From b81036aa3558b934e2ea17e93e637f99796d88a0 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 23 Jan 2014 15:53:59 -0800 Subject: [PATCH 01/34] conditionally define U32_MAX commit 77719536dc00f8fd8f5abe6dadbde5331c37f996 upstream. The symbol U32_MAX is defined in several spots. Change these definitions to be conditional. This is in preparation for the next patch, which centralizes the definition in . Signed-off-by: Alex Elder Cc: Sage Weil Cc: David Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/reiserfs/reiserfs.h | 2 ++ include/linux/ceph/decode.h | 2 ++ net/ipv4/tcp_illinois.c | 2 ++ 3 files changed, 6 insertions(+) diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 157e474ab30..55dc1b079ed 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -1954,7 +1954,9 @@ struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} #define MAX_US_INT 0xffff // reiserfs version 2 has max offset 60 bits. Version 1 - 32 bit offset +#ifndef U32_MAX #define U32_MAX (~(__u32)0) +#endif /* !U32_MAX */ static inline loff_t max_reiserfs_offset(struct inode *inode) { diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 0442c3d800f..27fe66a279b 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -10,6 +10,7 @@ /* This seemed to be the easiest place to define these */ +#ifndef U32_MAX #define U8_MAX ((u8)(~0U)) #define U16_MAX ((u16)(~0U)) #define U32_MAX ((u32)(~0U)) @@ -24,6 +25,7 @@ #define S16_MIN ((s16)(-S16_MAX - 1)) #define S32_MIN ((s32)(-S32_MAX - 1)) #define S64_MIN ((s64)(-S64_MAX - 1LL)) +#endif /* !U32_MAX */ /* * in all cases, diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 834857f3c87..ffb2615d286 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -23,7 +23,9 @@ #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ +#ifndef U32_MAX #define U32_MAX ((u32)~0U) +#endif /* !U32_MAX */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 From 1554b19c4080476e4e5b678febd5fc7f2d102322 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 23 Jan 2014 15:54:01 -0800 Subject: [PATCH 02/34] remove extra definitions of U32_MAX commit 04f9b74e4d96d349de12fdd4e6626af4a9f75e09 upstream. Now that the definition is centralized in , the definitions of U32_MAX (and related) elsewhere in the kernel can be removed. Signed-off-by: Alex Elder Acked-by: Sage Weil Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/reiserfs/reiserfs.h | 4 ---- include/linux/ceph/decode.h | 19 ------------------- net/ipv4/tcp_illinois.c | 3 --- 3 files changed, 26 deletions(-) diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 55dc1b079ed..635a1425d37 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -1954,10 +1954,6 @@ struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} #define MAX_US_INT 0xffff // reiserfs version 2 has max offset 60 bits. Version 1 - 32 bit offset -#ifndef U32_MAX -#define U32_MAX (~(__u32)0) -#endif /* !U32_MAX */ - static inline loff_t max_reiserfs_offset(struct inode *inode) { if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5) diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 27fe66a279b..a6ef9cc267e 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -8,25 +8,6 @@ #include -/* This seemed to be the easiest place to define these */ - -#ifndef U32_MAX -#define U8_MAX ((u8)(~0U)) -#define U16_MAX ((u16)(~0U)) -#define U32_MAX ((u32)(~0U)) -#define U64_MAX ((u64)(~0ULL)) - -#define S8_MAX ((s8)(U8_MAX >> 1)) -#define S16_MAX ((s16)(U16_MAX >> 1)) -#define S32_MAX ((s32)(U32_MAX >> 1)) -#define S64_MAX ((s64)(U64_MAX >> 1LL)) - -#define S8_MIN ((s8)(-S8_MAX - 1)) -#define S16_MIN ((s16)(-S16_MAX - 1)) -#define S32_MIN ((s32)(-S32_MAX - 1)) -#define S64_MIN ((s64)(-S64_MAX - 1LL)) -#endif /* !U32_MAX */ - /* * in all cases, * void **p pointer to position pointer diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index ffb2615d286..86183c4e4fd 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -23,9 +23,6 @@ #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ -#ifndef U32_MAX -#define U32_MAX ((u32)~0U) -#endif /* !U32_MAX */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 From 1b946e381d185db8700e96634074052a62a11509 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Mon, 23 Mar 2015 15:14:00 +0100 Subject: [PATCH 03/34] tcp: prevent fetching dst twice in early demux code [ Upstream commit d0c294c53a771ae7e84506dfbd8c18c30f078735 ] On s390x, gcc 4.8 compiles this part of tcp_v6_early_demux() struct dst_entry *dst = sk->sk_rx_dst; if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); to code reading sk->sk_rx_dst twice, once for the test and once for the argument of ip6_dst_check() (dst_check() is inline). This allows ip6_dst_check() to be called with null first argument, causing a crash. Protect sk->sk_rx_dst access by ACCESS_ONCE() both in IPv4 and IPv6 TCP early demux code. Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Fixes: c7109986db3c ("ipv6: Early TCP socket demux") Signed-off-by: Michal Kubecek Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cce35e5a7ee..7c3eec386a4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1901,7 +1901,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1a87659a613..4659b8ab55d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1616,7 +1616,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); From 5a2267373e3d66b6df7d37b7366ed7a11bc29f4f Mon Sep 17 00:00:00 2001 From: "D.S. Ljungmark" Date: Wed, 25 Mar 2015 09:28:15 +0100 Subject: [PATCH 04/34] ipv6: Don't reduce hop limit for an interface [ Upstream commit 6fd99094de2b83d1d4c8457f2c83483b2828e75a ] A local route may have a lower hop_limit set than global routes do. RFC 3756, Section 4.2.7, "Parameter Spoofing" > 1. The attacker includes a Current Hop Limit of one or another small > number which the attacker knows will cause legitimate packets to > be dropped before they reach their destination. > As an example, one possible approach to mitigate this threat is to > ignore very small hop limits. The nodes could implement a > configurable minimum hop limit, and ignore attempts to set it below > said limit. Signed-off-by: D.S. Ljungmark Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ndisc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 060a0449aca..05f361338c2 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1193,7 +1193,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); From c31d60c29774e1c5650f89d5edccfd8314152af6 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Wed, 1 Apr 2015 20:26:46 -0400 Subject: [PATCH 05/34] tcp: fix FRTO undo on cumulative ACK of SACKed range [ Upstream commit 666b805150efd62f05810ff0db08f44a2370c937 ] On processing cumulative ACKs, the FRTO code was not checking the SACKed bit, meaning that there could be a spurious FRTO undo on a cumulative ACK of a previously SACKed skb. The FRTO code should only consider a cumulative ACK to indicate that an original/unretransmitted skb is newly ACKed if the skb was not yet SACKed. The effect of the spurious FRTO undo would typically be to make the connection think that all previously-sent packets were in flight when they really weren't, leading to a stall and an RTO. Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Fixes: e33099f96d99c ("tcp: implement RFC5682 F-RTO") Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ea7f52f3062..a8be45e4d34 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3076,10 +3076,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (seq_rtt < 0) { seq_rtt = ca_seq_rtt; } - if (!(sacked & TCPCB_SACKED_ACKED)) + if (!(sacked & TCPCB_SACKED_ACKED)) { reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; + } } if (sacked & TCPCB_SACKED_ACKED) From ef15025a4eb2cecc162a349bef1392b620966e40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Apr 2015 13:31:56 -0700 Subject: [PATCH 06/34] tcp: tcp_make_synack() should clear skb->tstamp [ Upstream commit b50edd7812852d989f2ef09dcfc729690f54a42d ] I noticed tcpdump was giving funky timestamps for locally generated SYNACK messages on loopback interface. 11:42:46.938990 IP 127.0.0.1.48245 > 127.0.0.2.23850: S 945476042:945476042(0) win 43690 20:28:58.502209 IP 127.0.0.2.23850 > 127.0.0.1.48245: S 3160535375:3160535375(0) ack 945476043 win 43690 This is because we need to clear skb->tstamp before entering lower stack, otherwise net_timestamp_check() does not set skb->tstamp. Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_output.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 92b5e1f7d3b..7681a1bbd97 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2772,6 +2772,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } #endif + /* Do not fool tcpdump (if any), clean our debris */ + skb->tstamp.tv64 = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); From 16767ec632cffde8a1176d2038a3d2f34c6fefa9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:14:58 -0700 Subject: [PATCH 07/34] 8139cp: Call dev_kfree_skby_any instead of kfree_skb. Replace kfree_skb with dev_kfree_skb_any in cp_start_xmit as it can be called in both hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/8139cp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 064425d3178..437d4cfd42c 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -899,7 +899,7 @@ out_unlock: return NETDEV_TX_OK; out_dma_error: - kfree_skb(skb); + dev_kfree_skb_any(skb); cp->dev->stats.tx_dropped++; goto out_unlock; } From 2886482ca51647ab0625231052caf626cf018729 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:15:36 -0700 Subject: [PATCH 08/34] 8139too: Call dev_kfree_skby_any instead of dev_kfree_skb. Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/8139too.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 3ccedeb8aba..942673fcb39 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -1715,9 +1715,9 @@ static netdev_tx_t rtl8139_start_xmit (struct sk_buff *skb, if (len < ETH_ZLEN) memset(tp->tx_buf[entry], 0, ETH_ZLEN); skb_copy_and_csum_dev(skb, tp->tx_buf[entry]); - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); } else { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } From 4324a943dcc772a304f6d2f82294c42c51afdd4d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:16:14 -0700 Subject: [PATCH 09/34] r8169: Call dev_kfree_skby_any instead of dev_kfree_skb. Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/r8169.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index e9b5d77a90d..2183c618914 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5768,7 +5768,7 @@ static void rtl8169_tx_clear_range(struct rtl8169_private *tp, u32 start, tp->TxDescArray + entry); if (skb) { tp->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_skb->skb = NULL; } } @@ -5993,7 +5993,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, err_dma_1: rtl8169_unmap_tx_skb(d, tp->tx_skb + entry, txd); err_dma_0: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); err_update_stats: dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -6076,7 +6076,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp) tp->tx_stats.packets++; tp->tx_stats.bytes += tx_skb->skb->len; u64_stats_update_end(&tp->tx_stats.syncp); - dev_kfree_skb(tx_skb->skb); + dev_kfree_skb_any(tx_skb->skb); tx_skb->skb = NULL; } dirty_tx++; From 248b28006ace38a3b91c347fcdff7d695d11776a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:17:41 -0700 Subject: [PATCH 10/34] bnx2: Call dev_kfree_skby_any instead of dev_kfree_skb. Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/bnx2.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 5d204492c60..161dcba13c4 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2869,7 +2869,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget) sw_cons = BNX2_NEXT_TX_BD(sw_cons); tx_bytes += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_pkt++; if (tx_pkt == budget) break; @@ -6610,7 +6610,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE); if (dma_mapping_error(&bp->pdev->dev, mapping)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -6703,7 +6703,7 @@ dma_error: PCI_DMA_TODEVICE); } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } From 543c297eca0a06cfddabc54672805864c8777ce3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:18:14 -0700 Subject: [PATCH 11/34] tg3: Call dev_kfree_skby_any instead of dev_kfree_skb. Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/tg3.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 8c1eab1151b..680d26d6d2c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6437,7 +6437,7 @@ static void tg3_tx(struct tg3_napi *tnapi) pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); if (unlikely(tx_bug)) { tg3_tx_recover(tp); @@ -6769,7 +6769,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) if (len > (tp->dev->mtu + ETH_HLEN) && skb->protocol != htons(ETH_P_8021Q) && skb->protocol != htons(ETH_P_8021AD)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); goto drop_it_no_recycle; } @@ -7652,7 +7652,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, PCI_DMA_TODEVICE); /* Make sure the mapping succeeded */ if (pci_dma_mapping_error(tp->pdev, new_addr)) { - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } else { u32 save_entry = *entry; @@ -7667,13 +7667,13 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, new_skb->len, base_flags, mss, vlan)) { tg3_tx_skb_unmap(tnapi, save_entry, -1); - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } } } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); *pskb = new_skb; return ret; } @@ -7716,7 +7716,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb) } while (segs); tg3_tso_bug_end: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -7954,7 +7954,7 @@ dma_error: tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, --i); tnapi->tx_buffers[tnapi->tx_prod].skb = NULL; drop: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); drop_nofree: tp->tx_dropped++; return NETDEV_TX_OK; From 97aa254018122e86bf2b3498d610c6c662bbc8c0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:18:42 -0700 Subject: [PATCH 12/34] ixgb: Call dev_kfree_skby_any instead of dev_kfree_skb. Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ixgb/ixgb_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index fce3e92f9d1..c5a9dcc01ca 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1527,12 +1527,12 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) int tso; if (test_bit(__IXGB_DOWN, &adapter->flags)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } if (skb->len <= 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1549,7 +1549,7 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tso = ixgb_tso(adapter, skb); if (tso < 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } From 57a99bf7d2f467714ba9db090a2f700cb080e0d9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 11 Mar 2014 14:19:50 -0700 Subject: [PATCH 13/34] benet: Call dev_kfree_skby_any instead of kfree_skb. Replace free_skb with dev_kfree_skb_any in be_tx_compl_process as which can be called in hard irq by netpoll, softirq context by normal napi polling, and in normal sleepable context by the network device close method. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index d81a7dbfeef..88e85cb8834 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1767,7 +1767,7 @@ static u16 be_tx_compl_process(struct be_adapter *adapter, queue_tail_inc(txq); } while (cur_index != last_index); - kfree_skb(sent_skb); + dev_kfree_skb_any(sent_skb); return num_wrbs; } From e3f5ff371c1e9ad273f403c6a487f972bc5bd058 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 11 Mar 2015 09:19:16 -0400 Subject: [PATCH 14/34] serial: 8250_dw: Fix deadlock in LCR workaround commit 7fd6f640f2dd17dac6ddd6702c378cb0bb9cfa11 upstream. Trying to write console output from within the serial console driver while the port->lock is held causes recursive deadlock: CPU 0 spin_lock_irqsave(&port->lock) printk() console_unlock() call_console_drivers() serial8250_console_write() spin_lock_irqsave(&port->lock) ** DEADLOCK ** The 8250_dw i/o accessors try to write a console error message if the LCR workaround was unsuccessful. When the port->lock is already held (eg., when called from serial8250_set_termios()), this deadlocks. Make the error message a FIXME until a general solution is devised. Cc: Tim Kryger Reported-by: Zhang Zhen Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_dw.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 345b5ddcb1a..86281fa5dcc 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -98,7 +98,10 @@ static void dw8250_serial_out(struct uart_port *p, int offset, int value) dw8250_force_idle(p); writeb(value, p->membase + (UART_LCR << p->regshift)); } - dev_err(p->dev, "Couldn't set LCR to %d\n", value); + /* + * FIXME: this deadlocks if port->lock is already held + * dev_err(p->dev, "Couldn't set LCR to %d\n", value); + */ } } @@ -128,7 +131,10 @@ static void dw8250_serial_out32(struct uart_port *p, int offset, int value) dw8250_force_idle(p); writel(value, p->membase + (UART_LCR << p->regshift)); } - dev_err(p->dev, "Couldn't set LCR to %d\n", value); + /* + * FIXME: this deadlocks if port->lock is already held + * dev_err(p->dev, "Couldn't set LCR to %d\n", value); + */ } } From 1ca630d975c5abb422ef7969494cacd91a1c125a Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Mon, 23 Mar 2015 16:06:26 -0500 Subject: [PATCH 15/34] jfs: fix readdir regression Upstream commit 44512449, "jfs: fix readdir cookie incompatibility with NFSv4", was backported incorrectly into the stable trees which used the filldir callback (rather than dir_emit). The position is being incorrectly passed to filldir for the . and .. entries. The still-maintained stable trees that need to be fixed are 3.2.y, 3.4.y and 3.10.y. https://bugzilla.kernel.org/show_bug.cgi?id=94741 Signed-off-by: Dave Kleikamp Cc: jfs-discussion@lists.sourceforge.net Signed-off-by: Greg Kroah-Hartman --- fs/jfs/jfs_dtree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index c450fdb3d78..5d876b1c9ea 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -3103,7 +3103,7 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir) * self "." */ filp->f_pos = 1; - if (filldir(dirent, ".", 1, 0, ip->i_ino, + if (filldir(dirent, ".", 1, 1, ip->i_ino, DT_DIR)) return 0; } @@ -3111,7 +3111,7 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir) * parent ".." */ filp->f_pos = 2; - if (filldir(dirent, "..", 2, 1, PARENT(ip), DT_DIR)) + if (filldir(dirent, "..", 2, 2, PARENT(ip), DT_DIR)) return 0; /* From 13d32f27d15c5c53254ed88e3d2042c34de1bfaa Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 29 Jan 2015 02:50:33 +0000 Subject: [PATCH 16/34] splice: Apply generic position and size checks to each write commit 894c6350eaad7e613ae267504014a456e00a3e2a from the 3.2-stable branch. We need to check the position and size of file writes against various limits, using generic_write_check(). This was not being done for the splice write path. It was fixed upstream by commit 8d0207652cbe ("->splice_write() via ->write_iter()") but we can't apply that. CVE-2014-7822 Signed-off-by: Ben Hutchings [Ben fixed it in 3.2 stable, i ported it to 3.10 stable] Signed-off-by: Zhang Zhen Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/file.c | 8 +++++--- fs/splice.c | 8 ++++++-- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8cd6474e248..d0e8c0b1767 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2459,12 +2459,14 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; struct splice_desc sd = { - .total_len = len, .flags = flags, - .pos = *ppos, .u.file = out, }; - + ret = generic_write_checks(out, ppos, &len, 0); + if(ret) + return ret; + sd.total_len = len; + sd.pos = *ppos; trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, diff --git a/fs/splice.c b/fs/splice.c index 4b5a5fac338..f183f1342c0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1012,13 +1012,17 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; struct splice_desc sd = { - .total_len = len, .flags = flags, - .pos = *ppos, .u.file = out, }; ssize_t ret; + ret = generic_write_checks(out, ppos, &len, S_ISBLK(inode->i_mode)); + if (ret) + return ret; + sd.total_len = len; + sd.pos = *ppos; + pipe_lock(pipe); splice_from_pipe_begin(&sd); From 23f1538b9cffe4229e703d72101e73e168abae57 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 20 Dec 2013 15:10:03 +0200 Subject: [PATCH 17/34] mm: Fix NULL pointer dereference in madvise(MADV_WILLNEED) support commit ee53664bda169f519ce3c6a22d378f0b946c8178 upstream. Sasha Levin found a NULL pointer dereference that is due to a missing page table lock, which in turn is due to the pmd entry in question being a transparent huge-table entry. The code - introduced in commit 1998cc048901 ("mm: make madvise(MADV_WILLNEED) support swap file prefetch") - correctly checks for this situation using pmd_none_or_trans_huge_or_clear_bad(), but it turns out that that function doesn't work correctly. pmd_none_or_trans_huge_or_clear_bad() expected that pmd_bad() would trigger if the transparent hugepage bit was set, but it doesn't do that if pmd_numa() is also set. Note that the NUMA bit only gets set on real NUMA machines, so people trying to reproduce this on most normal development systems would never actually trigger this. Fix it by removing the very subtle (and subtly incorrect) expectation, and instead just checking pmd_trans_huge() explicitly. Reported-by: Sasha Levin Acked-by: Andrea Arcangeli [ Additionally remove the now stale test for pmd_trans_huge() inside the pmd_bad() case - Linus ] Signed-off-by: Linus Torvalds Cc: Wang Long Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/pgtable.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 17bccd3a4b0..dd6d9b89d33 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -550,11 +550,10 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) #ifdef CONFIG_TRANSPARENT_HUGEPAGE barrier(); #endif - if (pmd_none(pmdval)) + if (pmd_none(pmdval) || pmd_trans_huge(pmdval)) return 1; if (unlikely(pmd_bad(pmdval))) { - if (!pmd_trans_huge(pmdval)) - pmd_clear_bad(pmd); + pmd_clear_bad(pmd); return 1; } return 0; From a713ad60cb761fcc48c2b71f798b8389852051f1 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 16 Jan 2014 15:37:11 +0100 Subject: [PATCH 18/34] Bluetooth: Enable Atheros 0cf3:311e for firmware upload commit b131237ca3995edad9efc162d0bc959c3b1dddc2 upstream. The device will bind to btusb without firmware, but with the original buggy firmware device discovery does not work. No devices are detected. Device descriptor without firmware: T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cf3 ProdID=311e Rev= 0.01 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms with firmware: T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 3 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cf3 ProdID=311e Rev= 0.02 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Oliver Neukum Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/ath3k.c | 2 ++ drivers/bluetooth/btusb.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index dad8891ecbf..72b64567b19 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -77,6 +77,7 @@ static struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0CF3, 0x3004) }, { USB_DEVICE(0x0CF3, 0x3008) }, { USB_DEVICE(0x0CF3, 0x311D) }, + { USB_DEVICE(0x0CF3, 0x311E) }, { USB_DEVICE(0x0CF3, 0x817a) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x04CA, 0x3004) }, @@ -120,6 +121,7 @@ static struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311E), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 61a8ec4e5f4..0f301012270 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -141,6 +141,7 @@ static struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, From 3672f3f2159e90132bf827791f6960e396c81c02 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 16 Jan 2014 16:02:58 +0100 Subject: [PATCH 19/34] Bluetooth: Add firmware update for Atheros 0cf3:311f commit 1e56f1eb2bbeab0ddc3a1e536d2a0065cfe4c131 upstream. The device is not functional without firmware. The device without firmware: T: Bus=02 Lev=02 Prnt=02 Port=05 Cnt=01 Dev#= 3 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cf3 ProdID=311f Rev=00.01 C: #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb I: If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb The device with firmware: T: Bus=02 Lev=02 Prnt=02 Port=05 Cnt=01 Dev#= 4 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cf3 ProdID=3007 Rev=00.01 C: #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb I: If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb Signed-off-by: Oliver Neukum Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/ath3k.c | 2 ++ drivers/bluetooth/btusb.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 72b64567b19..9c2c4eca52e 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -78,6 +78,7 @@ static struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0CF3, 0x3008) }, { USB_DEVICE(0x0CF3, 0x311D) }, { USB_DEVICE(0x0CF3, 0x311E) }, + { USB_DEVICE(0x0CF3, 0x311F) }, { USB_DEVICE(0x0CF3, 0x817a) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x04CA, 0x3004) }, @@ -122,6 +123,7 @@ static struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311E), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311F), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 0f301012270..c67c3a1a3b8 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -142,6 +142,7 @@ static struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x311f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, From 7ac28a3240ed0035ac1d203269169da20e2fee14 Mon Sep 17 00:00:00 2001 From: Jurgen Kramer Date: Sat, 15 Feb 2014 12:01:09 +0100 Subject: [PATCH 20/34] Bluetooth: btusb: Add IMC Networks (Broadcom based) commit 9113bfd82dc8ece9cbb898df8794f58a78a36e97 upstream. Add support for IMC Networks (Broadcom based) to btusb driver. Below the output of /sys/kernel/debug/usb/devices for this device: T: Bus=01 Lev=02 Prnt=02 Port=04 Cnt=01 Dev#= 3 Spd=12 MxCh= 0 D: Ver= 2.00 Cls=ff(vend.) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3404 Rev= 1.12 S: Manufacturer=Broadcom Corp S: Product=BCM20702A0 S: SerialNumber=240A649F8246 C:* #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr= 0mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=ff(vend.) Sub=01 Prot=01 Driver=btusb E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=84(I) Atr=02(Bulk) MxPS= 32 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 32 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 0 Cls=fe(app. ) Sub=01 Prot=01 Driver=(none) Signed-off-by: Jurgen Kramer Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c67c3a1a3b8..8d1c2f7c8ba 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -113,6 +113,9 @@ static struct usb_device_id btusb_table[] = { /*Broadcom devices with vendor specific id */ { USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) }, + /* IMC Networks - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01) }, + { } /* Terminating entry */ }; From 541086495d38c4d9811e93df545663c515b231e1 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 6 Jul 2014 13:29:58 +0200 Subject: [PATCH 21/34] Bluetooth: Add support for Intel bootloader devices commit 40df783d1ef1989ac454e3dfcda017270b8950e6 upstream. Intel Bluetooth devices that boot up in bootloader mode can not be used as generic HCI devices, but their HCI transport is still valuable and so bring that up as raw-only devices. T: Bus=02 Lev=02 Prnt=03 Port=00 Cnt=01 Dev#= 14 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=ff(vend.) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=8087 ProdID=0a5a Rev= 0.00 S: Manufacturer=Intel(R) Corporation S: Product=Intel(R) Wilkins Peak 2x2 S: SerialNumber=001122334455 WP_A0 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=81(I) Atr=03(Int.) MxPS= 64 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg [bwh: Backported to 3.14: adjust context] Signed-off-by: Johan Hedberg Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 8d1c2f7c8ba..5fd1674fd15 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -49,6 +49,7 @@ static struct usb_driver btusb_driver; #define BTUSB_WRONG_SCO_MTU 0x40 #define BTUSB_ATH3012 0x80 #define BTUSB_INTEL 0x100 +#define BTUSB_INTEL_BOOT 0x200 static struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -116,6 +117,9 @@ static struct usb_device_id btusb_table[] = { /* IMC Networks - Broadcom based */ { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01) }, + /* Intel Bluetooth USB Bootloader (RAM module) */ + { USB_DEVICE(0x8087, 0x0a5a), .driver_info = BTUSB_INTEL_BOOT }, + { } /* Terminating entry */ }; @@ -1449,6 +1453,9 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_INTEL) hdev->setup = btusb_setup_intel; + if (id->driver_info & BTUSB_INTEL_BOOT) + set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + /* Interface numbers are hardcoded in the specification */ data->isoc = usb_ifnum_to_if(data->udev, 1); From 532caffeb3b1b52e07d97fc3530cf7670895880e Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 6 Jul 2014 14:53:55 +0200 Subject: [PATCH 22/34] Bluetooth: Ignore isochronous endpoints for Intel USB bootloader commit d92f2df0565ea04101d6ac04bdc10feeb1d93c94 upstream. The isochronous endpoints are not valid when the Intel Bluetooth controller boots up in bootloader mode. So just mark these endpoints as broken and then they will not be configured. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5fd1674fd15..92b98531777 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -118,7 +118,8 @@ static struct usb_device_id btusb_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01) }, /* Intel Bluetooth USB Bootloader (RAM module) */ - { USB_DEVICE(0x8087, 0x0a5a), .driver_info = BTUSB_INTEL_BOOT }, + { USB_DEVICE(0x8087, 0x0a5a), + .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC }, { } /* Terminating entry */ }; From 752b388c92ed22e527ddb22fe137fa21095fb554 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 26 Sep 2014 11:35:42 +0200 Subject: [PATCH 23/34] netfilter: conntrack: disable generic tracking for known protocols commit db29a9508a9246e77087c5531e45b2c88ec6988b upstream. Given following iptables ruleset: -P FORWARD DROP -A FORWARD -m sctp --dport 9 -j ACCEPT -A FORWARD -p tcp --dport 80 -j ACCEPT -A FORWARD -p tcp -m conntrack -m state ESTABLISHED,RELATED -j ACCEPT One would assume that this allows SCTP on port 9 and TCP on port 80. Unfortunately, if the SCTP conntrack module is not loaded, this allows *all* SCTP communication, to pass though, i.e. -p sctp -j ACCEPT, which we think is a security issue. This is because on the first SCTP packet on port 9, we create a dummy "generic l4" conntrack entry without any port information (since conntrack doesn't know how to extract this information). All subsequent packets that are unknown will then be in established state since they will fallback to proto_generic and will match the 'generic' entry. Our originally proposed version [1] completely disabled generic protocol tracking, but Jozsef suggests to not track protocols for which a more suitable helper is available, hence we now mitigate the issue for in tree known ct protocol helpers only, so that at least NAT and direction information will still be preserved for others. [1] http://www.spinics.net/lists/netfilter-devel/msg33430.html Joint work with Daniel Borkmann. Fixes CVE-2014-8160. Signed-off-by: Florian Westphal Signed-off-by: Daniel Borkmann Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso Signed-off-by: Zhiqiang Zhang Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conntrack_proto_generic.c | 26 +++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index d25f2937764..957c1db6665 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -14,6 +14,30 @@ static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; +static bool nf_generic_should_process(u8 proto) +{ + switch (proto) { +#ifdef CONFIG_NF_CT_PROTO_SCTP_MODULE + case IPPROTO_SCTP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP_MODULE + case IPPROTO_DCCP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE + case IPPROTO_GRE: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE_MODULE + case IPPROTO_UDPLITE: + return false; +#endif + default: + return true; + } +} + static inline struct nf_generic_net *generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; @@ -67,7 +91,7 @@ static int generic_packet(struct nf_conn *ct, static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { - return true; + return nf_generic_should_process(nf_ct_protonum(ct)); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) From 3478a33e0c6204b4368c508a1175b2c027644968 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 1 Jan 2015 23:11:11 +0200 Subject: [PATCH 24/34] KVM: x86: SYSENTER emulation is broken commit f3747379accba8e95d70cec0eae0582c8c182050 upstream. SYSENTER emulation is broken in several ways: 1. It misses the case of 16-bit code segments completely (CVE-2015-0239). 2. MSR_IA32_SYSENTER_CS is checked in 64-bit mode incorrectly (bits 0 and 1 can still be set without causing #GP). 3. MSR_IA32_SYSENTER_EIP and MSR_IA32_SYSENTER_ESP are not masked in legacy-mode. 4. There is some unneeded code. Fix it. Signed-off-by: Nadav Amit Signed-off-by: Paolo Bonzini [zhangzhiqiang: backport to 3.10: - adjust context - in 3.10 context "ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF)" is replaced by "ctxt->eflags &= ~(EFLG_VM | EFLG_IF)" in upstream, which was changed by another commit. - After the above adjustments, becomes same to the original patch: https://github.com/torvalds/linux/commit/f3747379accba8e95d70cec0eae0582c8c182050 ] Signed-off-by: Zhiqiang Zhang Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/emulate.c | 27 ++++++++------------------- 1 file changed, 8 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index af88fa20dbe..ddad189e596 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2450,7 +2450,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) * Not recognized on AMD in compat mode (but is recognized in legacy * mode). */ - if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) && !vendor_intel(ctxt)) return emulate_ud(ctxt); @@ -2463,25 +2463,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); - switch (ctxt->mode) { - case X86EMUL_MODE_PROT32: - if ((msr_data & 0xfffc) == 0x0) - return emulate_gp(ctxt, 0); - break; - case X86EMUL_MODE_PROT64: - if (msr_data == 0x0) - return emulate_gp(ctxt, 0); - break; - default: - break; - } + if ((msr_data & 0xfffc) == 0x0) + return emulate_gp(ctxt, 0); ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF); - cs_sel = (u16)msr_data; - cs_sel &= ~SELECTOR_RPL_MASK; + cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; ss_sel = cs_sel + 8; - ss_sel &= ~SELECTOR_RPL_MASK; - if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) { + if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } @@ -2490,10 +2478,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); - ctxt->_eip = msr_data; + ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data; ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); - *reg_write(ctxt, VCPU_REGS_RSP) = msr_data; + *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : + (u32)msr_data; return X86EMUL_CONTINUE; } From f2b1b66341df87cd33cf7db7cb43c409c0fc23f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Peter=20K=C3=BCmmel?= Date: Tue, 4 Nov 2014 12:01:59 +0100 Subject: [PATCH 25/34] =?UTF-8?q?kconfig:=20Fix=20warning=20"=E2=80=98jump?= =?UTF-8?q?=E2=80=99=20may=20be=20used=20uninitialized"?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2d560306096739e2251329ab5c16059311a151b0 upstream. Warning: In file included from scripts/kconfig/zconf.tab.c:2537:0: scripts/kconfig/menu.c: In function ‘get_symbol_str’: scripts/kconfig/menu.c:590:18: warning: ‘jump’ may be used uninitialized in this function [-Wmaybe-uninitialized] jump->offset = strlen(r->s); Simplifies the test logic because (head && local) means (jump != 0) and makes GCC happy when checking if the jump pointer was initialized. Signed-off-by: Peter Kümmel Signed-off-by: Michal Marek [ dileks: v2: Backported to fit v3.10 ] Cc: Sedat Dilek Signed-off-by: Greg Kroah-Hartman --- scripts/kconfig/menu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index fd3f0180e08..6af1c42a9cf 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -525,7 +525,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, { int i, j; struct menu *submenu[8], *menu, *location = NULL; - struct jump_key *jump; + struct jump_key *jump = NULL; str_printf(r, _("Prompt: %s\n"), _(prop->text)); menu = prop->menu->parent; @@ -563,7 +563,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, str_printf(r, _(" Location:\n")); for (j = 4; --i >= 0; j += 2) { menu = submenu[i]; - if (head && location && menu == location) + if (jump && menu == location) jump->offset = r->len - 1; str_printf(r, "%*c-> %s", j, ' ', _(menu_get_prompt(menu))); From 6637ecd306a94a03dd5b8e4e8d3f260d9877c5b0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Oct 2014 19:19:16 -0400 Subject: [PATCH 26/34] move d_rcu from overlapping d_child to overlapping d_alias commit 946e51f2bf37f1656916eb75bd0742ba33983c28 upstream. Signed-off-by: Al Viro Cc: Ben Hutchings [hujianyang: Backported to 3.10 refer to the work of Ben Hutchings in 3.2: - Apply name changes in all the different places we use d_alias and d_child - Move the WARN_ON() in __d_free() to d_free() as we don't have dentry_free()] Signed-off-by: hujianyang Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- fs/affs/amigaffs.c | 2 +- fs/autofs4/expire.c | 12 ++-- fs/autofs4/root.c | 2 +- fs/ceph/dir.c | 8 +-- fs/ceph/inode.c | 6 +- fs/cifs/inode.c | 2 +- fs/coda/cache.c | 2 +- fs/dcache.c | 72 +++++++++++------------ fs/debugfs/inode.c | 6 +- fs/exportfs/expfs.c | 2 +- fs/libfs.c | 12 ++-- fs/ncpfs/dir.c | 2 +- fs/ncpfs/ncplib_kernel.h | 4 +- fs/nfs/getroot.c | 2 +- fs/notify/fsnotify.c | 4 +- fs/ocfs2/dcache.c | 2 +- include/linux/dcache.h | 8 +-- kernel/cgroup.c | 2 +- kernel/trace/trace.c | 4 +- kernel/trace/trace_events.c | 2 +- security/selinux/selinuxfs.c | 6 +- 22 files changed, 82 insertions(+), 82 deletions(-) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 35f77a42bed..c5c5788e8a1 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir) struct dentry *dentry, *tmp; mutex_lock(&dir->d_inode->i_mutex); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry)) && dentry->d_inode) { dget_dlock(dentry); diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index d9a43674cb9..9cca0ea4e47 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -126,7 +126,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 13ddec92341..8ad277990ea 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -91,7 +91,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, spin_lock(&root->d_lock); if (prev) - next = prev->d_u.d_child.next; + next = prev->d_child.next; else { prev = dget_dlock(root); next = prev->d_subdirs.next; @@ -105,13 +105,13 @@ cont: return NULL; } - q = list_entry(next, struct dentry, d_u.d_child); + q = list_entry(next, struct dentry, d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); /* Already gone or negative dentry (under construction) - try next */ if (q->d_count == 0 || !simple_positive(q)) { spin_unlock(&q->d_lock); - next = q->d_u.d_child.next; + next = q->d_child.next; goto cont; } dget_dlock(q); @@ -161,13 +161,13 @@ again: goto relock; } spin_unlock(&p->d_lock); - next = p->d_u.d_child.next; + next = p->d_child.next; p = parent; if (next != &parent->d_subdirs) break; } } - ret = list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_child); spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); /* Negative dentry - try next */ @@ -447,7 +447,7 @@ found: spin_lock(&sbi->lookup_lock); spin_lock(&expired->d_parent->d_lock); spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + list_move(&expired->d_parent->d_subdirs, &expired->d_child); spin_unlock(&expired->d_lock); spin_unlock(&expired->d_parent->d_lock); spin_unlock(&sbi->lookup_lock); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 085da86e07c..79ab4cb3590 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -655,7 +655,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry) /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; - d_child = &dentry->d_u.d_child; + d_child = &dentry->d_child; /* Set parent managed if it's becoming empty */ if (d_child->next == &parent->d_subdirs && d_child->prev == &parent->d_subdirs) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index f02d82b7933..ccb43298e27 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -103,7 +103,7 @@ static unsigned fpos_off(loff_t p) /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_u.d_child when we initially get results back from the MDS, and + * d_child when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * @@ -139,11 +139,11 @@ static int __dcache_readdir(struct file *filp, p = parent->d_subdirs.prev; dout(" initial p %p/%p\n", p->prev, p->next); } else { - p = last->d_u.d_child.prev; + p = last->d_child.prev; } more: - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); while (1) { dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next, @@ -165,7 +165,7 @@ more: !dentry->d_inode ? " null" : ""); spin_unlock(&dentry->d_lock); p = p->prev; - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index be0f7e20d62..0cf23a7b88c 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -867,9 +867,9 @@ static void ceph_set_dentry_offset(struct dentry *dn) spin_lock(&dir->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &dir->d_subdirs); + list_move(&dn->d_child, &dir->d_subdirs); dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset, - dn->d_u.d_child.prev, dn->d_u.d_child.next); + dn->d_child.prev, dn->d_child.next); spin_unlock(&dn->d_lock); spin_unlock(&dir->d_lock); } @@ -1296,7 +1296,7 @@ retry_lookup: /* reorder parent's d_subdirs */ spin_lock(&parent->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &parent->d_subdirs); + list_move(&dn->d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); spin_unlock(&parent->d_lock); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 0dee93706c9..54304ccae7e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -832,7 +832,7 @@ inode_has_hashed_dentries(struct inode *inode) struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 1da168c61d3..9bc1147a6c5 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(de, &parent->d_subdirs, d_child) { /* don't know what to do with negative dentries */ if (de->d_inode ) coda_flag_inode(de->d_inode, flag); diff --git a/fs/dcache.c b/fs/dcache.c index 25c0a1b5f6c..b3cb521809e 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -43,7 +43,7 @@ /* * Usage: * dcache->d_inode->i_lock protects: - * - i_dentry, d_alias, d_inode of aliases + * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_anon bl list spinlock protects: @@ -58,7 +58,7 @@ * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent - * - d_alias, d_inode + * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock @@ -215,7 +215,6 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!hlist_unhashed(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); @@ -226,6 +225,7 @@ static void __d_free(struct rcu_head *head) */ static void d_free(struct dentry *dentry) { + WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); BUG_ON(dentry->d_count); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) @@ -264,7 +264,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -288,7 +288,7 @@ static void dentry_unlink_inode(struct dentry * dentry) { struct inode *inode = dentry->d_inode; dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -364,7 +364,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) __releases(parent->d_lock) __releases(dentry->d_inode->i_lock) { - list_del(&dentry->d_u.d_child); + list_del(&dentry->d_child); /* * Inform try_to_ascend() that we are no longer attached to the * dentry tree @@ -660,7 +660,7 @@ static struct dentry *__d_find_alias(struct inode *inode, int want_discon) again: discon_alias = NULL; - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -713,7 +713,7 @@ void d_prune_aliases(struct inode *inode) struct dentry *dentry; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_count) { __dget_dlock(dentry); @@ -893,7 +893,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) /* descend to the first leaf in the current subtree */ while (!list_empty(&dentry->d_subdirs)) dentry = list_entry(dentry->d_subdirs.next, - struct dentry, d_u.d_child); + struct dentry, d_child); /* consume the dentries from this leaf up through its parents * until we find one with children or run out altogether */ @@ -927,17 +927,17 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) if (IS_ROOT(dentry)) { parent = NULL; - list_del(&dentry->d_u.d_child); + list_del(&dentry->d_child); } else { parent = dentry->d_parent; parent->d_count--; - list_del(&dentry->d_u.d_child); + list_del(&dentry->d_child); } inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else @@ -955,7 +955,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) } while (list_empty(&dentry->d_subdirs)); dentry = list_entry(dentry->d_subdirs.next, - struct dentry, d_u.d_child); + struct dentry, d_child); } } @@ -1048,7 +1048,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -1075,7 +1075,7 @@ resume: this_parent = try_to_ascend(this_parent, locked, seq); if (!this_parent) goto rename_retry; - next = child->d_u.d_child.next; + next = child->d_child.next; goto resume; } spin_unlock(&this_parent->d_lock); @@ -1131,7 +1131,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -1182,7 +1182,7 @@ resume: this_parent = try_to_ascend(this_parent, locked, seq); if (!this_parent) goto rename_retry; - next = child->d_u.d_child.next; + next = child->d_child.next; goto resume; } out: @@ -1278,8 +1278,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_HLIST_NODE(&dentry->d_alias); - INIT_LIST_HEAD(&dentry->d_u.d_child); + INIT_HLIST_NODE(&dentry->d_u.d_alias); + INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); this_cpu_inc(nr_dentry); @@ -1309,7 +1309,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) */ __dget_dlock(parent); dentry->d_parent = parent; - list_add(&dentry->d_u.d_child, &parent->d_subdirs); + list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; @@ -1369,7 +1369,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) if (inode) { if (unlikely(IS_AUTOMOUNT(inode))) dentry->d_flags |= DCACHE_NEED_AUTOMOUNT; - hlist_add_head(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); } dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); @@ -1394,7 +1394,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1433,7 +1433,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, return NULL; } - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1459,7 +1459,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1502,7 +1502,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode) if (hlist_empty(&inode->i_dentry)) return NULL; - alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } @@ -1576,7 +1576,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= DCACHE_DISCONNECTED; - hlist_add_head(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -2019,7 +2019,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent) struct dentry *child; spin_lock(&dparent->d_lock); - list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dparent->d_subdirs, d_child) { if (dentry == child) { spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); __dget_dlock(dentry); @@ -2266,8 +2266,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target) /* Unhash the target: dput() will then get rid of it */ __d_drop(target); - list_del(&dentry->d_u.d_child); - list_del(&target->d_u.d_child); + list_del(&dentry->d_child); + list_del(&target->d_child); /* Switch the names.. */ switch_names(dentry, target); @@ -2277,15 +2277,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target) if (IS_ROOT(dentry)) { dentry->d_parent = target->d_parent; target->d_parent = target; - INIT_LIST_HEAD(&target->d_u.d_child); + INIT_LIST_HEAD(&target->d_child); } else { swap(dentry->d_parent, target->d_parent); /* And add them back to the (new) parent lists */ - list_add(&target->d_u.d_child, &target->d_parent->d_subdirs); + list_add(&target->d_child, &target->d_parent->d_subdirs); } - list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + list_add(&dentry->d_child, &dentry->d_parent->d_subdirs); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); @@ -2392,9 +2392,9 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon) swap(dentry->d_name.hash, anon->d_name.hash); dentry->d_parent = dentry; - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); anon->d_parent = dparent; - list_move(&anon->d_u.d_child, &dparent->d_subdirs); + list_move(&anon->d_child, &dparent->d_subdirs); write_seqcount_end(&dentry->d_seq); write_seqcount_end(&anon->d_seq); @@ -2933,7 +2933,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -2963,7 +2963,7 @@ resume: this_parent = try_to_ascend(this_parent, locked, seq); if (!this_parent) goto rename_retry; - next = child->d_u.d_child.next; + next = child->d_child.next; goto resume; } spin_unlock(&this_parent->d_lock); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7269ec329c0..26d7fff8d78 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -545,7 +545,7 @@ void debugfs_remove_recursive(struct dentry *dentry) parent = dentry; down: mutex_lock(&parent->d_inode->i_mutex); - list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry_safe(child, next, &parent->d_subdirs, d_child) { if (!debugfs_positive(child)) continue; @@ -566,8 +566,8 @@ void debugfs_remove_recursive(struct dentry *dentry) mutex_lock(&parent->d_inode->i_mutex); if (child != dentry) { - next = list_entry(child->d_u.d_child.next, struct dentry, - d_u.d_child); + next = list_entry(child->d_child.next, struct dentry, + d_child); goto up; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 262fc994098..b4eec4c9a79 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result, inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) diff --git a/fs/libfs.c b/fs/libfs.c index 916da8c4158..1299bd5e07b 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -104,18 +104,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) spin_lock(&dentry->d_lock); /* d_lock not required for cursor */ - list_del(&cursor->d_u.d_child); + list_del(&cursor->d_child); p = dentry->d_subdirs.next; while (n && p != &dentry->d_subdirs) { struct dentry *next; - next = list_entry(p, struct dentry, d_u.d_child); + next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(next)) n--; spin_unlock(&next->d_lock); p = p->next; } - list_add_tail(&cursor->d_u.d_child, p); + list_add_tail(&cursor->d_child, p); spin_unlock(&dentry->d_lock); } } @@ -139,7 +139,7 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir) { struct dentry *dentry = filp->f_path.dentry; struct dentry *cursor = filp->private_data; - struct list_head *p, *q = &cursor->d_u.d_child; + struct list_head *p, *q = &cursor->d_child; ino_t ino; int i = filp->f_pos; @@ -165,7 +165,7 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir) for (p=q->next; p != &dentry->d_subdirs; p=p->next) { struct dentry *next; - next = list_entry(p, struct dentry, d_u.d_child); + next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (!simple_positive(next)) { spin_unlock(&next->d_lock); @@ -289,7 +289,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 6792ce11f2b..c578ba9949e 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -391,7 +391,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dent = list_entry(next, struct dentry, d_u.d_child); + dent = list_entry(next, struct dentry, d_child); if ((unsigned long)dent->d_fsdata == fpos) { if (dent->d_inode) dget(dent); diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 32c06587351..6d5e7c56c79 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -194,7 +194,7 @@ ncp_renew_dentries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); if (dentry->d_fsdata == NULL) ncp_age_dentry(server, dentry); @@ -216,7 +216,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); dentry->d_fsdata = NULL; ncp_age_dentry(server, dentry); next = next->next; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 44efaa8c5f7..0fe3ced6438 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -58,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - hlist_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_u.d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 4bb21d67d9b..a3153e2d0f1 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index ef999729e27..ce37013b4a5 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -172,7 +172,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9be5ac960fd..c1999d1fe6f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -120,15 +120,15 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ /* - * d_child and d_rcu can share memory + * d_alias and d_rcu can share memory */ union { - struct list_head d_child; /* child of parent list */ + struct hlist_node d_alias; /* inode alias list */ struct rcu_head d_rcu; } d_u; - struct list_head d_subdirs; /* our children */ - struct hlist_node d_alias; /* inode alias list */ }; /* diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d0def7fc284..ef130605ac4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -984,7 +984,7 @@ static void cgroup_d_remove_dir(struct dentry *dentry) parent = dentry->d_parent; spin_lock(&parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); remove_dir(dentry); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8d7e8098e76..640e4c44b17 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6063,7 +6063,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; @@ -6090,7 +6090,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry) int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 001b349af93..5a898f15bfc 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -425,7 +425,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) if (dir) { spin_lock(&dir->d_lock); /* probably unneeded */ - list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dir->d_subdirs, d_child) { if (child->d_inode) /* probably unneeded */ child->d_inode->i_private = NULL; } diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 464be51025f..a96bed4db3e 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1190,7 +1190,7 @@ static void sel_remove_entries(struct dentry *de) spin_lock(&de->d_lock); node = de->d_subdirs.next; while (node != &de->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + struct dentry *d = list_entry(node, struct dentry, d_child); spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); @@ -1664,12 +1664,12 @@ static void sel_remove_classes(void) list_for_each(class_node, &class_dir->d_subdirs) { struct dentry *class_subdir = list_entry(class_node, - struct dentry, d_u.d_child); + struct dentry, d_child); struct list_head *class_subdir_node; list_for_each(class_subdir_node, &class_subdir->d_subdirs) { struct dentry *d = list_entry(class_subdir_node, - struct dentry, d_u.d_child); + struct dentry, d_child); if (d->d_inode) if (d->d_inode->i_mode & S_IFDIR) From 5f03ac13d87590b0ee879c77e68df63a3d9b3e07 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Oct 2014 19:31:10 -0400 Subject: [PATCH 27/34] deal with deadlock in d_walk() commit ca5358ef75fc69fee5322a38a340f5739d997c10 upstream. ... by not hitting rename_retry for reasons other than rename having happened. In other words, do _not_ restart when finding that between unlocking the child and locking the parent the former got into __dentry_kill(). Skip the killed siblings instead... Signed-off-by: Al Viro Cc: Ben Hutchings [hujianyang: Backported to 3.10 refer to the work of Ben Hutchings in 3.2: - As we only have try_to_ascend() and not d_walk(), apply this change to all callers of try_to_ascend() - Adjust context to make __dentry_kill() apply to d_kill()] Signed-off-by: hujianyang Signed-off-by: Greg Kroah-Hartman --- fs/dcache.c | 102 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 62 insertions(+), 40 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index b3cb521809e..b1b8a7e9db0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -364,9 +364,9 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) __releases(parent->d_lock) __releases(dentry->d_inode->i_lock) { - list_del(&dentry->d_child); + __list_del_entry(&dentry->d_child); /* - * Inform try_to_ascend() that we are no longer attached to the + * Inform ascending readers that we are no longer attached to the * dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; @@ -987,35 +987,6 @@ void shrink_dcache_for_umount(struct super_block *sb) } } -/* - * This tries to ascend one level of parenthood, but - * we can race with renaming, so we need to re-check - * the parenthood after dropping the lock and check - * that the sequence number still matches. - */ -static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq) -{ - struct dentry *new = old->d_parent; - - rcu_read_lock(); - spin_unlock(&old->d_lock); - spin_lock(&new->d_lock); - - /* - * might go back up the wrong parent if we have had a rename - * or deletion - */ - if (new != old->d_parent || - (old->d_flags & DCACHE_DENTRY_KILLED) || - (!locked && read_seqretry(&rename_lock, seq))) { - spin_unlock(&new->d_lock); - new = NULL; - } - rcu_read_unlock(); - return new; -} - - /* * Search for at least 1 mount point in the dentry's subdirs. * We descend to the next level whenever the d_subdirs @@ -1070,17 +1041,32 @@ resume: /* * All done at this level ... ascend and resume the search. */ + rcu_read_lock(); +ascend: if (this_parent != parent) { struct dentry *child = this_parent; - this_parent = try_to_ascend(this_parent, locked, seq); - if (!this_parent) + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* might go back up the wrong parent if we have had a rename. */ + if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; next = child->d_child.next; + while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + next = next->next; + } + rcu_read_unlock(); goto resume; } - spin_unlock(&this_parent->d_lock); if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (locked) write_sequnlock(&rename_lock); return 0; /* No mount points found in tree */ @@ -1092,6 +1078,8 @@ positive: return 1; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (locked) goto again; locked = 1; @@ -1177,23 +1165,40 @@ resume: /* * All done at this level ... ascend and resume the search. */ + rcu_read_lock(); +ascend: if (this_parent != parent) { struct dentry *child = this_parent; - this_parent = try_to_ascend(this_parent, locked, seq); - if (!this_parent) + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* might go back up the wrong parent if we have had a rename. */ + if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; next = child->d_child.next; + while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + next = next->next; + } + rcu_read_unlock(); goto resume; } out: - spin_unlock(&this_parent->d_lock); if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (locked) write_sequnlock(&rename_lock); return found; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (found) return found; if (locked) @@ -2954,26 +2959,43 @@ resume: } spin_unlock(&dentry->d_lock); } + rcu_read_lock(); +ascend: if (this_parent != root) { struct dentry *child = this_parent; if (!(this_parent->d_flags & DCACHE_GENOCIDE)) { this_parent->d_flags |= DCACHE_GENOCIDE; this_parent->d_count--; } - this_parent = try_to_ascend(this_parent, locked, seq); - if (!this_parent) + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* might go back up the wrong parent if we have had a rename. */ + if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; next = child->d_child.next; + while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + next = next->next; + } + rcu_read_unlock(); goto resume; } - spin_unlock(&this_parent->d_lock); if (!locked && read_seqretry(&rename_lock, seq)) goto rename_retry; + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (locked) write_sequnlock(&rename_lock); return; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); if (locked) goto again; locked = 1; From 0c42d1fbb33f7e3fc97a4854e1f9804951ebdd0d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 29 Jan 2015 10:51:32 -0800 Subject: [PATCH 28/34] vm: add VM_FAULT_SIGSEGV handling support commit 33692f27597fcab536d7cbbcc8f52905133e4aa7 upstream. The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: Takashi Iwai Tested-by: Jan Engelhardt Acked-by: Heiko Carstens # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Signed-off-by: Linus Torvalds [shengyong: Backport to 3.10 - adjust context - ignore modification for arch nios2, because 3.10 does not support it - ignore modification for driver lustre, because 3.10 does not support it - ignore VM_FAULT_FALLBACK in VM_FAULT_ERROR, becase 3.10 does not support this flag - add SIGSEGV handling to powerpc/cell spu_fault.c, because 3.10 does not separate it to copro_fault.c - add SIGSEGV handling in mm/memory.c, because 3.10 does not separate it to gup.c ] Signed-off-by: Sheng Yong Signed-off-by: Greg Kroah-Hartman --- arch/alpha/mm/fault.c | 2 ++ arch/arc/mm/fault.c | 2 ++ arch/avr32/mm/fault.c | 2 ++ arch/cris/mm/fault.c | 2 ++ arch/frv/mm/fault.c | 2 ++ arch/ia64/mm/fault.c | 2 ++ arch/m32r/mm/fault.c | 2 ++ arch/m68k/mm/fault.c | 2 ++ arch/metag/mm/fault.c | 2 ++ arch/microblaze/mm/fault.c | 2 ++ arch/mips/mm/fault.c | 2 ++ arch/mn10300/mm/fault.c | 2 ++ arch/openrisc/mm/fault.c | 2 ++ arch/parisc/mm/fault.c | 2 ++ arch/powerpc/mm/fault.c | 2 ++ arch/powerpc/platforms/cell/spu_fault.c | 2 +- arch/s390/mm/fault.c | 6 ++++++ arch/score/mm/fault.c | 2 ++ arch/sh/mm/fault.c | 2 ++ arch/sparc/mm/fault_32.c | 2 ++ arch/sparc/mm/fault_64.c | 2 ++ arch/tile/mm/fault.c | 2 ++ arch/um/kernel/trap.c | 2 ++ arch/x86/mm/fault.c | 2 ++ arch/xtensa/mm/fault.c | 2 ++ include/linux/mm.h | 5 +++-- mm/ksm.c | 2 +- mm/memory.c | 5 +++-- 28 files changed, 60 insertions(+), 6 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 98838a05ba6..9d0ac091a52 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -156,6 +156,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 50533b750a9..4b70fc309c1 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -160,6 +160,8 @@ good_area: /* TBD: switch to pagefault_out_of_memory() */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 0eca9332719..d223a8b57c1 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -142,6 +142,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 1790f22e71a..2686a7aa8ec 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -176,6 +176,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 9a66372fc7c..ec4917ddf67 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 7225dad8709..ba5ba7accd0 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -172,6 +172,8 @@ retry: */ if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto bad_area; } else if (fault & VM_FAULT_SIGBUS) { signal = SIGBUS; goto bad_area; diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e9c6a8014bd..e3d4d489010 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -200,6 +200,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index eb1d61f6872..f0eef0491f7 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -153,6 +153,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto map_err; else if (fault & VM_FAULT_SIGBUS) goto bus_err; BUG(); diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 332680e5ebf..2de5dc695a8 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -141,6 +141,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index fa4cf52aa7a..d46a5ebb757 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -224,6 +224,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 0214a43b991..c40a8d1c43b 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -157,6 +157,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 3516cbdf1ee..0c2cc5d39c8 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -262,6 +262,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 0703acf7d32..230ac20ae79 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -171,6 +171,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index d10d27a720c..c45130f56a9 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -220,6 +220,8 @@ good_area: */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto bad_area; BUG(); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d9196c9f93d..d51a0c110eb 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -425,6 +425,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (fault & VM_FAULT_SIGSEGV) + goto bad_area; rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) goto bail; diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c index 641e7273d75..62f3e4e48a0 100644 --- a/arch/powerpc/platforms/cell/spu_fault.c +++ b/arch/powerpc/platforms/cell/spu_fault.c @@ -75,7 +75,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea, if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; goto out_unlock; - } else if (*flt & VM_FAULT_SIGBUS) { + } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { ret = -EFAULT; goto out_unlock; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 416facec4a3..d214321db72 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -244,6 +244,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) do_no_context(regs); else pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) + do_no_context(regs); + else + do_sigsegv(regs, SEGV_MAPERR); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 52238983527..6860beb2a28 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -114,6 +114,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 541dc610150..a58fec9b55e 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); + else if (fault & VM_FAULT_SIGSEGV) + bad_area(regs, error_code, address); else BUG(); } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 59dbd464572..163c7871211 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -252,6 +252,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 3841a081beb..ac2db923e51 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -443,6 +443,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 3ff289f422e..12b732f593b 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -446,6 +446,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 5c3aef74237..06ab0ebe0a0 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -80,6 +80,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto out; } else if (fault & VM_FAULT_SIGBUS) { err = -EACCES; goto out; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d8b1ff68dbb..18bce18b2a7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -873,6 +873,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 70fa7bc42b4..38278337d85 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -117,6 +117,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/include/linux/mm.h b/include/linux/mm.h index c4085192c2b..53b0d70120a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -891,6 +891,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ +#define VM_FAULT_SIGSEGV 0x0040 #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ @@ -898,8 +899,8 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_HWPOISON_LARGE) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \ + VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) diff --git a/mm/ksm.c b/mm/ksm.c index 784d1e4bc38..7bf748f30aa 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) else ret = VM_FAULT_WRITE; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM))); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop because handle_mm_fault() may back out if there's * any difficulty e.g. if pte accessed bit gets updated concurrently. diff --git a/mm/memory.c b/mm/memory.c index 04232bb173f..cca32308587 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1844,7 +1844,8 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, else return -EFAULT; } - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | + VM_FAULT_SIGSEGV)) return i ? i : -EFAULT; BUG(); } @@ -1954,7 +1955,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } From 1f74b26b0f118db0e658cbef2816d11d5ae0242c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 29 Jan 2015 11:15:17 -0800 Subject: [PATCH 29/34] vm: make stack guard page errors return VM_FAULT_SIGSEGV rather than SIGBUS commit 9c145c56d0c8a0b62e48c8d71e055ad0fb2012ba upstream. The stack guard page error case has long incorrectly caused a SIGBUS rather than a SIGSEGV, but nobody actually noticed until commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page") because that error case was never actually triggered in any normal situations. Now that we actually report the error, people noticed the wrong signal that resulted. So far, only the test suite of libsigsegv seems to have actually cared, but there are real applications that use libsigsegv, so let's not wait for any of those to break. Reported-and-tested-by: Takashi Iwai Tested-by: Jan Engelhardt Acked-by: Heiko Carstens # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index cca32308587..e6b1da3a892 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3232,7 +3232,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) - return VM_FAULT_SIGBUS; + return VM_FAULT_SIGSEGV; /* Use the zero-page for reads */ if (!(flags & FAULT_FLAG_WRITE)) { From 2d892c7a1b4aa0dd42004a217c13cc90a37ae4dd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 15 Dec 2014 14:46:06 -0800 Subject: [PATCH 30/34] x86: mm: move mmap_sem unlock from mm_fault_error() to caller commit 7fb08eca45270d0ae86e1ad9d39c40b7a55d0190 upstream. This replaces four copies in various stages of mm_fault_error() handling with just a single one. It will also allow for more natural placement of the unlocking after some further cleanup. Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/fault.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 18bce18b2a7..e4780b05253 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -812,11 +812,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; int code = BUS_ADRERR; - up_read(&mm->mmap_sem); - /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); @@ -847,7 +844,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, 0, 0); return; } @@ -855,14 +851,11 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { - up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } - up_read(¤t->mm->mmap_sem); - /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got @@ -1195,6 +1188,7 @@ good_area: return; if (unlikely(fault & VM_FAULT_ERROR)) { + up_read(&mm->mmap_sem); mm_fault_error(regs, error_code, address, fault); return; } From ebe7e30a9986c36388a5f304b10715d403a57097 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Fri, 5 Sep 2014 14:28:47 -0500 Subject: [PATCH 31/34] sb_edac: avoid INTERNAL ERROR message in EDAC with unspecified channel commit 351fc4a99d49fde63fe5ab7412beb35c40d27269 upstream. Intel IA32 SDM Table 15-14 defines channel 0xf as 'not specified', but EDAC doesn't know about this and returns and INTERNAL ERROR when the channel is greater than NUM_CHANNELS: kernel: [ 1538.886456] CPU 0: Machine Check Exception: 0 Bank 1: 940000000000009f kernel: [ 1538.886669] TSC 2bc68b22e7e812 ADDR 46dae7000 MISC 0 PROCESSOR 0:306e4 TIME 1390414572 SOCKET 0 APIC 0 kernel: [ 1538.971948] EDAC MC1: INTERNAL ERROR: channel value is out of range (15 >= 4) kernel: [ 1538.972203] EDAC MC1: 0 CE memory read error on unknown memory (slot:0 page:0x46dae7 offset:0x0 grain:0 syndrome:0x0 - area:DRAM err_code:0000:009f socket:1 channel_mask:1 rank:0) This commit changes sb_edac to forward a channel of -1 to EDAC if the channel is not specified. edac_mc_handle_error() sets the channel to -1 internally after the error message anyway, so this commit should have no effect other than avoiding the INTERNAL ERROR message when the channel is not specified. Signed-off-by: Seth Jennings Signed-off-by: Mauro Carvalho Chehab Cc: Vinson Lee Signed-off-by: Greg Kroah-Hartman --- drivers/edac/sb_edac.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index e04462b6075..f505e4ca6d5 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -270,8 +270,9 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 4 -#define MAX_DIMMS 3 /* Max DIMMS per channel */ +#define NUM_CHANNELS 4 +#define MAX_DIMMS 3 /* Max DIMMS per channel */ +#define CHANNEL_UNSPECIFIED 0xf /* Intel IA32 SDM 15-14 */ struct sbridge_info { u32 mcmtr; @@ -1451,6 +1452,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, /* FIXME: need support for channel mask */ + if (channel == CHANNEL_UNSPECIFIED) + channel = -1; + /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, From 9e505ae71ac8c8f643498a9e8c01ace136140606 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 29 Jan 2015 19:15:33 -0800 Subject: [PATCH 32/34] arc: mm: Fix build failure commit e262eb9381ad51b5de7a9e762ee773bbd25ce650 upstream. Fix misspelled define. Fixes: 33692f27597f ("vm: add VM_FAULT_SIGSEGV handling support") Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/arc/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 4b70fc309c1..08f65bcf913 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -160,7 +160,7 @@ good_area: /* TBD: switch to pagefault_out_of_memory() */ if (fault & VM_FAULT_OOM) goto out_of_memory; - else if (fault & VM_FAULT_SIGSEV) + else if (fault & VM_FAULT_SIGSEGV) goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; From c190d250d8db5620218d5d56999580ed8488ec24 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 11 Feb 2015 03:16:35 +0000 Subject: [PATCH 33/34] dcache: Fix locking bugs in backported "deal with deadlock in d_walk()" commit 20defcec264ceab2630356fb9d397f3d237b5e6d upstream in 3.2-stable Steven Rostedt reported: > Porting -rt to the latest 3.2 stable tree I triggered this bug: > > ===================================== > [ BUG: bad unlock balance detected! ] > ------------------------------------- > rm/1638 is trying to release lock (rcu_read_lock) at: > [] rcu_read_unlock+0x0/0x23 > but there are no more locks to release! > > other info that might help us debug this: > 2 locks held by rm/1638: > #0: (&sb->s_type->i_mutex_key#9/1){+.+.+.}, at: [] do_rmdir+0x5f/0xd2 > #1: (&sb->s_type->i_mutex_key#9){+.+.+.}, at: [] vfs_rmdir+0x49/0xac > > stack backtrace: > Pid: 1638, comm: rm Not tainted 3.2.66-test-rt96+ #2 > Call Trace: > [] ? printk+0x1d/0x1f > [] print_unlock_inbalance_bug+0xc3/0xcd > [] lock_release_non_nested+0x98/0x1ec > [] ? trace_hardirqs_off_caller+0x18/0x90 > [] ? local_clock+0x2d/0x50 > [] ? d_hash+0x2f/0x2f > [] ? d_hash+0x2f/0x2f > [] lock_release+0x192/0x1ad > [] rcu_read_unlock+0x17/0x23 > [] shrink_dcache_parent+0x227/0x270 > [] vfs_rmdir+0x68/0xac > [] do_rmdir+0x98/0xd2 > [] ? fput+0x1a3/0x1ab > [] ? sysenter_exit+0xf/0x1a > [] ? trace_hardirqs_on_caller+0x118/0x149 > [] sys_unlinkat+0x2b/0x35 > [] sysenter_do_call+0x12/0x12 > > > > > There's a path to calling rcu_read_unlock() without calling > rcu_read_lock() in have_submounts(). > > goto positive; > > positive: > if (!locked && read_seqretry(&rename_lock, seq)) > goto rename_retry; > > rename_retry: > rcu_read_unlock(); > > in the above path, rcu_read_lock() is never done before calling > rcu_read_unlock(); I reviewed locking contexts in all three functions that I changed when backporting "deal with deadlock in d_walk()". It's actually worse than this: - We don't hold this_parent->d_lock at the 'positive' label in have_submounts(), but it is unlocked after 'rename_retry'. - There is an rcu_read_unlock() after the 'out' label in select_parent(), but it's not held at the 'goto out'. Fix all three lock imbalances. Reported-by: Steven Rostedt Signed-off-by: Ben Hutchings Tested-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- fs/dcache.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/dcache.c b/fs/dcache.c index b1b8a7e9db0..efa4602e064 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1072,7 +1072,7 @@ ascend: return 0; /* No mount points found in tree */ positive: if (!locked && read_seqretry(&rename_lock, seq)) - goto rename_retry; + goto rename_retry_unlocked; if (locked) write_sequnlock(&rename_lock); return 1; @@ -1082,6 +1082,7 @@ rename_retry: rcu_read_unlock(); if (locked) goto again; +rename_retry_unlocked: locked = 1; write_seqlock(&rename_lock); goto again; @@ -1146,6 +1147,7 @@ resume: */ if (found && need_resched()) { spin_unlock(&dentry->d_lock); + rcu_read_lock(); goto out; } From 89bf6007dd14768791598eca6fd387b9637226eb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 29 Apr 2015 10:34:22 +0200 Subject: [PATCH 34/34] Linux 3.10.76 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 87909d8302a..019a6a4b386 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 10 -SUBLEVEL = 75 +SUBLEVEL = 76 EXTRAVERSION = NAME = TOSSUG Baby Fish