goto err_alloc_page_failed;
 		}
+		page->alloc = alloc;
+		INIT_LIST_HEAD(&page->lru);
+
 		ret = map_kernel_range_noflush((unsigned long)page_addr,
-					PAGE_SIZE, PAGE_KERNEL, page);
+					       PAGE_SIZE, PAGE_KERNEL,
+					       &page->page_ptr);
 		flush_cache_vmap((unsigned long)page_addr,
 				(unsigned long)page_addr + PAGE_SIZE);
 		if (ret != 1) {
@@ -239,12 +275,14 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		}
 		user_page_addr =
 			(uintptr_t)page_addr + alloc->user_buffer_offset;
-		ret = vm_insert_page(vma, user_page_addr, page[0]);
+		ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr);
 		if (ret) {
 			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
 			       alloc->pid, user_page_addr);
 			goto err_vm_insert_page_failed;
 		}
+
+		trace_binder_alloc_page_end(alloc, index);
 		/* vm_insert_page does not seem to increment the refcount */
 	}
 	if (mm) {
@@ -256,16 +294,27 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 free_range:
 	for (page_addr = end - PAGE_SIZE; page_addr >= start;
 	     page_addr -= PAGE_SIZE) {
-		page = &alloc->pages[(page_addr - alloc->buffer) / PAGE_SIZE];
-		if (vma)
-			zap_page_range(vma, (uintptr_t)page_addr +
-				alloc->user_buffer_offset, PAGE_SIZE, NULL);
+		bool ret;
+		size_t index;
+
+		index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		page = &alloc->pages[index];
+
+		trace_binder_free_lru_start(alloc, index);
+
+		ret = list_lru_add(&binder_alloc_lru, &page->lru);
+		WARN_ON(!ret);
+
+		trace_binder_free_lru_end(alloc, index);
+		continue;
+
 err_vm_insert_page_failed:
 		unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
 err_map_kernel_failed:
-		__free_page(*page);
-		*page = NULL;
+		__free_page(page->page_ptr);
+		page->page_ptr = NULL;
 err_alloc_page_failed:
+err_page_ptr_cleared:
 		;
 	}
 err_no_vma:
@@ -321,6 +370,9 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc,
 		return ERR_PTR(-ENOSPC);
 	}
 
+	/* Pad 0-size buffers so they get assigned unique addresses */
+	size = max(size, sizeof(void *));
+
 	while (n) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		BUG_ON(!buffer->free);
@@ -380,32 +432,35 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc,
 
 	has_page_addr =
 		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
-	if (n == NULL) {
-		if (size + sizeof(struct binder_buffer) + 4 >= buffer_size)
-			buffer_size = size; /* no room for other buffers */
-		else
-			buffer_size = size + sizeof(struct binder_buffer);
-	}
+	WARN_ON(n && buffer_size != size);
 	end_page_addr =
-		(void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size);
+		(void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
 	if (end_page_addr > has_page_addr)
 		end_page_addr = has_page_addr;
 	ret = binder_update_page_range(alloc, 1,
-	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL);
+	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr);
 	if (ret)
 		return ERR_PTR(ret);
 
+	if (buffer_size != size) {
+		struct binder_buffer *new_buffer;
+
+		new_buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+		if (!new_buffer) {
+			pr_err("%s: %d failed to alloc new buffer struct\n",
+			       __func__, alloc->pid);
+			goto err_alloc_buf_struct_failed;
+		}
+		new_buffer->data = (u8 *)buffer->data + size;
+		list_add(&new_buffer->entry, &buffer->entry);
+		new_buffer->free = 1;
+		binder_insert_free_buffer(alloc, new_buffer);
+	}
+
 	rb_erase(best_fit, &alloc->free_buffers);
 	buffer->free = 0;
 	buffer->free_in_progress = 0;
 	binder_insert_allocated_buffer_locked(alloc, buffer);
-	if (buffer_size != size) {
-		struct binder_buffer *new_buffer = (void *)buffer->data + size;
-
-		list_add(&new_buffer->entry, &buffer->entry);
-		new_buffer->free = 1;
-		binder_insert_free_buffer(alloc, new_buffer);
-	}
 	binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 		     "%d: binder_alloc_buf size %zd got %pK\n",
 		      alloc->pid, size, buffer);
@@ -420,6 +475,12 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc,
 			      alloc->pid, size, alloc->free_async_space);
 	}
 	return buffer;
+
+err_alloc_buf_struct_failed:
+	binder_update_page_range(alloc, 0,
+				 (void *)PAGE_ALIGN((uintptr_t)buffer->data),
+				 end_page_addr);
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
@@ -454,57 +515,58 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 
 static void *buffer_start_page(struct binder_buffer *buffer)
 {
-	return (void *)((uintptr_t)buffer & PAGE_MASK);
+	return (void *)((uintptr_t)buffer->data & PAGE_MASK);
 }
 
-static void *buffer_end_page(struct binder_buffer *buffer)
+static void *prev_buffer_end_page(struct binder_buffer *buffer)
 {
-	return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK);
+	return (void *)(((uintptr_t)(buffer->data) - 1) & PAGE_MASK);
 }
 
 static void binder_delete_free_buffer(struct binder_alloc *alloc,
 				      struct binder_buffer *buffer)
 {
 	struct binder_buffer *prev, *next = NULL;
-	int free_page_end = 1;
-	int free_page_start = 1;
-
+	bool to_free = true;
 	BUG_ON(alloc->buffers.next == &buffer->entry);
-	prev = list_entry(buffer->entry.prev, struct binder_buffer, entry);
+	prev = binder_buffer_prev(buffer);
 	BUG_ON(!prev->free);
-	if (buffer_end_page(prev) == buffer_start_page(buffer)) {
-		free_page_start = 0;
-		if (buffer_end_page(prev) == buffer_end_page(buffer))
-			free_page_end = 0;
+	if (prev_buffer_end_page(prev) == buffer_start_page(buffer)) {
+		to_free = false;
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			     "%d: merge free, buffer %pK share page with %pK\n",
-			      alloc->pid, buffer, prev);
+				   "%d: merge free, buffer %pK share page with %pK\n",
+				   alloc->pid, buffer->data, prev->data);
 	}
 
 	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
-		next = list_entry(buffer->entry.next,
-				  struct binder_buffer, entry);
-		if (buffer_start_page(next) == buffer_end_page(buffer)) {
-			free_page_end = 0;
-			if (buffer_start_page(next) ==
-			    buffer_start_page(buffer))
-				free_page_start = 0;
+		next = binder_buffer_next(buffer);
+		if (buffer_start_page(next) == buffer_start_page(buffer)) {
+			to_free = false;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%d: merge free, buffer %pK share page with %pK\n",
-				      alloc->pid, buffer, prev);
+					   "%d: merge free, buffer %pK share page with %pK\n",
+					   alloc->pid,
+					   buffer->data,
+					   next->data);
 		}
 	}
-	list_del(&buffer->entry);
-	if (free_page_start || free_page_end) {
+
+	if (PAGE_ALIGNED(buffer->data)) {
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			     "%d: merge free, buffer %pK do not share page%s%s with %pK or %pK\n",
-			     alloc->pid, buffer, free_page_start ? "" : " end",
-			     free_page_end ? "" : " start", prev, next);
-		binder_update_page_range(alloc, 0, free_page_start ?
-			buffer_start_page(buffer) : buffer_end_page(buffer),
-			(free_page_end ? buffer_end_page(buffer) :
-			buffer_start_page(buffer)) + PAGE_SIZE, NULL);
+				   "%d: merge free, buffer start %pK is page aligned\n",
+				   alloc->pid, buffer->data);
+		to_free = false;
 	}
+
+	if (to_free) {
+		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				   "%d: merge free, buffer %pK do not share page with %pK or %pK\n",
+				   alloc->pid, buffer->data,
+				   prev->data, next->data);
+		binder_update_page_range(alloc, 0, buffer_start_page(buffer),
+					 buffer_start_page(buffer) + PAGE_SIZE);
+	}
+	list_del(&buffer->entry);
+	kfree(buffer);
 }
 
 static void binder_free_buf_locked(struct binder_alloc *alloc,
@@ -525,8 +587,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->free);
 	BUG_ON(size > buffer_size);
 	BUG_ON(buffer->transaction != NULL);
-	BUG_ON((void *)buffer < alloc->buffer);
-	BUG_ON((void *)buffer > alloc->buffer + alloc->buffer_size);
+	BUG_ON(buffer->data < alloc->buffer);
+	BUG_ON(buffer->data > alloc->buffer + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
 		alloc->free_async_space += size + sizeof(struct binder_buffer);
@@ -538,14 +600,12 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 
 	binder_update_page_range(alloc, 0,
 		(void *)PAGE_ALIGN((uintptr_t)buffer->data),
-		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK),
-		NULL);
+		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK));
 
 	rb_erase(&buffer->rb_node, &alloc->allocated_buffers);
 	buffer->free = 1;
 	if (!list_is_last(&buffer->entry, &alloc->buffers)) {
-		struct binder_buffer *next = list_entry(buffer->entry.next,
-						struct binder_buffer, entry);
+		struct binder_buffer *next = binder_buffer_next(buffer);
 
 		if (next->free) {
 			rb_erase(&next->rb_node, &alloc->free_buffers);
@@ -553,8 +613,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 		}
 	}
 	if (alloc->buffers.next != &buffer->entry) {
-		struct binder_buffer *prev = list_entry(buffer->entry.prev,
-						struct binder_buffer, entry);
+		struct binder_buffer *prev = binder_buffer_prev(buffer);
 
 		if (prev->free) {
 			binder_delete_free_buffer(alloc, buffer);
@@ -640,14 +699,14 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	}
 	alloc->buffer_size = vma->vm_end - vma->vm_start;
 
-	if (binder_update_page_range(alloc, 1, alloc->buffer,
-				     alloc->buffer + PAGE_SIZE, vma)) {
+	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+	if (!buffer) {
 		ret = -ENOMEM;
-		failure_string = "alloc small buf";
-		goto err_alloc_small_buf_failed;
+		failure_string = "alloc buffer struct";
+		goto err_alloc_buf_struct_failed;
 	}
-	buffer = alloc->buffer;
-	INIT_LIST_HEAD(&alloc->buffers);
+
+	buffer->data = alloc->buffer;
 	list_add(&buffer->entry, &alloc->buffers);
 	buffer->free = 1;
 	binder_insert_free_buffer(alloc, buffer);
@@ -655,10 +714,12 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	barrier();
 	alloc->vma = vma;
 	alloc->vma_vm_mm = vma->vm_mm;
+	/* Same as mmgrab() in later kernel versions */
+	atomic_inc(&alloc->vma_vm_mm->mm_count);
 
 	return 0;
 
-err_alloc_small_buf_failed:
+err_alloc_buf_struct_failed:
 	kfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
@@ -678,14 +739,13 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 {
 	struct rb_node *n;
 	int buffers, page_count;
+	struct binder_buffer *buffer;
 
 	BUG_ON(alloc->vma);
 
 	buffers = 0;
 	mutex_lock(&alloc->mutex);
 	while ((n = rb_first(&alloc->allocated_buffers))) {
-		struct binder_buffer *buffer;
-
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 
 		/* Transaction should already have been freed */
@@ -695,28 +755,44 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		buffers++;
 	}
 
+	while (!list_empty(&alloc->buffers)) {
+		buffer = list_first_entry(&alloc->buffers,
+					  struct binder_buffer, entry);
+		WARN_ON(!buffer->free);
+
+		list_del(&buffer->entry);
+		WARN_ON_ONCE(!list_empty(&alloc->buffers));
+		kfree(buffer);
+	}
+
 	page_count = 0;
 	if (alloc->pages) {
 		int i;
 
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
 			void *page_addr;
+			bool on_lru;
 
-			if (!alloc->pages[i])
+			if (!alloc->pages[i].page_ptr)
 				continue;
 
+			on_lru = list_lru_del(&binder_alloc_lru,
+					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %pK not freed\n",
-				     __func__, alloc->pid, i, page_addr);
+				     "%s: %d: page %d at %pK %s\n",
+				     __func__, alloc->pid, i, page_addr,
+				     on_lru ? "on lru" : "active");
 			unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
-			__free_page(alloc->pages[i]);
+			__free_page(alloc->pages[i].page_ptr);
 			page_count++;
 		}
 		kfree(alloc->pages);
 		vfree(alloc->buffer);
 	}
 	mutex_unlock(&alloc->mutex);
+	if (alloc->vma_vm_mm)
+		mmdrop(alloc->vma_vm_mm);
 
 	binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE,
 		     "%s: %d buffers %d, pages %d\n",
@@ -753,6 +829,34 @@ void binder_alloc_print_allocated(struct seq_file *m,
 	mutex_unlock(&alloc->mutex);
 }
 
+/**
+ * binder_alloc_print_pages() - print page usage
+ * @m:     seq_file for output via seq_printf()
+ * @alloc: binder_alloc for this proc
+ */
+void binder_alloc_print_pages(struct seq_file *m,
+			      struct binder_alloc *alloc)
+{
+	struct binder_lru_page *page;
+	int i;
+	int active = 0;
+	int lru = 0;
+	int free = 0;
+
+	mutex_lock(&alloc->mutex);
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		page = &alloc->pages[i];
+		if (!page->page_ptr)
+			free++;
+		else if (list_empty(&page->lru))
+			active++;
+		else
+			lru++;
+	}
+	mutex_unlock(&alloc->mutex);
+	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
+}
+
 /**
  * binder_alloc_get_allocated_count() - return count of buffers
  * @alloc: binder_alloc for this proc
@@ -783,9 +887,111 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 void binder_alloc_vma_close(struct binder_alloc *alloc)
 {
 	WRITE_ONCE(alloc->vma, NULL);
-	WRITE_ONCE(alloc->vma_vm_mm, NULL);
 }
 
+/**
+ * binder_alloc_free_page() - shrinker callback to free pages
+ * @item:   item to free
+ * @lock:   lock protecting the item
+ * @cb_arg: callback argument
+ *
+ * Called from list_lru_walk() in binder_shrink_scan() to free
+ * up pages when the system is under memory pressure.
+ */
+enum lru_status binder_alloc_free_page(struct list_head *item,
+				       struct list_lru_one *lru,
+				       spinlock_t *lock,
+				       void *cb_arg)
+{
+	struct mm_struct *mm = NULL;
+	struct binder_lru_page *page = container_of(item,
+						    struct binder_lru_page,
+						    lru);
+	struct binder_alloc *alloc;
+	uintptr_t page_addr;
+	size_t index;
+	struct vm_area_struct *vma;
+
+	alloc = page->alloc;
+	if (!mutex_trylock(&alloc->mutex))
+		goto err_get_alloc_mutex_failed;
+
+	if (!page->page_ptr)
+		goto err_page_already_freed;
+
+	index = page - alloc->pages;
+	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+	vma = alloc->vma;
+	if (vma) {
+		/* Same as mmget_not_zero() in later kernel versions */
+		if (!atomic_inc_not_zero(&alloc->vma_vm_mm->mm_users))
+			goto err_mmget;
+		mm = alloc->vma_vm_mm;
+		if (!down_write_trylock(&mm->mmap_sem))
+			goto err_down_write_mmap_sem_failed;
+	}
+
+	list_lru_isolate(lru, item);
+	spin_unlock(lock);
+
+	if (vma) {
+		trace_binder_unmap_user_start(alloc, index);
+
+		zap_page_range(vma,
+			       page_addr +
+			       alloc->user_buffer_offset,
+			       PAGE_SIZE, NULL);
+
+		trace_binder_unmap_user_end(alloc, index);
+
+		up_write(&mm->mmap_sem);
+		mmput(mm);
+	}
+
+	trace_binder_unmap_kernel_start(alloc, index);
+
+	unmap_kernel_range(page_addr, PAGE_SIZE);
+	__free_page(page->page_ptr);
+	page->page_ptr = NULL;
+
+	trace_binder_unmap_kernel_end(alloc, index);
+
+	spin_lock(lock);
+	mutex_unlock(&alloc->mutex);
+	return LRU_REMOVED_RETRY;
+
+err_down_write_mmap_sem_failed:
+	mmput_async(mm);
+err_mmget:
+err_page_already_freed:
+	mutex_unlock(&alloc->mutex);
+err_get_alloc_mutex_failed:
+	return LRU_SKIP;
+}
+
+static unsigned long
+binder_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	unsigned long ret = list_lru_count(&binder_alloc_lru);
+	return ret;
+}
+
+static unsigned long
+binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	unsigned long ret;
+
+	ret = list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+			    NULL, sc->nr_to_scan);
+	return ret;
+}
+
+struct shrinker binder_shrinker = {
+	.count_objects = binder_shrink_count,
+	.scan_objects = binder_shrink_scan,
+	.seeks = DEFAULT_SEEKS,
+};
+
 /**
  * binder_alloc_init() - called by binder_open() for per-proc initialization
  * @alloc: binder_alloc for this proc
@@ -795,8 +1001,13 @@ void binder_alloc_vma_close(struct binder_alloc *alloc)
  */
 void binder_alloc_init(struct binder_alloc *alloc)
 {
-	alloc->tsk = current->group_leader;
 	alloc->pid = current->group_leader->pid;
 	mutex_init(&alloc->mutex);
+	INIT_LIST_HEAD(&alloc->buffers);
 }
 
+void binder_alloc_shrinker_init(void)
+{
+	list_lru_init(&binder_alloc_lru);
+	register_shrinker(&binder_shrinker);
+}

drivers/android/binder_alloc.h

@@ -21,7 +21,9 @@
 #include <linux/rtmutex.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/list_lru.h>
 
+extern struct list_lru binder_alloc_lru;
 struct binder_transaction;
 
 /**
@@ -57,7 +59,19 @@ struct binder_buffer {
 	size_t data_size;
 	size_t offsets_size;
 	size_t extra_buffers_size;
-	uint8_t data[0];
+	void *data;
+};
+
+/**
+ * struct binder_lru_page - page object used for binder shrinker
+ * @page_ptr: pointer to physical page in mmap'd space
+ * @lru:      entry in binder_alloc_lru
+ * @alloc:    binder_alloc for a proc
+ */
+struct binder_lru_page {
+	struct list_head lru;
+	struct page *page_ptr;
+	struct binder_alloc *alloc;
 };
 
 /**
@@ -75,8 +89,7 @@ struct binder_buffer {
  * @allocated_buffers:  rb tree of allocated buffers sorted by address
  * @free_async_space:   VA space available for async buffers. This is
  *                      initialized at mmap time to 1/2 the full VA space
- * @pages:              array of physical page addresses for each
- *                      page of mmap'd space
+ * @pages:              array of binder_lru_page
  * @buffer_size:        size of address space specified via mmap
  * @pid:                pid for associated binder_proc (invariant after init)
  *
@@ -87,7 +100,6 @@ struct binder_buffer {
  */
 struct binder_alloc {
 	struct mutex mutex;
-	struct task_struct *tsk;
 	struct vm_area_struct *vma;
 	struct mm_struct *vma_vm_mm;
 	void *buffer;
@@ -96,18 +108,27 @@ struct binder_alloc {
 	struct rb_root free_buffers;
 	struct rb_root allocated_buffers;
 	size_t free_async_space;
-	struct page **pages;
+	struct binder_lru_page *pages;
 	size_t buffer_size;
 	uint32_t buffer_free;
 	int pid;
 };
 
+#ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST
+void binder_selftest_alloc(struct binder_alloc *alloc);
+#else
+static inline void binder_selftest_alloc(struct binder_alloc *alloc) {}
+#endif
+enum lru_status binder_alloc_free_page(struct list_head *item,
+				       struct list_lru_one *lru,
+				       spinlock_t *lock, void *cb_arg);
 extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 						  size_t data_size,
 						  size_t offsets_size,
 						  size_t extra_buffers_size,
 						  int is_async);
 extern void binder_alloc_init(struct binder_alloc *alloc);
+void binder_alloc_shrinker_init(void);
 extern void binder_alloc_vma_close(struct binder_alloc *alloc);
 extern struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,
@@ -120,6 +141,8 @@ extern void binder_alloc_deferred_release(struct binder_alloc *alloc);
 extern int binder_alloc_get_allocated_count(struct binder_alloc *alloc);
 extern void binder_alloc_print_allocated(struct seq_file *m,
 					 struct binder_alloc *alloc);
+void binder_alloc_print_pages(struct seq_file *m,
+			      struct binder_alloc *alloc);
 
 /**
  * binder_alloc_get_free_async_space() - get free space available for async

drivers/android/binder_alloc_selftest.c

@@ -0,0 +1,310 @@
+/* binder_alloc_selftest.c
+ *
+ * Android IPC Subsystem
+ *
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm_types.h>
+#include <linux/err.h>
+#include "binder_alloc.h"
+
+#define BUFFER_NUM 5
+#define BUFFER_MIN_SIZE (PAGE_SIZE / 8)
+
+static bool binder_selftest_run = true;
+static int binder_selftest_failures;
+static DEFINE_MUTEX(binder_selftest_lock);
+
+/**
+ * enum buf_end_align_type - Page alignment of a buffer
+ * end with regard to the end of the previous buffer.
+ *
+ * In the pictures below, buf2 refers to the buffer we
+ * are aligning. buf1 refers to previous buffer by addr.
+ * Symbol [ means the start of a buffer, ] means the end
+ * of a buffer, and | means page boundaries.
+ */
+enum buf_end_align_type {
+	/**
+	 * @SAME_PAGE_UNALIGNED: The end of this buffer is on
+	 * the same page as the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 ][ ...
+	 * buf1 ]|[ buf2 ][ ...
+	 */
+	SAME_PAGE_UNALIGNED = 0,
+	/**
+	 * @SAME_PAGE_ALIGNED: When the end of the previous buffer
+	 * is not page aligned, the end of this buffer is on the
+	 * same page as the end of the previous buffer and is page
+	 * aligned. When the previous buffer is page aligned, the
+	 * end of this buffer is aligned to the next page boundary.
+	 * Examples:
+	 * buf1 ][ buf2 ]| ...
+	 * buf1 ]|[ buf2 ]| ...
+	 */
+	SAME_PAGE_ALIGNED,
+	/**
+	 * @NEXT_PAGE_UNALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 ][ ...
+	 */
+	NEXT_PAGE_UNALIGNED,
+	/**
+	 * @NEXT_PAGE_ALIGNED: The end of this buffer is on
+	 * the page next to the end of the previous buffer and
+	 * is page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 ]| ...
+	 * buf1 ]|[ buf2 | buf2 ]| ...
+	 */
+	NEXT_PAGE_ALIGNED,
+	/**
+	 * @NEXT_NEXT_UNALIGNED: The end of this buffer is on
+	 * the page that follows the page after the end of the
+	 * previous buffer and is not page aligned. Examples:
+	 * buf1 ][ buf2 | buf2 | buf2 ][ ...
+	 * buf1 ]|[ buf2 | buf2 | buf2 ][ ...
+	 */
+	NEXT_NEXT_UNALIGNED,
+	LOOP_END,
+};
+
+static void pr_err_size_seq(size_t *sizes, int *seq)
+{
+	int i;
+
+	pr_err("alloc sizes: ");
+	for (i = 0; i < BUFFER_NUM; i++)
+		pr_cont("[%zu]", sizes[i]);
+	pr_cont("\n");
+	pr_err("free seq: ");
+	for (i = 0; i < BUFFER_NUM; i++)
+		pr_cont("[%d]", seq[i]);
+	pr_cont("\n");
+}
+
+static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
+					 struct binder_buffer *buffer,
+					 size_t size)
+{
+	void *page_addr, *end;
+	int page_index;
+
+	end = (void *)PAGE_ALIGN((uintptr_t)buffer->data + size);
+	page_addr = buffer->data;
+	for (; page_addr < end; page_addr += PAGE_SIZE) {
+		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
+		if (!alloc->pages[page_index].page_ptr ||
+		    !list_empty(&alloc->pages[page_index].lru)) {
+			pr_err("expect alloc but is %s at page index %d\n",
+			       alloc->pages[page_index].page_ptr ?
+			       "lru" : "free", page_index);
+			return false;
+		}
+	}
+	return true;
+}
+
+static void binder_selftest_alloc_buf(struct binder_alloc *alloc,
+				      struct binder_buffer *buffers[],
+				      size_t *sizes, int *seq)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++) {
+		buffers[i] = binder_alloc_new_buf(alloc, sizes[i], 0, 0, 0);
+		if (IS_ERR(buffers[i]) ||
+		    !check_buffer_pages_allocated(alloc, buffers[i],
+						  sizes[i])) {
+			pr_err_size_seq(sizes, seq);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_free_buf(struct binder_alloc *alloc,
+				     struct binder_buffer *buffers[],
+				     size_t *sizes, int *seq, size_t end)
+{
+	int i;
+
+	for (i = 0; i < BUFFER_NUM; i++)
+		binder_alloc_free_buf(alloc, buffers[seq[i]]);
+
+	for (i = 0; i < end / PAGE_SIZE; i++) {
+		/**
+		 * Error message on a free page can be false positive
+		 * if binder shrinker ran during binder_alloc_free_buf
+		 * calls above.
+		 */
+		if (list_empty(&alloc->pages[i].lru)) {
+			pr_err_size_seq(sizes, seq);
+			pr_err("expect lru but is %s at page index %d\n",
+			       alloc->pages[i].page_ptr ? "alloc" : "free", i);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_free_page(struct binder_alloc *alloc)
+{
+	int i;
+	unsigned long count;
+
+	while ((count = list_lru_count(&binder_alloc_lru))) {
+		list_lru_walk(&binder_alloc_lru, binder_alloc_free_page,
+			      NULL, count);
+	}
+
+	for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
+		if (alloc->pages[i].page_ptr) {
+			pr_err("expect free but is %s at page index %d\n",
+			       list_empty(&alloc->pages[i].lru) ?
+			       "alloc" : "lru", i);
+			binder_selftest_failures++;
+		}
+	}
+}
+
+static void binder_selftest_alloc_free(struct binder_alloc *alloc,
+				       size_t *sizes, int *seq, size_t end)
+{
+	struct binder_buffer *buffers[BUFFER_NUM];
+
+	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+
+	/* Allocate from lru. */
+	binder_selftest_alloc_buf(alloc, buffers, sizes, seq);
+	if (list_lru_count(&binder_alloc_lru))
+		pr_err("lru list should be empty but is not\n");
+
+	binder_selftest_free_buf(alloc, buffers, sizes, seq, end);
+	binder_selftest_free_page(alloc);
+}
+
+static bool is_dup(int *seq, int index, int val)
+{
+	int i;
+
+	for (i = 0; i < index; i++) {
+		if (seq[i] == val)
+			return true;
+	}
+	return false;
+}
+
+/* Generate BUFFER_NUM factorial free orders. */
+static void binder_selftest_free_seq(struct binder_alloc *alloc,
+				     size_t *sizes, int *seq,
+				     int index, size_t end)
+{
+	int i;
+
+	if (index == BUFFER_NUM) {
+		binder_selftest_alloc_free(alloc, sizes, seq, end);
+		return;
+	}
+	for (i = 0; i < BUFFER_NUM; i++) {
+		if (is_dup(seq, index, i))
+			continue;
+		seq[index] = i;
+		binder_selftest_free_seq(alloc, sizes, seq, index + 1, end);
+	}
+}
+
+static void binder_selftest_alloc_size(struct binder_alloc *alloc,
+				       size_t *end_offset)
+{
+	int i;
+	int seq[BUFFER_NUM] = {0};
+	size_t front_sizes[BUFFER_NUM];
+	size_t back_sizes[BUFFER_NUM];
+	size_t last_offset, offset = 0;
+
+	for (i = 0; i < BUFFER_NUM; i++) {
+		last_offset = offset;
+		offset = end_offset[i];
+		front_sizes[i] = offset - last_offset;
+		back_sizes[BUFFER_NUM - i - 1] = front_sizes[i];
+	}
+	/*
+	 * Buffers share the first or last few pages.
+	 * Only BUFFER_NUM - 1 buffer sizes are adjustable since
+	 * we need one giant buffer before getting to the last page.
+	 */
+	back_sizes[0] += alloc->buffer_size - end_offset[BUFFER_NUM - 1];
+	binder_selftest_free_seq(alloc, front_sizes, seq, 0,
+				 end_offset[BUFFER_NUM - 1]);
+	binder_selftest_free_seq(alloc, back_sizes, seq, 0, alloc->buffer_size);
+}
+
+static void binder_selftest_alloc_offset(struct binder_alloc *alloc,
+					 size_t *end_offset, int index)
+{
+	int align;
+	size_t end, prev;
+
+	if (index == BUFFER_NUM) {
+		binder_selftest_alloc_size(alloc, end_offset);
+		return;
+	}
+	prev = index == 0 ? 0 : end_offset[index - 1];
+	end = prev;
+
+	BUILD_BUG_ON(BUFFER_MIN_SIZE * BUFFER_NUM >= PAGE_SIZE);
+
+	for (align = SAME_PAGE_UNALIGNED; align < LOOP_END; align++) {
+		if (align % 2)
+			end = ALIGN(end, PAGE_SIZE);
+		else
+			end += BUFFER_MIN_SIZE;
+		end_offset[index] = end;
+		binder_selftest_alloc_offset(alloc, end_offset, index + 1);
+	}
+}
+
+/**
+ * binder_selftest_alloc() - Test alloc and free of buffer pages.
+ * @alloc: Pointer to alloc struct.
+ *
+ * Allocate BUFFER_NUM buffers to cover all page alignment cases,
+ * then free them in all orders possible. Check that pages are
+ * correctly allocated, put onto lru when buffers are freed, and
+ * are freed when binder_alloc_free_page is called.
+ */
+void binder_selftest_alloc(struct binder_alloc *alloc)
+{
+	size_t end_offset[BUFFER_NUM];
+
+	if (!binder_selftest_run)
+		return;
+	mutex_lock(&binder_selftest_lock);
+	if (!binder_selftest_run || !alloc->vma)
+		goto done;
+	pr_info("STARTED\n");
+	binder_selftest_alloc_offset(alloc, end_offset, 0);
+	binder_selftest_run = false;
+	if (binder_selftest_failures > 0)
+		pr_info("%d tests FAILED\n", binder_selftest_failures);
+	else
+		pr_info("PASSED\n");
+
+done:
+	mutex_unlock(&binder_selftest_lock);
+}

drivers/android/binder_trace.h

@@ -291,6 +291,61 @@ TRACE_EVENT(binder_update_page_range,
 		  __entry->offset, __entry->size)
 );
 
+DECLARE_EVENT_CLASS(binder_lru_page_class,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index),
+	TP_STRUCT__entry(
+		__field(int, proc)
+		__field(size_t, page_index)
+	),
+	TP_fast_assign(
+		__entry->proc = alloc->pid;
+		__entry->page_index = page_index;
+	),
+	TP_printk("proc=%d page_index=%zu",
+		  __entry->proc, __entry->page_index)
+);
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_lru_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_free_lru_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_alloc_page_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_user_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_start,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
+DEFINE_EVENT(binder_lru_page_class, binder_unmap_kernel_end,
+	TP_PROTO(const struct binder_alloc *alloc, size_t page_index),
+	TP_ARGS(alloc, page_index));
+
 TRACE_EVENT(binder_command,
 	TP_PROTO(uint32_t cmd),
 	TP_ARGS(cmd),

drivers/ata/pata_amd.c

@@ -616,6 +616,7 @@ static const struct pci_device_id amd[] = {
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE),	8 },
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE),	8 },
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE),		9 },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE),	9 },
 
 	{ },
 };

drivers/ata/pata_cs5536.c

@@ -289,6 +289,7 @@ static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 static const struct pci_device_id cs5536[] = {
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE), },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE), },
 	{ },
 };
 

drivers/base/bus.c

@@ -737,7 +737,7 @@ int bus_add_driver(struct device_driver *drv)
 
 out_unregister:
 	kobject_put(&priv->kobj);
-	kfree(drv->p);
+	/* drv->p is freed in driver_release()  */
 	drv->p = NULL;
 out_put_bus:
 	bus_put(bus);

drivers/block/skd_main.c

@@ -2214,6 +2214,9 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 		 */
 		qcmd |= FIT_QCMD_MSGSIZE_64;
 
+	/* Make sure skd_msg_buf is written before the doorbell is triggered. */
+	smp_wmb();
+
 	SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND);
 
 }
@@ -2260,6 +2263,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 	qcmd = skspcl->mb_dma_address;
 	qcmd |= FIT_QCMD_QID_NORMAL + FIT_QCMD_MSGSIZE_128;
 
+	/* Make sure skd_msg_buf is written before the doorbell is triggered. */
+	smp_wmb();
+
 	SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND);
 }
 
@@ -4679,15 +4685,16 @@ static void skd_free_disk(struct skd_device *skdev)
 {
 	struct gendisk *disk = skdev->disk;
 
-	if (disk != NULL) {
-		struct request_queue *q = disk->queue;
+	if (disk && (disk->flags & GENHD_FL_UP))
+		del_gendisk(disk);
 
-		if (disk->flags & GENHD_FL_UP)
-			del_gendisk(disk);
-		if (q)
-			blk_cleanup_queue(q);
-		put_disk(disk);
+	if (skdev->queue) {
+		blk_cleanup_queue(skdev->queue);
+		skdev->queue = NULL;
+		disk->queue = NULL;
 	}
+
+	put_disk(disk);
 	skdev->disk = NULL;
 }
 

drivers/bluetooth/btusb.c

@@ -333,6 +333,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3410), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3416), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3459), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3494), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8821AE Bluetooth devices */
 	{ USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK },

drivers/cpufreq/cpufreq-dt.c

@@ -279,6 +279,13 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->cpuinfo.transition_latency = transition_latency;
 
+        /*
+         * Android: set default parameters for parity between schedutil and
+         * schedfreq
+         */
+	policy->up_transition_delay_us = transition_latency / NSEC_PER_USEC;
+	policy->down_transition_delay_us = 50000; /* 50ms */
+
 	return 0;
 
 out_free_cpufreq_table:

drivers/cpufreq/cpufreq_interactive.c

@@ -1825,6 +1825,7 @@ struct cpufreq_governor cpufreq_gov_interactive = {
 static int __init cpufreq_interactive_init(void)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	int ret = 0;
 
 	spin_lock_init(&speedchange_cpumask_lock);
 	mutex_init(&gov_lock);
@@ -1841,7 +1842,12 @@ static int __init cpufreq_interactive_init(void)
 	/* NB: wake up so the thread does not look hung to the freezer */
 	wake_up_process_no_notif(speedchange_task);
 
-	return cpufreq_register_governor(&cpufreq_gov_interactive);
+	ret = cpufreq_register_governor(&cpufreq_gov_interactive);
+	if (ret) {
+		kthread_stop(speedchange_task);
+		put_task_struct(speedchange_task);
+	}
+	return ret;
 }
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE

drivers/gpu/drm/i2c/adv7511.c

@@ -36,7 +36,10 @@ struct adv7511 {
 	bool edid_read;
 
 	wait_queue_head_t wq;
+	struct work_struct hpd_work;
+
 	struct drm_encoder *encoder;
+	struct drm_connector connector;
 
 	bool embedded_sync;
 	enum adv7511_sync_polarity vsync_polarity;
@@ -48,6 +51,10 @@ struct adv7511 {
 	struct gpio_desc *gpio_pd;
 };
 
+static const int edid_i2c_addr = 0x7e;
+static const int packet_i2c_addr = 0x70;
+static const int cec_i2c_addr = 0x78;
+
 static struct adv7511 *encoder_to_adv7511(struct drm_encoder *encoder)
 {
 	return to_encoder_slave(encoder)->slave_priv;
@@ -362,12 +369,19 @@ static void adv7511_power_on(struct adv7511 *adv7511)
 {
 	adv7511->current_edid_segment = -1;
 
-	regmap_write(adv7511->regmap, ADV7511_REG_INT(0),
-		     ADV7511_INT0_EDID_READY);
-	regmap_write(adv7511->regmap, ADV7511_REG_INT(1),
-		     ADV7511_INT1_DDC_ERROR);
 	regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER,
 			   ADV7511_POWER_POWER_DOWN, 0);
+	if (adv7511->i2c_main->irq) {
+		/*
+		 * Documentation says the INT_ENABLE registers are reset in
+		 * POWER_DOWN mode. My 7511w preserved the bits, however.
+		 * Still, let's be safe and stick to the documentation.
+		 */
+		regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(0),
+			     ADV7511_INT0_EDID_READY);
+		regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(1),
+			     ADV7511_INT1_DDC_ERROR);
+	}
 
 	/*
 	 * Per spec it is allowed to pulse the HDP signal to indicate that the
@@ -422,7 +436,27 @@ static bool adv7511_hpd(struct adv7511 *adv7511)
 	return false;
 }
 
-static int adv7511_irq_process(struct adv7511 *adv7511)
+static void adv7511_hpd_work(struct work_struct *work)
+{
+	struct adv7511 *adv7511 = container_of(work, struct adv7511, hpd_work);
+	enum drm_connector_status status;
+	unsigned int val;
+	int ret;
+	ret = regmap_read(adv7511->regmap, ADV7511_REG_STATUS, &val);
+	if (ret < 0)
+		status = connector_status_disconnected;
+	else if (val & ADV7511_STATUS_HPD)
+		status = connector_status_connected;
+	else
+		status = connector_status_disconnected;
+
+	if (adv7511->connector.status != status) {
+		adv7511->connector.status = status;
+		drm_kms_helper_hotplug_event(adv7511->connector.dev);
+	}
+}
+
+static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd)
 {
 	unsigned int irq0, irq1;
 	int ret;
@@ -438,8 +472,8 @@ static int adv7511_irq_process(struct adv7511 *adv7511)
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0);
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1);
 
-	if (irq0 & ADV7511_INT0_HDP && adv7511->encoder)
-		drm_helper_hpd_irq_event(adv7511->encoder->dev);
+	if (process_hpd && irq0 & ADV7511_INT0_HDP && adv7511->encoder)
+		schedule_work(&adv7511->hpd_work);
 
 	if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) {
 		adv7511->edid_read = true;
@@ -456,7 +490,7 @@ static irqreturn_t adv7511_irq_handler(int irq, void *devid)
 	struct adv7511 *adv7511 = devid;
 	int ret;
 
-	ret = adv7511_irq_process(adv7511);
+	ret = adv7511_irq_process(adv7511, true);
 	return ret < 0 ? IRQ_NONE : IRQ_HANDLED;
 }
 
@@ -473,7 +507,7 @@ static int adv7511_wait_for_edid(struct adv7511 *adv7511, int timeout)
 				adv7511->edid_read, msecs_to_jiffies(timeout));
 	} else {
 		for (; timeout > 0; timeout -= 25) {
-			ret = adv7511_irq_process(adv7511);
+			ret = adv7511_irq_process(adv7511, false);
 			if (ret < 0)
 				break;
 
@@ -567,13 +601,18 @@ static int adv7511_get_modes(struct drm_encoder *encoder,
 
 	/* Reading the EDID only works if the device is powered */
 	if (!adv7511->powered) {
-		regmap_write(adv7511->regmap, ADV7511_REG_INT(0),
-			     ADV7511_INT0_EDID_READY);
-		regmap_write(adv7511->regmap, ADV7511_REG_INT(1),
-			     ADV7511_INT1_DDC_ERROR);
 		regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER,
 				   ADV7511_POWER_POWER_DOWN, 0);
+		if (adv7511->i2c_main->irq) {
+			regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(0),
+				     ADV7511_INT0_EDID_READY);
+			regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(1),
+				     ADV7511_INT1_DDC_ERROR);
+		}
 		adv7511->current_edid_segment = -1;
+		/* Reset the EDID_I2C_ADDR register as it might be cleared */
+		regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR,
+				edid_i2c_addr);
 	}
 
 	edid = drm_do_get_edid(connector, adv7511_get_edid_block, adv7511);
@@ -849,10 +888,6 @@ static int adv7511_parse_dt(struct device_node *np,
 	return 0;
 }
 
-static const int edid_i2c_addr = 0x7e;
-static const int packet_i2c_addr = 0x70;
-static const int cec_i2c_addr = 0x78;
-
 static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 {
 	struct adv7511_link_config link_config;
@@ -913,6 +948,8 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	if (!adv7511->i2c_edid)
 		return -ENOMEM;
 
+	INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work);
+
 	if (i2c->irq) {
 		init_waitqueue_head(&adv7511->wq);
 

drivers/gpu/drm/i915/intel_uncore.c

@@ -635,7 +635,8 @@ hsw_unclaimed_reg_detect(struct drm_i915_private *dev_priv)
 			  "enabling oneshot unclaimed register reporting. "
 			  "Please use i915.mmio_debug=N for more information.\n");
 		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-		i915.mmio_debug = mmio_debug_once--;
+		i915.mmio_debug = mmio_debug_once;
+		mmio_debug_once = false;
 	}
 }
 

drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c

@@ -180,6 +180,10 @@ nvkm_pci_new_(const struct nvkm_pci_func *func, struct nvkm_device *device,
 		}
 	}
 
+#ifdef __BIG_ENDIAN
+	pci->msi = false;
+#endif
+
 	pci->msi = nvkm_boolopt(device->cfgopt, "NvMSI", pci->msi);
 	if (pci->msi && func->msi_rearm) {
 		pci->msi = pci_enable_msi(pci->pdev) == 0;

drivers/gpu/drm/ttm/ttm_page_alloc.c

@@ -612,7 +612,7 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 		} else {
 			pr_err("Failed to fill pool (%p)\n", pool);
 			/* If we have any pages left put them to the pool. */
-			list_for_each_entry(p, &pool->list, lru) {
+			list_for_each_entry(p, &new_pages, lru) {
 				++cpages;
 			}
 			list_splice(&new_pages, &pool->list);

drivers/hwtracing/intel_th/pci.c

@@ -72,6 +72,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6),
 		.driver_data = (kernel_ulong_t)0,
 	},
+	{
+		/* Cannon Lake H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa326),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Cannon Lake LP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6),
+		.driver_data = (kernel_ulong_t)0,
+	},
 	{ 0 },
 };
 

drivers/i2c/busses/i2c-ismt.c

@@ -339,8 +339,10 @@ static int ismt_process_desc(const struct ismt_desc *desc,
 			break;
 		case I2C_SMBUS_BLOCK_DATA:
 		case I2C_SMBUS_I2C_BLOCK_DATA:
-			memcpy(&data->block[1], dma_buffer, desc->rxbytes);
-			data->block[0] = desc->rxbytes;
+			if (desc->rxbytes != dma_buffer[0] + 1)
+				return -EMSGSIZE;
+
+			memcpy(data->block, dma_buffer, desc->rxbytes);
 			break;
 		}
 		return 0;

drivers/i2c/busses/i2c-jz4780.c

@@ -786,10 +786,6 @@ static int jz4780_i2c_probe(struct platform_device *pdev)
 
 	jz4780_i2c_writew(i2c, JZ4780_I2C_INTM, 0x0);
 
-	i2c->cmd = 0;
-	memset(i2c->cmd_buf, 0, BUFSIZE);
-	memset(i2c->data_buf, 0, BUFSIZE);
-
 	i2c->irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, i2c->irq, jz4780_i2c_irq, 0,
 			       dev_name(&pdev->dev), i2c);

drivers/input/mouse/trackpoint.c

@@ -381,8 +381,8 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties)
 		return 0;
 
 	if (trackpoint_read(&psmouse->ps2dev, TP_EXT_BTN, &button_info)) {
-		psmouse_warn(psmouse, "failed to get extended button data\n");
-		button_info = 0;
+		psmouse_warn(psmouse, "failed to get extended button data, assuming 3 buttons\n");
+		button_info = 0x33;
 	}
 
 	psmouse->private = kzalloc(sizeof(struct trackpoint_data), GFP_KERNEL);

drivers/input/serio/i8042-x86ia64io.h

@@ -904,6 +904,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
 		},
 	},
+	{
+		/* Gigabyte P57 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P57"),
+		},
+	},
 	{
 		/* Schenker XMG C504 - Elantech touchpad */
 		.matches = {

drivers/irqchip/irq-mips-gic.c

@@ -915,8 +915,11 @@ static int __init gic_of_init(struct device_node *node,
 		gic_len = resource_size(&res);
 	}
 
-	if (mips_cm_present())
+	if (mips_cm_present()) {
 		write_gcr_gic_base(gic_base | CM_GCR_GIC_BASE_GICEN_MSK);
+		/* Ensure GIC region is enabled before trying to access it */
+		__sync();
+	}
 	gic_present = true;
 
 	__gic_init(gic_base, gic_len, cpu_vec, 0, node);

drivers/md/bcache/bcache.h

@@ -333,6 +333,7 @@ struct cached_dev {
 	/* Limit number of writeback bios in flight */
 	struct semaphore	in_flight;
 	struct task_struct	*writeback_thread;
+	struct workqueue_struct	*writeback_write_wq;
 
 	struct keybuf		writeback_keys;
 

drivers/md/bcache/request.c

@@ -196,12 +196,12 @@ static void bch_data_insert_start(struct closure *cl)
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
-	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
-		wake_up_gc(op->c);
-
 	if (op->bypass)
 		return bch_data_invalidate(cl);
 
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
+		wake_up_gc(op->c);
+
 	/*
 	 * Journal writes are marked REQ_FLUSH; if the original write was a
 	 * flush, it'll wait on the journal write.

drivers/md/bcache/super.c

@@ -1023,7 +1023,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	}
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
-		bch_sectors_dirty_init(dc);
+		bch_sectors_dirty_init(&dc->disk);
 		atomic_set(&dc->has_dirty, 1);
 		atomic_inc(&dc->count);
 		bch_writeback_queue(dc);
@@ -1056,6 +1056,8 @@ static void cached_dev_free(struct closure *cl)
 	cancel_delayed_work_sync(&dc->writeback_rate_update);
 	if (!IS_ERR_OR_NULL(dc->writeback_thread))
 		kthread_stop(dc->writeback_thread);
+	if (dc->writeback_write_wq)
+		destroy_workqueue(dc->writeback_write_wq);
 
 	mutex_lock(&bch_register_lock);
 
@@ -1227,6 +1229,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 		goto err;
 
 	bcache_device_attach(d, c, u - c->uuids);
+	bch_sectors_dirty_init(d);
 	bch_flash_dev_request_init(d);
 	add_disk(d->disk);
 
@@ -1959,6 +1962,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			else
 				err = "device busy";
 			mutex_unlock(&bch_register_lock);
+			if (!IS_ERR(bdev))
+				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
 				goto out;
 		}

drivers/md/bcache/sysfs.c

@@ -191,7 +191,7 @@ STORE(__cached_dev)
 {
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
-	unsigned v = size;
+	ssize_t v = size;
 	struct cache_set *c;
 	struct kobj_uevent_env *env;
 
@@ -226,7 +226,7 @@ STORE(__cached_dev)
 		bch_cached_dev_run(dc);
 
 	if (attr == &sysfs_cache_mode) {
-		ssize_t v = bch_read_string_list(buf, bch_cache_modes + 1);
+		v = bch_read_string_list(buf, bch_cache_modes + 1);
 
 		if (v < 0)
 			return v;

drivers/md/bcache/util.c

@@ -73,24 +73,44 @@ STRTO_H(strtouint, unsigned int)
 STRTO_H(strtoll, long long)
 STRTO_H(strtoull, unsigned long long)
 
+/**
+ * bch_hprint() - formats @v to human readable string for sysfs.
+ *
+ * @v - signed 64 bit integer
+ * @buf - the (at least 8 byte) buffer to format the result into.
+ *
+ * Returns the number of bytes used by format.
+ */
 ssize_t bch_hprint(char *buf, int64_t v)
 {
 	static const char units[] = "?kMGTPEZY";
-	char dec[4] = "";
-	int u, t = 0;
+	int u = 0, t;
 
-	for (u = 0; v >= 1024 || v <= -1024; u++) {
-		t = v & ~(~0 << 10);
-		v >>= 10;
-	}
+	uint64_t q;
 
-	if (!u)
-		return sprintf(buf, "%llu", v);
+	if (v < 0)
+		q = -v;
+	else
+		q = v;
 
-	if (v < 100 && v > -100)
-		snprintf(dec, sizeof(dec), ".%i", t / 100);
+	/* For as long as the number is more than 3 digits, but at least
+	 * once, shift right / divide by 1024.  Keep the remainder for
+	 * a digit after the decimal point.
+	 */
+	do {
+		u++;
 
-	return sprintf(buf, "%lli%s%c", v, dec, units[u]);
+		t = q & ~(~0 << 10);
+		q >>= 10;
+	} while (q >= 1000);
+
+	if (v < 0)
+		/* '-', up to 3 digits, '.', 1 digit, 1 character, null;
+		 * yields 8 bytes.
+		 */
+		return sprintf(buf, "-%llu.%i%c", q, t * 10 / 1024, units[u]);
+	else
+		return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]);
 }
 
 ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],

drivers/md/bcache/writeback.c

@@ -21,7 +21,8 @@
 static void __update_writeback_rate(struct cached_dev *dc)
 {
 	struct cache_set *c = dc->disk.c;
-	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size;
+	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
+				bcache_flash_devs_sectors_dirty(c);
 	uint64_t cache_dirty_target =
 		div_u64(cache_sectors * dc->writeback_percent, 100);
 
@@ -190,7 +191,7 @@ static void write_dirty(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl);
 
-	continue_at(cl, write_dirty_finish, system_wq);
+	continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq);
 }
 
 static void read_dirty_endio(struct bio *bio)
@@ -210,7 +211,7 @@ static void read_dirty_submit(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl);
 
-	continue_at(cl, write_dirty, system_wq);
+	continue_at(cl, write_dirty, io->dc->writeback_write_wq);
 }
 
 static void read_dirty(struct cached_dev *dc)
@@ -488,17 +489,17 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 	return MAP_CONTINUE;
 }
 
-void bch_sectors_dirty_init(struct cached_dev *dc)
+void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
 
 	bch_btree_op_init(&op.op, -1);
-	op.inode = dc->disk.id;
+	op.inode = d->id;
 
-	bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0),
+	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
 			   sectors_dirty_init_fn, 0);
 
-	dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk);
+	d->sectors_dirty_last = bcache_dev_sectors_dirty(d);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -522,6 +523,11 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 
 int bch_cached_dev_writeback_start(struct cached_dev *dc)
 {
+	dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq",
+						WQ_MEM_RECLAIM, 0);
+	if (!dc->writeback_write_wq)
+		return -ENOMEM;
+
 	dc->writeback_thread = kthread_create(bch_writeback_thread, dc,
 					      "bcache_writeback");
 	if (IS_ERR(dc->writeback_thread))

drivers/md/bcache/writeback.h

@@ -14,6 +14,25 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
+static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
+{
+	uint64_t i, ret = 0;
+
+	mutex_lock(&bch_register_lock);
+
+	for (i = 0; i < c->nr_uuids; i++) {
+		struct bcache_device *d = c->devices[i];
+
+		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
+			continue;
+	   ret += bcache_dev_sectors_dirty(d);
+	}
+
+	mutex_unlock(&bch_register_lock);
+
+	return ret;
+}
+
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
@@ -85,7 +104,7 @@ static inline void bch_writeback_add(struct cached_dev *dc)
 
 void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int);
 
-void bch_sectors_dirty_init(struct cached_dev *dc);
+void bch_sectors_dirty_init(struct bcache_device *);
 void bch_cached_dev_writeback_init(struct cached_dev *);
 int bch_cached_dev_writeback_start(struct cached_dev *);
 

drivers/md/bitmap.c

@@ -1960,6 +1960,11 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	long pages;
 	struct bitmap_page *new_bp;
 
+	if (bitmap->storage.file && !init) {
+		pr_info("md: cannot resize file-based bitmap\n");
+		return -EINVAL;
+	}
+
 	if (chunksize == 0) {
 		/* If there is enough space, leave the chunk size unchanged,
 		 * else increase by factor of two until there is enough space.

drivers/md/raid5.c

@@ -5822,6 +5822,8 @@ static void raid5_do_work(struct work_struct *work)
 
 	spin_unlock_irq(&conf->device_lock);
 
+	r5l_flush_stripe_to_raid(conf->log);
+
 	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 

drivers/media/usb/uvc/uvc_ctrl.c

@@ -2004,6 +2004,13 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 		goto done;
 	}
 
+	/* Validate the user-provided bit-size and offset */
+	if (mapping->size > 32 ||
+	    mapping->offset + mapping->size > ctrl->info.size * 8) {
+		ret = -EINVAL;
+		goto done;
+	}
+
 	list_for_each_entry(map, &ctrl->info.mappings, list) {
 		if (mapping->id == map->id) {
 			uvc_trace(UVC_TRACE_CONTROL, "Can't add mapping '%s', "

drivers/media/v4l2-core/v4l2-compat-ioctl32.c

@@ -788,7 +788,8 @@ static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *u
 		copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
 		put_user(kp->pending, &up->pending) ||
 		put_user(kp->sequence, &up->sequence) ||
-		compat_put_timespec(&kp->timestamp, &up->timestamp) ||
+		put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) ||
+		put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) ||
 		put_user(kp->id, &up->id) ||
 		copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
 			return -EFAULT;

drivers/net/ethernet/freescale/gianfar.c

@@ -3676,7 +3676,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))

drivers/net/ethernet/qlogic/qlge/qlge_dbg.c

@@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header(
 	seg_hdr->cookie = MPI_COREDUMP_COOKIE;
 	seg_hdr->segNum = seg_number;
 	seg_hdr->segSize = seg_size;
-	memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
+	strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
 }
 
 /*

drivers/net/phy/phy.c

@@ -541,9 +541,6 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
-
-	/* Now we can run the state machine synchronously */
-	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**

drivers/net/wireless/mwifiex/cfg80211.c

@@ -3740,7 +3740,7 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter)
 	if (adapter->config_bands & BAND_A)
 		n_channels_a = mwifiex_band_5ghz.n_channels;
 
-	adapter->num_in_chan_stats = max_t(u32, n_channels_bg, n_channels_a);
+	adapter->num_in_chan_stats = n_channels_bg + n_channels_a;
 	adapter->chan_stats = vmalloc(sizeof(*adapter->chan_stats) *
 				      adapter->num_in_chan_stats);
 

drivers/net/wireless/mwifiex/scan.c

@@ -2170,6 +2170,12 @@ mwifiex_update_chan_statistics(struct mwifiex_private *priv,
 					      sizeof(struct mwifiex_chan_stats);
 
 	for (i = 0 ; i < num_chan; i++) {
+		if (adapter->survey_idx >= adapter->num_in_chan_stats) {
+			mwifiex_dbg(adapter, WARN,
+				    "FW reported too many channel results (max %d)\n",
+				    adapter->num_in_chan_stats);
+			return;
+		}
 		chan_stats.chan_num = fw_chan_stats->chan_num;
 		chan_stats.bandcfg = fw_chan_stats->bandcfg;
 		chan_stats.flags = fw_chan_stats->flags;

drivers/net/wireless/p54/fwio.c

@@ -488,7 +488,7 @@ int p54_scan(struct p54_common *priv, u16 mode, u16 dwell)
 
 			entry += sizeof(__le16);
 			chan->pa_points_per_curve = 8;
-			memset(chan->curve_data, 0, sizeof(*chan->curve_data));
+			memset(chan->curve_data, 0, sizeof(chan->curve_data));
 			memcpy(chan->curve_data, entry,
 			       sizeof(struct p54_pa_curve_data_sample) *
 			       min((u8)8, curve_data->points_per_channel));

drivers/net/wireless/realtek/rtlwifi/pci.c

@@ -2269,7 +2269,7 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	/* find adapter */
 	if (!_rtl_pci_find_adapter(pdev, hw)) {
 		err = -ENODEV;
-		goto fail3;
+		goto fail2;
 	}
 
 	/* Init IO handler */
@@ -2339,10 +2339,10 @@ fail3:
 	pci_set_drvdata(pdev, NULL);
 	rtl_deinit_core(hw);
 
+fail2:
 	if (rtlpriv->io.pci_mem_start != 0)
 		pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start);
 
-fail2:
 	pci_release_regions(pdev);
 	complete(&rtlpriv->firmware_loading_complete);
 

drivers/net/wireless/ti/wl1251/main.c

@@ -1567,6 +1567,7 @@ struct ieee80211_hw *wl1251_alloc_hw(void)
 
 	wl->state = WL1251_STATE_OFF;
 	mutex_init(&wl->mutex);
+	spin_lock_init(&wl->wl_lock);
 
 	wl->tx_mgmt_frm_rate = DEFAULT_HW_GEN_TX_RATE;
 	wl->tx_mgmt_frm_mod = DEFAULT_HW_GEN_MODULATION_TYPE;

drivers/pci/hotplug/shpchp_hpc.c

@@ -1062,6 +1062,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 		if (rc) {
 			ctrl_info(ctrl, "Can't get msi for the hotplug controller\n");
 			ctrl_info(ctrl, "Use INTx for the hotplug controller\n");
+		} else {
+			pci_set_master(pdev);
 		}
 
 		rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,

drivers/s390/scsi/zfcp_dbf.c

@@ -3,7 +3,7 @@
  *
  * Debug traces for zfcp.
  *
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2017
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -447,6 +447,7 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
 	struct fc_ct_hdr *reqh = sg_virt(ct_els->req);
 	struct fc_ns_gid_ft *reqn = (struct fc_ns_gid_ft *)(reqh + 1);
 	struct scatterlist *resp_entry = ct_els->resp;
+	struct fc_ct_hdr *resph;
 	struct fc_gpn_ft_resp *acc;
 	int max_entries, x, last = 0;
 
@@ -473,6 +474,13 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
 		return len; /* not GPN_FT response so do not cap */
 
 	acc = sg_virt(resp_entry);
+
+	/* cap all but accept CT responses to at least the CT header */
+	resph = (struct fc_ct_hdr *)acc;
+	if ((ct_els->status) ||
+	    (resph->ct_cmd != cpu_to_be16(FC_FS_ACC)))
+		return max(FC_CT_HDR_LEN, ZFCP_DBF_SAN_MAX_PAYLOAD);
+
 	max_entries = (reqh->ct_mr_size * 4 / sizeof(struct fc_gpn_ft_resp))
 		+ 1 /* zfcp_fc_scan_ports: bytes correct, entries off-by-one
 		     * to account for header as 1st pseudo "entry" */;
@@ -555,8 +563,8 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
 	rec->scsi_retries = sc->retries;
 	rec->scsi_allowed = sc->allowed;
 	rec->scsi_id = sc->device->id;
-	/* struct zfcp_dbf_scsi needs to be updated to handle 64bit LUNs */
 	rec->scsi_lun = (u32)sc->device->lun;
+	rec->scsi_lun_64_hi = (u32)(sc->device->lun >> 32);
 	rec->host_scribble = (unsigned long)sc->host_scribble;
 
 	memcpy(rec->scsi_opcode, sc->cmnd,
@@ -564,19 +572,32 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
 
 	if (fsf) {
 		rec->fsf_req_id = fsf->req_id;
+		rec->pl_len = FCP_RESP_WITH_EXT;
 		fcp_rsp = (struct fcp_resp_with_ext *)
 				&(fsf->qtcb->bottom.io.fcp_rsp);
+		/* mandatory parts of FCP_RSP IU in this SCSI record */
 		memcpy(&rec->fcp_rsp, fcp_rsp, FCP_RESP_WITH_EXT);
 		if (fcp_rsp->resp.fr_flags & FCP_RSP_LEN_VAL) {
 			fcp_rsp_info = (struct fcp_resp_rsp_info *) &fcp_rsp[1];
 			rec->fcp_rsp_info = fcp_rsp_info->rsp_code;
+			rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_rsp_len);
 		}
 		if (fcp_rsp->resp.fr_flags & FCP_SNS_LEN_VAL) {
-			rec->pl_len = min((u16)SCSI_SENSE_BUFFERSIZE,
-					  (u16)ZFCP_DBF_PAY_MAX_REC);
-			zfcp_dbf_pl_write(dbf, sc->sense_buffer, rec->pl_len,
-					  "fcp_sns", fsf->req_id);
+			rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_sns_len);
 		}
+		/* complete FCP_RSP IU in associated PAYload record
+		 * but only if there are optional parts
+		 */
+		if (fcp_rsp->resp.fr_flags != 0)
+			zfcp_dbf_pl_write(
+				dbf, fcp_rsp,
+				/* at least one full PAY record
+				 * but not beyond hardware response field
+				 */
+				min_t(u16, max_t(u16, rec->pl_len,
+						 ZFCP_DBF_PAY_MAX_REC),
+				      FSF_FCP_RSP_SIZE),
+				"fcp_riu", fsf->req_id);
 	}
 
 	debug_event(dbf->scsi, level, rec, sizeof(*rec));

drivers/s390/scsi/zfcp_dbf.h

@@ -2,7 +2,7 @@
  * zfcp device driver
  * debug feature declarations
  *
- * Copyright IBM Corp. 2008, 2016
+ * Copyright IBM Corp. 2008, 2017
  */
 
 #ifndef ZFCP_DBF_H
@@ -204,7 +204,7 @@ enum zfcp_dbf_scsi_id {
  * @id: unique number of recovery record type
  * @tag: identifier string specifying the location of initiation
  * @scsi_id: scsi device id
- * @scsi_lun: scsi device logical unit number
+ * @scsi_lun: scsi device logical unit number, low part of 64 bit, old 32 bit
  * @scsi_result: scsi result
  * @scsi_retries: current retry number of scsi request
  * @scsi_allowed: allowed retries
@@ -214,6 +214,7 @@ enum zfcp_dbf_scsi_id {
  * @host_scribble: LLD specific data attached to SCSI request
  * @pl_len: length of paload stored as zfcp_dbf_pay
  * @fsf_rsp: response for fsf request
+ * @scsi_lun_64_hi: scsi device logical unit number, high part of 64 bit
  */
 struct zfcp_dbf_scsi {
 	u8 id;
@@ -230,6 +231,7 @@ struct zfcp_dbf_scsi {
 	u64 host_scribble;
 	u16 pl_len;
 	struct fcp_resp_with_ext fcp_rsp;
+	u32 scsi_lun_64_hi;
 } __packed;
 
 /**
@@ -323,7 +325,11 @@ void zfcp_dbf_hba_fsf_response(struct zfcp_fsf_req *req)
 {
 	struct fsf_qtcb *qtcb = req->qtcb;
 
-	if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) &&
+	if (unlikely(req->status & (ZFCP_STATUS_FSFREQ_DISMISSED |
+				    ZFCP_STATUS_FSFREQ_ERROR))) {
+		zfcp_dbf_hba_fsf_resp("fs_rerr", 3, req);
+
+	} else if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) &&
 	    (qtcb->prefix.prot_status != FSF_PROT_FSF_STATUS_PRESENTED)) {
 		zfcp_dbf_hba_fsf_resp("fs_perr", 1, req);
 
@@ -401,7 +407,8 @@ void zfcp_dbf_scsi_abort(char *tag, struct scsi_cmnd *scmd,
  * @flag: indicates type of reset (Target Reset, Logical Unit Reset)
  */
 static inline
-void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
+void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag,
+			    struct zfcp_fsf_req *fsf_req)
 {
 	char tmp_tag[ZFCP_DBF_TAG_LEN];
 
@@ -411,7 +418,7 @@ void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
 		memcpy(tmp_tag, "lr_", 3);
 
 	memcpy(&tmp_tag[3], tag, 4);
-	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, NULL);
+	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, fsf_req);
 }
 
 /**

drivers/s390/scsi/zfcp_fc.h

@@ -4,7 +4,7 @@
  * Fibre Channel related definitions and inline functions for the zfcp
  * device driver
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009, 2017
  */
 
 #ifndef ZFCP_FC_H
@@ -279,6 +279,10 @@ void zfcp_fc_eval_fcp_rsp(struct fcp_resp_with_ext *fcp_rsp,
 		     !(rsp_flags & FCP_SNS_LEN_VAL) &&
 		     fcp_rsp->resp.fr_status == SAM_STAT_GOOD)
 			set_host_byte(scsi, DID_ERROR);
+	} else if (unlikely(rsp_flags & FCP_RESID_OVER)) {
+		/* FCP_DL was not sufficient for SCSI data length */
+		if (fcp_rsp->resp.fr_status == SAM_STAT_GOOD)
+			set_host_byte(scsi, DID_ERROR);
 	}
 }
 

drivers/s390/scsi/zfcp_fsf.c

@@ -928,8 +928,8 @@ static void zfcp_fsf_send_ct_handler(struct zfcp_fsf_req *req)
 
 	switch (header->fsf_status) {
         case FSF_GOOD:
-		zfcp_dbf_san_res("fsscth2", req);
 		ct->status = 0;
+		zfcp_dbf_san_res("fsscth2", req);
 		break;
         case FSF_SERVICE_CLASS_NOT_SUPPORTED:
 		zfcp_fsf_class_not_supp(req);
@@ -1109,8 +1109,8 @@ static void zfcp_fsf_send_els_handler(struct zfcp_fsf_req *req)
 
 	switch (header->fsf_status) {
 	case FSF_GOOD:
-		zfcp_dbf_san_res("fsselh1", req);
 		send_els->status = 0;
+		zfcp_dbf_san_res("fsselh1", req);
 		break;
 	case FSF_SERVICE_CLASS_NOT_SUPPORTED:
 		zfcp_fsf_class_not_supp(req);
@@ -2258,7 +2258,8 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 	fcp_cmnd = (struct fcp_cmnd *) &req->qtcb->bottom.io.fcp_cmnd;
 	zfcp_fc_scsi_to_fcp(fcp_cmnd, scsi_cmnd, 0);
 
-	if (scsi_prot_sg_count(scsi_cmnd)) {
+	if ((scsi_get_prot_op(scsi_cmnd) != SCSI_PROT_NORMAL) &&
+	    scsi_prot_sg_count(scsi_cmnd)) {
 		zfcp_qdio_set_data_div(qdio, &req->qdio_req,
 				       scsi_prot_sg_count(scsi_cmnd));
 		retval = zfcp_qdio_sbals_from_sg(qdio, &req->qdio_req,

drivers/s390/scsi/zfcp_scsi.c

@@ -3,7 +3,7 @@
  *
  * Interface to Linux SCSI midlayer.
  *
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2017
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -273,25 +273,29 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 
 		zfcp_erp_wait(adapter);
 		ret = fc_block_scsi_eh(scpnt);
-		if (ret)
+		if (ret) {
+			zfcp_dbf_scsi_devreset("fiof", scpnt, tm_flags, NULL);
 			return ret;
+		}
 
 		if (!(atomic_read(&adapter->status) &
 		      ZFCP_STATUS_COMMON_RUNNING)) {
-			zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags);
+			zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags, NULL);
 			return SUCCESS;
 		}
 	}
-	if (!fsf_req)
+	if (!fsf_req) {
+		zfcp_dbf_scsi_devreset("reqf", scpnt, tm_flags, NULL);
 		return FAILED;
+	}
 
 	wait_for_completion(&fsf_req->completion);
 
 	if (fsf_req->status & ZFCP_STATUS_FSFREQ_TMFUNCFAILED) {
-		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags);
+		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags, fsf_req);
 		retval = FAILED;
 	} else {
-		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags);
+		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags, fsf_req);
 		zfcp_scsi_forget_cmnds(zfcp_sdev, tm_flags);
 	}
 

drivers/scsi/isci/remote_node_context.c

@@ -66,6 +66,9 @@ const char *rnc_state_name(enum scis_sds_remote_node_context_states state)
 {
 	static const char * const strings[] = RNC_STATES;
 
+	if (state >= ARRAY_SIZE(strings))
+		return "UNKNOWN";
+
 	return strings[state];
 }
 #undef C

drivers/scsi/lpfc/lpfc_els.c

@@ -1054,7 +1054,10 @@ stop_rr_fcf_flogi:
 					lpfc_sli4_unreg_all_rpis(vport);
 				}
 			}
-			lpfc_issue_reg_vfi(vport);
+
+			/* Do not register VFI if the driver aborted FLOGI */
+			if (!lpfc_error_lost_link(irsp))
+				lpfc_issue_reg_vfi(vport);
 			lpfc_nlp_put(ndlp);
 			goto out;
 		}

drivers/scsi/megaraid/megaraid_sas_base.c

@@ -1824,9 +1824,12 @@ static void megasas_complete_outstanding_ioctls(struct megasas_instance *instanc
 			if (cmd_fusion->sync_cmd_idx != (u32)ULONG_MAX) {
 				cmd_mfi = instance->cmd_list[cmd_fusion->sync_cmd_idx];
 				if (cmd_mfi->sync_cmd &&
-					cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT)
+				    (cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT)) {
+					cmd_mfi->frame->hdr.cmd_status =
+							MFI_STAT_WRONG_STATE;
 					megasas_complete_cmd(instance,
 							     cmd_mfi, DID_OK);
+				}
 			}
 		}
 	} else {
@@ -5094,6 +5097,14 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num,
 		prev_aen.word =
 			le32_to_cpu(instance->aen_cmd->frame->dcmd.mbox.w[1]);
 
+		if ((curr_aen.members.class < MFI_EVT_CLASS_DEBUG) ||
+		    (curr_aen.members.class > MFI_EVT_CLASS_DEAD)) {
+			dev_info(&instance->pdev->dev,
+				 "%s %d out of range class %d send by application\n",
+				 __func__, __LINE__, curr_aen.members.class);
+			return 0;
+		}
+
 		/*
 		 * A class whose enum value is smaller is inclusive of all
 		 * higher values. If a PROGRESS (= -1) was previously

drivers/scsi/qla2xxx/qla_attr.c

@@ -404,6 +404,8 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		return -EINVAL;
 	if (start > ha->optrom_size)
 		return -EINVAL;
+	if (size > ha->optrom_size - start)
+		size = ha->optrom_size - start;
 
 	mutex_lock(&ha->optrom_mutex);
 	switch (val) {
@@ -429,8 +431,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		}
 
 		ha->optrom_region_start = start;
-		ha->optrom_region_size = start + size > ha->optrom_size ?
-		    ha->optrom_size - start : size;
+		ha->optrom_region_size = start + size;
 
 		ha->optrom_state = QLA_SREADING;
 		ha->optrom_buffer = vmalloc(ha->optrom_region_size);
@@ -503,8 +504,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		}
 
 		ha->optrom_region_start = start;
-		ha->optrom_region_size = start + size > ha->optrom_size ?
-		    ha->optrom_size - start : size;
+		ha->optrom_region_size = start + size;
 
 		ha->optrom_state = QLA_SWRITING;
 		ha->optrom_buffer = vmalloc(ha->optrom_region_size);

drivers/scsi/sg.c

@@ -133,7 +133,7 @@ struct sg_device;		/* forward declarations */
 struct sg_fd;
 
 typedef struct sg_request {	/* SG_MAX_QUEUE requests outstanding per file */
-	struct sg_request *nextrp;	/* NULL -> tail request (slist) */
+	struct list_head entry;	/* list entry */
 	struct sg_fd *parentfp;	/* NULL -> not in use */
 	Sg_scatter_hold data;	/* hold buffer, perhaps scatter list */
 	sg_io_hdr_t header;	/* scsi command+info, see <scsi/sg.h> */
@@ -153,11 +153,11 @@ typedef struct sg_fd {		/* holds the state of a file descriptor */
 	struct sg_device *parentdp;	/* owning device */
 	wait_queue_head_t read_wait;	/* queue read until command done */
 	rwlock_t rq_list_lock;	/* protect access to list in req_arr */
+	struct mutex f_mutex;	/* protect against changes in this fd */
 	int timeout;		/* defaults to SG_DEFAULT_TIMEOUT      */
 	int timeout_user;	/* defaults to SG_DEFAULT_TIMEOUT_USER */
 	Sg_scatter_hold reserve;	/* buffer held for this file descriptor */
-	unsigned save_scat_len;	/* original length of trunc. scat. element */
-	Sg_request *headrp;	/* head of request slist, NULL->empty */
+	struct list_head rq_list; /* head of request list */
 	struct fasync_struct *async_qp;	/* used by asynchronous notification */
 	Sg_request req_arr[SG_MAX_QUEUE];	/* used as singly-linked list */
 	char low_dma;		/* as in parent but possibly overridden to 1 */
@@ -166,6 +166,7 @@ typedef struct sg_fd {		/* holds the state of a file descriptor */
 	unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */
 	char keep_orphan;	/* 0 -> drop orphan (def), 1 -> keep for read() */
 	char mmap_called;	/* 0 -> mmap() never called on this fd */
+	char res_in_use;	/* 1 -> 'reserve' array in use */
 	struct kref f_ref;
 	struct execute_work ew;
 } Sg_fd;
@@ -209,7 +210,6 @@ static void sg_remove_sfp(struct kref *);
 static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
 static Sg_request *sg_add_request(Sg_fd * sfp);
 static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
-static int sg_res_in_use(Sg_fd * sfp);
 static Sg_device *sg_get_dev(int dev);
 static void sg_device_destroy(struct kref *kref);
 
@@ -625,6 +625,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	}
 	buf += SZ_SG_HEADER;
 	__get_user(opcode, buf);
+	mutex_lock(&sfp->f_mutex);
 	if (sfp->next_cmd_len > 0) {
 		cmd_size = sfp->next_cmd_len;
 		sfp->next_cmd_len = 0;	/* reset so only this write() effected */
@@ -633,6 +634,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 		if ((opcode >= 0xc0) && old_hdr.twelve_byte)
 			cmd_size = 12;
 	}
+	mutex_unlock(&sfp->f_mutex);
 	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
 		"sg_write:   scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size));
 /* Determine buffer size.  */
@@ -732,7 +734,7 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
 			sg_remove_request(sfp, srp);
 			return -EINVAL;	/* either MMAP_IO or DIRECT_IO (not both) */
 		}
-		if (sg_res_in_use(sfp)) {
+		if (sfp->res_in_use) {
 			sg_remove_request(sfp, srp);
 			return -EBUSY;	/* reserve buffer already being used */
 		}
@@ -837,6 +839,39 @@ static int max_sectors_bytes(struct request_queue *q)
 	return max_sectors << 9;
 }
 
+static void
+sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo)
+{
+	Sg_request *srp;
+	int val;
+	unsigned int ms;
+
+	val = 0;
+	list_for_each_entry(srp, &sfp->rq_list, entry) {
+		if (val > SG_MAX_QUEUE)
+			break;
+		rinfo[val].req_state = srp->done + 1;
+		rinfo[val].problem =
+			srp->header.masked_status &
+			srp->header.host_status &
+			srp->header.driver_status;
+		if (srp->done)
+			rinfo[val].duration =
+				srp->header.duration;
+		else {
+			ms = jiffies_to_msecs(jiffies);
+			rinfo[val].duration =
+				(ms > srp->header.duration) ?
+				(ms - srp->header.duration) : 0;
+		}
+		rinfo[val].orphan = srp->orphan;
+		rinfo[val].sg_io_owned = srp->sg_io_owned;
+		rinfo[val].pack_id = srp->header.pack_id;
+		rinfo[val].usr_ptr = srp->header.usr_ptr;
+		val++;
+	}
+}
+
 static long
 sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
@@ -902,7 +937,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return result;
 		if (val) {
 			sfp->low_dma = 1;
-			if ((0 == sfp->low_dma) && (0 == sg_res_in_use(sfp))) {
+			if ((0 == sfp->low_dma) && !sfp->res_in_use) {
 				val = (int) sfp->reserve.bufflen;
 				sg_remove_scat(sfp, &sfp->reserve);
 				sg_build_reserve(sfp, val);
@@ -948,7 +983,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		if (!access_ok(VERIFY_WRITE, ip, sizeof (int)))
 			return -EFAULT;
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
-		for (srp = sfp->headrp; srp; srp = srp->nextrp) {
+		list_for_each_entry(srp, &sfp->rq_list, entry) {
 			if ((1 == srp->done) && (!srp->sg_io_owned)) {
 				read_unlock_irqrestore(&sfp->rq_list_lock,
 						       iflags);
@@ -961,7 +996,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		return 0;
 	case SG_GET_NUM_WAITING:
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
-		for (val = 0, srp = sfp->headrp; srp; srp = srp->nextrp) {
+		val = 0;
+		list_for_each_entry(srp, &sfp->rq_list, entry) {
 			if ((1 == srp->done) && (!srp->sg_io_owned))
 				++val;
 		}
@@ -977,12 +1013,18 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
                         return -EINVAL;
 		val = min_t(int, val,
 			    max_sectors_bytes(sdp->device->request_queue));
+		mutex_lock(&sfp->f_mutex);
 		if (val != sfp->reserve.bufflen) {
-			if (sg_res_in_use(sfp) || sfp->mmap_called)
+			if (sfp->mmap_called ||
+			    sfp->res_in_use) {
+				mutex_unlock(&sfp->f_mutex);
 				return -EBUSY;
+			}
+
 			sg_remove_scat(sfp, &sfp->reserve);
 			sg_build_reserve(sfp, val);
 		}
+		mutex_unlock(&sfp->f_mutex);
 		return 0;
 	case SG_GET_RESERVED_SIZE:
 		val = min_t(int, sfp->reserve.bufflen,
@@ -1023,42 +1065,15 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return -EFAULT;
 		else {
 			sg_req_info_t *rinfo;
-			unsigned int ms;
 
-			rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
-								GFP_KERNEL);
+			rinfo = kzalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
+					GFP_KERNEL);
 			if (!rinfo)
 				return -ENOMEM;
 			read_lock_irqsave(&sfp->rq_list_lock, iflags);
-			for (srp = sfp->headrp, val = 0; val < SG_MAX_QUEUE;
-			     ++val, srp = srp ? srp->nextrp : srp) {
-				memset(&rinfo[val], 0, SZ_SG_REQ_INFO);
-				if (srp) {
-					rinfo[val].req_state = srp->done + 1;
-					rinfo[val].problem =
-					    srp->header.masked_status & 
-					    srp->header.host_status & 
-					    srp->header.driver_status;
-					if (srp->done)
-						rinfo[val].duration =
-							srp->header.duration;
-					else {
-						ms = jiffies_to_msecs(jiffies);
-						rinfo[val].duration =
-						    (ms > srp->header.duration) ?
-						    (ms - srp->header.duration) : 0;
-					}
-					rinfo[val].orphan = srp->orphan;
-					rinfo[val].sg_io_owned =
-							srp->sg_io_owned;
-					rinfo[val].pack_id =
-							srp->header.pack_id;
-					rinfo[val].usr_ptr =
-							srp->header.usr_ptr;
-				}
-			}
+			sg_fill_request_table(sfp, rinfo);
 			read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-			result = __copy_to_user(p, rinfo, 
+			result = __copy_to_user(p, rinfo,
 						SZ_SG_REQ_INFO * SG_MAX_QUEUE);
 			result = result ? -EFAULT : 0;
 			kfree(rinfo);
@@ -1164,7 +1179,7 @@ sg_poll(struct file *filp, poll_table * wait)
 		return POLLERR;
 	poll_wait(filp, &sfp->read_wait, wait);
 	read_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (srp = sfp->headrp; srp; srp = srp->nextrp) {
+	list_for_each_entry(srp, &sfp->rq_list, entry) {
 		/* if any read waiting, flag it */
 		if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned))
 			res = POLLIN | POLLRDNORM;
@@ -1245,6 +1260,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	unsigned long req_sz, len, sa;
 	Sg_scatter_hold *rsv_schp;
 	int k, length;
+	int ret = 0;
 
 	if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data)))
 		return -ENXIO;
@@ -1255,8 +1271,11 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (vma->vm_pgoff)
 		return -EINVAL;	/* want no offset */
 	rsv_schp = &sfp->reserve;
-	if (req_sz > rsv_schp->bufflen)
-		return -ENOMEM;	/* cannot map more than reserved buffer */
+	mutex_lock(&sfp->f_mutex);
+	if (req_sz > rsv_schp->bufflen) {
+		ret = -ENOMEM;	/* cannot map more than reserved buffer */
+		goto out;
+	}
 
 	sa = vma->vm_start;
 	length = 1 << (PAGE_SHIFT + rsv_schp->page_order);
@@ -1270,7 +1289,9 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_private_data = sfp;
 	vma->vm_ops = &sg_mmap_vm_ops;
-	return 0;
+out:
+	mutex_unlock(&sfp->f_mutex);
+	return ret;
 }
 
 static void
@@ -1734,13 +1755,25 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 		md = &map_data;
 
 	if (md) {
-		if (!sg_res_in_use(sfp) && dxfer_len <= rsv_schp->bufflen)
+		mutex_lock(&sfp->f_mutex);
+		if (dxfer_len <= rsv_schp->bufflen &&
+		    !sfp->res_in_use) {
+			sfp->res_in_use = 1;
 			sg_link_reserve(sfp, srp, dxfer_len);
-		else {
+		} else if (hp->flags & SG_FLAG_MMAP_IO) {
+			res = -EBUSY; /* sfp->res_in_use == 1 */
+			if (dxfer_len > rsv_schp->bufflen)
+				res = -ENOMEM;
+			mutex_unlock(&sfp->f_mutex);
+			return res;
+		} else {
 			res = sg_build_indirect(req_schp, sfp, dxfer_len);
-			if (res)
+			if (res) {
+				mutex_unlock(&sfp->f_mutex);
 				return res;
+			}
 		}
+		mutex_unlock(&sfp->f_mutex);
 
 		md->pages = req_schp->pages;
 		md->page_order = req_schp->page_order;
@@ -2029,8 +2062,9 @@ sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp)
 	req_schp->pages = NULL;
 	req_schp->page_order = 0;
 	req_schp->sglist_len = 0;
-	sfp->save_scat_len = 0;
 	srp->res_used = 0;
+	/* Called without mutex lock to avoid deadlock */
+	sfp->res_in_use = 0;
 }
 
 static Sg_request *
@@ -2040,7 +2074,7 @@ sg_get_rq_mark(Sg_fd * sfp, int pack_id)
 	unsigned long iflags;
 
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (resp = sfp->headrp; resp; resp = resp->nextrp) {
+	list_for_each_entry(resp, &sfp->rq_list, entry) {
 		/* look for requests that are ready + not SG_IO owned */
 		if ((1 == resp->done) && (!resp->sg_io_owned) &&
 		    ((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
@@ -2058,70 +2092,45 @@ sg_add_request(Sg_fd * sfp)
 {
 	int k;
 	unsigned long iflags;
-	Sg_request *resp;
 	Sg_request *rp = sfp->req_arr;
 
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	resp = sfp->headrp;
-	if (!resp) {
-		memset(rp, 0, sizeof (Sg_request));
-		rp->parentfp = sfp;
-		resp = rp;
-		sfp->headrp = resp;
-	} else {
-		if (0 == sfp->cmd_q)
-			resp = NULL;	/* command queuing disallowed */
-		else {
-			for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) {
-				if (!rp->parentfp)
-					break;
-			}
-			if (k < SG_MAX_QUEUE) {
-				memset(rp, 0, sizeof (Sg_request));
-				rp->parentfp = sfp;
-				while (resp->nextrp)
-					resp = resp->nextrp;
-				resp->nextrp = rp;
-				resp = rp;
-			} else
-				resp = NULL;
+	if (!list_empty(&sfp->rq_list)) {
+		if (!sfp->cmd_q)
+			goto out_unlock;
+
+		for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) {
+			if (!rp->parentfp)
+				break;
 		}
+		if (k >= SG_MAX_QUEUE)
+			goto out_unlock;
 	}
-	if (resp) {
-		resp->nextrp = NULL;
-		resp->header.duration = jiffies_to_msecs(jiffies);
-	}
+	memset(rp, 0, sizeof (Sg_request));
+	rp->parentfp = sfp;
+	rp->header.duration = jiffies_to_msecs(jiffies);
+	list_add_tail(&rp->entry, &sfp->rq_list);
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-	return resp;
+	return rp;
+out_unlock:
+	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+	return NULL;
 }
 
 /* Return of 1 for found; 0 for not found */
 static int
 sg_remove_request(Sg_fd * sfp, Sg_request * srp)
 {
-	Sg_request *prev_rp;
-	Sg_request *rp;
 	unsigned long iflags;
 	int res = 0;
 
-	if ((!sfp) || (!srp) || (!sfp->headrp))
+	if (!sfp || !srp || list_empty(&sfp->rq_list))
 		return res;
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
-	prev_rp = sfp->headrp;
-	if (srp == prev_rp) {
-		sfp->headrp = prev_rp->nextrp;
-		prev_rp->parentfp = NULL;
+	if (!list_empty(&srp->entry)) {
+		list_del(&srp->entry);
+		srp->parentfp = NULL;
 		res = 1;
-	} else {
-		while ((rp = prev_rp->nextrp)) {
-			if (srp == rp) {
-				prev_rp->nextrp = rp->nextrp;
-				rp->parentfp = NULL;
-				res = 1;
-				break;
-			}
-			prev_rp = rp;
-		}
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
 	return res;
@@ -2140,8 +2149,9 @@ sg_add_sfp(Sg_device * sdp)
 
 	init_waitqueue_head(&sfp->read_wait);
 	rwlock_init(&sfp->rq_list_lock);
-
+	INIT_LIST_HEAD(&sfp->rq_list);
 	kref_init(&sfp->f_ref);
+	mutex_init(&sfp->f_mutex);
 	sfp->timeout = SG_DEFAULT_TIMEOUT;
 	sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
 	sfp->force_packid = SG_DEF_FORCE_PACK_ID;
@@ -2180,10 +2190,13 @@ sg_remove_sfp_usercontext(struct work_struct *work)
 {
 	struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work);
 	struct sg_device *sdp = sfp->parentdp;
+	Sg_request *srp;
 
 	/* Cleanup any responses which were never read(). */
-	while (sfp->headrp)
-		sg_finish_rem_req(sfp->headrp);
+	while (!list_empty(&sfp->rq_list)) {
+		srp = list_first_entry(&sfp->rq_list, Sg_request, entry);
+		sg_finish_rem_req(srp);
+	}
 
 	if (sfp->reserve.bufflen > 0) {
 		SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp,
@@ -2217,20 +2230,6 @@ sg_remove_sfp(struct kref *kref)
 	schedule_work(&sfp->ew.work);
 }
 
-static int
-sg_res_in_use(Sg_fd * sfp)
-{
-	const Sg_request *srp;
-	unsigned long iflags;
-
-	read_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (srp = sfp->headrp; srp; srp = srp->nextrp)
-		if (srp->res_used)
-			break;
-	read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-	return srp ? 1 : 0;
-}
-
 #ifdef CONFIG_SCSI_PROC_FS
 static int
 sg_idr_max_id(int id, void *p, void *data)
@@ -2600,7 +2599,7 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
 /* must be called while holding sg_index_lock */
 static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 {
-	int k, m, new_interface, blen, usg;
+	int k, new_interface, blen, usg;
 	Sg_request *srp;
 	Sg_fd *fp;
 	const sg_io_hdr_t *hp;
@@ -2620,13 +2619,11 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 		seq_printf(s, "   cmd_q=%d f_packid=%d k_orphan=%d closed=0\n",
 			   (int) fp->cmd_q, (int) fp->force_packid,
 			   (int) fp->keep_orphan);
-		for (m = 0, srp = fp->headrp;
-				srp != NULL;
-				++m, srp = srp->nextrp) {
+		list_for_each_entry(srp, &fp->rq_list, entry) {
 			hp = &srp->header;
 			new_interface = (hp->interface_id == '\0') ? 0 : 1;
 			if (srp->res_used) {
-				if (new_interface && 
+				if (new_interface &&
 				    (SG_FLAG_MMAP_IO & hp->flags))
 					cp = "     mmap>> ";
 				else
@@ -2657,7 +2654,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 			seq_printf(s, "ms sgat=%d op=0x%02x\n", usg,
 				   (int) srp->data.cmd_opcode);
 		}
-		if (0 == m)
+		if (list_empty(&fp->rq_list))
 			seq_puts(s, "     No requests active\n");
 		read_unlock(&fp->rq_list_lock);
 	}

drivers/scsi/storvsc_drv.c

@@ -1511,6 +1511,8 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	ret = storvsc_do_io(dev, cmd_request);
 
 	if (ret == -EAGAIN) {
+		if (payload_sz > sizeof(cmd_request->mpb))
+			kfree(payload);
 		/* no more space */
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}

drivers/staging/android/fiq_debugger/fiq_debugger.c

@@ -402,7 +402,7 @@ static void fiq_debugger_work(struct work_struct *work)
 		cmd += 6;
 		while (*cmd == ' ')
 			cmd++;
-		if ((cmd != '\0') && sysrq_on())
+		if ((*cmd != '\0') && sysrq_on())
 			kernel_restart(cmd);
 		else
 			kernel_restart(NULL);

drivers/staging/rts5208/rtsx_scsi.c

@@ -414,7 +414,7 @@ void set_sense_data(struct rtsx_chip *chip, unsigned int lun, u8 err_code,
 	sense->ascq = ascq;
 	if (sns_key_info0 != 0) {
 		sense->sns_key_info[0] = SKSV | sns_key_info0;
-		sense->sns_key_info[1] = (sns_key_info1 & 0xf0) >> 8;
+		sense->sns_key_info[1] = (sns_key_info1 & 0xf0) >> 4;
 		sense->sns_key_info[2] = sns_key_info1 & 0x0f;
 	}
 }

drivers/tty/tty_buffer.c

@@ -361,6 +361,32 @@ int tty_insert_flip_string_flags(struct tty_port *port,
 }
 EXPORT_SYMBOL(tty_insert_flip_string_flags);
 
+/**
+ *	__tty_insert_flip_char   -	Add one character to the tty buffer
+ *	@port: tty port
+ *	@ch: character
+ *	@flag: flag byte
+ *
+ *	Queue a single byte to the tty buffering, with an optional flag.
+ *	This is the slow path of tty_insert_flip_char.
+ */
+int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag)
+{
+	struct tty_buffer *tb;
+	int flags = (flag == TTY_NORMAL) ? TTYB_NORMAL : 0;
+
+	if (!__tty_buffer_request_room(port, 1, flags))
+		return 0;
+
+	tb = port->buf.tail;
+	if (~tb->flags & TTYB_NORMAL)
+		*flag_buf_ptr(tb, tb->used) = flag;
+	*char_buf_ptr(tb, tb->used++) = ch;
+
+	return 1;
+}
+EXPORT_SYMBOL(__tty_insert_flip_char);
+
 /**
  *	tty_schedule_flip	-	push characters to ldisc
  *	@port: tty port to push from

drivers/usb/core/devio.c

@@ -519,6 +519,8 @@ static void async_completed(struct urb *urb)
 	if (as->status < 0 && as->bulk_addr && as->status != -ECONNRESET &&
 			as->status != -ENOENT)
 		cancel_bulk_urbs(ps, as->bulk_addr);
+
+	wake_up(&ps->wait);
 	spin_unlock(&ps->lock);
 
 	if (signr) {
@@ -526,8 +528,6 @@ static void async_completed(struct urb *urb)
 		put_pid(pid);
 		put_cred(cred);
 	}
-
-	wake_up(&ps->wait);
 }
 
 static void destroy_async(struct usb_dev_state *ps, struct list_head *list)

drivers/usb/core/quirks.c

@@ -57,8 +57,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
-	/* Logitech HD Pro Webcams C920 and C930e */
+	/* Logitech HD Pro Webcams C920, C920-C and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Logitech ConferenceCam CC3000e */
@@ -217,6 +218,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Corsair Strafe RGB */
+	{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Acer C120 LED Projector */
 	{ USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
 

drivers/usb/host/pci-quirks.c

@@ -133,29 +133,30 @@ static int amd_chipset_sb_type_init(struct amd_chipset_info *pinfo)
 			pinfo->sb_type.gen = AMD_CHIPSET_SB700;
 		else if (rev >= 0x40 && rev <= 0x4f)
 			pinfo->sb_type.gen = AMD_CHIPSET_SB800;
-	}
-	pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
-					  0x145c, NULL);
-	if (pinfo->smbus_dev) {
-		pinfo->sb_type.gen = AMD_CHIPSET_TAISHAN;
 	} else {
 		pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
 				PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL);
 
-		if (!pinfo->smbus_dev) {
-			pinfo->sb_type.gen = NOT_AMD_CHIPSET;
-			return 0;
+		if (pinfo->smbus_dev) {
+			rev = pinfo->smbus_dev->revision;
+			if (rev >= 0x11 && rev <= 0x14)
+				pinfo->sb_type.gen = AMD_CHIPSET_HUDSON2;
+			else if (rev >= 0x15 && rev <= 0x18)
+				pinfo->sb_type.gen = AMD_CHIPSET_BOLTON;
+			else if (rev >= 0x39 && rev <= 0x3a)
+				pinfo->sb_type.gen = AMD_CHIPSET_YANGTZE;
+		} else {
+			pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
+							  0x145c, NULL);
+			if (pinfo->smbus_dev) {
+				rev = pinfo->smbus_dev->revision;
+				pinfo->sb_type.gen = AMD_CHIPSET_TAISHAN;
+			} else {
+				pinfo->sb_type.gen = NOT_AMD_CHIPSET;
+				return 0;
+			}
 		}
-
-		rev = pinfo->smbus_dev->revision;
-		if (rev >= 0x11 && rev <= 0x14)
-			pinfo->sb_type.gen = AMD_CHIPSET_HUDSON2;
-		else if (rev >= 0x15 && rev <= 0x18)
-			pinfo->sb_type.gen = AMD_CHIPSET_BOLTON;
-		else if (rev >= 0x39 && rev <= 0x3a)
-			pinfo->sb_type.gen = AMD_CHIPSET_YANGTZE;
 	}
-
 	pinfo->sb_type.rev = rev;
 	return 1;
 }

drivers/usb/serial/option.c

@@ -2023,6 +2023,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff) },			/* D-Link DWM-158 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d0e, 0xff) },			/* D-Link DWM-157 C1 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff),			/* D-Link DWM-221 B1 */
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff),			/* D-Link DWM-222 */

fs/Kconfig

@@ -73,6 +73,8 @@ config FILE_LOCKING
           for filesystems like NFS and for the flock() system
           call. Disabling this option saves about 11k.
 
+source "fs/crypto/Kconfig"
+
 source "fs/notify/Kconfig"
 
 source "fs/quota/Kconfig"

fs/Makefile

@@ -30,6 +30,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
+obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o

fs/btrfs/super.c

@@ -1727,6 +1727,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 		}
 
+		btrfs_qgroup_rescan_resume(fs_info);
+
 		if (!fs_info->uuid_root) {
 			btrfs_info(fs_info, "creating UUID tree");
 			ret = btrfs_create_uuid_tree(fs_info);

fs/btrfs/volumes.c

@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	},
 };
 
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
 	[BTRFS_RAID_RAID1]  = BTRFS_BLOCK_GROUP_RAID1,
 	[BTRFS_RAID_DUP]    = BTRFS_BLOCK_GROUP_DUP,

fs/ceph/addr.c

@@ -189,7 +189,7 @@ static int ceph_releasepage(struct page *page, gfp_t g)
 /*
  * read a single page, without unlocking it.
  */
-static int readpage_nounlock(struct file *filp, struct page *page)
+static int ceph_do_readpage(struct file *filp, struct page *page)
 {
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -219,7 +219,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 
 	err = ceph_readpage_from_fscache(inode, page);
 	if (err == 0)
-		goto out;
+		return -EINPROGRESS;
 
 	dout("readpage inode %p file %p page %p index %lu\n",
 	     inode, filp, page, page->index);
@@ -249,8 +249,11 @@ out:
 
 static int ceph_readpage(struct file *filp, struct page *page)
 {
-	int r = readpage_nounlock(filp, page);
-	unlock_page(page);
+	int r = ceph_do_readpage(filp, page);
+	if (r != -EINPROGRESS)
+		unlock_page(page);
+	else
+		r = 0;
 	return r;
 }
 
@@ -1094,7 +1097,7 @@ retry_locked:
 			goto retry_locked;
 		r = writepage_nounlock(page, NULL);
 		if (r < 0)
-			goto fail_nosnap;
+			goto fail_unlock;
 		goto retry_locked;
 	}
 
@@ -1122,11 +1125,14 @@ retry_locked:
 	}
 
 	/* we need to read it. */
-	r = readpage_nounlock(file, page);
-	if (r < 0)
-		goto fail_nosnap;
+	r = ceph_do_readpage(file, page);
+	if (r < 0) {
+		if (r == -EINPROGRESS)
+			return -EAGAIN;
+		goto fail_unlock;
+	}
 	goto retry_locked;
-fail_nosnap:
+fail_unlock:
 	unlock_page(page);
 	return r;
 }

fs/ceph/cache.c

@@ -224,13 +224,7 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
 	fscache_relinquish_cookie(cookie, 0);
 }
 
-static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
-{
-	if (!error)
-		SetPageUptodate(page);
-}
-
-static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
 {
 	if (!error)
 		SetPageUptodate(page);
@@ -259,7 +253,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_page(ci->fscache, page,
-					 ceph_vfs_readpage_complete, NULL,
+					 ceph_readpage_from_fscache_complete, NULL,
 					 GFP_KERNEL);
 
 	switch (ret) {
@@ -288,7 +282,7 @@ int ceph_readpages_from_fscache(struct inode *inode,
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
-					  ceph_vfs_readpage_complete_unlock,
+					  ceph_readpage_from_fscache_complete,
 					  NULL, mapping_gfp_mask(mapping));
 
 	switch (ret) {

fs/cifs/dir.c

@@ -194,7 +194,7 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 	int i;
 
 	if (unlikely(direntry->d_name.len >
-		     tcon->fsAttrInfo.MaxPathNameComponentLength))
+		     le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
 		return -ENAMETOOLONG;
 
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {

fs/cifs/smb2pdu.h

@@ -82,8 +82,8 @@
 
 #define NUMBER_OF_SMB2_COMMANDS	0x0013
 
-/* BB FIXME - analyze following length BB */
-#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
+/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
+#define MAX_SMB2_HDR_SIZE 0x00b0
 
 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 

fs/crypto/Kconfig

@@ -0,0 +1,18 @@
+config FS_ENCRYPTION
+	tristate "FS Encryption (Per-file encryption)"
+	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_XTS
+	select CRYPTO_CTS
+	select CRYPTO_CTR
+	select CRYPTO_SHA256
+	select KEYS
+	select ENCRYPTED_KEYS
+	help
+	  Enable encryption of files and directories.  This
+	  feature is similar to ecryptfs, but it is more memory
+	  efficient since it avoids caching the encrypted and
+	  decrypted pages in the page cache.

fs/crypto/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
+
+fscrypto-y := crypto.o fname.o policy.o keyinfo.o

fs/crypto/crypto.c

@@ -0,0 +1,568 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <linux/namei.h>
+#include <linux/fscrypto.h>
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+		"Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+		"Number of crypto contexts to preallocate");
+
+static mempool_t *fscrypt_bounce_page_pool = NULL;
+
+static LIST_HEAD(fscrypt_free_ctxs);
+static DEFINE_SPINLOCK(fscrypt_ctx_lock);
+
+static struct workqueue_struct *fscrypt_read_workqueue;
+static DEFINE_MUTEX(fscrypt_init_mutex);
+
+static struct kmem_cache *fscrypt_ctx_cachep;
+struct kmem_cache *fscrypt_info_cachep;
+
+/**
+ * fscrypt_release_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+	unsigned long flags;
+
+	if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+		mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
+		ctx->w.bounce_page = NULL;
+	}
+	ctx->w.control_page = NULL;
+	if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+		kmem_cache_free(fscrypt_ctx_cachep, ctx);
+	} else {
+		spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+		spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	}
+}
+EXPORT_SYMBOL(fscrypt_release_ctx);
+
+/**
+ * fscrypt_get_ctx() - Gets an encryption context
+ * @inode:       The inode for which we are doing the crypto
+ * @gfp_flags:   The gfp flag for memory allocation
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
+{
+	struct fscrypt_ctx *ctx = NULL;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	unsigned long flags;
+
+	if (ci == NULL)
+		return ERR_PTR(-ENOKEY);
+
+	/*
+	 * We first try getting the ctx from a free list because in
+	 * the common case the ctx will have an allocated and
+	 * initialized crypto tfm, so it's probably a worthwhile
+	 * optimization. For the bounce page, we first try getting it
+	 * from the kernel allocator because that's just about as fast
+	 * as getting it from a list and because a cache of free pages
+	 * should generally be a "last resort" option for a filesystem
+	 * to be able to do its job.
+	 */
+	spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+	ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
+					struct fscrypt_ctx, free_list);
+	if (ctx)
+		list_del(&ctx->free_list);
+	spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	if (!ctx) {
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags);
+		if (!ctx)
+			return ERR_PTR(-ENOMEM);
+		ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	} else {
+		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	}
+	ctx->flags &= ~FS_WRITE_PATH_FL;
+	return ctx;
+}
+EXPORT_SYMBOL(fscrypt_get_ctx);
+
+/**
+ * page_crypt_complete() - completion callback for page crypto
+ * @req: The asynchronous cipher request context
+ * @res: The result of the cipher operation
+ */
+static void page_crypt_complete(struct crypto_async_request *req, int res)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (res == -EINPROGRESS)
+		return;
+	ecr->res = res;
+	complete(&ecr->completion);
+}
+
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
+static int do_page_crypto(struct inode *inode,
+			fscrypt_direction_t rw, pgoff_t index,
+			struct page *src_page, struct page *dest_page,
+			gfp_t gfp_flags)
+{
+	struct {
+		__le64 index;
+		u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
+	} xts_tweak;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist dst, src;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+
+	req = skcipher_request_alloc(tfm, gfp_flags);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+				"%s: crypto_request_alloc() failed\n",
+				__func__);
+		return -ENOMEM;
+	}
+
+	skcipher_request_set_callback(
+		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+		page_crypt_complete, &ecr);
+
+	BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
+	xts_tweak.index = cpu_to_le64(index);
+	memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
+
+	sg_init_table(&dst, 1);
+	sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
+	sg_init_table(&src, 1);
+	sg_set_page(&src, src_page, PAGE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak);
+	if (rw == FS_DECRYPT)
+		res = crypto_skcipher_decrypt(req);
+	else
+		res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		BUG_ON(req->base.data != &ecr);
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res) {
+		printk_ratelimited(KERN_ERR
+			"%s: crypto_skcipher_encrypt() returned %d\n",
+			__func__, res);
+		return res;
+	}
+	return 0;
+}
+
+static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
+{
+	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
+	if (ctx->w.bounce_page == NULL)
+		return ERR_PTR(-ENOMEM);
+	ctx->flags |= FS_WRITE_PATH_FL;
+	return ctx->w.bounce_page;
+}
+
+/**
+ * fscypt_encrypt_page() - Encrypts a page
+ * @inode:          The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ * @gfp_flags:      The gfp flag for memory allocation
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path.  The caller must call
+ * fscrypt_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *fscrypt_encrypt_page(struct inode *inode,
+				struct page *plaintext_page, gfp_t gfp_flags)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	int err;
+
+	BUG_ON(!PageLocked(plaintext_page));
+
+	ctx = fscrypt_get_ctx(inode, gfp_flags);
+	if (IS_ERR(ctx))
+		return (struct page *)ctx;
+
+	/* The encryption operation will require a bounce page. */
+	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+	if (IS_ERR(ciphertext_page))
+		goto errout;
+
+	ctx->w.control_page = plaintext_page;
+	err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
+					plaintext_page, ciphertext_page,
+					gfp_flags);
+	if (err) {
+		ciphertext_page = ERR_PTR(err);
+		goto errout;
+	}
+	SetPagePrivate(ciphertext_page);
+	set_page_private(ciphertext_page, (unsigned long)ctx);
+	lock_page(ciphertext_page);
+	return ciphertext_page;
+
+errout:
+	fscrypt_release_ctx(ctx);
+	return ciphertext_page;
+}
+EXPORT_SYMBOL(fscrypt_encrypt_page);
+
+/**
+ * f2crypt_decrypt_page() - Decrypts a page in-place
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_decrypt_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	return do_page_crypto(page->mapping->host,
+			FS_DECRYPT, page->index, page, page, GFP_NOFS);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_page);
+
+int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
+					ZERO_PAGE(0), ciphertext_page,
+					GFP_NOFS);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_NOWAIT, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(WRITE, bio);
+		if ((err == 0) && bio->bi_error)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *dir;
+	struct fscrypt_info *ci;
+	int dir_has_key, cached_with_key;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	dir = dget_parent(dentry);
+	if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) {
+		dput(dir);
+		return 0;
+	}
+
+	ci = d_inode(dir)->i_crypt_info;
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	spin_lock(&dentry->d_lock);
+	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+	dir_has_key = (ci != NULL);
+	dput(dir);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+			(!cached_with_key && dir_has_key) ||
+			(cached_with_key && !dir_has_key))
+		return 0;
+	return 1;
+}
+
+const struct dentry_operations fscrypt_d_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+EXPORT_SYMBOL(fscrypt_d_ops);
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+void fscrypt_restore_control_page(struct page *page)
+{
+	struct fscrypt_ctx *ctx;
+
+	ctx = (struct fscrypt_ctx *)page_private(page);
+	set_page_private(page, (unsigned long)NULL);
+	ClearPagePrivate(page);
+	unlock_page(page);
+	fscrypt_release_ctx(ctx);
+}
+EXPORT_SYMBOL(fscrypt_restore_control_page);
+
+static void fscrypt_destroy(void)
+{
+	struct fscrypt_ctx *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
+		kmem_cache_free(fscrypt_ctx_cachep, pos);
+	INIT_LIST_HEAD(&fscrypt_free_ctxs);
+	mempool_destroy(fscrypt_bounce_page_pool);
+	fscrypt_bounce_page_pool = NULL;
+}
+
+/**
+ * fscrypt_initialize() - allocate major buffers for fs encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_initialize(void)
+{
+	int i, res = -ENOMEM;
+
+	if (fscrypt_bounce_page_pool)
+		return 0;
+
+	mutex_lock(&fscrypt_init_mutex);
+	if (fscrypt_bounce_page_pool)
+		goto already_initialized;
+
+	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+		struct fscrypt_ctx *ctx;
+
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			goto fail;
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+	}
+
+	fscrypt_bounce_page_pool =
+		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+	if (!fscrypt_bounce_page_pool)
+		goto fail;
+
+already_initialized:
+	mutex_unlock(&fscrypt_init_mutex);
+	return 0;
+fail:
+	fscrypt_destroy();
+	mutex_unlock(&fscrypt_init_mutex);
+	return res;
+}
+EXPORT_SYMBOL(fscrypt_initialize);
+
+/**
+ * fscrypt_init() - Set up for fs encryption.
+ */
+static int __init fscrypt_init(void)
+{
+	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
+							WQ_HIGHPRI, 0);
+	if (!fscrypt_read_workqueue)
+		goto fail;
+
+	fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_ctx_cachep)
+		goto fail_free_queue;
+
+	fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_info_cachep)
+		goto fail_free_ctx;
+
+	return 0;
+
+fail_free_ctx:
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+fail_free_queue:
+	destroy_workqueue(fscrypt_read_workqueue);
+fail:
+	return -ENOMEM;
+}
+module_init(fscrypt_init)
+
+/**
+ * fscrypt_exit() - Shutdown the fs encryption system
+ */
+static void __exit fscrypt_exit(void)
+{
+	fscrypt_destroy();
+
+	if (fscrypt_read_workqueue)
+		destroy_workqueue(fscrypt_read_workqueue);
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+	kmem_cache_destroy(fscrypt_info_cachep);
+}
+module_exit(fscrypt_exit);
+
+MODULE_LICENSE("GPL");

fs/crypto/fname.c

@@ -0,0 +1,414 @@
+/*
+ * This contains functions for filename crypto management
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Uday Savagaonkar, 2014.
+ * Modified by Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ */
+
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/fscrypto.h>
+
+/**
+ * fname_crypt_complete() - completion callback for filename crypto
+ * @req: The asynchronous cipher request context
+ * @res: The result of the cipher operation
+ */
+static void fname_crypt_complete(struct crypto_async_request *req, int res)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (res == -EINPROGRESS)
+		return;
+	ecr->res = res;
+	complete(&ecr->completion);
+}
+
+/**
+ * fname_encrypt() - encrypt a filename
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int fname_encrypt(struct inode *inode,
+			const struct qstr *iname, struct fscrypt_str *oname)
+{
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	struct scatterlist sg;
+	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	unsigned int lim;
+	unsigned int cryptlen;
+
+	lim = inode->i_sb->s_cop->max_namelen(inode);
+	if (iname->len <= 0 || iname->len > lim)
+		return -EIO;
+
+	/*
+	 * Copy the filename to the output buffer for encrypting in-place and
+	 * pad it with the needed number of NUL bytes.
+	 */
+	cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE);
+	cryptlen = round_up(cryptlen, padding);
+	cryptlen = min(cryptlen, lim);
+	memcpy(oname->name, iname->name, iname->len);
+	memset(oname->name + iname->len, 0, cryptlen - iname->len);
+
+	/* Initialize the IV */
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
+
+	/* Set up the encryption request */
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+			"%s: skcipher_request_alloc() failed\n", __func__);
+		return -ENOMEM;
+	}
+	skcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			fname_crypt_complete, &ecr);
+	sg_init_one(&sg, oname->name, cryptlen);
+	skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv);
+
+	/* Do the encryption */
+	res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		/* Request is being completed asynchronously; wait for it */
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res < 0) {
+		printk_ratelimited(KERN_ERR
+				"%s: Error (error code %d)\n", __func__, res);
+		return res;
+	}
+
+	oname->len = cryptlen;
+	return 0;
+}
+
+/**
+ * fname_decrypt() - decrypt a filename
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int fname_decrypt(struct inode *inode,
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
+{
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	unsigned lim;
+
+	lim = inode->i_sb->s_cop->max_namelen(inode);
+	if (iname->len <= 0 || iname->len > lim)
+		return -EIO;
+
+	/* Allocate request */
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+			"%s: crypto_request_alloc() failed\n",  __func__);
+		return -ENOMEM;
+	}
+	skcipher_request_set_callback(req,
+		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+		fname_crypt_complete, &ecr);
+
+	/* Initialize IV */
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
+
+	/* Create decryption request */
+	sg_init_one(&src_sg, iname->name, iname->len);
+	sg_init_one(&dst_sg, oname->name, oname->len);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res < 0) {
+		printk_ratelimited(KERN_ERR
+				"%s: Error (error code %d)\n", __func__, res);
+		return res;
+	}
+
+	oname->len = strnlen(oname->name, iname->len);
+	return 0;
+}
+
+static const char *lookup_table =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+/**
+ * digest_encode() -
+ *
+ * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
+ * The encoded string is roughly 4/3 times the size of the input string.
+ */
+static int digest_encode(const char *src, int len, char *dst)
+{
+	int i = 0, bits = 0, ac = 0;
+	char *cp = dst;
+
+	while (i < len) {
+		ac += (((unsigned char) src[i]) << bits);
+		bits += 8;
+		do {
+			*cp++ = lookup_table[ac & 0x3f];
+			ac >>= 6;
+			bits -= 6;
+		} while (bits >= 6);
+		i++;
+	}
+	if (bits)
+		*cp++ = lookup_table[ac & 0x3f];
+	return cp - dst;
+}
+
+static int digest_decode(const char *src, int len, char *dst)
+{
+	int i = 0, bits = 0, ac = 0;
+	const char *p;
+	char *cp = dst;
+
+	while (i < len) {
+		p = strchr(lookup_table, src[i]);
+		if (p == NULL || src[i] == 0)
+			return -2;
+		ac += (p - lookup_table) << bits;
+		bits += 6;
+		if (bits >= 8) {
+			*cp++ = ac & 0xff;
+			ac >>= 8;
+			bits -= 8;
+		}
+		i++;
+	}
+	if (ac)
+		return -1;
+	return cp - dst;
+}
+
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
+{
+	int padding = 32;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (ci)
+		padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	ilen = max(ilen, (u32)FS_CRYPTO_BLOCK_SIZE);
+	return round_up(ilen, padding);
+}
+EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
+
+/**
+ * fscrypt_fname_crypto_alloc_obuff() -
+ *
+ * Allocates an output buffer that is sufficient for the crypto operation
+ * specified by the context and the direction.
+ */
+int fscrypt_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
+{
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
+
+	crypto_str->len = olen;
+	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+	/*
+	 * Allocated buffer can hold one more character to null-terminate the
+	 * string
+	 */
+	crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
+	if (!(crypto_str->name))
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
+
+/**
+ * fscrypt_fname_crypto_free_buffer() -
+ *
+ * Frees the buffer allocated for crypto operation.
+ */
+void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
+{
+	if (!crypto_str)
+		return;
+	kfree(crypto_str->name);
+	crypto_str->name = NULL;
+}
+EXPORT_SYMBOL(fscrypt_fname_free_buffer);
+
+/**
+ * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
+ * space
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			struct fscrypt_str *oname)
+{
+	const struct qstr qname = FSTR_TO_QSTR(iname);
+	char buf[24];
+
+	if (fscrypt_is_dot_dotdot(&qname)) {
+		oname->name[0] = '.';
+		oname->name[iname->len - 1] = '.';
+		oname->len = iname->len;
+		return 0;
+	}
+
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+		return -EUCLEAN;
+
+	if (inode->i_crypt_info)
+		return fname_decrypt(inode, iname, oname);
+
+	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
+		oname->len = digest_encode(iname->name, iname->len,
+					   oname->name);
+		return 0;
+	}
+	if (hash) {
+		memcpy(buf, &hash, 4);
+		memcpy(buf + 4, &minor_hash, 4);
+	} else {
+		memset(buf, 0, 8);
+	}
+	memcpy(buf + 8, iname->name + iname->len - 16, 16);
+	oname->name[0] = '_';
+	oname->len = 1 + digest_encode(buf, 24, oname->name + 1);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
+
+/**
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_fname_usr_to_disk(struct inode *inode,
+			const struct qstr *iname,
+			struct fscrypt_str *oname)
+{
+	if (fscrypt_is_dot_dotdot(iname)) {
+		oname->name[0] = '.';
+		oname->name[iname->len - 1] = '.';
+		oname->len = iname->len;
+		return 0;
+	}
+	if (inode->i_crypt_info)
+		return fname_encrypt(inode, iname, oname);
+	/*
+	 * Without a proper key, a user is not allowed to modify the filenames
+	 * in a directory. Consequently, a user space name cannot be mapped to
+	 * a disk-space name
+	 */
+	return -EACCES;
+}
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
+
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct fscrypt_name *fname)
+{
+	int ret = 0, bigname = 0;
+
+	memset(fname, 0, sizeof(struct fscrypt_name));
+	fname->usr_fname = iname;
+
+	if (!dir->i_sb->s_cop->is_encrypted(dir) ||
+				fscrypt_is_dot_dotdot(iname)) {
+		fname->disk_name.name = (unsigned char *)iname->name;
+		fname->disk_name.len = iname->len;
+		return 0;
+	}
+	ret = get_crypt_info(dir);
+	if (ret && ret != -EOPNOTSUPP)
+		return ret;
+
+	if (dir->i_crypt_info) {
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
+							&fname->crypto_buf);
+		if (ret)
+			return ret;
+		ret = fname_encrypt(dir, iname, &fname->crypto_buf);
+		if (ret)
+			goto errout;
+		fname->disk_name.name = fname->crypto_buf.name;
+		fname->disk_name.len = fname->crypto_buf.len;
+		return 0;
+	}
+	if (!lookup)
+		return -EACCES;
+
+	/*
+	 * We don't have the key and we are doing a lookup; decode the
+	 * user-supplied name
+	 */
+	if (iname->name[0] == '_')
+		bigname = 1;
+	if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
+		return -ENOENT;
+
+	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
+	if (fname->crypto_buf.name == NULL)
+		return -ENOMEM;
+
+	ret = digest_decode(iname->name + bigname, iname->len - bigname,
+				fname->crypto_buf.name);
+	if (ret < 0) {
+		ret = -ENOENT;
+		goto errout;
+	}
+	fname->crypto_buf.len = ret;
+	if (bigname) {
+		memcpy(&fname->hash, fname->crypto_buf.name, 4);
+		memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
+	} else {
+		fname->disk_name.name = fname->crypto_buf.name;
+		fname->disk_name.len = fname->crypto_buf.len;
+	}
+	return 0;
+
+errout:
+	fscrypt_fname_free_buffer(&fname->crypto_buf);
+	return ret;
+}
+EXPORT_SYMBOL(fscrypt_setup_filename);
+
+void fscrypt_free_filename(struct fscrypt_name *fname)
+{
+	kfree(fname->crypto_buf.name);
+	fname->crypto_buf.name = NULL;
+	fname->usr_fname = NULL;
+	fname->disk_name.name = NULL;
+}
+EXPORT_SYMBOL(fscrypt_free_filename);

fs/crypto/keyinfo.c

@@ -0,0 +1,333 @@
+/*
+ * key management facility for FS encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/user-type.h>
+#include <linux/scatterlist.h>
+#include <linux/fscrypto.h>
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (rc == -EINPROGRESS)
+		return;
+
+	ecr->res = rc;
+	complete(&ecr->completion);
+}
+
+/**
+ * derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivation.
+ * @source_key:   Source key to which to apply derivation.
+ * @derived_key:  Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
+				u8 source_key[FS_AES_256_XTS_KEY_SIZE],
+				u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+{
+	int res = 0;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	skcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+					FS_AES_128_ECB_KEY_SIZE);
+	if (res < 0)
+		goto out;
+
+	sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
+	sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+					FS_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+out:
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	return res;
+}
+
+static int validate_user_key(struct fscrypt_info *crypt_info,
+			struct fscrypt_context *ctx, u8 *raw_key,
+			u8 *prefix, int prefix_size)
+{
+	u8 *full_key_descriptor;
+	struct key *keyring_key;
+	struct fscrypt_key *master_key;
+	const struct user_key_payload *ukp;
+	int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
+	int res;
+
+	full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
+	if (!full_key_descriptor)
+		return -ENOMEM;
+
+	memcpy(full_key_descriptor, prefix, prefix_size);
+	sprintf(full_key_descriptor + prefix_size,
+			"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+			ctx->master_key_descriptor);
+	full_key_descriptor[full_key_len - 1] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	kfree(full_key_descriptor);
+	if (IS_ERR(keyring_key))
+		return PTR_ERR(keyring_key);
+
+	if (keyring_key->type != &key_type_logon) {
+		printk_once(KERN_WARNING
+				"%s: key type must be logon\n", __func__);
+		res = -ENOKEY;
+		goto out;
+	}
+	down_read(&keyring_key->sem);
+	ukp = user_key_payload(keyring_key);
+	if (ukp->datalen != sizeof(struct fscrypt_key)) {
+		res = -EINVAL;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	master_key = (struct fscrypt_key *)ukp->data;
+	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+		printk_once(KERN_WARNING
+				"%s: key size incorrect: %d\n",
+				__func__, master_key->size);
+		res = -ENOKEY;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
+	up_read(&keyring_key->sem);
+	if (res)
+		goto out;
+
+	crypt_info->ci_keyring_key = keyring_key;
+	return 0;
+out:
+	key_put(keyring_key);
+	return res;
+}
+
+static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
+				 const char **cipher_str_ret, int *keysize_ret)
+{
+	if (S_ISREG(inode->i_mode)) {
+		if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) {
+			*cipher_str_ret = "xts(aes)";
+			*keysize_ret = FS_AES_256_XTS_KEY_SIZE;
+			return 0;
+		}
+		pr_warn_once("fscrypto: unsupported contents encryption mode "
+			     "%d for inode %lu\n",
+			     ci->ci_data_mode, inode->i_ino);
+		return -ENOKEY;
+	}
+
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
+		if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) {
+			*cipher_str_ret = "cts(cbc(aes))";
+			*keysize_ret = FS_AES_256_CTS_KEY_SIZE;
+			return 0;
+		}
+		pr_warn_once("fscrypto: unsupported filenames encryption mode "
+			     "%d for inode %lu\n",
+			     ci->ci_filename_mode, inode->i_ino);
+		return -ENOKEY;
+	}
+
+	pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n",
+		     (inode->i_mode & S_IFMT), inode->i_ino);
+	return -ENOKEY;
+}
+
+static void put_crypt_info(struct fscrypt_info *ci)
+{
+	if (!ci)
+		return;
+
+	key_put(ci->ci_keyring_key);
+	crypto_free_skcipher(ci->ci_ctfm);
+	kmem_cache_free(fscrypt_info_cachep, ci);
+}
+
+int get_crypt_info(struct inode *inode)
+{
+	struct fscrypt_info *crypt_info;
+	struct fscrypt_context ctx;
+	struct crypto_skcipher *ctfm;
+	const char *cipher_str;
+	int keysize;
+	u8 *raw_key = NULL;
+	int res;
+
+	res = fscrypt_initialize();
+	if (res)
+		return res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return -EOPNOTSUPP;
+retry:
+	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
+	if (crypt_info) {
+		if (!crypt_info->ci_keyring_key ||
+				key_validate(crypt_info->ci_keyring_key) == 0)
+			return 0;
+		fscrypt_put_encryption_info(inode, crypt_info);
+		goto retry;
+	}
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		if (!fscrypt_dummy_context_enabled(inode))
+			return res;
+		ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+	} else if (res != sizeof(ctx)) {
+		return -EINVAL;
+	}
+
+	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+		return -EINVAL;
+
+	if (ctx.flags & ~FS_POLICY_FLAGS_VALID)
+		return -EINVAL;
+
+	crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS);
+	if (!crypt_info)
+		return -ENOMEM;
+
+	crypt_info->ci_flags = ctx.flags;
+	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+	crypt_info->ci_ctfm = NULL;
+	crypt_info->ci_keyring_key = NULL;
+	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+				sizeof(crypt_info->ci_master_key));
+
+	res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
+	if (res)
+		goto out;
+
+	/*
+	 * This cannot be a stack buffer because it is passed to the scatterlist
+	 * crypto API as part of key derivation.
+	 */
+	res = -ENOMEM;
+	raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+	if (!raw_key)
+		goto out;
+
+	if (fscrypt_dummy_context_enabled(inode)) {
+		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		goto got_key;
+	}
+
+	res = validate_user_key(crypt_info, &ctx, raw_key,
+			FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+	if (res && inode->i_sb->s_cop->key_prefix) {
+		u8 *prefix = NULL;
+		int prefix_size, res2;
+
+		prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
+		res2 = validate_user_key(crypt_info, &ctx, raw_key,
+							prefix, prefix_size);
+		if (res2) {
+			if (res2 == -ENOKEY)
+				res = -ENOKEY;
+			goto out;
+		}
+	} else if (res) {
+		goto out;
+	}
+got_key:
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
+	if (!ctfm || IS_ERR(ctfm)) {
+		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+		printk(KERN_DEBUG
+		       "%s: error %d (inode %u) allocating crypto tfm\n",
+		       __func__, res, (unsigned) inode->i_ino);
+		goto out;
+	}
+	crypt_info->ci_ctfm = ctfm;
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
+	if (res)
+		goto out;
+
+	kzfree(raw_key);
+	raw_key = NULL;
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
+		put_crypt_info(crypt_info);
+		goto retry;
+	}
+	return 0;
+
+out:
+	if (res == -ENOKEY)
+		res = 0;
+	put_crypt_info(crypt_info);
+	kzfree(raw_key);
+	return res;
+}
+
+void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+{
+	struct fscrypt_info *prev;
+
+	if (ci == NULL)
+		ci = ACCESS_ONCE(inode->i_crypt_info);
+	if (ci == NULL)
+		return;
+
+	prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
+	if (prev != ci)
+		return;
+
+	put_crypt_info(ci);
+}
+EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (!ci ||
+		(ci->ci_keyring_key &&
+		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					       (1 << KEY_FLAG_REVOKED) |
+					       (1 << KEY_FLAG_DEAD)))))
+		return get_crypt_info(inode);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);

fs/crypto/policy.c

@@ -0,0 +1,250 @@
+/*
+ * Encryption policy functions for per-file encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/fscrypto.h>
+#include <linux/mount.h>
+
+static int inode_has_encryption_context(struct inode *inode)
+{
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int is_encryption_context_consistent_with_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return 0;
+
+	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(ctx.flags == policy->flags) &&
+			(ctx.contents_encryption_mode ==
+			 policy->contents_encryption_mode) &&
+			(ctx.filenames_encryption_mode ==
+			 policy->filenames_encryption_mode));
+}
+
+static int create_encryption_context_from_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	if (inode->i_sb->s_cop->prepare_context) {
+		res = inode->i_sb->s_cop->prepare_context(inode);
+		if (res)
+			return res;
+	}
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+					FS_KEY_DESCRIPTOR_SIZE);
+
+	if (!fscrypt_valid_contents_enc_mode(
+				policy->contents_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid contents encryption mode %d\n", __func__,
+			policy->contents_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (!fscrypt_valid_filenames_enc_mode(
+				policy->filenames_encryption_mode)) {
+		printk(KERN_WARNING
+			"%s: Invalid filenames encryption mode %d\n", __func__,
+			policy->filenames_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
+		return -EINVAL;
+
+	ctx.contents_encryption_mode = policy->contents_encryption_mode;
+	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+	ctx.flags = policy->flags;
+	BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE);
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
+}
+
+int fscrypt_process_policy(struct file *filp,
+				const struct fscrypt_policy *policy)
+{
+	struct inode *inode = file_inode(filp);
+	int ret;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (policy->version != 0)
+		return -EINVAL;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
+	if (!inode_has_encryption_context(inode)) {
+		if (!S_ISDIR(inode->i_mode))
+			ret = -EINVAL;
+		else if (!inode->i_sb->s_cop->empty_dir)
+			ret = -EOPNOTSUPP;
+		else if (!inode->i_sb->s_cop->empty_dir(inode))
+			ret = -ENOTEMPTY;
+		else
+			ret = create_encryption_context_from_policy(inode,
+								    policy);
+	} else if (!is_encryption_context_consistent_with_policy(inode,
+								 policy)) {
+		printk(KERN_WARNING
+		       "%s: Policy inconsistent with encryption context\n",
+		       __func__);
+		ret = -EINVAL;
+	}
+
+	inode_unlock(inode);
+
+	mnt_drop_write_file(filp);
+	return ret;
+}
+EXPORT_SYMBOL(fscrypt_process_policy);
+
+int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context ||
+			!inode->i_sb->s_cop->is_encrypted(inode))
+		return -ENODATA;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return -ENODATA;
+	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+		return -EINVAL;
+
+	policy->version = 0;
+	policy->contents_encryption_mode = ctx.contents_encryption_mode;
+	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+	policy->flags = ctx.flags;
+	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+				FS_KEY_DESCRIPTOR_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_policy);
+
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
+{
+	struct fscrypt_info *parent_ci, *child_ci;
+	int res;
+
+	if ((parent == NULL) || (child == NULL)) {
+		printk(KERN_ERR	"parent %p child %p\n", parent, child);
+		BUG_ON(1);
+	}
+
+	/* no restrictions if the parent directory is not encrypted */
+	if (!parent->i_sb->s_cop->is_encrypted(parent))
+		return 1;
+	/* if the child directory is not encrypted, this is always a problem */
+	if (!parent->i_sb->s_cop->is_encrypted(child))
+		return 0;
+	res = fscrypt_get_encryption_info(parent);
+	if (res)
+		return 0;
+	res = fscrypt_get_encryption_info(child);
+	if (res)
+		return 0;
+	parent_ci = parent->i_crypt_info;
+	child_ci = child->i_crypt_info;
+	if (!parent_ci && !child_ci)
+		return 1;
+	if (!parent_ci || !child_ci)
+		return 0;
+
+	return (memcmp(parent_ci->ci_master_key,
+			child_ci->ci_master_key,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+		(parent_ci->ci_flags == child_ci->ci_flags));
+}
+EXPORT_SYMBOL(fscrypt_has_permitted_context);
+
+/**
+ * fscrypt_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child:  Child inode that inherits the context from @parent.
+ * @fs_data:  private data given by FS.
+ * @preload:  preload child i_crypt_info
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int fscrypt_inherit_context(struct inode *parent, struct inode *child,
+						void *fs_data, bool preload)
+{
+	struct fscrypt_context ctx;
+	struct fscrypt_info *ci;
+	int res;
+
+	if (!parent->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	res = fscrypt_get_encryption_info(parent);
+	if (res < 0)
+		return res;
+
+	ci = parent->i_crypt_info;
+	if (ci == NULL)
+		return -ENOKEY;
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	if (fscrypt_dummy_context_enabled(parent)) {
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
+		res = 0;
+	} else {
+		ctx.contents_encryption_mode = ci->ci_data_mode;
+		ctx.filenames_encryption_mode = ci->ci_filename_mode;
+		ctx.flags = ci->ci_flags;
+		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+				FS_KEY_DESCRIPTOR_SIZE);
+	}
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	res = parent->i_sb->s_cop->set_context(child, &ctx,
+						sizeof(ctx), fs_data);
+	if (res)
+		return res;
+	return preload ? fscrypt_get_encryption_info(child): 0;
+}
+EXPORT_SYMBOL(fscrypt_inherit_context);

fs/dlm/user.c

@@ -355,6 +355,10 @@ static int dlm_device_register(struct dlm_ls *ls, char *name)
 	error = misc_register(&ls->ls_device);
 	if (error) {
 		kfree(ls->ls_device.name);
+		/* this has to be set to NULL
+		 * to avoid a double-free in dlm_device_deregister
+		 */
+		ls->ls_device.name = NULL;
 	}
 fail:
 	return error;