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

* refs/heads/tmp-d68ba9f
  Linux 4.4.89
  ftrace: Fix memleak when unregistering dynamic ops when tracing disabled
  bcache: fix bch_hprint crash and improve output
  bcache: fix for gc and write-back race
  bcache: Correct return value for sysfs attach errors
  bcache: correct cache_dirty_target in __update_writeback_rate()
  bcache: do not subtract sectors_to_gc for bypassed IO
  bcache: Fix leak of bdev reference
  bcache: initialize dirty stripes in flash_dev_run()
  media: uvcvideo: Prevent heap overflow when accessing mapped controls
  media: v4l2-compat-ioctl32: Fix timespec conversion
  PCI: shpchp: Enable bridge bus mastering if MSI is enabled
  ARC: Re-enable MMU upon Machine Check exception
  tracing: Apply trace_clock changes to instance max buffer
  ftrace: Fix selftest goto location on error
  scsi: qla2xxx: Fix an integer overflow in sysfs code
  scsi: sg: fixup infoleak when using SG_GET_REQUEST_TABLE
  scsi: sg: factor out sg_fill_request_table()
  scsi: sg: off by one in sg_ioctl()
  scsi: sg: use standard lists for sg_requests
  scsi: sg: remove 'save_scat_len'
  scsi: storvsc: fix memory leak on ring buffer busy
  scsi: megaraid_sas: Return pended IOCTLs with cmd_status MFI_STAT_WRONG_STATE in case adapter is dead
  scsi: megaraid_sas: Check valid aen class range to avoid kernel panic
  scsi: zfcp: trace high part of "new" 64 bit SCSI LUN
  scsi: zfcp: trace HBA FSF response by default on dismiss or timedout late response
  scsi: zfcp: fix payload with full FCP_RSP IU in SCSI trace records
  scsi: zfcp: fix missing trace records for early returns in TMF eh handlers
  scsi: zfcp: fix passing fsf_req to SCSI trace on TMF to correlate with HBA
  scsi: zfcp: fix capping of unsuccessful GPN_FT SAN response trace records
  scsi: zfcp: add handling for FCP_RESID_OVER to the fcp ingress path
  scsi: zfcp: fix queuecommand for scsi_eh commands when DIX enabled
  skd: Submit requests to firmware before triggering the doorbell
  skd: Avoid that module unloading triggers a use-after-free
  md/bitmap: disable bitmap_resize for file-backed bitmaps.
  block: Relax a check in blk_start_queue()
  powerpc: Fix DAR reporting when alignment handler faults
  ext4: fix quota inconsistency during orphan cleanup for read-only mounts
  ext4: fix incorrect quotaoff if the quota feature is enabled
  crypto: AF_ALG - remove SGL terminator indicator when chaining
  MIPS: math-emu: MINA.<D|S>: Fix some cases of infinity and zero inputs
  MIPS: math-emu: <MAXA|MINA>.<D|S>: Fix cases of both infinite inputs
  MIPS: math-emu: <MAXA|MINA>.<D|S>: Fix cases of input values with opposite signs
  MIPS: math-emu: <MAX|MIN>.<D|S>: Fix cases of both inputs negative
  MIPS: math-emu: <MAX|MAXA|MIN|MINA>.<D|S>: Fix cases of both inputs zero
  MIPS: math-emu: <MAX|MAXA|MIN|MINA>.<D|S>: Fix quiet NaN propagation
  Input: i8042 - add Gigabyte P57 to the keyboard reset table
  tty: fix __tty_insert_flip_char regression
  tty: improve tty_insert_flip_char() slow path
  tty: improve tty_insert_flip_char() fast path
  mm: prevent double decrease of nr_reserved_highatomic
  nfsd: Fix general protection fault in release_lock_stateid()
  md/raid5: release/flush io in raid5_do_work()
  x86/fsgsbase/64: Report FSBASE and GSBASE correctly in core dumps
  f2fs: check hot_data for roll-forward recovery
  ipv6: fix typo in fib6_net_exit()
  ipv6: fix memory leak with multiple tables during netns destruction
  gianfar: Fix Tx flow control deactivation
  Revert "net: fix percpu memory leaks"
  Revert "net: use lib/percpu_counter API for fragmentation mem accounting"
  tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0
  Revert "net: phy: Correctly process PHY_HALTED in phy_stop_machine()"
  qlge: avoid memcpy buffer overflow
  ipv6: fix sparse warning on rt6i_node
  ipv6: add rcu grace period before freeing fib6_node
  ipv6: accept 64k - 1 packet length in ip6_find_1stfragopt()
  f2fs: fix a missing size change in f2fs_setattr
  f2fs: fix to access nullified flush_cmd_control pointer
  f2fs: free meta pages if sanity check for ckpt is failed
  f2fs: detect wrong layout
  f2fs: call sync_fs when f2fs is idle
  Revert "f2fs: use percpu_counter for # of dirty pages in inode"
  f2fs: return AOP_WRITEPAGE_ACTIVATE for writepage
  f2fs: do not activate auto_recovery for fallocated i_size
  f2fs: fix 32-bit build
  f2fs: fix incorrect free inode count in ->statfs
  f2fs: drop duplicate header timer.h
  f2fs: fix wrong AUTO_RECOVER condition
  f2fs: do not recover i_size if it's valid
  f2fs: fix fdatasync
  f2fs: fix to account total free nid correctly
  f2fs: fix an infinite loop when flush nodes in cp
  f2fs: don't wait writeback for datas during checkpoint
  f2fs: fix wrong written_valid_blocks counting
  f2fs: avoid BG_GC in f2fs_balance_fs
  f2fs: fix redundant block allocation
  f2fs: use err for f2fs_preallocate_blocks
  f2fs: support multiple devices
  f2fs: allow dio read for LFS mode
  f2fs: revert segment allocation for direct IO
  f2fs: return directly if block has been removed from the victim
  Revert "f2fs: do not recover from previous remained wrong dnodes"
  f2fs: remove checkpoint in f2fs_freeze
  f2fs: assign segments correctly for direct_io
  f2fs: fix wrong i_atime recovery
  f2fs: record inode updating status correctly
  f2fs: Trace reset zone events
  f2fs: Reset sequential zones on zoned block devices
  f2fs: Cache zoned block devices zone type
  f2fs: Do not allow adaptive mode for host-managed zoned block devices
  f2fs: Always enable discard for zoned blocks devices
  f2fs: Suppress discard warning message for zoned block devices
  f2fs: Check zoned block feature for host-managed zoned block devices
  f2fs: Use generic zoned block device terminology
  f2fs: Add missing break in switch-case
  f2fs: avoid infinite loop in the EIO case on recover_orphan_inodes
  f2fs: report error of f2fs_fill_dentries
  fs/crypto: catch up 4.9-rc6
  f2fs: hide a maybe-uninitialized warning
  f2fs: remove percpu_count due to performance regression
  f2fs: make clean inodes when flushing inode page
  f2fs: keep dirty inodes selectively for checkpoint
  f2fs: Replace CURRENT_TIME_SEC with current_time() for inode timestamps
  f2fs: use BIO_MAX_PAGES for bio allocation
  f2fs: declare static function for __build_free_nids
  f2fs: call f2fs_balance_fs for setattr
  f2fs: count dirty inodes to flush node pages during checkpoint
  f2fs: avoid casted negative value as shrink count
  f2fs: don't interrupt free nids building during nid allocation
  f2fs: clean up free nid list operations
  f2fs: split free nid list
  f2fs: clear nlink if fail to add_link
  f2fs: fix sparse warnings
  f2fs: fix error handling in fsync_node_pages
  f2fs: fix to update largest extent under lock
  f2fs: be aware of extent beyond EOF in fiemap
  f2fs: don't miss any f2fs_balance_fs cases
  f2fs: add missing f2fs_balance_fs in f2fs_zero_range
  f2fs: give a chance to detach from dirty list
  f2fs: fix to release discard entries during checkpoint
  f2fs: exclude free nids building and allocation
  f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
  f2fs: fix overflow due to condition check order
  posix_acl: Clear SGID bit when setting file permissions
  f2fs: fix wrong sum_page pointer in f2fs_gc
  f2fs: backport from (4c1fad64 - Merge tag 'for-f2fs-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs)
  Revert "ANDROID: sched/tune: Initialize raw_spin_lock in boosted_groups"
  BACKPORT: partial: mm, oom_reaper: do not mmput synchronously from the oom reaper context
  FROMLIST: android: binder: Don't get mm from task
  FROMLIST: android: binder: Remove unused vma argument
  FROMLIST: android: binder: Drop lru lock in isolate callback
  ANDROID: configs: remove config fragments
  drivers: cpufreq_interactive: handle error for module load fail
  UPSTREAM: Fix build break in fork.c when THREAD_SIZE < PAGE_SIZE

Conflicts:
	android/configs/android-base.cfg
	android/configs/android-recommended.cfg
	fs/f2fs/data.c
	fs/f2fs/f2fs.h
	fs/f2fs/super.c
	include/linux/mm_types.h
	include/linux/sched.h
	kernel/fork.c

Change-Id: I21a427f17e8a1892a212df7c8707f74fb37ce400
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

8 files changed, 337 insertions, 136 deletions

diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 2efb0625331d..db1eee5fe502 100644
--- a/arch/arc/kernel/entry.S
+++ b/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
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index daf2bf52b984..97e9582dcf99 100644
--- a/arch/arc/mm/tlb.c
+++ b/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++) {
 
diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c
index fd71b8daaaf2..5bec64f2884e 100644
--- a/arch/mips/math-emu/dp_fmax.c
+++ b/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;
 }
diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c
index c1072b0dfb95..a287b23818d8 100644
--- a/arch/mips/math-emu/dp_fmin.c
+++ b/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;
 }
diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c
index 4d000844e48e..74a5a00d2f22 100644
--- a/arch/mips/math-emu/sp_fmax.c
+++ b/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;
 }
diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c
index 4eb1bb9e9dec..c51385f46b09 100644
--- a/arch/mips/math-emu/sp_fmin.c
+++ b/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;
 }
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 91e5c1758b5c..64e016abb2a5 100644
--- a/arch/powerpc/kernel/align.c
+++ b/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
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index bcd3d6199464..bb16a58cf7e4 100644
--- a/arch/x86/include/asm/elf.h
+++ b/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;	\