Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1525927 > unrolled thread

[PATCH 4.8 00/49] 4.8.10-stable review

Started byGreg Kroah-Hartman <gregkh@linuxfoundation.org>
First post2016-11-19 10:30 +0100
Last post2016-11-21 17:40 +0100
Articles 20 on this page of 22 — 3 participants

Back to article view | Back to linux.kernel


Contents

  [PATCH 4.8 00/49] 4.8.10-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 07/49] ipv4: allow local fragmentation in ip_finish_output_gso() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 42/49] sparc64: Convert NG4copy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 36/49] sparc64: Handle extremely large kernel TLB range flushes more gracefully. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 43/49] sparc64: Convert NGcopy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 24/49] mlxsw: spectrum: Fix refcount bug on span entries Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 33/49] sparc64: Fix illegal relative branches in hypervisor patched TLB code. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
    [PATCH 4.8 37/49] sparc64: Delete __ret_efault. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 11/49] dccp: fix out of bound access in dccp_v4_err() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 32/49] sparc64: Handle extremely large kernel TSB range flushes sanely. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 02/49] net: clear sk_err_soft in sk_clone_lock() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 28/49] sctp: change sk state only when it has assocs in sctp_shutdown Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 10/49] dccp: do not send reset to already closed sockets Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 38/49] sparc64: Prepare to move to more saner user copy exception handling. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 09/49] dccp: do not release listeners too soon Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 40/49] sparc64: Convert GENcopy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 15/49] bpf: fix htab map destruction when extra reserve is in use Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    [PATCH 4.8 13/49] ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
    Re: [PATCH 4.8 00/49] 4.8.10-stable review Guenter Roeck <linux@roeck-us.net> - 2016-11-19 17:30 +0100
      Re: [PATCH 4.8 00/49] 4.8.10-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 18:00 +0100
    Re: [PATCH 4.8 00/49] 4.8.10-stable review Shuah Khan <shuah.kh@samsung.com> - 2016-11-21 17:40 +0100

Page 1 of 2  [1] 2  Next page →


#1525927 — [PATCH 4.8 00/49] 4.8.10-stable review

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 00/49] 4.8.10-stable review
Message-ID<sFa89-33e-3@gated-at.bofh.it>
This is the start of the stable review cycle for the 4.8.10 release.
There are 49 patches in this series, all will be posted as a response
to this one.  If anyone has any issues with these being applied, please
let me know.

Responses should be made by Mon Nov 21 09:20:18 UTC 2016.
Anything received after that time might be too late.

The whole patch series can be found in one patch at:
	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.8.10-rc1.gz
or in the git tree and branch at:
  git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.8.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <gregkh@linuxfoundation.org>
    Linux 4.8.10-rc1

Michal Nazarewicz <mina86@mina86.com>
    usb: gadget: f_fs: stop sleeping in ffs_func_eps_disable

Michal Nazarewicz <mina86@mina86.com>
    usb: gadget: f_fs: edit epfile->ep under lock

David S. Miller <davem@davemloft.net>
    sparc64: Delete now unused user copy fixup functions.

David S. Miller <davem@davemloft.net>
    sparc64: Delete now unused user copy assembler helpers.

David S. Miller <davem@davemloft.net>
    sparc64: Convert U3copy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert NG2copy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert NGcopy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert NG4copy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert U1copy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert GENcopy_{from,to}_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Convert copy_in_user to accurate exception reporting.

David S. Miller <davem@davemloft.net>
    sparc64: Prepare to move to more saner user copy exception handling.

David S. Miller <davem@davemloft.net>
    sparc64: Delete __ret_efault.

David S. Miller <davem@davemloft.net>
    sparc64: Handle extremely large kernel TLB range flushes more gracefully.

David S. Miller <davem@davemloft.net>
    sparc64: Fix illegal relative branches in hypervisor patched TLB cross-call code.

David S. Miller <davem@davemloft.net>
    sparc64: Fix instruction count in comment for __hypervisor_flush_tlb_pending.

David S. Miller <davem@davemloft.net>
    sparc64: Fix illegal relative branches in hypervisor patched TLB code.

David S. Miller <davem@davemloft.net>
    sparc64: Handle extremely large kernel TSB range flushes sanely.

James Clarke <jrtc27@jrtc27.com>
    sparc: Handle negative offsets in arch_jump_label_transform

Baruch Siach <baruch@tkos.co.il>
    spi: spidev_test: fix build with musl libc

Florian Fainelli <f.fainelli@gmail.com>
    net: stmmac: Fix lack of link transition for fixed PHYs

Xin Long <lucien.xin@gmail.com>
    sctp: change sk state only when it has assocs in sctp_shutdown

Baoquan He <bhe@redhat.com>
    bnx2: Wait for in-flight DMA to complete at probe stage

Baoquan He <bhe@redhat.com>
    Revert "bnx2: Reset device during driver initialization"

Arkadi Sharshevsky <arkadis@mellanox.com>
    mlxsw: spectrum_router: Correctly dump neighbour activity

Yotam Gigi <yotamg@mellanox.com>
    mlxsw: spectrum: Fix refcount bug on span entries

Mike Frysinger <vapier@gentoo.org>
    Revert "include/uapi/linux/atm_zatm.h: include linux/time.h"

Eric Dumazet <edumazet@google.com>
    tcp: take care of truncations done by sk_filter()

Stephen Suryaputra Lin <stephen.suryaputra.lin@gmail.com>
    ipv4: use new_gw for redirect neigh lookup

Eric Dumazet <edumazet@google.com>
    net: __skb_flow_dissect() must cap its return value

David Ahern <dsa@cumulusnetworks.com>
    net: icmp_route_lookup should use rt dev to determine L3 domain

Soheil Hassas Yeganeh <soheil@google.com>
    sock: fix sendmmsg for partial sendmsg

Alexander Duyck <alexander.h.duyck@intel.com>
    fib_trie: Correct /proc/net/route off by one error

David Ahern <dsa@cumulusnetworks.com>
    net: icmp6_send should use dst dev to determine L3 domain

Daniel Borkmann <daniel@iogearbox.net>
    bpf: fix htab map destruction when extra reserve is in use

Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
    sctp: assign assoc_id earlier in __sctp_connect

Eric Dumazet <edumazet@google.com>
    ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped

Eric Dumazet <edumazet@google.com>
    ipv6: dccp: fix out of bound access in dccp_v6_err()

Eric Dumazet <edumazet@google.com>
    dccp: fix out of bound access in dccp_v4_err()

Eric Dumazet <edumazet@google.com>
    dccp: do not send reset to already closed sockets

Eric Dumazet <edumazet@google.com>
    dccp: do not release listeners too soon

Eric Dumazet <edumazet@google.com>
    tcp: fix return value for partial writes

Lance Richardson <lrichard@redhat.com>
    ipv4: allow local fragmentation in ip_finish_output_gso()

Eric Dumazet <edumazet@google.com>
    tcp: fix potential memory corruption

Eli Cooper <elicooper@gmx.com>
    ip6_tunnel: Clear IP6CB in ip6tunnel_xmit()

Andy Gospodarek <gospo@broadcom.com>
    bgmac: stop clearing DMA receive control register right after it is set

Eric Dumazet <edumazet@google.com>
    net: mangle zero checksum in skb_checksum_help()

Eric Dumazet <edumazet@google.com>
    net: clear sk_err_soft in sk_clone_lock()

Florian Westphal <fw@strlen.de>
    dctcp: avoid bogus doubling of cwnd after loss


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

Diffstat:

 Makefile                                           |   4 +-
 arch/sparc/include/asm/uaccess_64.h                |  28 +-
 arch/sparc/kernel/head_64.S                        |  36 --
 arch/sparc/kernel/jump_label.c                     |  23 +-
 arch/sparc/kernel/sparc_ksyms_64.c                 |   1 -
 arch/sparc/lib/GENcopy_from_user.S                 |   4 +-
 arch/sparc/lib/GENcopy_to_user.S                   |   4 +-
 arch/sparc/lib/GENmemcpy.S                         |  48 ++-
 arch/sparc/lib/Makefile                            |   2 +-
 arch/sparc/lib/NG2copy_from_user.S                 |   8 +-
 arch/sparc/lib/NG2copy_to_user.S                   |   8 +-
 arch/sparc/lib/NG2memcpy.S                         | 228 ++++++++-----
 arch/sparc/lib/NG4copy_from_user.S                 |   8 +-
 arch/sparc/lib/NG4copy_to_user.S                   |   8 +-
 arch/sparc/lib/NG4memcpy.S                         | 294 ++++++++++++----
 arch/sparc/lib/NGcopy_from_user.S                  |   4 +-
 arch/sparc/lib/NGcopy_to_user.S                    |   4 +-
 arch/sparc/lib/NGmemcpy.S                          | 233 ++++++++-----
 arch/sparc/lib/U1copy_from_user.S                  |   8 +-
 arch/sparc/lib/U1copy_to_user.S                    |   8 +-
 arch/sparc/lib/U1memcpy.S                          | 345 ++++++++++++-------
 arch/sparc/lib/U3copy_from_user.S                  |   8 +-
 arch/sparc/lib/U3copy_to_user.S                    |   8 +-
 arch/sparc/lib/U3memcpy.S                          | 227 +++++++++----
 arch/sparc/lib/copy_in_user.S                      |  35 +-
 arch/sparc/lib/user_fixup.c                        |  71 ----
 arch/sparc/mm/tsb.c                                |  17 +
 arch/sparc/mm/ultra.S                              | 374 +++++++++++++++++----
 drivers/net/ethernet/broadcom/bgmac.c              |   5 +-
 drivers/net/ethernet/broadcom/bnx2.c               |  48 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |   4 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  22 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |   7 +
 drivers/usb/gadget/function/f_fs.c                 | 107 +++++-
 include/net/ip.h                                   |   1 -
 include/net/ip6_tunnel.h                           |   1 +
 include/net/sock.h                                 |   4 +-
 include/net/tcp.h                                  |   1 +
 include/uapi/linux/atm_zatm.h                      |   1 -
 kernel/bpf/hashtab.c                               |   3 +-
 net/core/dev.c                                     |   2 +-
 net/core/flow_dissector.c                          |  11 +-
 net/core/sock.c                                    |   6 +-
 net/dccp/ipv4.c                                    |  16 +-
 net/dccp/ipv6.c                                    |  19 +-
 net/dccp/proto.c                                   |   4 +
 net/ipv4/fib_trie.c                                |  21 +-
 net/ipv4/icmp.c                                    |   4 +-
 net/ipv4/ip_forward.c                              |   2 +-
 net/ipv4/ip_output.c                               |   6 +-
 net/ipv4/ip_tunnel_core.c                          |  11 -
 net/ipv4/ipmr.c                                    |   2 +-
 net/ipv4/route.c                                   |   4 +-
 net/ipv4/tcp.c                                     |   4 +-
 net/ipv4/tcp_dctcp.c                               |  13 +-
 net/ipv4/tcp_ipv4.c                                |  19 +-
 net/ipv6/icmp.c                                    |   2 +-
 net/ipv6/tcp_ipv6.c                                |   6 +-
 net/sctp/socket.c                                  |  22 +-
 net/socket.c                                       |   2 +
 tools/spi/spidev_test.c                            |   1 +
 61 files changed, 1625 insertions(+), 802 deletions(-)

[toc] | [next] | [standalone]


#1525928 — [PATCH 4.8 07/49] ipv4: allow local fragmentation in ip_finish_output_gso()

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 07/49] ipv4: allow local fragmentation in ip_finish_output_gso()
Message-ID<sFa8c-33e-107@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Lance Richardson <lrichard@redhat.com>


[ Upstream commit 9ee6c5dc816aa8256257f2cd4008a9291ec7e985 ]

Some configurations (e.g. geneve interface with default
MTU of 1500 over an ethernet interface with 1500 MTU) result
in the transmission of packets that exceed the configured MTU.
While this should be considered to be a "bad" configuration,
it is still allowed and should not result in the sending
of packets that exceed the configured MTU.

Fix by dropping the assumption in ip_finish_output_gso() that
locally originated gso packets will never need fragmentation.
Basic testing using iperf (observing CPU usage and bandwidth)
have shown no measurable performance impact for traffic not
requiring fragmentation.

Fixes: c7ba65d7b649 ("net: ip: push gso skb forwarding handling down the stack")
Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/net/ip.h          |    1 -
 net/ipv4/ip_forward.c     |    2 +-
 net/ipv4/ip_output.c      |    6 ++----
 net/ipv4/ip_tunnel_core.c |   11 -----------
 net/ipv4/ipmr.c           |    2 +-
 5 files changed, 4 insertions(+), 18 deletions(-)

--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -47,7 +47,6 @@ struct inet_skb_parm {
 #define IPSKB_REROUTED		BIT(4)
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
-#define IPSKB_FRAG_SEGS		BIT(7)
 
 	u16			frag_max_size;
 };
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
 	if (ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -223,11 +223,9 @@ static int ip_finish_output_gso(struct n
 	struct sk_buff *segs;
 	int ret = 0;
 
-	/* common case: fragmentation of segments is not allowed,
-	 * or seglen is <= mtu
+	/* common case: seglen is <= mtu
 	 */
-	if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
-	      skb_gso_validate_mtu(skb, mtu))
+	if (skb_gso_validate_mtu(skb, mtu))
 		return ip_finish_output2(net, sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, stru
 	int pkt_len = skb->len - skb_inner_network_offset(skb);
 	struct net *net = dev_net(rt->dst.dev);
 	struct net_device *dev = skb->dev;
-	int skb_iif = skb->skb_iif;
 	struct iphdr *iph;
 	int err;
 
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, stru
 	skb_dst_set(skb, &rt->dst);
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-	if (skb_iif && !(df & htons(IP_DF))) {
-		/* Arrived from an ingress interface, got encapsulated, with
-		 * fragmentation of encapulating frames allowed.
-		 * If skb is gso, the resulting encapsulated network segments
-		 * may exceed dst mtu.
-		 * Allow IP Fragmentation of segments.
-		 */
-		IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
-	}
-
 	/* Push down and install the IP header. */
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *
 		vif->dev->stats.tx_bytes += skb->len;
 	}
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 
 	/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
 	 * not only before forwarding, but after forwarding on all output

[toc] | [prev] | [next] | [standalone]


#1525930 — [PATCH 4.8 42/49] sparc64: Convert NG4copy_{from,to}_user to accurate exception reporting.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 42/49] sparc64: Convert NG4copy_{from,to}_user to accurate exception reporting.
Message-ID<sFa8c-33e-103@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit 95707704800988093a9b9a27e0f2f67f5b4bf2fa ]

Report the exact number of bytes which have not been successfully
copied when an exception occurs, using the running remaining length.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/lib/NG4copy_from_user.S |    8 -
 arch/sparc/lib/NG4copy_to_user.S   |    8 -
 arch/sparc/lib/NG4memcpy.S         |  294 ++++++++++++++++++++++++++++---------
 3 files changed, 231 insertions(+), 79 deletions(-)

--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x, y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -46,22 +47,19 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
-#endif
 
 #ifndef LOAD
 #define LOAD(type,addr,dest)	type [addr], dest
@@ -94,6 +92,158 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi_fp:
+	VISExitHalf
+__restore_asi:
+	retl
+	 wr	%g0, ASI_AIUS, %asi
+
+ENTRY(NG4_retl_o2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%o2, %o0
+ENDPROC(NG4_retl_o2)
+ENTRY(NG4_retl_o2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 1, %o0
+ENDPROC(NG4_retl_o2_plus_1)
+ENTRY(NG4_retl_o2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 4, %o0
+ENDPROC(NG4_retl_o2_plus_4)
+ENTRY(NG4_retl_o2_plus_o5)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5)
+ENTRY(NG4_retl_o2_plus_o5_plus_4)
+	add	%o5, 4, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_4)
+ENTRY(NG4_retl_o2_plus_o5_plus_8)
+	add	%o5, 8, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_8)
+ENTRY(NG4_retl_o2_plus_o5_plus_16)
+	add	%o5, 16, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_16)
+ENTRY(NG4_retl_o2_plus_o5_plus_24)
+	add	%o5, 24, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_24)
+ENTRY(NG4_retl_o2_plus_o5_plus_32)
+	add	%o5, 32, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_32)
+ENTRY(NG4_retl_o2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1)
+ENTRY(NG4_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_1)
+ENTRY(NG4_retl_o2_plus_g1_plus_8)
+	add	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_8)
+ENTRY(NG4_retl_o2_plus_o4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4)
+ENTRY(NG4_retl_o2_plus_o4_plus_8)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8)
+ENTRY(NG4_retl_o2_plus_o4_plus_16)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16)
+ENTRY(NG4_retl_o2_plus_o4_plus_24)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24)
+ENTRY(NG4_retl_o2_plus_o4_plus_32)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32)
+ENTRY(NG4_retl_o2_plus_o4_plus_40)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40)
+ENTRY(NG4_retl_o2_plus_o4_plus_48)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48)
+ENTRY(NG4_retl_o2_plus_o4_plus_56)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56)
+ENTRY(NG4_retl_o2_plus_o4_plus_64)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64)
+ENTRY(NG4_retl_o2_plus_o4_fp)
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_8_fp)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_16_fp)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_24_fp)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_32_fp)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_40_fp)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_48_fp)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_56_fp)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_64_fp)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp)
+#endif
 	.align		64
 
 	.globl	FUNC_NAME
@@ -124,12 +274,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	brz,pt		%g1, 51f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 
 51:	LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
 	LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
@@ -154,43 +305,43 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	brz,pt		%g1, .Llarge_aligned
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 8, %o1
 	subcc		%g1, 8, %g1
 	add		%o0, 8, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g2, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8)
 
 .Llarge_aligned:
 	/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4)
 	add		%o1, 0x40, %o1
-	EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
+	EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
-	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
-	EX_ST(STORE_INIT(%g1, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
-	EX_ST(STORE_INIT(%o5, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
@@ -216,17 +367,17 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	sub		%o2, %o4, %o2
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
-	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
-1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4)
+1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f2, %f4, %f18
 	add		%g1, 0x40, %g1
 	faligndata	%f4, %f6, %f20
@@ -235,14 +386,14 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
-	EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
-	EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
-	EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
-	EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
-	EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
-	EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
-	EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
+	EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56)
+	EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24)
+	EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16)
+	EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
@@ -270,37 +421,38 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	andncc		%o2, 0x20 - 1, %o5
 	be,pn		%icc, 2f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
-	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5)
 	add		%o1, 0x20, %o1
 	subcc		%o5, 0x20, %o5
-	EX_ST(STORE(stx, %g1, %o0 + 0x00))
-	EX_ST(STORE(stx, %g2, %o0 + 0x08))
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
-	EX_ST(STORE(stx, %o4, %o0 + 0x18))
+	EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32)
+	EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x20, %o0
 2:	andcc		%o2, 0x18, %o5
 	be,pt		%icc, 3f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	add		%o0, 0x08, %o0
 	subcc		%o5, 0x08, %o5
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g1, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8)
 3:	brz,pt		%o2, .Lexit
 	 cmp		%o2, 0x04
 	bl,pn		%icc, .Ltiny
 	 nop
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 0x04, %o1
 	add		%o0, 0x04, %o0
 	subcc		%o2, 0x04, %o2
 	bne,pn		%icc, .Ltiny
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4)
 	ba,a,pt		%icc, .Lexit
 .Lmedium_unaligned:
 	/* First get dest 8 byte aligned.  */
@@ -309,12 +461,12 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	brz,pt		%g1, 2f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 2:
 	and		%o1, 0x7, %g1
 	brz,pn		%g1, .Lmedium_noprefetch
@@ -322,16 +474,16 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	mov		64, %g2
 	sub		%g2, %g1, %g2
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
+	EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2)
 	sllx		%o4, %g1, %o4
 	andn		%o2, 0x08 - 1, %o5
 	sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	subcc		%o5, 0x08, %o5
 	srlx		%g3, %g2, GLOBAL_SPARE
 	or		GLOBAL_SPARE, %o4, GLOBAL_SPARE
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 sllx		%g3, %g1, %o4
@@ -342,17 +494,17 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	ba,pt		%icc, .Lsmall_unaligned
 
 .Ltiny:
-	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x00))
-	EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x01))
-	EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2)
 	ba,pt		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x02))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2)
 
 .Lsmall:
 	andcc		%g2, 0x3, %g0
@@ -360,22 +512,22 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	 andn		%o2, 0x4 - 1, %o5
 	sub		%o2, %o5, %o2
 1:
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x04, %o1
 	subcc		%o5, 0x04, %o5
 	add		%o0, 0x04, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4)
 	brz,pt		%o2, .Lexit
 	 nop
 	ba,a,pt		%icc, .Ltiny
 
 .Lsmall_unaligned:
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 1, %o1
 	add		%o0, 1, %o0
 	subcc		%o2, 1, %o2
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g1, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
 	ba,a,pt		%icc, .Lexit
 	.size		FUNC_NAME, .-FUNC_NAME

[toc] | [prev] | [next] | [standalone]


#1525931 — [PATCH 4.8 36/49] sparc64: Handle extremely large kernel TLB range flushes more gracefully.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 36/49] sparc64: Handle extremely large kernel TLB range flushes more gracefully.
Message-ID<sFa8c-33e-111@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit a74ad5e660a9ee1d071665e7e8ad822784a2dc7f ]

When the vmalloc area gets fragmented, and because the firmware
mapping area sits between where modules live and the vmalloc area, we
can sometimes receive requests for enormous kernel TLB range flushes.

When this happens the cpu just spins flushing billions of pages and
this triggers the NMI watchdog and other problems.

We took care of this on the TSB side by doing a linear scan of the
table once we pass a certain threshold.

Do something similar for the TLB flush, however we are limited by
the TLB flush facilities provided by the different chip variants.

First of all we use an (mostly arbitrary) cut-off of 256K which is
about 32 pages.  This can be tuned in the future.

The huge range code path for each chip works as follows:

1) On spitfire we flush all non-locked TLB entries using diagnostic
   acceses.

2) On cheetah we use the "flush all" TLB flush.

3) On sun4v/hypervisor we do a TLB context flush on context 0, which
   unlike previous chips does not remove "permanent" or locked
   entries.

We could probably do something better on spitfire, such as limiting
the flush to kernel TLB entries or even doing range comparisons.
However that probably isn't worth it since those chips are old and
the TLB only had 64 entries.

Reported-by: James Clarke <jrtc27@jrtc27.com>
Tested-by: James Clarke <jrtc27@jrtc27.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/mm/ultra.S |  283 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 228 insertions(+), 55 deletions(-)

--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -113,12 +113,14 @@ __flush_tlb_pending:	/* 27 insns */
 
 	.align		32
 	.globl		__flush_tlb_kernel_range
-__flush_tlb_kernel_range:	/* 19 insns */
+__flush_tlb_kernel_range:	/* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, __spitfire_flush_tlb_kernel_range_slow
 	 sethi		%hi(PAGE_SIZE), %o4
-	sub		%o1, %o0, %o3
 	sub		%o3, %o4, %o3
 	or		%o0, 0x20, %o0		! Nucleus
 1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -134,6 +136,38 @@ __flush_tlb_kernel_range:	/* 19 insns */
 	nop
 	nop
 	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+	mov		63 * 8, %o4
+1:	ldxa		[%o4] ASI_ITLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_IMMU
+	stxa		%g0, [%o4] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%o4] ASI_DTLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_DMMU
+	stxa		%g0, [%o4] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%o4, 8, %o4
+	brgez,pt	%o4, 1b
+	 nop
+	retl
+	 nop
 
 __spitfire_flush_tlb_mm_slow:
 	rdpr		%pstate, %g1
@@ -288,6 +322,40 @@ __cheetah_flush_tlb_pending:	/* 27 insns
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_kernel_range:	/* 31 insns */
+	/* %o0=start, %o1=end */
+	cmp		%o0, %o1
+	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, 3f
+	 sethi		%hi(PAGE_SIZE), %o4
+	sub		%o3, %o4, %o3
+	or		%o0, 0x20, %o0		! Nucleus
+1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
+	stxa		%g0, [%o0 + %o3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%o3, 1b
+	 sub		%o3, %o4, %o3
+2:	sethi		%hi(KERNBASE), %o3
+	flush		%o3
+	retl
+	 nop
+3:	mov		0x80, %o4
+	stxa		%g0, [%o4] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%o4] ASI_IMMU_DEMAP
+	membar		#Sync
+	retl
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 __cheetah_flush_dcache_page: /* 11 insns */
 	sethi		%hi(PAGE_OFFSET), %g1
@@ -388,13 +456,15 @@ __hypervisor_flush_tlb_pending: /* 27 in
 	nop
 	nop
 
-__hypervisor_flush_tlb_kernel_range: /* 19 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
-	 sethi		%hi(PAGE_SIZE), %g3
-	mov		%o0, %g1
-	sub		%o1, %g1, %g2
+	 sub		%o1, %o0, %g2
+	srlx		%g2, 18, %g3
+	brnz,pn		%g3, 4f
+	 mov		%o0, %g1
+	sethi		%hi(PAGE_SIZE), %g3
 	sub		%g2, %g3, %g2
 1:	add		%g1, %g2, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
@@ -409,6 +479,16 @@ __hypervisor_flush_tlb_kernel_range: /*
 3:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
 	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
 	 nop
+4:	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	brnz,pn		%o0, 3b
+	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
+	retl
+	 nop
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -431,43 +511,6 @@ tlb_patch_one:
 	retl
 	 nop
 
-	.globl		cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
-	save		%sp, -128, %sp
-
-	sethi		%hi(__flush_tlb_mm), %o0
-	or		%o0, %lo(__flush_tlb_mm), %o0
-	sethi		%hi(__cheetah_flush_tlb_mm), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
-	call		tlb_patch_one
-	 mov		19, %o2
-
-	sethi		%hi(__flush_tlb_page), %o0
-	or		%o0, %lo(__flush_tlb_page), %o0
-	sethi		%hi(__cheetah_flush_tlb_page), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
-	call		tlb_patch_one
-	 mov		22, %o2
-
-	sethi		%hi(__flush_tlb_pending), %o0
-	or		%o0, %lo(__flush_tlb_pending), %o0
-	sethi		%hi(__cheetah_flush_tlb_pending), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
-	call		tlb_patch_one
-	 mov		27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
-	sethi		%hi(__flush_dcache_page), %o0
-	or		%o0, %lo(__flush_dcache_page), %o0
-	sethi		%hi(__cheetah_flush_dcache_page), %o1
-	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
-	call		tlb_patch_one
-	 mov		11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
-	ret
-	 restore
-
 #ifdef CONFIG_SMP
 	/* These are all called by the slaves of a cross call, at
 	 * trap level 1, with interrupts fully disabled.
@@ -535,13 +578,15 @@ xcall_flush_tlb_page:	/* 20 insns */
 	nop
 
 	.globl		xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range:	/* 28 insns */
+xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
-	add		%g2, 1, %g2
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -550,11 +595,25 @@ xcall_flush_tlb_kernel_range:	/* 28 insn
 	brnz,pt		%g3, 1b
 	 sub		%g3, %g2, %g3
 	retry
-	nop
-	nop
-	nop
-	nop
-	nop
+2:	mov		63 * 8, %g1
+1:	ldxa		[%g1] ASI_ITLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_IMMU
+	stxa		%g0, [%g1] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%g1] ASI_DTLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_DMMU
+	stxa		%g0, [%g1] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%g1, 8, %g1
+	brgez,pt	%g1, 1b
+	 nop
+	retry
 	nop
 	nop
 	nop
@@ -683,6 +742,52 @@ xcall_fetch_glob_pmu_n4:
 
 	retry
 
+__cheetah_xcall_flush_tlb_kernel_range:	/* 44 insns */
+	sethi		%hi(PAGE_SIZE - 1), %g2
+	or		%g2, %lo(PAGE_SIZE - 1), %g2
+	andn		%g1, %g2, %g1
+	andn		%g7, %g2, %g7
+	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
+	sub		%g3, %g2, %g3
+	or		%g1, 0x20, %g1		! Nucleus
+1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
+	stxa		%g0, [%g1 + %g3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%g3, 1b
+	 sub		%g3, %g2, %g3
+	retry
+2:	mov		0x80, %g2
+	stxa		%g0, [%g2] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%g2] ASI_IMMU_DEMAP
+	membar		#Sync
+	retry
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 	.align		32
 	.globl		xcall_flush_dcache_page_cheetah
@@ -798,18 +903,20 @@ __hypervisor_xcall_flush_tlb_page: /* 20
 	 nop
 
 	.globl		__hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 28 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
 	/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g7
 	add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	mov		%o0, %g2
 	mov		%o1, %g4
-	mov		%o2, %g7
+	brnz,pn		%g7, 2f
+	 mov		%o2, %g7
 1:	add		%g1, %g3, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
@@ -820,7 +927,7 @@ __hypervisor_xcall_flush_tlb_kernel_rang
 	sethi		%hi(PAGE_SIZE), %o2
 	brnz,pt		%g3, 1b
 	 sub		%g3, %o2, %g3
-	mov		%g2, %o0
+5:	mov		%g2, %o0
 	mov		%g4, %o1
 	mov		%g7, %o2
 	membar		#Sync
@@ -828,6 +935,20 @@ __hypervisor_xcall_flush_tlb_kernel_rang
 1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
 	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
 	 nop
+2:	mov		%o3, %g1
+	mov		%o5, %g3
+	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	mov		%g1, %o3
+	brz,pt		%o0, 5b
+	 mov		%g3, %o5
+	mov		HV_FAST_MMU_DEMAP_CTX, %g6
+	ba,pt		%xcc, 1b
+	 clr		%g5
 
 	/* These just get rescheduled to PIL vectors. */
 	.globl		xcall_call_function
@@ -864,6 +985,58 @@ xcall_kgdb_capture:
 
 #endif /* CONFIG_SMP */
 
+	.globl		cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+	save		%sp, -128, %sp
+
+	sethi		%hi(__flush_tlb_mm), %o0
+	or		%o0, %lo(__flush_tlb_mm), %o0
+	sethi		%hi(__cheetah_flush_tlb_mm), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
+	call		tlb_patch_one
+	 mov		19, %o2
+
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
+	sethi		%hi(__flush_tlb_pending), %o0
+	or		%o0, %lo(__flush_tlb_pending), %o0
+	sethi		%hi(__cheetah_flush_tlb_pending), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
+	call		tlb_patch_one
+	 mov		27, %o2
+
+	sethi		%hi(__flush_tlb_kernel_range), %o0
+	or		%o0, %lo(__flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+	sethi		%hi(__flush_dcache_page), %o0
+	or		%o0, %lo(__flush_dcache_page), %o0
+	sethi		%hi(__cheetah_flush_dcache_page), %o1
+	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
+	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		44, %o2
+#endif /* CONFIG_SMP */
+
+	ret
+	 restore
 
 	.globl		hypervisor_patch_cachetlbops
 hypervisor_patch_cachetlbops:
@@ -895,7 +1068,7 @@ hypervisor_patch_cachetlbops:
 	sethi		%hi(__hypervisor_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		19, %o2
+	 mov		31, %o2
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	sethi		%hi(__flush_dcache_page), %o0
@@ -926,7 +1099,7 @@ hypervisor_patch_cachetlbops:
 	sethi		%hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		28, %o2
+	 mov		44, %o2
 #endif /* CONFIG_SMP */
 
 	ret

[toc] | [prev] | [next] | [standalone]


#1525933 — [PATCH 4.8 43/49] sparc64: Convert NGcopy_{from,to}_user to accurate exception reporting.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 43/49] sparc64: Convert NGcopy_{from,to}_user to accurate exception reporting.
Message-ID<sFa8c-33e-113@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit 7ae3aaf53f1695877ccd5ebbc49ea65991e41f1e ]

Report the exact number of bytes which have not been successfully
copied when an exception occurs, using the running remaining length.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/lib/NGcopy_from_user.S |    4 
 arch/sparc/lib/NGcopy_to_user.S   |    4 
 arch/sparc/lib/NGmemcpy.S         |  233 +++++++++++++++++++++++++-------------
 3 files changed, 162 insertions(+), 79 deletions(-)

--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_mone_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_mone_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/asi.h>
 #include <asm/thread_info.h>
 #define GLOBAL_SPARE	%g7
@@ -27,15 +28,11 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -79,6 +76,92 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi:
+	ret
+	wr	%g0, ASI_AIUS, %asi
+	 restore
+ENTRY(NG_ret_i2_plus_i4_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i5, %i0
+ENDPROC(NG_ret_i2_plus_i4_plus_1)
+ENTRY(NG_ret_i2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1)
+ENTRY(NG_ret_i2_plus_g1_minus_8)
+	sub	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_8)
+ENTRY(NG_ret_i2_plus_g1_minus_16)
+	sub	%g1, 16, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_16)
+ENTRY(NG_ret_i2_plus_g1_minus_24)
+	sub	%g1, 24, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_24)
+ENTRY(NG_ret_i2_plus_g1_minus_32)
+	sub	%g1, 32, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_32)
+ENTRY(NG_ret_i2_plus_g1_minus_40)
+	sub	%g1, 40, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_40)
+ENTRY(NG_ret_i2_plus_g1_minus_48)
+	sub	%g1, 48, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_48)
+ENTRY(NG_ret_i2_plus_g1_minus_56)
+	sub	%g1, 56, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_56)
+ENTRY(NG_ret_i2_plus_i4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_minus_8)
+	sub	%i4, 8, %i4
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENTRY(NG_ret_i2_plus_8)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 8, %i0
+ENDPROC(NG_ret_i2_plus_8)
+ENTRY(NG_ret_i2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 4, %i0
+ENDPROC(NG_ret_i2_plus_4)
+ENTRY(NG_ret_i2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 1, %i0
+ENDPROC(NG_ret_i2_plus_1)
+ENTRY(NG_ret_i2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_plus_1)
+ENTRY(NG_ret_i2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%i2, %i0
+ENDPROC(NG_ret_i2)
+ENTRY(NG_ret_i2_and_7_plus_i4)
+	and	%i2, 7, %i2
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -126,8 +209,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	sub		%g0, %i4, %i4	! bytes to align dst
 	sub		%i2, %i4, %i2
 1:	subcc		%i4, 1, %i4
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
+	EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
 	add		%i1, 1, %i1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -160,7 +243,7 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	and		%i4, 0x7, GLOBAL_SPARE
 	sll		GLOBAL_SPARE, 3, GLOBAL_SPARE
 	mov		64, %i5
-	EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
 	sub		%i5, GLOBAL_SPARE, %i5
 	mov		16, %o4
 	mov		32, %o5
@@ -178,31 +261,31 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	srlx		WORD3, PRE_SHIFT, TMP; \
 	or		WORD2, TMP, WORD2;
 
-8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x00))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x20))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 8b
@@ -211,31 +294,31 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	ba,pt		%XCC, 60f
 	 add		%i1, %i4, %i1
 
-9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x00))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 9b
@@ -249,25 +332,25 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	 * one twin load ahead, then add 8 back into source when
 	 * we finish the loop.
 	 */
-	EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+	EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
 	mov	16, %o7
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o5, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
-	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+	EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 1b
 	 add		%o0, 64, %o0
@@ -282,20 +365,20 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o4, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o5, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	add	%i1, 64, %i1
-	EX_ST(STORE_INIT(%o4, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x28))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc	%g1, 64, %g1
 	bne,pt	%XCC, 1b
 	 add	%o0, 64, %o0
@@ -321,28 +404,28 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	andn		%i2, 0xf, %i4
 	and		%i2, 0xf, %i2
 1:	subcc		%i4, 0x10, %i4
-	EX_LD(LOAD(ldx, %i1, %o4))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
 	add		%i1, 0x08, %i1
-	EX_LD(LOAD(ldx, %i1, %g1))
+	EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
 	sub		%i1, 0x08, %i1
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
 	add		%i1, 0x8, %i1
-	EX_ST(STORE(stx, %g1, %i1 + %i3))
+	EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 0x8, %i1
 73:	andcc		%i2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x8, %i2
-	EX_LD(LOAD(ldx, %i1, %o4))
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
 	add		%i1, 0x8, %i1
 1:	andcc		%i2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x4, %i2
-	EX_LD(LOAD(lduw, %i1, %i5))
-	EX_ST(STORE(stw, %i5, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
 	add		%i1, 0x4, %i1
 1:	cmp		%i2, 0
 	be,pt		%XCC, 85f
@@ -358,8 +441,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	sub		%i2, %g1, %i2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %i1, %i5))
-	EX_ST(STORE(stb, %i5, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%i1, 1, %i1
 
@@ -375,16 +458,16 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 
 8:	mov		64, %i3
 	andn		%i1, 0x7, %i1
-	EX_LD(LOAD(ldx, %i1, %g2))
+	EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
 	sub		%i3, %g1, %i3
 	andn		%i2, 0x7, %i4
 	sllx		%g2, %g1, %g2
 1:	add		%i1, 0x8, %i1
-	EX_LD(LOAD(ldx, %i1, %g3))
+	EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
 	subcc		%i4, 0x8, %i4
 	srlx		%g3, %i3, %i5
 	or		%i5, %g2, %i5
-	EX_ST(STORE(stx, %i5, %o0))
+	EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -404,8 +487,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 
 1:
 	subcc		%i2, 4, %i2
-	EX_LD(LOAD(lduw, %i1, %g1))
-	EX_ST(STORE(stw, %g1, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 4, %i1
 
@@ -415,8 +498,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len
 	.align		32
 90:
 	subcc		%i2, 1, %i2
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
+	EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%i1, 1, %i1
 	ret

[toc] | [prev] | [next] | [standalone]


#1525934 — [PATCH 4.8 24/49] mlxsw: spectrum: Fix refcount bug on span entries

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 24/49] mlxsw: spectrum: Fix refcount bug on span entries
Message-ID<sFa8c-33e-117@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Yotam Gigi <yotamg@mellanox.com>


[ Upstream commit 2d644d4c7506646f9c4a2afceb7fd5f030bc0c9f ]

When binding port to a newly created span entry, its refcount is
initialized to zero even though it has a bound port. That leads
to unexpected behaviour when the user tries to delete that port
from the span entry.

Fix this by initializing the reference count to 1.

Also add a warning to put function.

Fixes: 763b4b70afcd ("mlxsw: spectrum: Add support in matchall mirror TC offloading")
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -231,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_
 
 	span_entry->used = true;
 	span_entry->id = index;
-	span_entry->ref_count = 0;
+	span_entry->ref_count = 1;
 	span_entry->local_port = local_port;
 	return span_entry;
 }
@@ -268,6 +268,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_spa
 
 	span_entry = mlxsw_sp_span_entry_find(port);
 	if (span_entry) {
+		/* Already exists, just take a reference */
 		span_entry->ref_count++;
 		return span_entry;
 	}
@@ -278,6 +279,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_spa
 static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_span_entry *span_entry)
 {
+	WARN_ON(!span_entry->ref_count);
 	if (--span_entry->ref_count == 0)
 		mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry);
 	return 0;

[toc] | [prev] | [next] | [standalone]


#1525935 — [PATCH 4.8 33/49] sparc64: Fix illegal relative branches in hypervisor patched TLB code.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:30 +0100
Subject[PATCH 4.8 33/49] sparc64: Fix illegal relative branches in hypervisor patched TLB code.
Message-ID<sFa8c-33e-119@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit b429ae4d5b565a71dfffd759dfcd4f6c093ced94 ]

When we copy code over to patch another piece of code, we can only use
PC-relative branches that target code within that piece of code.

Such PC-relative branches cannot be made to external symbols because
the patch moves the location of the code and thus modifies the
relative address of external symbols.

Use an absolute jmpl to fix this problem.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/mm/ultra.S |   65 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 51 insertions(+), 14 deletions(-)

--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
 	.text
 	.align		32
 	.globl		__flush_tlb_mm
-__flush_tlb_mm:		/* 18 insns */
+__flush_tlb_mm:		/* 19 insns */
 	/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
 	ldxa		[%o1] ASI_DMMU, %g2
 	cmp		%g2, %o0
@@ -81,7 +81,7 @@ __flush_tlb_page:	/* 22 insns */
 
 	.align		32
 	.globl		__flush_tlb_pending
-__flush_tlb_pending:	/* 26 insns */
+__flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
 	sllx		%o1, 3, %o1
@@ -113,7 +113,7 @@ __flush_tlb_pending:	/* 26 insns */
 
 	.align		32
 	.globl		__flush_tlb_kernel_range
-__flush_tlb_kernel_range:	/* 16 insns */
+__flush_tlb_kernel_range:	/* 19 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
@@ -131,6 +131,9 @@ __flush_tlb_kernel_range:	/* 16 insns */
 	retl
 	 nop
 	nop
+	nop
+	nop
+	nop
 
 __spitfire_flush_tlb_mm_slow:
 	rdpr		%pstate, %g1
@@ -309,19 +312,28 @@ __hypervisor_tlb_tl0_error:
 	ret
 	 restore
 
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
 	mov		%o0, %o2	/* ARG2: mmu context */
 	mov		0, %o0		/* ARG0: CPU lists unimplemented */
 	mov		0, %o1		/* ARG1: CPU lists unimplemented */
 	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
 	mov		HV_FAST_MMU_DEMAP_CTX, %o5
 	ta		HV_FAST_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o5
+	jmpl		%o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
 	/* %o0 = context, %o1 = vaddr */
 	mov		%o0, %g2
 	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
@@ -330,10 +342,21 @@ __hypervisor_flush_tlb_page: /* 11 insns
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
 __hypervisor_flush_tlb_pending: /* 16 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
@@ -347,14 +370,25 @@ __hypervisor_flush_tlb_pending: /* 16 in
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g1, 1b
 	 nop
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 19 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
@@ -366,12 +400,15 @@ __hypervisor_flush_tlb_kernel_range: /*
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 3f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g2, 1b
 	 sub		%g2, %g3, %g2
 2:	retl
 	 nop
+3:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -819,28 +856,28 @@ hypervisor_patch_cachetlbops:
 	sethi		%hi(__hypervisor_flush_tlb_mm), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_mm), %o1
 	call		tlb_patch_one
-	 mov		10, %o2
+	 mov		19, %o2
 
 	sethi		%hi(__flush_tlb_page), %o0
 	or		%o0, %lo(__flush_tlb_page), %o0
 	sethi		%hi(__hypervisor_flush_tlb_page), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		11, %o2
+	 mov		22, %o2
 
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_pending), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		27, %o2
 
 	sethi		%hi(__flush_tlb_kernel_range), %o0
 	or		%o0, %lo(__flush_tlb_kernel_range), %o0
 	sethi		%hi(__hypervisor_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		19, %o2
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	sethi		%hi(__flush_dcache_page), %o0

[toc] | [prev] | [next] | [standalone]


#1525937 — [PATCH 4.8 37/49] sparc64: Delete __ret_efault.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 37/49] sparc64: Delete __ret_efault.
Message-ID<sFahP-36w-11@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit aa95ce361ed95c72ac42dcb315166bce5cf1a014 ]

It is completely unused.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/include/asm/uaccess_64.h |    1 -
 arch/sparc/kernel/head_64.S         |    7 +------
 arch/sparc/kernel/sparc_ksyms_64.c  |    1 -
 3 files changed, 1 insertion(+), 8 deletions(-)

--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -98,7 +98,6 @@ struct exception_table_entry {
         unsigned int insn, fixup;
 };
 
-void __ret_efault(void);
 void __retl_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -922,12 +922,7 @@ prom_tba:	.xword	0
 tlb_type:	.word	0	/* Must NOT end up in BSS */
 	.section	".fixup",#alloc,#execinstr
 
-	.globl	__ret_efault, __retl_efault, __ret_one, __retl_one
-ENTRY(__ret_efault)
-	ret
-	 restore %g0, -EFAULT, %o0
-ENDPROC(__ret_efault)
-
+	.globl	__retl_efault, __ret_one, __retl_one
 ENTRY(__retl_efault)
 	retl
 	 mov	-EFAULT, %o0
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -27,7 +27,6 @@ EXPORT_SYMBOL(__flushw_user);
 EXPORT_SYMBOL_GPL(real_hard_smp_processor_id);
 
 /* from head_64.S */
-EXPORT_SYMBOL(__ret_efault);
 EXPORT_SYMBOL(tlb_type);
 EXPORT_SYMBOL(sun4v_chip_type);
 EXPORT_SYMBOL(prom_root_node);

[toc] | [prev] | [next] | [standalone]


#1525938 — [PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set
Message-ID<sFahP-36w-9@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Andy Gospodarek <gospo@broadcom.com>


[ Upstream commit fcdefccac976ee51dd6071832b842d8fb41c479c ]

Current bgmac code initializes some DMA settings in the receive control
register for some hardware and then immediately clears those settings.
Not clearing those settings results in ~420Mbps *improvement* in
throughput; this system can now receive frames at line-rate on Broadcom
5871x hardware compared to ~520Mbps today.  I also tested a few other
values but found there to be no discernible difference in CPU
utilization even if burst size and prefetching values are different.

On the hardware tested there was no need to keep the code that cleared
all but bits 16-17, but since there is a wide variety of hardware that
used this driver (I did not look at all hardware docs for hardware using
this IP block), I find it wise to move this call up and clear bits just
after reading the default value from the hardware rather than completely
removing it.

This is a good candidate for -stable >=3.14 since that is when the code
that was supposed to improve performance (but did not) was introduced.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Fixes: 56ceecde1f29 ("bgmac: initialize the DMA controller of core...")
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/broadcom/bgmac.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct b
 	u32 ctl;
 
 	ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+	/* preserve ONLY bits 16-17 from current hardware value */
+	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
 	if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) {
 		ctl &= ~BGMAC_DMA_RX_BL_MASK;
 		ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct b
 		ctl &= ~BGMAC_DMA_RX_PT_MASK;
 		ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
 	}
-	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
 	ctl |= BGMAC_DMA_RX_ENABLE;
 	ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
 	ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;

[toc] | [prev] | [next] | [standalone]


#1525940 — [PATCH 4.8 11/49] dccp: fix out of bound access in dccp_v4_err()

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 11/49] dccp: fix out of bound access in dccp_v4_err()
Message-ID<sFahQ-36w-27@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Eric Dumazet <edumazet@google.com>


[ Upstream commit 6706a97fec963d6cb3f7fc2978ec1427b4651214 ]

dccp_v4_err() does not use pskb_may_pull() and might access garbage.

We only need 4 bytes at the beginning of the DCCP header, like TCP,
so the 8 bytes pulled in icmp_socket_deliver() are more than enough.

This patch might allow to process more ICMP messages, as some routers
are still limiting the size of reflected bytes to 28 (RFC 792), instead
of extended lengths (RFC 1812 4.3.2.3)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/ipv4.c |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const u8 offset = iph->ihl << 2;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
 				       iph->daddr, dh->dccph_dport,

[toc] | [prev] | [next] | [standalone]


#1525941 — [PATCH 4.8 32/49] sparc64: Handle extremely large kernel TSB range flushes sanely.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 32/49] sparc64: Handle extremely large kernel TSB range flushes sanely.
Message-ID<sFahQ-36w-29@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit 849c498766060a16aad5b0e0d03206726e7d2fa4 ]

If the number of pages we are flushing is more than twice the number
of entries in the TSB, just scan the TSB table for matches rather
than probing each and every page in the range.

Based upon a patch and report by James Clarke.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/mm/tsb.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned l
 	return (tag == (vaddr >> 22));
 }
 
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+	unsigned long idx;
+
+	for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+		struct tsb *ent = &swapper_tsb[idx];
+		unsigned long match = idx << 13;
+
+		match |= (ent->tag << 22);
+		if (match >= start && match < end)
+			ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+	}
+}
+
 /* TSB flushes need only occur on the processor initiating the address
  * space modification, not on each cpu the address space has run on.
  * Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned lon
 {
 	unsigned long v;
 
+	if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+		return flush_tsb_kernel_range_scan(start, end);
+
 	for (v = start; v < end; v += PAGE_SIZE) {
 		unsigned long hash = tsb_hash(v, PAGE_SHIFT,
 					      KERNEL_TSB_NENTRIES);

[toc] | [prev] | [next] | [standalone]


#1525943 — [PATCH 4.8 02/49] net: clear sk_err_soft in sk_clone_lock()

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 02/49] net: clear sk_err_soft in sk_clone_lock()
Message-ID<sFahP-36w-21@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Eric Dumazet <edumazet@google.com>


[ Upstream commit e551c32d57c88923f99f8f010e89ca7ed0735e83 ]

At accept() time, it is possible the parent has a non zero
sk_err_soft, leftover from a prior error.

Make sure we do not leave this value in the child, as it
makes future getsockopt(SO_ERROR) calls quite unreliable.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/core/sock.c |    1 +
 1 file changed, 1 insertion(+)

--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1563,6 +1563,7 @@ struct sock *sk_clone_lock(const struct
 		RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
 
 		newsk->sk_err	   = 0;
+		newsk->sk_err_soft = 0;
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);

[toc] | [prev] | [next] | [standalone]


#1525944 — [PATCH 4.8 28/49] sctp: change sk state only when it has assocs in sctp_shutdown

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 28/49] sctp: change sk state only when it has assocs in sctp_shutdown
Message-ID<sFahQ-36w-35@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Xin Long <lucien.xin@gmail.com>


[ Upstream commit 5bf35ddfee052d44f39ebaa395d87101c8918405 ]

Now when users shutdown a sock with SEND_SHUTDOWN in sctp, even if
this sock has no connection (assoc), sk state would be changed to
SCTP_SS_CLOSING, which is not as we expect.

Besides, after that if users try to listen on this sock, kernel
could even panic when it dereference sctp_sk(sk)->bind_hash in
sctp_inet_listen, as bind_hash is null when sock has no assoc.

This patch is to move sk state change after checking sk assocs
is not empty, and also merge these two if() conditions and reduce
indent level.

Fixes: d46e416c11c8 ("sctp: sctp should change socket state when shutdown is received")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sctp/socket.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4281,19 +4281,18 @@ static void sctp_shutdown(struct sock *s
 {
 	struct net *net = sock_net(sk);
 	struct sctp_endpoint *ep;
-	struct sctp_association *asoc;
 
 	if (!sctp_style(sk, TCP))
 		return;
 
-	if (how & SEND_SHUTDOWN) {
+	ep = sctp_sk(sk)->ep;
+	if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
+		struct sctp_association *asoc;
+
 		sk->sk_state = SCTP_SS_CLOSING;
-		ep = sctp_sk(sk)->ep;
-		if (!list_empty(&ep->asocs)) {
-			asoc = list_entry(ep->asocs.next,
-					  struct sctp_association, asocs);
-			sctp_primitive_SHUTDOWN(net, asoc, NULL);
-		}
+		asoc = list_entry(ep->asocs.next,
+				  struct sctp_association, asocs);
+		sctp_primitive_SHUTDOWN(net, asoc, NULL);
 	}
 }
 

[toc] | [prev] | [next] | [standalone]


#1525945 — [PATCH 4.8 10/49] dccp: do not send reset to already closed sockets

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 10/49] dccp: do not send reset to already closed sockets
Message-ID<sFahQ-36w-39@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Eric Dumazet <edumazet@google.com>


[ Upstream commit 346da62cc186c4b4b1ac59f87f4482b47a047388 ]

Andrey reported following warning while fuzzing with syzkaller

WARNING: CPU: 1 PID: 21072 at net/dccp/proto.c:83 dccp_set_state+0x229/0x290
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 21072 Comm: syz-executor Not tainted 4.9.0-rc1+ #293
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 ffff88003d4c7738 ffffffff81b474f4 0000000000000003 dffffc0000000000
 ffffffff844f8b00 ffff88003d4c7804 ffff88003d4c7800 ffffffff8140c06a
 0000000041b58ab3 ffffffff8479ab7d ffffffff8140beae ffffffff8140cd00
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff81b474f4>] dump_stack+0xb3/0x10f lib/dump_stack.c:51
 [<ffffffff8140c06a>] panic+0x1bc/0x39d kernel/panic.c:179
 [<ffffffff8111125c>] __warn+0x1cc/0x1f0 kernel/panic.c:542
 [<ffffffff8111144c>] warn_slowpath_null+0x2c/0x40 kernel/panic.c:585
 [<ffffffff8389e5d9>] dccp_set_state+0x229/0x290 net/dccp/proto.c:83
 [<ffffffff838a0aa2>] dccp_close+0x612/0xc10 net/dccp/proto.c:1016
 [<ffffffff8316bf1f>] inet_release+0xef/0x1c0 net/ipv4/af_inet.c:415
 [<ffffffff82b6e89e>] sock_release+0x8e/0x1d0 net/socket.c:570
 [<ffffffff82b6e9f6>] sock_close+0x16/0x20 net/socket.c:1017
 [<ffffffff815256ad>] __fput+0x29d/0x720 fs/file_table.c:208
 [<ffffffff81525bb5>] ____fput+0x15/0x20 fs/file_table.c:244
 [<ffffffff811727d8>] task_work_run+0xf8/0x170 kernel/task_work.c:116
 [<     inline     >] exit_task_work include/linux/task_work.h:21
 [<ffffffff8111bc53>] do_exit+0x883/0x2ac0 kernel/exit.c:828
 [<ffffffff811221fe>] do_group_exit+0x10e/0x340 kernel/exit.c:931
 [<ffffffff81143c94>] get_signal+0x634/0x15a0 kernel/signal.c:2307
 [<ffffffff81054aad>] do_signal+0x8d/0x1a30 arch/x86/kernel/signal.c:807
 [<ffffffff81003a05>] exit_to_usermode_loop+0xe5/0x130
arch/x86/entry/common.c:156
 [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [<ffffffff81006298>] syscall_return_slowpath+0x1a8/0x1e0
arch/x86/entry/common.c:259
 [<ffffffff83fc1a62>] entry_SYSCALL_64_fastpath+0xc0/0xc2
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled

Fix this the same way we did for TCP in commit 565b7b2d2e63
("tcp: do not send reset to already closed sockets")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/proto.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long ti
 		__kfree_skb(skb);
 	}
 
+	/* If socket has been already reset kill it. */
+	if (sk->sk_state == DCCP_CLOSED)
+		goto adjudge_to_death;
+
 	if (data_was_unread) {
 		/* Unread data was tossed, send an appropriate Reset Code */
 		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);

[toc] | [prev] | [next] | [standalone]


#1525946 — [PATCH 4.8 38/49] sparc64: Prepare to move to more saner user copy exception handling.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 38/49] sparc64: Prepare to move to more saner user copy exception handling.
Message-ID<sFahQ-36w-31@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit 83a17d2661674d8c198adc0e183418f72aabab79 ]

The fixup helper function mechanism for handling user copy fault
handling is not %100 accurrate, and can never be made so.

We are going to transition the code to return the running return
return length, which is always kept track in one or more registers
of each of these routines.

In order to convert them one by one, we have to allow the existing
behavior to continue functioning.

Therefore make all the copy code that wants the fixup helper to be
used return negative one.

After all of the user copy routines have been converted, this logic
and the fixup helpers themselves can be removed completely.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/include/asm/uaccess_64.h |   21 +++++++++++++++------
 arch/sparc/kernel/head_64.S         |   23 +++++++++++------------
 arch/sparc/lib/GENcopy_from_user.S  |    2 +-
 arch/sparc/lib/GENcopy_to_user.S    |    2 +-
 arch/sparc/lib/NG2copy_from_user.S  |    4 ++--
 arch/sparc/lib/NG2copy_to_user.S    |    4 ++--
 arch/sparc/lib/NG4copy_from_user.S  |    4 ++--
 arch/sparc/lib/NG4copy_to_user.S    |    4 ++--
 arch/sparc/lib/NGcopy_from_user.S   |    2 +-
 arch/sparc/lib/NGcopy_to_user.S     |    2 +-
 arch/sparc/lib/U1copy_from_user.S   |    4 ++--
 arch/sparc/lib/U1copy_to_user.S     |    4 ++--
 arch/sparc/lib/U3copy_from_user.S   |    4 ++--
 arch/sparc/lib/U3copy_to_user.S     |    4 ++--
 arch/sparc/lib/copy_in_user.S       |    2 +-
 15 files changed, 47 insertions(+), 39 deletions(-)

--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -214,8 +214,11 @@ copy_from_user(void *to, const void __us
 	check_object_size(to, size, false);
 
 	ret = ___copy_from_user(to, from, size);
-	if (unlikely(ret))
-		ret = copy_from_user_fixup(to, from, size);
+	if (unlikely(ret)) {
+		if ((long)ret < 0)
+			ret = copy_from_user_fixup(to, from, size);
+		return ret;
+	}
 
 	return ret;
 }
@@ -234,8 +237,11 @@ copy_to_user(void __user *to, const void
 	check_object_size(from, size, true);
 
 	ret = ___copy_to_user(to, from, size);
-	if (unlikely(ret))
-		ret = copy_to_user_fixup(to, from, size);
+	if (unlikely(ret)) {
+		if ((long)ret < 0)
+			ret = copy_to_user_fixup(to, from, size);
+		return ret;
+	}
 	return ret;
 }
 #define __copy_to_user copy_to_user
@@ -250,8 +256,11 @@ copy_in_user(void __user *to, void __use
 {
 	unsigned long ret = ___copy_in_user(to, from, size);
 
-	if (unlikely(ret))
-		ret = copy_in_user_fixup(to, from, size);
+	if (unlikely(ret)) {
+		if ((long)ret < 0)
+			ret = copy_in_user_fixup(to, from, size);
+		return ret;
+	}
 	return ret;
 }
 #define __copy_in_user copy_in_user
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -922,41 +922,40 @@ prom_tba:	.xword	0
 tlb_type:	.word	0	/* Must NOT end up in BSS */
 	.section	".fixup",#alloc,#execinstr
 
-	.globl	__retl_efault, __ret_one, __retl_one
 ENTRY(__retl_efault)
 	retl
 	 mov	-EFAULT, %o0
 ENDPROC(__retl_efault)
 
-ENTRY(__retl_one)
+ENTRY(__retl_mone)
 	retl
-	 mov	1, %o0
-ENDPROC(__retl_one)
+	 mov	-1, %o0
+ENDPROC(__retl_mone)
 
-ENTRY(__retl_one_fp)
+ENTRY(__retl_mone_fp)
 	VISExitHalf
 	retl
 	 mov	1, %o0
-ENDPROC(__retl_one_fp)
+ENDPROC(__retl_mone_fp)
 
-ENTRY(__ret_one_asi)
+ENTRY(__ret_mone_asi)
 	wr	%g0, ASI_AIUS, %asi
 	ret
 	 restore %g0, 1, %o0
-ENDPROC(__ret_one_asi)
+ENDPROC(__ret_mone_asi)
 
-ENTRY(__retl_one_asi)
+ENTRY(__retl_mone_asi)
 	wr	%g0, ASI_AIUS, %asi
 	retl
 	 mov	1, %o0
-ENDPROC(__retl_one_asi)
+ENDPROC(__retl_mone_asi)
 
-ENTRY(__retl_one_asi_fp)
+ENTRY(__retl_mone_asi_fp)
 	wr	%g0, ASI_AIUS, %asi
 	VISExitHalf
 	retl
 	 mov	1, %o0
-ENDPROC(__retl_one_asi_fp)
+ENDPROC(__retl_mone_asi_fp)
 
 ENTRY(__retl_o1)
 	retl
--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, __retl_mone_asi;\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, __retl_mone_asi_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, __retl_mone_asi;\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, __retl_mone_asi_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, __retl_mone_asi;\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, __retl_mone_asi_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, __retl_mone_asi;\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, __retl_mone_asi_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, __ret_mone_asi;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, __ret_mone_asi;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, __retl_mone_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, __retl_mone_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, __retl_mone_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -7,7 +7,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 
@@ -15,7 +15,7 @@
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, __retl_mone_fp;\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
@@ -12,7 +12,7 @@
 98:	x,y;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, __retl_mone;	\
 	.text;			\
 	.align 4;
 

[toc] | [prev] | [next] | [standalone]


#1525949 — [PATCH 4.8 09/49] dccp: do not release listeners too soon

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 09/49] dccp: do not release listeners too soon
Message-ID<sFahQ-36w-47@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Eric Dumazet <edumazet@google.com>


[ Upstream commit c3f24cfb3e508c70c26ee8569d537c8ca67a36c6 ]

Andrey Konovalov reported following error while fuzzing with syzkaller :

IPv4: Attempt to release alive inet socket ffff880068e98940
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 3905 Comm: a.out Not tainted 4.9.0-rc3+ #333
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff88006b9e0000 task.stack: ffff880068770000
RIP: 0010:[<ffffffff819ead5f>]  [<ffffffff819ead5f>]
selinux_socket_sock_rcv_skb+0xff/0x6a0 security/selinux/hooks.c:4639
RSP: 0018:ffff8800687771c8  EFLAGS: 00010202
RAX: ffff88006b9e0000 RBX: 1ffff1000d0eee3f RCX: 1ffff1000d1d312a
RDX: 1ffff1000d1d31a6 RSI: dffffc0000000000 RDI: 0000000000000010
RBP: ffff880068777360 R08: 0000000000000000 R09: 0000000000000002
R10: dffffc0000000000 R11: 0000000000000006 R12: ffff880068e98940
R13: 0000000000000002 R14: ffff880068777338 R15: 0000000000000000
FS:  00007f00ff760700(0000) GS:ffff88006cd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020008000 CR3: 000000006a308000 CR4: 00000000000006e0
Stack:
 ffff8800687771e0 ffffffff812508a5 ffff8800686f3168 0000000000000007
 ffff88006ac8cdfc ffff8800665ea500 0000000041b58ab3 ffffffff847b5480
 ffffffff819eac60 ffff88006b9e0860 ffff88006b9e0868 ffff88006b9e07f0
Call Trace:
 [<ffffffff819c8dd5>] security_sock_rcv_skb+0x75/0xb0 security/security.c:1317
 [<ffffffff82c2a9e7>] sk_filter_trim_cap+0x67/0x10e0 net/core/filter.c:81
 [<ffffffff82b81e60>] __sk_receive_skb+0x30/0xa00 net/core/sock.c:460
 [<ffffffff838bbf12>] dccp_v4_rcv+0xdb2/0x1910 net/dccp/ipv4.c:873
 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0
net/ipv4/ip_input.c:216
 [<     inline     >] NF_HOOK_THRESH ./include/linux/netfilter.h:232
 [<     inline     >] NF_HOOK ./include/linux/netfilter.h:255
 [<ffffffff8306abd2>] ip_local_deliver+0x1c2/0x4b0 net/ipv4/ip_input.c:257
 [<     inline     >] dst_input ./include/net/dst.h:507
 [<ffffffff83068500>] ip_rcv_finish+0x750/0x1c40 net/ipv4/ip_input.c:396
 [<     inline     >] NF_HOOK_THRESH ./include/linux/netfilter.h:232
 [<     inline     >] NF_HOOK ./include/linux/netfilter.h:255
 [<ffffffff8306b82f>] ip_rcv+0x96f/0x12f0 net/ipv4/ip_input.c:487
 [<ffffffff82bd9fb7>] __netif_receive_skb_core+0x1897/0x2a50 net/core/dev.c:4213
 [<ffffffff82bdb19a>] __netif_receive_skb+0x2a/0x170 net/core/dev.c:4251
 [<ffffffff82bdb493>] netif_receive_skb_internal+0x1b3/0x390 net/core/dev.c:4279
 [<ffffffff82bdb6b8>] netif_receive_skb+0x48/0x250 net/core/dev.c:4303
 [<ffffffff8241fc75>] tun_get_user+0xbd5/0x28a0 drivers/net/tun.c:1308
 [<ffffffff82421b5a>] tun_chr_write_iter+0xda/0x190 drivers/net/tun.c:1332
 [<     inline     >] new_sync_write fs/read_write.c:499
 [<ffffffff8151bd44>] __vfs_write+0x334/0x570 fs/read_write.c:512
 [<ffffffff8151f85b>] vfs_write+0x17b/0x500 fs/read_write.c:560
 [<     inline     >] SYSC_write fs/read_write.c:607
 [<ffffffff81523184>] SyS_write+0xd4/0x1a0 fs/read_write.c:599
 [<ffffffff83fc02c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

It turns out DCCP calls __sk_receive_skb(), and this broke when
lookups no longer took a reference on listeners.

Fix this issue by adding a @refcounted parameter to __sk_receive_skb(),
so that sock_put() is used only when needed.

Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/net/sock.h |    4 ++--
 net/core/sock.c    |    5 +++--
 net/dccp/ipv4.c    |    2 +-
 net/dccp/ipv6.c    |    3 ++-
 4 files changed, 8 insertions(+), 6 deletions(-)

--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1587,11 +1587,11 @@ static inline void sock_put(struct sock
 void sock_gen_put(struct sock *sk);
 
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
-		     unsigned int trim_cap);
+		     unsigned int trim_cap, bool refcounted);
 static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 				 const int nested)
 {
-	return __sk_receive_skb(sk, skb, nested, 1);
+	return __sk_receive_skb(sk, skb, nested, 1, true);
 }
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk,
 EXPORT_SYMBOL(sock_queue_rcv_skb);
 
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
-		     const int nested, unsigned int trim_cap)
+		     const int nested, unsigned int trim_cap, bool refcounted)
 {
 	int rc = NET_RX_SUCCESS;
 
@@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, st
 
 	bh_unlock_sock(sk);
 out:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	return rc;
 discard_and_relse:
 	kfree_skb(skb);
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -868,7 +868,7 @@ lookup:
 		goto discard_and_relse;
 	nf_reset(skb);
 
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4);
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
 
 no_dccp_socket:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -738,7 +738,8 @@ lookup:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0;
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
+				refcounted) ? -1 : 0;
 
 no_dccp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))

[toc] | [prev] | [next] | [standalone]


#1525950 — [PATCH 4.8 40/49] sparc64: Convert GENcopy_{from,to}_user to accurate exception reporting.

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 40/49] sparc64: Convert GENcopy_{from,to}_user to accurate exception reporting.
Message-ID<sFahQ-36w-49@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: "David S. Miller" <davem@davemloft.net>


[ Upstream commit d0796b555ba60c22eb41ae39a8362156cb08eee9 ]

Report the exact number of bytes which have not been successfully
copied when an exception occurs, using the running remaining length.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/lib/GENcopy_from_user.S |    4 +--
 arch/sparc/lib/GENcopy_to_user.S   |    4 +--
 arch/sparc/lib/GENmemcpy.S         |   48 ++++++++++++++++++++++++++-----------
 3 files changed, 38 insertions(+), 18 deletions(-)

--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_mone;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
--- a/arch/sparc/lib/GENmemcpy.S
+++ b/arch/sparc/lib/GENmemcpy.S
@@ -4,21 +4,18 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #define GLOBAL_SPARE	%g7
 #else
 #define GLOBAL_SPARE	%g5
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -45,6 +42,29 @@
 	.register	%g3,#scratch
 
 	.text
+
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+ENTRY(GEN_retl_o4_1)
+	add	%o4, %o2, %o4
+	retl
+	 add	%o4, 1, %o0
+ENDPROC(GEN_retl_o4_1)
+ENTRY(GEN_retl_g1_8)
+	add	%g1, %o2, %g1
+	retl
+	 add	%g1, 8, %o0
+ENDPROC(GEN_retl_g1_8)
+ENTRY(GEN_retl_o2_4)
+	retl
+	 add	%o2, 4, %o0
+ENDPROC(GEN_retl_o2_4)
+ENTRY(GEN_retl_o2_1)
+	retl
+	 add	%o2, 1, %o0
+ENDPROC(GEN_retl_o2_1)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -73,8 +93,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	sub		%g0, %o4, %o4
 	sub		%o2, %o4, %o2
 1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1)
+	EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1)
 	add		%o1, 1, %o1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -82,8 +102,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	andn		%o2, 0x7, %g1
 	sub		%o2, %g1, %o2
 1:	subcc		%g1, 0x8, %g1
-	EX_LD(LOAD(ldx, %o1, %g2))
-	EX_ST(STORE(stx, %g2, %o0))
+	EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8)
+	EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8)
 	add		%o1, 0x8, %o1
 	bne,pt		%XCC, 1b
 	 add		%o0, 0x8, %o0
@@ -100,8 +120,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4)
+	EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -111,8 +131,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1)
+	EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl

[toc] | [prev] | [next] | [standalone]


#1525952 — [PATCH 4.8 15/49] bpf: fix htab map destruction when extra reserve is in use

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 15/49] bpf: fix htab map destruction when extra reserve is in use
Message-ID<sFahQ-36w-55@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Daniel Borkmann <daniel@iogearbox.net>


[ Upstream commit 483bed2b0ddd12ec33fc9407e0c6e1088e77a97c ]

Commit a6ed3ea65d98 ("bpf: restore behavior of bpf_map_update_elem")
added an extra per-cpu reserve to the hash table map to restore old
behaviour from pre prealloc times. When non-prealloc is in use for a
map, then problem is that once a hash table extra element has been
linked into the hash-table, and the hash table is destroyed due to
refcount dropping to zero, then htab_map_free() -> delete_all_elements()
will walk the whole hash table and drop all elements via htab_elem_free().
The problem is that the element from the extra reserve is first fed
to the wrong backend allocator and eventually freed twice.

Fixes: a6ed3ea65d98 ("bpf: restore behavior of bpf_map_update_elem")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/bpf/hashtab.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -687,7 +687,8 @@ static void delete_all_elements(struct b
 
 		hlist_for_each_entry_safe(l, n, head, hash_node) {
 			hlist_del_rcu(&l->hash_node);
-			htab_elem_free(htab, l);
+			if (l->state != HTAB_EXTRA_ELEM_USED)
+				htab_elem_free(htab, l);
 		}
 	}
 }

[toc] | [prev] | [next] | [standalone]


#1525956 — [PATCH 4.8 13/49] ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2016-11-19 10:40 +0100
Subject[PATCH 4.8 13/49] ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped
Message-ID<sFahQ-36w-57@gated-at.bofh.it>
In reply to#1525927
4.8-stable review patch.  If anyone has any objections, please let me know.

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

From: Eric Dumazet <edumazet@google.com>


[ Upstream commit 990ff4d84408fc55942ca6644f67e361737b3d8e ]

While fuzzing kernel with syzkaller, Andrey reported a nasty crash
in inet6_bind() caused by DCCP lacking a required method.

Fixes: ab1e0a13d7029 ("[SOCK] proto: Add hashinfo member to struct proto")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/ipv6.c |    1 +
 1 file changed, 1 insertion(+)

--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -958,6 +958,7 @@ static const struct inet_connection_sock
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
+	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,

[toc] | [prev] | [next] | [standalone]


#1526054

FromGuenter Roeck <linux@roeck-us.net>
Date2016-11-19 17:30 +0100
Message-ID<sFgGB-7k6-3@gated-at.bofh.it>
In reply to#1525927
On 11/19/2016 01:22 AM, Greg Kroah-Hartman wrote:
> This is the start of the stable review cycle for the 4.8.10 release.
> There are 49 patches in this series, all will be posted as a response
> to this one.  If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Mon Nov 21 09:20:18 UTC 2016.
> Anything received after that time might be too late.
>

Build results:
	total: 149 pass: 149 fail: 0
Qemu test results:
	total: 114 pass: 114 fail: 0

Details are available at http://kerneltests.org/builders.

Guenter

[toc] | [prev] | [next] | [standalone]


Page 1 of 2  [1] 2  Next page →

Back to top | Article view | linux.kernel


csiph-web