From 3b05debcd4dd78810c90dc8e2a07b7843275df2c Mon Sep 17 00:00:00 2001 From: Mike Pagano Date: Tue, 23 Jun 2015 08:54:37 -0400 Subject: Clean up master --- 1000_linux-4.0.1.patch | 479 -- 1001_linux-4.0.2.patch | 8587 -------------------- 1002_linux-4.0.3.patch | 2827 ------- 1003_linux-4.0.4.patch | 2713 ------- 1004_linux-4.0.5.patch | 4937 ----------- 1500_XATTR_USER_PREFIX.patch | 54 - ...ble-link-security-restrictions-by-default.patch | 22 - 2600_select-REGMAP_IRQ-for-rt5033.patch | 30 - 2700_ThinkPad-30-brightness-control-fix.patch | 67 - 2900_dev-root-proc-mount-fix.patch | 30 - 2905_2disk-resume-image-fix.patch | 24 - 2910_lz4-compression-fix.patch | 30 - 4200_fbcondecor-3.19.patch | 2119 ----- ...able-additional-cpu-optimizations-for-gcc.patch | 327 - ...roups-kconfig-build-bits-for-BFQ-v7r7-4.0.patch | 104 - ...introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1 | 6966 ---------------- ...rly-Queue-Merge-EQM-to-BFQ-v7r7-for-4.0.0.patch | 1222 --- ...-additional-cpu-optimizations-for-gcc-4.9.patch | 402 - 18 files changed, 30940 deletions(-) delete mode 100644 1000_linux-4.0.1.patch delete mode 100644 1001_linux-4.0.2.patch delete mode 100644 1002_linux-4.0.3.patch delete mode 100644 1003_linux-4.0.4.patch delete mode 100644 1004_linux-4.0.5.patch delete mode 100644 1500_XATTR_USER_PREFIX.patch delete mode 100644 1510_fs-enable-link-security-restrictions-by-default.patch delete mode 100644 2600_select-REGMAP_IRQ-for-rt5033.patch delete mode 100644 2700_ThinkPad-30-brightness-control-fix.patch delete mode 100644 2900_dev-root-proc-mount-fix.patch delete mode 100644 2905_2disk-resume-image-fix.patch delete mode 100644 2910_lz4-compression-fix.patch delete mode 100644 4200_fbcondecor-3.19.patch delete mode 100644 5000_enable-additional-cpu-optimizations-for-gcc.patch delete mode 100644 5001_block-cgroups-kconfig-build-bits-for-BFQ-v7r7-4.0.patch delete mode 100644 5002_block-introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1 delete mode 100644 5003_block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r7-for-4.0.0.patch delete mode 100644 5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch diff --git a/1000_linux-4.0.1.patch b/1000_linux-4.0.1.patch deleted file mode 100644 index ac585520..00000000 --- a/1000_linux-4.0.1.patch +++ /dev/null @@ -1,479 +0,0 @@ -diff --git a/Makefile b/Makefile -index fbd43bfe4445..f499cd2f5738 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 0 --SUBLEVEL = 0 -+SUBLEVEL = 1 - EXTRAVERSION = - NAME = Hurr durr I'ma sheep - -diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h -index 4085c4b31047..355d5fea5be9 100644 ---- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h -+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h -@@ -531,20 +531,8 @@ struct bnx2x_fastpath { - struct napi_struct napi; - - #ifdef CONFIG_NET_RX_BUSY_POLL -- unsigned int state; --#define BNX2X_FP_STATE_IDLE 0 --#define BNX2X_FP_STATE_NAPI (1 << 0) /* NAPI owns this FP */ --#define BNX2X_FP_STATE_POLL (1 << 1) /* poll owns this FP */ --#define BNX2X_FP_STATE_DISABLED (1 << 2) --#define BNX2X_FP_STATE_NAPI_YIELD (1 << 3) /* NAPI yielded this FP */ --#define BNX2X_FP_STATE_POLL_YIELD (1 << 4) /* poll yielded this FP */ --#define BNX2X_FP_OWNED (BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL) --#define BNX2X_FP_YIELD (BNX2X_FP_STATE_NAPI_YIELD | BNX2X_FP_STATE_POLL_YIELD) --#define BNX2X_FP_LOCKED (BNX2X_FP_OWNED | BNX2X_FP_STATE_DISABLED) --#define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD) -- /* protect state */ -- spinlock_t lock; --#endif /* CONFIG_NET_RX_BUSY_POLL */ -+ unsigned long busy_poll_state; -+#endif - - union host_hc_status_block status_blk; - /* chip independent shortcuts into sb structure */ -@@ -619,104 +607,83 @@ struct bnx2x_fastpath { - #define bnx2x_fp_qstats(bp, fp) (&((bp)->fp_stats[(fp)->index].eth_q_stats)) - - #ifdef CONFIG_NET_RX_BUSY_POLL --static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp) -+ -+enum bnx2x_fp_state { -+ BNX2X_STATE_FP_NAPI = BIT(0), /* NAPI handler owns the queue */ -+ -+ BNX2X_STATE_FP_NAPI_REQ_BIT = 1, /* NAPI would like to own the queue */ -+ BNX2X_STATE_FP_NAPI_REQ = BIT(1), -+ -+ BNX2X_STATE_FP_POLL_BIT = 2, -+ BNX2X_STATE_FP_POLL = BIT(2), /* busy_poll owns the queue */ -+ -+ BNX2X_STATE_FP_DISABLE_BIT = 3, /* queue is dismantled */ -+}; -+ -+static inline void bnx2x_fp_busy_poll_init(struct bnx2x_fastpath *fp) - { -- spin_lock_init(&fp->lock); -- fp->state = BNX2X_FP_STATE_IDLE; -+ WRITE_ONCE(fp->busy_poll_state, 0); - } - - /* called from the device poll routine to get ownership of a FP */ - static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp) - { -- bool rc = true; -- -- spin_lock_bh(&fp->lock); -- if (fp->state & BNX2X_FP_LOCKED) { -- WARN_ON(fp->state & BNX2X_FP_STATE_NAPI); -- fp->state |= BNX2X_FP_STATE_NAPI_YIELD; -- rc = false; -- } else { -- /* we don't care if someone yielded */ -- fp->state = BNX2X_FP_STATE_NAPI; -+ unsigned long prev, old = READ_ONCE(fp->busy_poll_state); -+ -+ while (1) { -+ switch (old) { -+ case BNX2X_STATE_FP_POLL: -+ /* make sure bnx2x_fp_lock_poll() wont starve us */ -+ set_bit(BNX2X_STATE_FP_NAPI_REQ_BIT, -+ &fp->busy_poll_state); -+ /* fallthrough */ -+ case BNX2X_STATE_FP_POLL | BNX2X_STATE_FP_NAPI_REQ: -+ return false; -+ default: -+ break; -+ } -+ prev = cmpxchg(&fp->busy_poll_state, old, BNX2X_STATE_FP_NAPI); -+ if (unlikely(prev != old)) { -+ old = prev; -+ continue; -+ } -+ return true; - } -- spin_unlock_bh(&fp->lock); -- return rc; - } - --/* returns true is someone tried to get the FP while napi had it */ --static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp) -+static inline void bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp) - { -- bool rc = false; -- -- spin_lock_bh(&fp->lock); -- WARN_ON(fp->state & -- (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_NAPI_YIELD)); -- -- if (fp->state & BNX2X_FP_STATE_POLL_YIELD) -- rc = true; -- -- /* state ==> idle, unless currently disabled */ -- fp->state &= BNX2X_FP_STATE_DISABLED; -- spin_unlock_bh(&fp->lock); -- return rc; -+ smp_wmb(); -+ fp->busy_poll_state = 0; - } - - /* called from bnx2x_low_latency_poll() */ - static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp) - { -- bool rc = true; -- -- spin_lock_bh(&fp->lock); -- if ((fp->state & BNX2X_FP_LOCKED)) { -- fp->state |= BNX2X_FP_STATE_POLL_YIELD; -- rc = false; -- } else { -- /* preserve yield marks */ -- fp->state |= BNX2X_FP_STATE_POLL; -- } -- spin_unlock_bh(&fp->lock); -- return rc; -+ return cmpxchg(&fp->busy_poll_state, 0, BNX2X_STATE_FP_POLL) == 0; - } - --/* returns true if someone tried to get the FP while it was locked */ --static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) -+static inline void bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) - { -- bool rc = false; -- -- spin_lock_bh(&fp->lock); -- WARN_ON(fp->state & BNX2X_FP_STATE_NAPI); -- -- if (fp->state & BNX2X_FP_STATE_POLL_YIELD) -- rc = true; -- -- /* state ==> idle, unless currently disabled */ -- fp->state &= BNX2X_FP_STATE_DISABLED; -- spin_unlock_bh(&fp->lock); -- return rc; -+ smp_mb__before_atomic(); -+ clear_bit(BNX2X_STATE_FP_POLL_BIT, &fp->busy_poll_state); - } - --/* true if a socket is polling, even if it did not get the lock */ -+/* true if a socket is polling */ - static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp) - { -- WARN_ON(!(fp->state & BNX2X_FP_OWNED)); -- return fp->state & BNX2X_FP_USER_PEND; -+ return READ_ONCE(fp->busy_poll_state) & BNX2X_STATE_FP_POLL; - } - - /* false if fp is currently owned */ - static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp) - { -- int rc = true; -- -- spin_lock_bh(&fp->lock); -- if (fp->state & BNX2X_FP_OWNED) -- rc = false; -- fp->state |= BNX2X_FP_STATE_DISABLED; -- spin_unlock_bh(&fp->lock); -+ set_bit(BNX2X_STATE_FP_DISABLE_BIT, &fp->busy_poll_state); -+ return !bnx2x_fp_ll_polling(fp); - -- return rc; - } - #else --static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp) -+static inline void bnx2x_fp_busy_poll_init(struct bnx2x_fastpath *fp) - { - } - -@@ -725,9 +692,8 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp) - return true; - } - --static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp) -+static inline void bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp) - { -- return false; - } - - static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp) -@@ -735,9 +701,8 @@ static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp) - return false; - } - --static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) -+static inline void bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp) - { -- return false; - } - - static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp) -diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c -index 0a9faa134a9a..2f63467bce46 100644 ---- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c -+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c -@@ -1849,7 +1849,7 @@ static void bnx2x_napi_enable_cnic(struct bnx2x *bp) - int i; - - for_each_rx_queue_cnic(bp, i) { -- bnx2x_fp_init_lock(&bp->fp[i]); -+ bnx2x_fp_busy_poll_init(&bp->fp[i]); - napi_enable(&bnx2x_fp(bp, i, napi)); - } - } -@@ -1859,7 +1859,7 @@ static void bnx2x_napi_enable(struct bnx2x *bp) - int i; - - for_each_eth_queue(bp, i) { -- bnx2x_fp_init_lock(&bp->fp[i]); -+ bnx2x_fp_busy_poll_init(&bp->fp[i]); - napi_enable(&bnx2x_fp(bp, i, napi)); - } - } -@@ -3191,9 +3191,10 @@ static int bnx2x_poll(struct napi_struct *napi, int budget) - } - } - -+ bnx2x_fp_unlock_napi(fp); -+ - /* Fall out from the NAPI loop if needed */ -- if (!bnx2x_fp_unlock_napi(fp) && -- !(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { -+ if (!(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { - - /* No need to update SB for FCoE L2 ring as long as - * it's connected to the default SB and the SB -diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c -index f8528a4cf54f..fceb637efd6b 100644 ---- a/drivers/net/vxlan.c -+++ b/drivers/net/vxlan.c -@@ -1713,12 +1713,6 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb, - } - } - -- skb = iptunnel_handle_offloads(skb, udp_sum, type); -- if (IS_ERR(skb)) { -- err = -EINVAL; -- goto err; -- } -- - skb_scrub_packet(skb, xnet); - - min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len -@@ -1738,6 +1732,12 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb, - goto err; - } - -+ skb = iptunnel_handle_offloads(skb, udp_sum, type); -+ if (IS_ERR(skb)) { -+ err = -EINVAL; -+ goto err; -+ } -+ - vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); - vxh->vx_flags = htonl(VXLAN_HF_VNI); - vxh->vx_vni = md->vni; -@@ -1798,10 +1798,6 @@ int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb, - } - } - -- skb = iptunnel_handle_offloads(skb, udp_sum, type); -- if (IS_ERR(skb)) -- return PTR_ERR(skb); -- - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + VXLAN_HLEN + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); -@@ -1817,6 +1813,10 @@ int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb, - if (WARN_ON(!skb)) - return -ENOMEM; - -+ skb = iptunnel_handle_offloads(skb, udp_sum, type); -+ if (IS_ERR(skb)) -+ return PTR_ERR(skb); -+ - vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); - vxh->vx_flags = htonl(VXLAN_HF_VNI); - vxh->vx_vni = md->vni; -diff --git a/fs/exec.c b/fs/exec.c -index c7f9b733406d..00400cf522dc 100644 ---- a/fs/exec.c -+++ b/fs/exec.c -@@ -1265,6 +1265,53 @@ static void check_unsafe_exec(struct linux_binprm *bprm) - spin_unlock(&p->fs->lock); - } - -+static void bprm_fill_uid(struct linux_binprm *bprm) -+{ -+ struct inode *inode; -+ unsigned int mode; -+ kuid_t uid; -+ kgid_t gid; -+ -+ /* clear any previous set[ug]id data from a previous binary */ -+ bprm->cred->euid = current_euid(); -+ bprm->cred->egid = current_egid(); -+ -+ if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) -+ return; -+ -+ if (task_no_new_privs(current)) -+ return; -+ -+ inode = file_inode(bprm->file); -+ mode = READ_ONCE(inode->i_mode); -+ if (!(mode & (S_ISUID|S_ISGID))) -+ return; -+ -+ /* Be careful if suid/sgid is set */ -+ mutex_lock(&inode->i_mutex); -+ -+ /* reload atomically mode/uid/gid now that lock held */ -+ mode = inode->i_mode; -+ uid = inode->i_uid; -+ gid = inode->i_gid; -+ mutex_unlock(&inode->i_mutex); -+ -+ /* We ignore suid/sgid if there are no mappings for them in the ns */ -+ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || -+ !kgid_has_mapping(bprm->cred->user_ns, gid)) -+ return; -+ -+ if (mode & S_ISUID) { -+ bprm->per_clear |= PER_CLEAR_ON_SETID; -+ bprm->cred->euid = uid; -+ } -+ -+ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { -+ bprm->per_clear |= PER_CLEAR_ON_SETID; -+ bprm->cred->egid = gid; -+ } -+} -+ - /* - * Fill the binprm structure from the inode. - * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes -@@ -1273,36 +1320,9 @@ static void check_unsafe_exec(struct linux_binprm *bprm) - */ - int prepare_binprm(struct linux_binprm *bprm) - { -- struct inode *inode = file_inode(bprm->file); -- umode_t mode = inode->i_mode; - int retval; - -- -- /* clear any previous set[ug]id data from a previous binary */ -- bprm->cred->euid = current_euid(); -- bprm->cred->egid = current_egid(); -- -- if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && -- !task_no_new_privs(current) && -- kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && -- kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { -- /* Set-uid? */ -- if (mode & S_ISUID) { -- bprm->per_clear |= PER_CLEAR_ON_SETID; -- bprm->cred->euid = inode->i_uid; -- } -- -- /* Set-gid? */ -- /* -- * If setgid is set but no group execute bit then this -- * is a candidate for mandatory locking, not a setgid -- * executable. -- */ -- if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { -- bprm->per_clear |= PER_CLEAR_ON_SETID; -- bprm->cred->egid = inode->i_gid; -- } -- } -+ bprm_fill_uid(bprm); - - /* fill in binprm security blob */ - retval = security_bprm_set_creds(bprm); -diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c -index a28e09c7825d..36508e69e92a 100644 ---- a/kernel/bpf/verifier.c -+++ b/kernel/bpf/verifier.c -@@ -1380,7 +1380,8 @@ peek_stack: - /* tell verifier to check for equivalent states - * after every call and jump - */ -- env->explored_states[t + 1] = STATE_LIST_MARK; -+ if (t + 1 < insn_cnt) -+ env->explored_states[t + 1] = STATE_LIST_MARK; - } else { - /* conditional jump with two edges */ - ret = push_insn(t, t + 1, FALLTHROUGH, env); -diff --git a/net/core/skbuff.c b/net/core/skbuff.c -index 8e4ac97c8477..98d45fe72f51 100644 ---- a/net/core/skbuff.c -+++ b/net/core/skbuff.c -@@ -4169,19 +4169,21 @@ EXPORT_SYMBOL(skb_try_coalesce); - */ - void skb_scrub_packet(struct sk_buff *skb, bool xnet) - { -- if (xnet) -- skb_orphan(skb); - skb->tstamp.tv64 = 0; - skb->pkt_type = PACKET_HOST; - skb->skb_iif = 0; - skb->ignore_df = 0; - skb_dst_drop(skb); -- skb->mark = 0; - skb_sender_cpu_clear(skb); -- skb_init_secmark(skb); - secpath_reset(skb); - nf_reset(skb); - nf_reset_trace(skb); -+ -+ if (!xnet) -+ return; -+ -+ skb_orphan(skb); -+ skb->mark = 0; - } - EXPORT_SYMBOL_GPL(skb_scrub_packet); - -diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c -index 5a4828ba05ad..a566a2e4715b 100644 ---- a/net/ipv4/geneve.c -+++ b/net/ipv4/geneve.c -@@ -113,10 +113,6 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, - int min_headroom; - int err; - -- skb = udp_tunnel_handle_offloads(skb, csum); -- if (IS_ERR(skb)) -- return PTR_ERR(skb); -- - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); -@@ -131,6 +127,10 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, - if (unlikely(!skb)) - return -ENOMEM; - -+ skb = udp_tunnel_handle_offloads(skb, csum); -+ if (IS_ERR(skb)) -+ return PTR_ERR(skb); -+ - gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); - -diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c -index 1db253e36045..d520492ba698 100644 ---- a/net/ipv4/tcp_output.c -+++ b/net/ipv4/tcp_output.c -@@ -2929,6 +2929,8 @@ 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); diff --git a/1001_linux-4.0.2.patch b/1001_linux-4.0.2.patch deleted file mode 100644 index 38a75b2f..00000000 --- a/1001_linux-4.0.2.patch +++ /dev/null @@ -1,8587 +0,0 @@ -diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt -index 99ca40e..5c204df 100644 ---- a/Documentation/networking/scaling.txt -+++ b/Documentation/networking/scaling.txt -@@ -282,7 +282,7 @@ following is true: - - - The current CPU's queue head counter >= the recorded tail counter - value in rps_dev_flow[i] --- The current CPU is unset (equal to RPS_NO_CPU) -+- The current CPU is unset (>= nr_cpu_ids) - - The current CPU is offline - - After this check, the packet is sent to the (possibly updated) current -diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt -index 4ceef53..d1ad9d5 100644 ---- a/Documentation/virtual/kvm/devices/s390_flic.txt -+++ b/Documentation/virtual/kvm/devices/s390_flic.txt -@@ -27,6 +27,9 @@ Groups: - Copies all floating interrupts into a buffer provided by userspace. - When the buffer is too small it returns -ENOMEM, which is the indication - for userspace to try again with a bigger buffer. -+ -ENOBUFS is returned when the allocation of a kernelspace buffer has -+ failed. -+ -EFAULT is returned when copying data to userspace failed. - All interrupts remain pending, i.e. are not deleted from the list of - currently pending interrupts. - attr->addr contains the userspace address of the buffer into which all -diff --git a/Makefile b/Makefile -index f499cd2..0649a60 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 0 --SUBLEVEL = 1 -+SUBLEVEL = 2 - EXTRAVERSION = - NAME = Hurr durr I'ma sheep - -diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts -index fec1fca..6c4bc53 100644 ---- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts -+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts -@@ -167,7 +167,13 @@ - - macb1: ethernet@f802c000 { - phy-mode = "rmii"; -+ #address-cells = <1>; -+ #size-cells = <0>; - status = "okay"; -+ -+ ethernet-phy@1 { -+ reg = <0x1>; -+ }; - }; - - dbgu: serial@ffffee00 { -diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi -index a5441d5..3cc8b83 100644 ---- a/arch/arm/boot/dts/dove.dtsi -+++ b/arch/arm/boot/dts/dove.dtsi -@@ -154,7 +154,7 @@ - - uart2: serial@12200 { - compatible = "ns16550a"; -- reg = <0x12000 0x100>; -+ reg = <0x12200 0x100>; - reg-shift = <2>; - interrupts = <9>; - clocks = <&core_clk 0>; -@@ -163,7 +163,7 @@ - - uart3: serial@12300 { - compatible = "ns16550a"; -- reg = <0x12100 0x100>; -+ reg = <0x12300 0x100>; - reg-shift = <2>; - interrupts = <10>; - clocks = <&core_clk 0>; -diff --git a/arch/arm/boot/dts/exynos5250-spring.dts b/arch/arm/boot/dts/exynos5250-spring.dts -index f027754..c41600e 100644 ---- a/arch/arm/boot/dts/exynos5250-spring.dts -+++ b/arch/arm/boot/dts/exynos5250-spring.dts -@@ -429,7 +429,6 @@ - &mmc_0 { - status = "okay"; - num-slots = <1>; -- supports-highspeed; - broken-cd; - card-detect-delay = <200>; - samsung,dw-mshc-ciu-div = <3>; -@@ -437,11 +436,8 @@ - samsung,dw-mshc-ddr-timing = <1 2>; - pinctrl-names = "default"; - pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_cd &sd0_bus4 &sd0_bus8>; -- -- slot@0 { -- reg = <0>; -- bus-width = <8>; -- }; -+ bus-width = <8>; -+ cap-mmc-highspeed; - }; - - /* -@@ -451,7 +447,6 @@ - &mmc_1 { - status = "okay"; - num-slots = <1>; -- supports-highspeed; - broken-cd; - card-detect-delay = <200>; - samsung,dw-mshc-ciu-div = <3>; -@@ -459,11 +454,8 @@ - samsung,dw-mshc-ddr-timing = <1 2>; - pinctrl-names = "default"; - pinctrl-0 = <&sd1_clk &sd1_cmd &sd1_cd &sd1_bus4>; -- -- slot@0 { -- reg = <0>; -- bus-width = <4>; -- }; -+ bus-width = <4>; -+ cap-sd-highspeed; - }; - - &pinctrl_0 { -diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h -index afb9caf..674d03f 100644 ---- a/arch/arm/include/asm/elf.h -+++ b/arch/arm/include/asm/elf.h -@@ -115,7 +115,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs); - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - --#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) -+#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) - - /* When the program starts, a1 contains a pointer to a function to be - registered with atexit, as per the SVR4 ABI. A value of 0 means we -diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h -index 0db25bc..3a42ac6 100644 ---- a/arch/arm/include/uapi/asm/kvm.h -+++ b/arch/arm/include/uapi/asm/kvm.h -@@ -195,8 +195,14 @@ struct kvm_arch_memory_slot { - #define KVM_ARM_IRQ_CPU_IRQ 0 - #define KVM_ARM_IRQ_CPU_FIQ 1 - --/* Highest supported SPI, from VGIC_NR_IRQS */ -+/* -+ * This used to hold the highest supported SPI, but it is now obsolete -+ * and only here to provide source code level compatibility with older -+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. -+ */ -+#ifndef __KERNEL__ - #define KVM_ARM_IRQ_GIC_MAX 127 -+#endif - - /* PSCI interface */ - #define KVM_PSCI_FN_BASE 0x95c1ba5e -diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c -index c4cc50e..cfb354f 100644 ---- a/arch/arm/kernel/hibernate.c -+++ b/arch/arm/kernel/hibernate.c -@@ -22,6 +22,7 @@ - #include - #include - #include -+#include "reboot.h" - - int pfn_is_nosave(unsigned long pfn) - { -@@ -61,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused) - - ret = swsusp_save(); - if (ret == 0) -- soft_restart(virt_to_phys(cpu_resume)); -+ _soft_restart(virt_to_phys(cpu_resume), false); - return ret; - } - -@@ -86,7 +87,7 @@ static void notrace arch_restore_image(void *unused) - for (pbe = restore_pblist; pbe; pbe = pbe->next) - copy_page(pbe->orig_address, pbe->address); - -- soft_restart(virt_to_phys(cpu_resume)); -+ _soft_restart(virt_to_phys(cpu_resume), false); - } - - static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; -diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c -index fdfa3a7..2bf1a16 100644 ---- a/arch/arm/kernel/process.c -+++ b/arch/arm/kernel/process.c -@@ -41,6 +41,7 @@ - #include - #include - #include -+#include "reboot.h" - - #ifdef CONFIG_CC_STACKPROTECTOR - #include -@@ -95,7 +96,7 @@ static void __soft_restart(void *addr) - BUG(); - } - --void soft_restart(unsigned long addr) -+void _soft_restart(unsigned long addr, bool disable_l2) - { - u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack); - -@@ -104,7 +105,7 @@ void soft_restart(unsigned long addr) - local_fiq_disable(); - - /* Disable the L2 if we're the last man standing. */ -- if (num_online_cpus() == 1) -+ if (disable_l2) - outer_disable(); - - /* Change to the new stack and continue with the reset. */ -@@ -114,6 +115,11 @@ void soft_restart(unsigned long addr) - BUG(); - } - -+void soft_restart(unsigned long addr) -+{ -+ _soft_restart(addr, num_online_cpus() == 1); -+} -+ - /* - * Function pointers to optional machine specific functions - */ -diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h -new file mode 100644 -index 0000000..c87f058 ---- /dev/null -+++ b/arch/arm/kernel/reboot.h -@@ -0,0 +1,6 @@ -+#ifndef REBOOT_H -+#define REBOOT_H -+ -+extern void _soft_restart(unsigned long addr, bool disable_l2); -+ -+#endif -diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c -index 5560f74..b652af5 100644 ---- a/arch/arm/kvm/arm.c -+++ b/arch/arm/kvm/arm.c -@@ -651,8 +651,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - -- if (irq_num < VGIC_NR_PRIVATE_IRQS || -- irq_num > KVM_ARM_IRQ_GIC_MAX) -+ if (irq_num < VGIC_NR_PRIVATE_IRQS) - return -EINVAL; - - return kvm_vgic_inject_irq(kvm, 0, irq_num, level); -diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c -index 8b9f5e2..4f4e222 100644 ---- a/arch/arm/mach-mvebu/pmsu.c -+++ b/arch/arm/mach-mvebu/pmsu.c -@@ -415,6 +415,9 @@ static __init int armada_38x_cpuidle_init(void) - void __iomem *mpsoc_base; - u32 reg; - -+ pr_warn("CPU idle is currently broken on Armada 38x: disabling"); -+ return 0; -+ - np = of_find_compatible_node(NULL, NULL, - "marvell,armada-380-coherency-fabric"); - if (!np) -@@ -476,6 +479,16 @@ static int __init mvebu_v7_cpu_pm_init(void) - return 0; - of_node_put(np); - -+ /* -+ * Currently the CPU idle support for Armada 38x is broken, as -+ * the CPU hotplug uses some of the CPU idle functions it is -+ * broken too, so let's disable it -+ */ -+ if (of_machine_is_compatible("marvell,armada380")) { -+ cpu_hotplug_disable(); -+ pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling"); -+ } -+ - if (of_machine_is_compatible("marvell,armadaxp")) - ret = armada_xp_cpuidle_init(); - else if (of_machine_is_compatible("marvell,armada370")) -@@ -489,7 +502,8 @@ static int __init mvebu_v7_cpu_pm_init(void) - return ret; - - mvebu_v7_pmsu_enable_l2_powerdown_onidle(); -- platform_device_register(&mvebu_v7_cpuidle_device); -+ if (mvebu_v7_cpuidle_device.name) -+ platform_device_register(&mvebu_v7_cpuidle_device); - cpu_pm_register_notifier(&mvebu_v7_cpu_pm_notifier); - - return 0; -diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h -index 7bc6668..dcbe17f 100644 ---- a/arch/arm/mach-s3c64xx/crag6410.h -+++ b/arch/arm/mach-s3c64xx/crag6410.h -@@ -14,6 +14,7 @@ - #include - - #define GLENFARCLAS_PMIC_IRQ_BASE IRQ_BOARD_START -+#define BANFF_PMIC_IRQ_BASE (IRQ_BOARD_START + 64) - - #define PCA935X_GPIO_BASE GPIO_BOARD_START - #define CODEC_GPIO_BASE (GPIO_BOARD_START + 8) -diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c -index 10b913b..65c426b 100644 ---- a/arch/arm/mach-s3c64xx/mach-crag6410.c -+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c -@@ -554,6 +554,7 @@ static struct wm831x_touch_pdata touch_pdata = { - - static struct wm831x_pdata crag_pmic_pdata = { - .wm831x_num = 1, -+ .irq_base = BANFF_PMIC_IRQ_BASE, - .gpio_base = BANFF_PMIC_GPIO_BASE, - .soft_shutdown = true, - -diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig -index 1b8e973..a6186c2 100644 ---- a/arch/arm64/Kconfig -+++ b/arch/arm64/Kconfig -@@ -361,6 +361,27 @@ config ARM64_ERRATUM_832075 - - If unsure, say Y. - -+config ARM64_ERRATUM_845719 -+ bool "Cortex-A53: 845719: a load might read incorrect data" -+ depends on COMPAT -+ default y -+ help -+ This option adds an alternative code sequence to work around ARM -+ erratum 845719 on Cortex-A53 parts up to r0p4. -+ -+ When running a compat (AArch32) userspace on an affected Cortex-A53 -+ part, a load at EL0 from a virtual address that matches the bottom 32 -+ bits of the virtual address used by a recent load at (AArch64) EL1 -+ might return incorrect data. -+ -+ The workaround is to write the contextidr_el1 register on exception -+ return to a 32-bit task. -+ Please note that this does not necessarily enable the workaround, -+ as it depends on the alternative framework, which will only patch -+ the kernel if an affected CPU is detected. -+ -+ If unsure, say Y. -+ - endmenu - - -@@ -470,6 +491,10 @@ config HOTPLUG_CPU - - source kernel/Kconfig.preempt - -+config UP_LATE_INIT -+ def_bool y -+ depends on !SMP -+ - config HZ - int - default 100 -diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile -index 69ceedc..4d2a925 100644 ---- a/arch/arm64/Makefile -+++ b/arch/arm64/Makefile -@@ -48,7 +48,7 @@ core-$(CONFIG_KVM) += arch/arm64/kvm/ - core-$(CONFIG_XEN) += arch/arm64/xen/ - core-$(CONFIG_CRYPTO) += arch/arm64/crypto/ - libs-y := arch/arm64/lib/ $(libs-y) --libs-$(CONFIG_EFI_STUB) += drivers/firmware/efi/libstub/ -+core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a - - # Default target when executing plain make - KBUILD_IMAGE := Image.gz -diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h -index b6c16d5..3f0c53c 100644 ---- a/arch/arm64/include/asm/cpufeature.h -+++ b/arch/arm64/include/asm/cpufeature.h -@@ -23,8 +23,9 @@ - - #define ARM64_WORKAROUND_CLEAN_CACHE 0 - #define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 -+#define ARM64_WORKAROUND_845719 2 - --#define ARM64_NCAPS 2 -+#define ARM64_NCAPS 3 - - #ifndef __ASSEMBLY__ - -diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h -index 59e2823..8dcd61e 100644 ---- a/arch/arm64/include/asm/smp_plat.h -+++ b/arch/arm64/include/asm/smp_plat.h -@@ -40,4 +40,6 @@ static inline u32 mpidr_hash_size(void) - extern u64 __cpu_logical_map[NR_CPUS]; - #define cpu_logical_map(cpu) __cpu_logical_map[cpu] - -+void __init do_post_cpus_up_work(void); -+ - #endif /* __ASM_SMP_PLAT_H */ -diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h -index 3ef77a4..bc49a18 100644 ---- a/arch/arm64/include/uapi/asm/kvm.h -+++ b/arch/arm64/include/uapi/asm/kvm.h -@@ -188,8 +188,14 @@ struct kvm_arch_memory_slot { - #define KVM_ARM_IRQ_CPU_IRQ 0 - #define KVM_ARM_IRQ_CPU_FIQ 1 - --/* Highest supported SPI, from VGIC_NR_IRQS */ -+/* -+ * This used to hold the highest supported SPI, but it is now obsolete -+ * and only here to provide source code level compatibility with older -+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS. -+ */ -+#ifndef __KERNEL__ - #define KVM_ARM_IRQ_GIC_MAX 127 -+#endif - - /* PSCI interface */ - #define KVM_PSCI_FN_BASE 0x95c1ba5e -diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c -index fa62637..ad6d523 100644 ---- a/arch/arm64/kernel/cpu_errata.c -+++ b/arch/arm64/kernel/cpu_errata.c -@@ -88,7 +88,16 @@ struct arm64_cpu_capabilities arm64_errata[] = { - /* Cortex-A57 r0p0 - r1p2 */ - .desc = "ARM erratum 832075", - .capability = ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE, -- MIDR_RANGE(MIDR_CORTEX_A57, 0x00, 0x12), -+ MIDR_RANGE(MIDR_CORTEX_A57, 0x00, -+ (1 << MIDR_VARIANT_SHIFT) | 2), -+ }, -+#endif -+#ifdef CONFIG_ARM64_ERRATUM_845719 -+ { -+ /* Cortex-A53 r0p[01234] */ -+ .desc = "ARM erratum 845719", -+ .capability = ARM64_WORKAROUND_845719, -+ MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04), - }, - #endif - { -diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S -index cf21bb3..959fe87 100644 ---- a/arch/arm64/kernel/entry.S -+++ b/arch/arm64/kernel/entry.S -@@ -21,8 +21,10 @@ - #include - #include - -+#include - #include - #include -+#include - #include - #include - #include -@@ -120,6 +122,24 @@ - ct_user_enter - ldr x23, [sp, #S_SP] // load return stack pointer - msr sp_el0, x23 -+ -+#ifdef CONFIG_ARM64_ERRATUM_845719 -+ alternative_insn \ -+ "nop", \ -+ "tbz x22, #4, 1f", \ -+ ARM64_WORKAROUND_845719 -+#ifdef CONFIG_PID_IN_CONTEXTIDR -+ alternative_insn \ -+ "nop; nop", \ -+ "mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:", \ -+ ARM64_WORKAROUND_845719 -+#else -+ alternative_insn \ -+ "nop", \ -+ "msr contextidr_el1, xzr; 1:", \ -+ ARM64_WORKAROUND_845719 -+#endif -+#endif - .endif - msr elr_el1, x21 // set up the return data - msr spsr_el1, x22 -diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S -index 07f9305..c237ffb 100644 ---- a/arch/arm64/kernel/head.S -+++ b/arch/arm64/kernel/head.S -@@ -426,6 +426,7 @@ __create_page_tables: - */ - mov x0, x25 - add x1, x26, #SWAPPER_DIR_SIZE -+ dmb sy - bl __inval_cache_range - - mov lr, x27 -diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c -index e8420f6..781f469 100644 ---- a/arch/arm64/kernel/setup.c -+++ b/arch/arm64/kernel/setup.c -@@ -207,6 +207,18 @@ static void __init smp_build_mpidr_hash(void) - } - #endif - -+void __init do_post_cpus_up_work(void) -+{ -+ apply_alternatives_all(); -+} -+ -+#ifdef CONFIG_UP_LATE_INIT -+void __init up_late_init(void) -+{ -+ do_post_cpus_up_work(); -+} -+#endif /* CONFIG_UP_LATE_INIT */ -+ - static void __init setup_processor(void) - { - struct cpu_info *cpu_info; -diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c -index 328b8ce..4257369 100644 ---- a/arch/arm64/kernel/smp.c -+++ b/arch/arm64/kernel/smp.c -@@ -309,7 +309,7 @@ void cpu_die(void) - void __init smp_cpus_done(unsigned int max_cpus) - { - pr_info("SMP: Total of %d processors activated.\n", num_online_cpus()); -- apply_alternatives_all(); -+ do_post_cpus_up_work(); - } - - void __init smp_prepare_boot_cpu(void) -diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c -index 356ee84..04845aa 100644 ---- a/arch/c6x/kernel/time.c -+++ b/arch/c6x/kernel/time.c -@@ -49,7 +49,7 @@ u64 sched_clock(void) - return (tsc * sched_clock_multiplier) >> SCHED_CLOCK_SHIFT; - } - --void time_init(void) -+void __init time_init(void) - { - u64 tmp = (u64)NSEC_PER_SEC << SCHED_CLOCK_SHIFT; - -diff --git a/arch/mips/include/asm/asm-eva.h b/arch/mips/include/asm/asm-eva.h -index e41c56e..1e38f0e 100644 ---- a/arch/mips/include/asm/asm-eva.h -+++ b/arch/mips/include/asm/asm-eva.h -@@ -11,6 +11,36 @@ - #define __ASM_ASM_EVA_H - - #ifndef __ASSEMBLY__ -+ -+/* Kernel variants */ -+ -+#define kernel_cache(op, base) "cache " op ", " base "\n" -+#define kernel_ll(reg, addr) "ll " reg ", " addr "\n" -+#define kernel_sc(reg, addr) "sc " reg ", " addr "\n" -+#define kernel_lw(reg, addr) "lw " reg ", " addr "\n" -+#define kernel_lwl(reg, addr) "lwl " reg ", " addr "\n" -+#define kernel_lwr(reg, addr) "lwr " reg ", " addr "\n" -+#define kernel_lh(reg, addr) "lh " reg ", " addr "\n" -+#define kernel_lb(reg, addr) "lb " reg ", " addr "\n" -+#define kernel_lbu(reg, addr) "lbu " reg ", " addr "\n" -+#define kernel_sw(reg, addr) "sw " reg ", " addr "\n" -+#define kernel_swl(reg, addr) "swl " reg ", " addr "\n" -+#define kernel_swr(reg, addr) "swr " reg ", " addr "\n" -+#define kernel_sh(reg, addr) "sh " reg ", " addr "\n" -+#define kernel_sb(reg, addr) "sb " reg ", " addr "\n" -+ -+#ifdef CONFIG_32BIT -+/* -+ * No 'sd' or 'ld' instructions in 32-bit but the code will -+ * do the correct thing -+ */ -+#define kernel_sd(reg, addr) user_sw(reg, addr) -+#define kernel_ld(reg, addr) user_lw(reg, addr) -+#else -+#define kernel_sd(reg, addr) "sd " reg", " addr "\n" -+#define kernel_ld(reg, addr) "ld " reg", " addr "\n" -+#endif /* CONFIG_32BIT */ -+ - #ifdef CONFIG_EVA - - #define __BUILD_EVA_INSN(insn, reg, addr) \ -@@ -41,37 +71,60 @@ - - #else - --#define user_cache(op, base) "cache " op ", " base "\n" --#define user_ll(reg, addr) "ll " reg ", " addr "\n" --#define user_sc(reg, addr) "sc " reg ", " addr "\n" --#define user_lw(reg, addr) "lw " reg ", " addr "\n" --#define user_lwl(reg, addr) "lwl " reg ", " addr "\n" --#define user_lwr(reg, addr) "lwr " reg ", " addr "\n" --#define user_lh(reg, addr) "lh " reg ", " addr "\n" --#define user_lb(reg, addr) "lb " reg ", " addr "\n" --#define user_lbu(reg, addr) "lbu " reg ", " addr "\n" --#define user_sw(reg, addr) "sw " reg ", " addr "\n" --#define user_swl(reg, addr) "swl " reg ", " addr "\n" --#define user_swr(reg, addr) "swr " reg ", " addr "\n" --#define user_sh(reg, addr) "sh " reg ", " addr "\n" --#define user_sb(reg, addr) "sb " reg ", " addr "\n" -+#define user_cache(op, base) kernel_cache(op, base) -+#define user_ll(reg, addr) kernel_ll(reg, addr) -+#define user_sc(reg, addr) kernel_sc(reg, addr) -+#define user_lw(reg, addr) kernel_lw(reg, addr) -+#define user_lwl(reg, addr) kernel_lwl(reg, addr) -+#define user_lwr(reg, addr) kernel_lwr(reg, addr) -+#define user_lh(reg, addr) kernel_lh(reg, addr) -+#define user_lb(reg, addr) kernel_lb(reg, addr) -+#define user_lbu(reg, addr) kernel_lbu(reg, addr) -+#define user_sw(reg, addr) kernel_sw(reg, addr) -+#define user_swl(reg, addr) kernel_swl(reg, addr) -+#define user_swr(reg, addr) kernel_swr(reg, addr) -+#define user_sh(reg, addr) kernel_sh(reg, addr) -+#define user_sb(reg, addr) kernel_sb(reg, addr) - - #ifdef CONFIG_32BIT --/* -- * No 'sd' or 'ld' instructions in 32-bit but the code will -- * do the correct thing -- */ --#define user_sd(reg, addr) user_sw(reg, addr) --#define user_ld(reg, addr) user_lw(reg, addr) -+#define user_sd(reg, addr) kernel_sw(reg, addr) -+#define user_ld(reg, addr) kernel_lw(reg, addr) - #else --#define user_sd(reg, addr) "sd " reg", " addr "\n" --#define user_ld(reg, addr) "ld " reg", " addr "\n" -+#define user_sd(reg, addr) kernel_sd(reg, addr) -+#define user_ld(reg, addr) kernel_ld(reg, addr) - #endif /* CONFIG_32BIT */ - - #endif /* CONFIG_EVA */ - - #else /* __ASSEMBLY__ */ - -+#define kernel_cache(op, base) cache op, base -+#define kernel_ll(reg, addr) ll reg, addr -+#define kernel_sc(reg, addr) sc reg, addr -+#define kernel_lw(reg, addr) lw reg, addr -+#define kernel_lwl(reg, addr) lwl reg, addr -+#define kernel_lwr(reg, addr) lwr reg, addr -+#define kernel_lh(reg, addr) lh reg, addr -+#define kernel_lb(reg, addr) lb reg, addr -+#define kernel_lbu(reg, addr) lbu reg, addr -+#define kernel_sw(reg, addr) sw reg, addr -+#define kernel_swl(reg, addr) swl reg, addr -+#define kernel_swr(reg, addr) swr reg, addr -+#define kernel_sh(reg, addr) sh reg, addr -+#define kernel_sb(reg, addr) sb reg, addr -+ -+#ifdef CONFIG_32BIT -+/* -+ * No 'sd' or 'ld' instructions in 32-bit but the code will -+ * do the correct thing -+ */ -+#define kernel_sd(reg, addr) user_sw(reg, addr) -+#define kernel_ld(reg, addr) user_lw(reg, addr) -+#else -+#define kernel_sd(reg, addr) sd reg, addr -+#define kernel_ld(reg, addr) ld reg, addr -+#endif /* CONFIG_32BIT */ -+ - #ifdef CONFIG_EVA - - #define __BUILD_EVA_INSN(insn, reg, addr) \ -@@ -101,31 +154,27 @@ - #define user_sd(reg, addr) user_sw(reg, addr) - #else - --#define user_cache(op, base) cache op, base --#define user_ll(reg, addr) ll reg, addr --#define user_sc(reg, addr) sc reg, addr --#define user_lw(reg, addr) lw reg, addr --#define user_lwl(reg, addr) lwl reg, addr --#define user_lwr(reg, addr) lwr reg, addr --#define user_lh(reg, addr) lh reg, addr --#define user_lb(reg, addr) lb reg, addr --#define user_lbu(reg, addr) lbu reg, addr --#define user_sw(reg, addr) sw reg, addr --#define user_swl(reg, addr) swl reg, addr --#define user_swr(reg, addr) swr reg, addr --#define user_sh(reg, addr) sh reg, addr --#define user_sb(reg, addr) sb reg, addr -+#define user_cache(op, base) kernel_cache(op, base) -+#define user_ll(reg, addr) kernel_ll(reg, addr) -+#define user_sc(reg, addr) kernel_sc(reg, addr) -+#define user_lw(reg, addr) kernel_lw(reg, addr) -+#define user_lwl(reg, addr) kernel_lwl(reg, addr) -+#define user_lwr(reg, addr) kernel_lwr(reg, addr) -+#define user_lh(reg, addr) kernel_lh(reg, addr) -+#define user_lb(reg, addr) kernel_lb(reg, addr) -+#define user_lbu(reg, addr) kernel_lbu(reg, addr) -+#define user_sw(reg, addr) kernel_sw(reg, addr) -+#define user_swl(reg, addr) kernel_swl(reg, addr) -+#define user_swr(reg, addr) kernel_swr(reg, addr) -+#define user_sh(reg, addr) kernel_sh(reg, addr) -+#define user_sb(reg, addr) kernel_sb(reg, addr) - - #ifdef CONFIG_32BIT --/* -- * No 'sd' or 'ld' instructions in 32-bit but the code will -- * do the correct thing -- */ --#define user_sd(reg, addr) user_sw(reg, addr) --#define user_ld(reg, addr) user_lw(reg, addr) -+#define user_sd(reg, addr) kernel_sw(reg, addr) -+#define user_ld(reg, addr) kernel_lw(reg, addr) - #else --#define user_sd(reg, addr) sd reg, addr --#define user_ld(reg, addr) ld reg, addr -+#define user_sd(reg, addr) kernel_sd(reg, addr) -+#define user_ld(reg, addr) kernel_sd(reg, addr) - #endif /* CONFIG_32BIT */ - - #endif /* CONFIG_EVA */ -diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h -index dd083e9..9f26b07 100644 ---- a/arch/mips/include/asm/fpu.h -+++ b/arch/mips/include/asm/fpu.h -@@ -170,6 +170,7 @@ static inline void lose_fpu(int save) - } - disable_msa(); - clear_thread_flag(TIF_USEDMSA); -+ __disable_fpu(); - } else if (is_fpu_owner()) { - if (save) - _save_fp(current); -diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h -index ac4fc71..f722b05 100644 ---- a/arch/mips/include/asm/kvm_host.h -+++ b/arch/mips/include/asm/kvm_host.h -@@ -322,6 +322,7 @@ enum mips_mmu_types { - #define T_TRAP 13 /* Trap instruction */ - #define T_VCEI 14 /* Virtual coherency exception */ - #define T_FPE 15 /* Floating point exception */ -+#define T_MSADIS 21 /* MSA disabled exception */ - #define T_WATCH 23 /* Watch address reference */ - #define T_VCED 31 /* Virtual coherency data */ - -@@ -578,6 +579,7 @@ struct kvm_mips_callbacks { - int (*handle_syscall)(struct kvm_vcpu *vcpu); - int (*handle_res_inst)(struct kvm_vcpu *vcpu); - int (*handle_break)(struct kvm_vcpu *vcpu); -+ int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); - int (*vm_init)(struct kvm *kvm); - int (*vcpu_init)(struct kvm_vcpu *vcpu); - int (*vcpu_setup)(struct kvm_vcpu *vcpu); -diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c -index bbb6969..7659da2 100644 ---- a/arch/mips/kernel/unaligned.c -+++ b/arch/mips/kernel/unaligned.c -@@ -109,10 +109,11 @@ static u32 unaligned_action; - extern void show_registers(struct pt_regs *regs); - - #ifdef __BIG_ENDIAN --#define LoadHW(addr, value, res) \ -+#define _LoadHW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ (".set\tnoat\n" \ -- "1:\t"user_lb("%0", "0(%2)")"\n" \ -- "2:\t"user_lbu("$1", "1(%2)")"\n\t" \ -+ "1:\t"type##_lb("%0", "0(%2)")"\n" \ -+ "2:\t"type##_lbu("$1", "1(%2)")"\n\t"\ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -127,13 +128,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - - #ifndef CONFIG_CPU_MIPSR6 --#define LoadW(addr, value, res) \ -+#define _LoadW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_lwl("%0", "(%2)")"\n" \ -- "2:\t"user_lwr("%0", "3(%2)")"\n\t" \ -+ "1:\t"type##_lwl("%0", "(%2)")"\n" \ -+ "2:\t"type##_lwr("%0", "3(%2)")"\n\t"\ - "li\t%1, 0\n" \ - "3:\n\t" \ - ".insn\n\t" \ -@@ -146,21 +149,24 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has no lwl instruction */ --#define LoadW(addr, value, res) \ -+#define _LoadW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n" \ - ".set\tnoat\n\t" \ -- "1:"user_lb("%0", "0(%2)")"\n\t" \ -- "2:"user_lbu("$1", "1(%2)")"\n\t" \ -+ "1:"type##_lb("%0", "0(%2)")"\n\t" \ -+ "2:"type##_lbu("$1", "1(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "3:"user_lbu("$1", "2(%2)")"\n\t" \ -+ "3:"type##_lbu("$1", "2(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "4:"user_lbu("$1", "3(%2)")"\n\t" \ -+ "4:"type##_lbu("$1", "3(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -178,14 +184,17 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t4b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #endif /* CONFIG_CPU_MIPSR6 */ - --#define LoadHWU(addr, value, res) \ -+#define _LoadHWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tnoat\n" \ -- "1:\t"user_lbu("%0", "0(%2)")"\n" \ -- "2:\t"user_lbu("$1", "1(%2)")"\n\t" \ -+ "1:\t"type##_lbu("%0", "0(%2)")"\n" \ -+ "2:\t"type##_lbu("$1", "1(%2)")"\n\t"\ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -201,13 +210,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - - #ifndef CONFIG_CPU_MIPSR6 --#define LoadWU(addr, value, res) \ -+#define _LoadWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_lwl("%0", "(%2)")"\n" \ -- "2:\t"user_lwr("%0", "3(%2)")"\n\t" \ -+ "1:\t"type##_lwl("%0", "(%2)")"\n" \ -+ "2:\t"type##_lwr("%0", "3(%2)")"\n\t"\ - "dsll\t%0, %0, 32\n\t" \ - "dsrl\t%0, %0, 32\n\t" \ - "li\t%1, 0\n" \ -@@ -222,9 +233,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define LoadDW(addr, value, res) \ -+#define _LoadDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - "1:\tldl\t%0, (%2)\n" \ - "2:\tldr\t%0, 7(%2)\n\t" \ -@@ -240,21 +253,24 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has not lwl and ldl instructions */ --#define LoadWU(addr, value, res) \ -+#define _LoadWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -- "1:"user_lbu("%0", "0(%2)")"\n\t" \ -- "2:"user_lbu("$1", "1(%2)")"\n\t" \ -+ "1:"type##_lbu("%0", "0(%2)")"\n\t" \ -+ "2:"type##_lbu("$1", "1(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "3:"user_lbu("$1", "2(%2)")"\n\t" \ -+ "3:"type##_lbu("$1", "2(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "4:"user_lbu("$1", "3(%2)")"\n\t" \ -+ "4:"type##_lbu("$1", "3(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -272,9 +288,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t4b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define LoadDW(addr, value, res) \ -+#define _LoadDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -@@ -319,16 +337,19 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t8b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #endif /* CONFIG_CPU_MIPSR6 */ - - --#define StoreHW(addr, value, res) \ -+#define _StoreHW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tnoat\n" \ -- "1:\t"user_sb("%1", "1(%2)")"\n" \ -+ "1:\t"type##_sb("%1", "1(%2)")"\n" \ - "srl\t$1, %1, 0x8\n" \ -- "2:\t"user_sb("$1", "0(%2)")"\n" \ -+ "2:\t"type##_sb("$1", "0(%2)")"\n" \ - ".set\tat\n\t" \ - "li\t%0, 0\n" \ - "3:\n\t" \ -@@ -342,13 +363,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT));\ -+} while(0) - - #ifndef CONFIG_CPU_MIPSR6 --#define StoreW(addr, value, res) \ -+#define _StoreW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_swl("%1", "(%2)")"\n" \ -- "2:\t"user_swr("%1", "3(%2)")"\n\t" \ -+ "1:\t"type##_swl("%1", "(%2)")"\n" \ -+ "2:\t"type##_swr("%1", "3(%2)")"\n\t"\ - "li\t%0, 0\n" \ - "3:\n\t" \ - ".insn\n\t" \ -@@ -361,9 +384,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define StoreDW(addr, value, res) \ -+#define _StoreDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - "1:\tsdl\t%1,(%2)\n" \ - "2:\tsdr\t%1, 7(%2)\n\t" \ -@@ -379,20 +404,23 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has no swl and sdl instructions */ --#define StoreW(addr, value, res) \ -+#define _StoreW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -- "1:"user_sb("%1", "3(%2)")"\n\t" \ -+ "1:"type##_sb("%1", "3(%2)")"\n\t" \ - "srl\t$1, %1, 0x8\n\t" \ -- "2:"user_sb("$1", "2(%2)")"\n\t" \ -+ "2:"type##_sb("$1", "2(%2)")"\n\t" \ - "srl\t$1, $1, 0x8\n\t" \ -- "3:"user_sb("$1", "1(%2)")"\n\t" \ -+ "3:"type##_sb("$1", "1(%2)")"\n\t" \ - "srl\t$1, $1, 0x8\n\t" \ -- "4:"user_sb("$1", "0(%2)")"\n\t" \ -+ "4:"type##_sb("$1", "0(%2)")"\n\t" \ - ".set\tpop\n\t" \ - "li\t%0, 0\n" \ - "10:\n\t" \ -@@ -409,9 +437,11 @@ extern void show_registers(struct pt_regs *regs); - ".previous" \ - : "=&r" (res) \ - : "r" (value), "r" (addr), "i" (-EFAULT) \ -- : "memory"); -+ : "memory"); \ -+} while(0) - - #define StoreDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -@@ -451,15 +481,18 @@ extern void show_registers(struct pt_regs *regs); - ".previous" \ - : "=&r" (res) \ - : "r" (value), "r" (addr), "i" (-EFAULT) \ -- : "memory"); -+ : "memory"); \ -+} while(0) -+ - #endif /* CONFIG_CPU_MIPSR6 */ - - #else /* __BIG_ENDIAN */ - --#define LoadHW(addr, value, res) \ -+#define _LoadHW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ (".set\tnoat\n" \ -- "1:\t"user_lb("%0", "1(%2)")"\n" \ -- "2:\t"user_lbu("$1", "0(%2)")"\n\t" \ -+ "1:\t"type##_lb("%0", "1(%2)")"\n" \ -+ "2:\t"type##_lbu("$1", "0(%2)")"\n\t"\ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -474,13 +507,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - - #ifndef CONFIG_CPU_MIPSR6 --#define LoadW(addr, value, res) \ -+#define _LoadW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_lwl("%0", "3(%2)")"\n" \ -- "2:\t"user_lwr("%0", "(%2)")"\n\t" \ -+ "1:\t"type##_lwl("%0", "3(%2)")"\n" \ -+ "2:\t"type##_lwr("%0", "(%2)")"\n\t"\ - "li\t%1, 0\n" \ - "3:\n\t" \ - ".insn\n\t" \ -@@ -493,21 +528,24 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has no lwl instruction */ --#define LoadW(addr, value, res) \ -+#define _LoadW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n" \ - ".set\tnoat\n\t" \ -- "1:"user_lb("%0", "3(%2)")"\n\t" \ -- "2:"user_lbu("$1", "2(%2)")"\n\t" \ -+ "1:"type##_lb("%0", "3(%2)")"\n\t" \ -+ "2:"type##_lbu("$1", "2(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "3:"user_lbu("$1", "1(%2)")"\n\t" \ -+ "3:"type##_lbu("$1", "1(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "4:"user_lbu("$1", "0(%2)")"\n\t" \ -+ "4:"type##_lbu("$1", "0(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -525,15 +563,18 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t4b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #endif /* CONFIG_CPU_MIPSR6 */ - - --#define LoadHWU(addr, value, res) \ -+#define _LoadHWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tnoat\n" \ -- "1:\t"user_lbu("%0", "1(%2)")"\n" \ -- "2:\t"user_lbu("$1", "0(%2)")"\n\t" \ -+ "1:\t"type##_lbu("%0", "1(%2)")"\n" \ -+ "2:\t"type##_lbu("$1", "0(%2)")"\n\t"\ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -549,13 +590,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - - #ifndef CONFIG_CPU_MIPSR6 --#define LoadWU(addr, value, res) \ -+#define _LoadWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_lwl("%0", "3(%2)")"\n" \ -- "2:\t"user_lwr("%0", "(%2)")"\n\t" \ -+ "1:\t"type##_lwl("%0", "3(%2)")"\n" \ -+ "2:\t"type##_lwr("%0", "(%2)")"\n\t"\ - "dsll\t%0, %0, 32\n\t" \ - "dsrl\t%0, %0, 32\n\t" \ - "li\t%1, 0\n" \ -@@ -570,9 +613,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define LoadDW(addr, value, res) \ -+#define _LoadDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - "1:\tldl\t%0, 7(%2)\n" \ - "2:\tldr\t%0, (%2)\n\t" \ -@@ -588,21 +633,24 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has not lwl and ldl instructions */ --#define LoadWU(addr, value, res) \ -+#define _LoadWU(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -- "1:"user_lbu("%0", "3(%2)")"\n\t" \ -- "2:"user_lbu("$1", "2(%2)")"\n\t" \ -+ "1:"type##_lbu("%0", "3(%2)")"\n\t" \ -+ "2:"type##_lbu("$1", "2(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "3:"user_lbu("$1", "1(%2)")"\n\t" \ -+ "3:"type##_lbu("$1", "1(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ -- "4:"user_lbu("$1", "0(%2)")"\n\t" \ -+ "4:"type##_lbu("$1", "0(%2)")"\n\t" \ - "sll\t%0, 0x8\n\t" \ - "or\t%0, $1\n\t" \ - "li\t%1, 0\n" \ -@@ -620,9 +668,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t4b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define LoadDW(addr, value, res) \ -+#define _LoadDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -@@ -667,15 +717,17 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t8b, 11b\n\t" \ - ".previous" \ - : "=&r" (value), "=r" (res) \ -- : "r" (addr), "i" (-EFAULT)); -+ : "r" (addr), "i" (-EFAULT)); \ -+} while(0) - #endif /* CONFIG_CPU_MIPSR6 */ - --#define StoreHW(addr, value, res) \ -+#define _StoreHW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tnoat\n" \ -- "1:\t"user_sb("%1", "0(%2)")"\n" \ -+ "1:\t"type##_sb("%1", "0(%2)")"\n" \ - "srl\t$1,%1, 0x8\n" \ -- "2:\t"user_sb("$1", "1(%2)")"\n" \ -+ "2:\t"type##_sb("$1", "1(%2)")"\n" \ - ".set\tat\n\t" \ - "li\t%0, 0\n" \ - "3:\n\t" \ -@@ -689,12 +741,15 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT));\ -+} while(0) -+ - #ifndef CONFIG_CPU_MIPSR6 --#define StoreW(addr, value, res) \ -+#define _StoreW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ -- "1:\t"user_swl("%1", "3(%2)")"\n" \ -- "2:\t"user_swr("%1", "(%2)")"\n\t" \ -+ "1:\t"type##_swl("%1", "3(%2)")"\n" \ -+ "2:\t"type##_swr("%1", "(%2)")"\n\t"\ - "li\t%0, 0\n" \ - "3:\n\t" \ - ".insn\n\t" \ -@@ -707,9 +762,11 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT)); \ -+} while(0) - --#define StoreDW(addr, value, res) \ -+#define _StoreDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - "1:\tsdl\t%1, 7(%2)\n" \ - "2:\tsdr\t%1, (%2)\n\t" \ -@@ -725,20 +782,23 @@ extern void show_registers(struct pt_regs *regs); - STR(PTR)"\t2b, 4b\n\t" \ - ".previous" \ - : "=r" (res) \ -- : "r" (value), "r" (addr), "i" (-EFAULT)); -+ : "r" (value), "r" (addr), "i" (-EFAULT)); \ -+} while(0) -+ - #else - /* MIPSR6 has no swl and sdl instructions */ --#define StoreW(addr, value, res) \ -+#define _StoreW(addr, value, res, type) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -- "1:"user_sb("%1", "0(%2)")"\n\t" \ -+ "1:"type##_sb("%1", "0(%2)")"\n\t" \ - "srl\t$1, %1, 0x8\n\t" \ -- "2:"user_sb("$1", "1(%2)")"\n\t" \ -+ "2:"type##_sb("$1", "1(%2)")"\n\t" \ - "srl\t$1, $1, 0x8\n\t" \ -- "3:"user_sb("$1", "2(%2)")"\n\t" \ -+ "3:"type##_sb("$1", "2(%2)")"\n\t" \ - "srl\t$1, $1, 0x8\n\t" \ -- "4:"user_sb("$1", "3(%2)")"\n\t" \ -+ "4:"type##_sb("$1", "3(%2)")"\n\t" \ - ".set\tpop\n\t" \ - "li\t%0, 0\n" \ - "10:\n\t" \ -@@ -755,9 +815,11 @@ extern void show_registers(struct pt_regs *regs); - ".previous" \ - : "=&r" (res) \ - : "r" (value), "r" (addr), "i" (-EFAULT) \ -- : "memory"); -+ : "memory"); \ -+} while(0) - --#define StoreDW(addr, value, res) \ -+#define _StoreDW(addr, value, res) \ -+do { \ - __asm__ __volatile__ ( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ -@@ -797,10 +859,28 @@ extern void show_registers(struct pt_regs *regs); - ".previous" \ - : "=&r" (res) \ - : "r" (value), "r" (addr), "i" (-EFAULT) \ -- : "memory"); -+ : "memory"); \ -+} while(0) -+ - #endif /* CONFIG_CPU_MIPSR6 */ - #endif - -+#define LoadHWU(addr, value, res) _LoadHWU(addr, value, res, kernel) -+#define LoadHWUE(addr, value, res) _LoadHWU(addr, value, res, user) -+#define LoadWU(addr, value, res) _LoadWU(addr, value, res, kernel) -+#define LoadWUE(addr, value, res) _LoadWU(addr, value, res, user) -+#define LoadHW(addr, value, res) _LoadHW(addr, value, res, kernel) -+#define LoadHWE(addr, value, res) _LoadHW(addr, value, res, user) -+#define LoadW(addr, value, res) _LoadW(addr, value, res, kernel) -+#define LoadWE(addr, value, res) _LoadW(addr, value, res, user) -+#define LoadDW(addr, value, res) _LoadDW(addr, value, res) -+ -+#define StoreHW(addr, value, res) _StoreHW(addr, value, res, kernel) -+#define StoreHWE(addr, value, res) _StoreHW(addr, value, res, user) -+#define StoreW(addr, value, res) _StoreW(addr, value, res, kernel) -+#define StoreWE(addr, value, res) _StoreW(addr, value, res, user) -+#define StoreDW(addr, value, res) _StoreDW(addr, value, res) -+ - static void emulate_load_store_insn(struct pt_regs *regs, - void __user *addr, unsigned int __user *pc) - { -@@ -872,7 +952,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, - set_fs(seg); - goto sigbus; - } -- LoadHW(addr, value, res); -+ LoadHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; -@@ -885,7 +965,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, - set_fs(seg); - goto sigbus; - } -- LoadW(addr, value, res); -+ LoadWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; -@@ -898,7 +978,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, - set_fs(seg); - goto sigbus; - } -- LoadHWU(addr, value, res); -+ LoadHWUE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; -@@ -913,7 +993,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; -- StoreHW(addr, value, res); -+ StoreHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; -@@ -926,7 +1006,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; -- StoreW(addr, value, res); -+ StoreWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; -@@ -943,7 +1023,15 @@ static void emulate_load_store_insn(struct pt_regs *regs, - if (!access_ok(VERIFY_READ, addr, 2)) - goto sigbus; - -- LoadHW(addr, value, res); -+ if (config_enabled(CONFIG_EVA)) { -+ if (segment_eq(get_fs(), get_ds())) -+ LoadHW(addr, value, res); -+ else -+ LoadHWE(addr, value, res); -+ } else { -+ LoadHW(addr, value, res); -+ } -+ - if (res) - goto fault; - compute_return_epc(regs); -@@ -954,7 +1042,15 @@ static void emulate_load_store_insn(struct pt_regs *regs, - if (!access_ok(VERIFY_READ, addr, 4)) - goto sigbus; - -- LoadW(addr, value, res); -+ if (config_enabled(CONFIG_EVA)) { -+ if (segment_eq(get_fs(), get_ds())) -+ LoadW(addr, value, res); -+ else -+ LoadWE(addr, value, res); -+ } else { -+ LoadW(addr, value, res); -+ } -+ - if (res) - goto fault; - compute_return_epc(regs); -@@ -965,7 +1061,15 @@ static void emulate_load_store_insn(struct pt_regs *regs, - if (!access_ok(VERIFY_READ, addr, 2)) - goto sigbus; - -- LoadHWU(addr, value, res); -+ if (config_enabled(CONFIG_EVA)) { -+ if (segment_eq(get_fs(), get_ds())) -+ LoadHWU(addr, value, res); -+ else -+ LoadHWUE(addr, value, res); -+ } else { -+ LoadHWU(addr, value, res); -+ } -+ - if (res) - goto fault; - compute_return_epc(regs); -@@ -1024,7 +1128,16 @@ static void emulate_load_store_insn(struct pt_regs *regs, - - compute_return_epc(regs); - value = regs->regs[insn.i_format.rt]; -- StoreHW(addr, value, res); -+ -+ if (config_enabled(CONFIG_EVA)) { -+ if (segment_eq(get_fs(), get_ds())) -+ StoreHW(addr, value, res); -+ else -+ StoreHWE(addr, value, res); -+ } else { -+ StoreHW(addr, value, res); -+ } -+ - if (res) - goto fault; - break; -@@ -1035,7 +1148,16 @@ static void emulate_load_store_insn(struct pt_regs *regs, - - compute_return_epc(regs); - value = regs->regs[insn.i_format.rt]; -- StoreW(addr, value, res); -+ -+ if (config_enabled(CONFIG_EVA)) { -+ if (segment_eq(get_fs(), get_ds())) -+ StoreW(addr, value, res); -+ else -+ StoreWE(addr, value, res); -+ } else { -+ StoreW(addr, value, res); -+ } -+ - if (res) - goto fault; - break; -diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c -index fb3e8df..838d3a6 100644 ---- a/arch/mips/kvm/emulate.c -+++ b/arch/mips/kvm/emulate.c -@@ -2176,6 +2176,7 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause, - case T_SYSCALL: - case T_BREAK: - case T_RES_INST: -+ case T_MSADIS: - break; - - case T_COP_UNUSABLE: -diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c -index c9eccf5..f5e7dda 100644 ---- a/arch/mips/kvm/mips.c -+++ b/arch/mips/kvm/mips.c -@@ -1119,6 +1119,10 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) - ret = kvm_mips_callbacks->handle_break(vcpu); - break; - -+ case T_MSADIS: -+ ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); -+ break; -+ - default: - kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", - exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, -diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c -index fd7257b..4372cc8 100644 ---- a/arch/mips/kvm/trap_emul.c -+++ b/arch/mips/kvm/trap_emul.c -@@ -330,6 +330,33 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu) - return ret; - } - -+static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) -+{ -+ struct kvm_run *run = vcpu->run; -+ uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; -+ unsigned long cause = vcpu->arch.host_cp0_cause; -+ enum emulation_result er = EMULATE_DONE; -+ int ret = RESUME_GUEST; -+ -+ /* No MSA supported in guest, guest reserved instruction exception */ -+ er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); -+ -+ switch (er) { -+ case EMULATE_DONE: -+ ret = RESUME_GUEST; -+ break; -+ -+ case EMULATE_FAIL: -+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR; -+ ret = RESUME_HOST; -+ break; -+ -+ default: -+ BUG(); -+ } -+ return ret; -+} -+ - static int kvm_trap_emul_vm_init(struct kvm *kvm) - { - return 0; -@@ -470,6 +497,7 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { - .handle_syscall = kvm_trap_emul_handle_syscall, - .handle_res_inst = kvm_trap_emul_handle_res_inst, - .handle_break = kvm_trap_emul_handle_break, -+ .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, - - .vm_init = kvm_trap_emul_vm_init, - .vcpu_init = kvm_trap_emul_vcpu_init, -diff --git a/arch/mips/loongson/loongson-3/irq.c b/arch/mips/loongson/loongson-3/irq.c -index 21221ed..0f75b6b 100644 ---- a/arch/mips/loongson/loongson-3/irq.c -+++ b/arch/mips/loongson/loongson-3/irq.c -@@ -44,6 +44,7 @@ void mach_irq_dispatch(unsigned int pending) - - static struct irqaction cascade_irqaction = { - .handler = no_action, -+ .flags = IRQF_NO_SUSPEND, - .name = "cascade", - }; - -diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c -index 8fddd2cd..efe366d 100644 ---- a/arch/mips/mti-malta/malta-memory.c -+++ b/arch/mips/mti-malta/malta-memory.c -@@ -53,6 +53,12 @@ fw_memblock_t * __init fw_getmdesc(int eva) - pr_warn("memsize not set in YAMON, set to default (32Mb)\n"); - physical_memsize = 0x02000000; - } else { -+ if (memsize > (256 << 20)) { /* memsize should be capped to 256M */ -+ pr_warn("Unsupported memsize value (0x%lx) detected! " -+ "Using 0x10000000 (256M) instead\n", -+ memsize); -+ memsize = 256 << 20; -+ } - /* If ememsize is set, then set physical_memsize to that */ - physical_memsize = ememsize ? : memsize; - } -diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S -index 32a7c82..e7567c8 100644 ---- a/arch/mips/power/hibernate.S -+++ b/arch/mips/power/hibernate.S -@@ -30,6 +30,8 @@ LEAF(swsusp_arch_suspend) - END(swsusp_arch_suspend) - - LEAF(swsusp_arch_resume) -+ /* Avoid TLB mismatch during and after kernel resume */ -+ jal local_flush_tlb_all - PTR_L t0, restore_pblist - 0: - PTR_L t1, PBE_ADDRESS(t0) /* source */ -@@ -43,7 +45,6 @@ LEAF(swsusp_arch_resume) - bne t1, t3, 1b - PTR_L t0, PBE_NEXT(t0) - bnez t0, 0b -- jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */ - PTR_LA t0, saved_regs - PTR_L ra, PT_R31(t0) - PTR_L sp, PT_R29(t0) -diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c -index ae77b7e..c641983 100644 ---- a/arch/powerpc/kernel/cacheinfo.c -+++ b/arch/powerpc/kernel/cacheinfo.c -@@ -61,12 +61,22 @@ struct cache_type_info { - }; - - /* These are used to index the cache_type_info array. */ --#define CACHE_TYPE_UNIFIED 0 --#define CACHE_TYPE_INSTRUCTION 1 --#define CACHE_TYPE_DATA 2 -+#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */ -+#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */ -+#define CACHE_TYPE_INSTRUCTION 2 -+#define CACHE_TYPE_DATA 3 - - static const struct cache_type_info cache_type_info[] = { - { -+ /* Embedded systems that use cache-size, cache-block-size, -+ * etc. for the Unified (typically L2) cache. */ -+ .name = "Unified", -+ .size_prop = "cache-size", -+ .line_size_props = { "cache-line-size", -+ "cache-block-size", }, -+ .nr_sets_prop = "cache-sets", -+ }, -+ { - /* PowerPC Processor binding says the [di]-cache-* - * must be equal on unified caches, so just use - * d-cache properties. */ -@@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache) - { - struct cache *iter; - -- if (cache->type == CACHE_TYPE_UNIFIED) -+ if (cache->type == CACHE_TYPE_UNIFIED || -+ cache->type == CACHE_TYPE_UNIFIED_D) - return cache; - - list_for_each_entry(iter, &cache_list, list) -@@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np) - return of_get_property(np, "cache-unified", NULL); - } - --static struct cache *cache_do_one_devnode_unified(struct device_node *node, -- int level) -+/* -+ * Unified caches can have two different sets of tags. Most embedded -+ * use cache-size, etc. for the unified cache size, but open firmware systems -+ * use d-cache-size, etc. Check on initialization for which type we have, and -+ * return the appropriate structure type. Assume it's embedded if it isn't -+ * open firmware. If it's yet a 3rd type, then there will be missing entries -+ * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need -+ * to be extended further. -+ */ -+static int cache_is_unified_d(const struct device_node *np) - { -- struct cache *cache; -+ return of_get_property(np, -+ cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ? -+ CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED; -+} - -+/* -+ */ -+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) -+{ - pr_debug("creating L%d ucache for %s\n", level, node->full_name); - -- cache = new_cache(CACHE_TYPE_UNIFIED, level, node); -- -- return cache; -+ return new_cache(cache_is_unified_d(node), level, node); - } - - static struct cache *cache_do_one_devnode_split(struct device_node *node, -diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c -index 7e408bf..cecbe00 100644 ---- a/arch/powerpc/mm/hugetlbpage.c -+++ b/arch/powerpc/mm/hugetlbpage.c -@@ -581,6 +581,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, - pmd = pmd_offset(pud, start); - pud_clear(pud); - pmd_free_tlb(tlb, pmd, start); -+ mm_dec_nr_pmds(tlb->mm); - } - - static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, -diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c -index 2396dda..ead5535 100644 ---- a/arch/powerpc/perf/callchain.c -+++ b/arch/powerpc/perf/callchain.c -@@ -243,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, - sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); - -- for (;;) { -+ while (entry->nr < PERF_MAX_STACK_DEPTH) { - fp = (unsigned long __user *) sp; - if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp)) - return; -diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c -index 4c11421..3af8324 100644 ---- a/arch/powerpc/platforms/cell/interrupt.c -+++ b/arch/powerpc/platforms/cell/interrupt.c -@@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) - - void iic_setup_cpu(void) - { -- out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff); -+ out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff); - } - - u8 iic_get_target_id(int cpu) -diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c -index c7c8720..63db1b0 100644 ---- a/arch/powerpc/platforms/cell/iommu.c -+++ b/arch/powerpc/platforms/cell/iommu.c -@@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, - - io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - -- for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) -+ for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift)) - io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); - - mb(); -diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c -index 6c9ff2b..1d9369e 100644 ---- a/arch/powerpc/platforms/powernv/pci-ioda.c -+++ b/arch/powerpc/platforms/powernv/pci-ioda.c -@@ -1777,7 +1777,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, - region.start += phb->ioda.io_segsize; - index++; - } -- } else if (res->flags & IORESOURCE_MEM) { -+ } else if ((res->flags & IORESOURCE_MEM) && -+ !pnv_pci_is_mem_pref_64(res->flags)) { - region.start = res->start - - hose->mem_offset[0] - - phb->ioda.m32_pci_base; -diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c -index 1c4c5ac..d3236c9 100644 ---- a/arch/s390/kernel/suspend.c -+++ b/arch/s390/kernel/suspend.c -@@ -138,6 +138,8 @@ int pfn_is_nosave(unsigned long pfn) - { - unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); - unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); -+ unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1; -+ unsigned long stext_pfn = PFN_DOWN(__pa(&_stext)); - - /* Always save lowcore pages (LC protection might be enabled). */ - if (pfn <= LC_PAGES) -@@ -145,6 +147,8 @@ int pfn_is_nosave(unsigned long pfn) - if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) - return 1; - /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ -+ if (pfn >= stext_pfn && pfn <= eshared_pfn) -+ return ipl_info.type == IPL_TYPE_NSS ? 1 : 0; - if (tprot(PFN_PHYS(pfn))) - return 1; - return 0; -diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c -index 073b5f3..e7bc2fd 100644 ---- a/arch/s390/kvm/interrupt.c -+++ b/arch/s390/kvm/interrupt.c -@@ -17,6 +17,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -1332,10 +1333,10 @@ int kvm_s390_inject_vm(struct kvm *kvm, - return rc; - } - --void kvm_s390_reinject_io_int(struct kvm *kvm, -+int kvm_s390_reinject_io_int(struct kvm *kvm, - struct kvm_s390_interrupt_info *inti) - { -- __inject_vm(kvm, inti); -+ return __inject_vm(kvm, inti); - } - - int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, -@@ -1455,61 +1456,66 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) - spin_unlock(&fi->lock); - } - --static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti, -- u8 *addr) -+static void inti_to_irq(struct kvm_s390_interrupt_info *inti, -+ struct kvm_s390_irq *irq) - { -- struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; -- struct kvm_s390_irq irq = {0}; -- -- irq.type = inti->type; -+ irq->type = inti->type; - switch (inti->type) { - case KVM_S390_INT_PFAULT_INIT: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - case KVM_S390_INT_SERVICE: -- irq.u.ext = inti->ext; -+ irq->u.ext = inti->ext; - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: -- irq.u.io = inti->io; -+ irq->u.io = inti->io; - break; - case KVM_S390_MCHK: -- irq.u.mchk = inti->mchk; -+ irq->u.mchk = inti->mchk; - break; -- default: -- return -EINVAL; - } -- -- if (copy_to_user(uptr, &irq, sizeof(irq))) -- return -EFAULT; -- -- return 0; - } - --static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len) -+static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) - { - struct kvm_s390_interrupt_info *inti; - struct kvm_s390_float_interrupt *fi; -+ struct kvm_s390_irq *buf; -+ int max_irqs; - int ret = 0; - int n = 0; - -+ if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) -+ return -EINVAL; -+ -+ /* -+ * We are already using -ENOMEM to signal -+ * userspace it may retry with a bigger buffer, -+ * so we need to use something else for this case -+ */ -+ buf = vzalloc(len); -+ if (!buf) -+ return -ENOBUFS; -+ -+ max_irqs = len / sizeof(struct kvm_s390_irq); -+ - fi = &kvm->arch.float_int; - spin_lock(&fi->lock); -- - list_for_each_entry(inti, &fi->list, list) { -- if (len < sizeof(struct kvm_s390_irq)) { -+ if (n == max_irqs) { - /* signal userspace to try again */ - ret = -ENOMEM; - break; - } -- ret = copy_irq_to_user(inti, buf); -- if (ret) -- break; -- buf += sizeof(struct kvm_s390_irq); -- len -= sizeof(struct kvm_s390_irq); -+ inti_to_irq(inti, &buf[n]); - n++; - } -- - spin_unlock(&fi->lock); -+ if (!ret && n > 0) { -+ if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) -+ ret = -EFAULT; -+ } -+ vfree(buf); - - return ret < 0 ? ret : n; - } -@@ -1520,7 +1526,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) - - switch (attr->group) { - case KVM_DEV_FLIC_GET_ALL_IRQS: -- r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr, -+ r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, - attr->attr); - break; - default: -diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h -index c34109a..6995a30 100644 ---- a/arch/s390/kvm/kvm-s390.h -+++ b/arch/s390/kvm/kvm-s390.h -@@ -151,8 +151,8 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, - int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); - struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid); --void kvm_s390_reinject_io_int(struct kvm *kvm, -- struct kvm_s390_interrupt_info *inti); -+int kvm_s390_reinject_io_int(struct kvm *kvm, -+ struct kvm_s390_interrupt_info *inti); - int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); - - /* implemented in intercept.c */ -diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c -index 3511169..b982fbc 100644 ---- a/arch/s390/kvm/priv.c -+++ b/arch/s390/kvm/priv.c -@@ -229,18 +229,19 @@ static int handle_tpi(struct kvm_vcpu *vcpu) - struct kvm_s390_interrupt_info *inti; - unsigned long len; - u32 tpi_data[3]; -- int cc, rc; -+ int rc; - u64 addr; - -- rc = 0; - addr = kvm_s390_get_base_disp_s(vcpu); - if (addr & 3) - return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); -- cc = 0; -+ - inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); -- if (!inti) -- goto no_interrupt; -- cc = 1; -+ if (!inti) { -+ kvm_s390_set_psw_cc(vcpu, 0); -+ return 0; -+ } -+ - tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; - tpi_data[1] = inti->io.io_int_parm; - tpi_data[2] = inti->io.io_int_word; -@@ -251,30 +252,38 @@ static int handle_tpi(struct kvm_vcpu *vcpu) - */ - len = sizeof(tpi_data) - 4; - rc = write_guest(vcpu, addr, &tpi_data, len); -- if (rc) -- return kvm_s390_inject_prog_cond(vcpu, rc); -+ if (rc) { -+ rc = kvm_s390_inject_prog_cond(vcpu, rc); -+ goto reinject_interrupt; -+ } - } else { - /* - * Store the three-word I/O interruption code into - * the appropriate lowcore area. - */ - len = sizeof(tpi_data); -- if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) -+ if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { -+ /* failed writes to the low core are not recoverable */ - rc = -EFAULT; -+ goto reinject_interrupt; -+ } - } -+ -+ /* irq was successfully handed to the guest */ -+ kfree(inti); -+ kvm_s390_set_psw_cc(vcpu, 1); -+ return 0; -+reinject_interrupt: - /* - * If we encounter a problem storing the interruption code, the - * instruction is suppressed from the guest's view: reinject the - * interrupt. - */ -- if (!rc) -+ if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { - kfree(inti); -- else -- kvm_s390_reinject_io_int(vcpu->kvm, inti); --no_interrupt: -- /* Set condition code and we're done. */ -- if (!rc) -- kvm_s390_set_psw_cc(vcpu, cc); -+ rc = -EFAULT; -+ } -+ /* don't set the cc, a pgm irq was injected or we drop to user space */ - return rc ? -EFAULT : 0; - } - -@@ -467,6 +476,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) - for (n = mem->count - 1; n > 0 ; n--) - memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); - -+ memset(&mem->vm[0], 0, sizeof(mem->vm[0])); - mem->vm[0].cpus_total = cpus; - mem->vm[0].cpus_configured = cpus; - mem->vm[0].cpus_standby = 0; -diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h -index 47f29b1..e7814b7 100644 ---- a/arch/x86/include/asm/insn.h -+++ b/arch/x86/include/asm/insn.h -@@ -69,7 +69,7 @@ struct insn { - const insn_byte_t *next_byte; - }; - --#define MAX_INSN_SIZE 16 -+#define MAX_INSN_SIZE 15 - - #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) - #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) -diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h -index a1410db..653dfa7 100644 ---- a/arch/x86/include/asm/mwait.h -+++ b/arch/x86/include/asm/mwait.h -@@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) - :: "a" (eax), "c" (ecx)); - } - -+static inline void __sti_mwait(unsigned long eax, unsigned long ecx) -+{ -+ trace_hardirqs_on(); -+ /* "mwait %eax, %ecx;" */ -+ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" -+ :: "a" (eax), "c" (ecx)); -+} -+ - /* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. -diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h -index d6b078e..25b1cc0 100644 ---- a/arch/x86/include/asm/pvclock.h -+++ b/arch/x86/include/asm/pvclock.h -@@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, - - struct pvclock_vsyscall_time_info { - struct pvclock_vcpu_time_info pvti; -+ u32 migrate_count; - } __attribute__((__aligned__(SMP_CACHE_BYTES))); - - #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c -index 0739833..666bcf1 100644 ---- a/arch/x86/kernel/cpu/perf_event_intel_ds.c -+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c -@@ -557,6 +557,8 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ -+ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ -+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), - EVENT_CONSTRAINT_END - }; - -@@ -564,6 +566,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ - INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ -+ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ -+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), - EVENT_CONSTRAINT_END - }; - -@@ -587,6 +591,8 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ -+ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ -+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), - EVENT_CONSTRAINT_END - }; - -@@ -602,6 +608,8 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ -+ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ -+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), - EVENT_CONSTRAINT_END - }; - -diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c -index 046e2d6..a388bb8 100644 ---- a/arch/x86/kernel/process.c -+++ b/arch/x86/kernel/process.c -@@ -24,6 +24,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -399,6 +400,53 @@ static void amd_e400_idle(void) - default_idle(); - } - -+/* -+ * Intel Core2 and older machines prefer MWAIT over HALT for C1. -+ * We can't rely on cpuidle installing MWAIT, because it will not load -+ * on systems that support only C1 -- so the boot default must be MWAIT. -+ * -+ * Some AMD machines are the opposite, they depend on using HALT. -+ * -+ * So for default C1, which is used during boot until cpuidle loads, -+ * use MWAIT-C1 on Intel HW that has it, else use HALT. -+ */ -+static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) -+{ -+ if (c->x86_vendor != X86_VENDOR_INTEL) -+ return 0; -+ -+ if (!cpu_has(c, X86_FEATURE_MWAIT)) -+ return 0; -+ -+ return 1; -+} -+ -+/* -+ * MONITOR/MWAIT with no hints, used for default default C1 state. -+ * This invokes MWAIT with interrutps enabled and no flags, -+ * which is backwards compatible with the original MWAIT implementation. -+ */ -+ -+static void mwait_idle(void) -+{ -+ if (!current_set_polling_and_test()) { -+ if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { -+ smp_mb(); /* quirk */ -+ clflush((void *)¤t_thread_info()->flags); -+ smp_mb(); /* quirk */ -+ } -+ -+ __monitor((void *)¤t_thread_info()->flags, 0, 0); -+ if (!need_resched()) -+ __sti_mwait(0, 0); -+ else -+ local_irq_enable(); -+ } else { -+ local_irq_enable(); -+ } -+ __current_clr_polling(); -+} -+ - void select_idle_routine(const struct cpuinfo_x86 *c) - { - #ifdef CONFIG_SMP -@@ -412,6 +460,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) - /* E400: APIC timer interrupt does not wake up CPU from C1e */ - pr_info("using AMD E400 aware idle routine\n"); - x86_idle = amd_e400_idle; -+ } else if (prefer_mwait_c1_over_halt(c)) { -+ pr_info("using mwait in idle threads\n"); -+ x86_idle = mwait_idle; - } else - x86_idle = default_idle; - } -diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c -index 2f355d2..e5ecd20 100644 ---- a/arch/x86/kernel/pvclock.c -+++ b/arch/x86/kernel/pvclock.c -@@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, - set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); - } - -+static struct pvclock_vsyscall_time_info *pvclock_vdso_info; -+ -+static struct pvclock_vsyscall_time_info * -+pvclock_get_vsyscall_user_time_info(int cpu) -+{ -+ if (!pvclock_vdso_info) { -+ BUG(); -+ return NULL; -+ } -+ -+ return &pvclock_vdso_info[cpu]; -+} -+ -+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -+{ -+ return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -+} -+ - #ifdef CONFIG_X86_64 -+static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, -+ void *v) -+{ -+ struct task_migration_notifier *mn = v; -+ struct pvclock_vsyscall_time_info *pvti; -+ -+ pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); -+ -+ /* this is NULL when pvclock vsyscall is not initialized */ -+ if (unlikely(pvti == NULL)) -+ return NOTIFY_DONE; -+ -+ pvti->migrate_count++; -+ -+ return NOTIFY_DONE; -+} -+ -+static struct notifier_block pvclock_migrate = { -+ .notifier_call = pvclock_task_migrate, -+}; -+ - /* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a -@@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - -+ pvclock_vdso_info = i; -+ - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { - __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, - __pa(i) + (idx*PAGE_SIZE), - PAGE_KERNEL_VVAR); - } - -+ -+ register_task_migration_notifier(&pvclock_migrate); -+ - return 0; - } - #endif -diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c -index ae4f6d3..a60bd3a 100644 ---- a/arch/x86/kvm/vmx.c -+++ b/arch/x86/kvm/vmx.c -@@ -3621,8 +3621,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) - - static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) - { -- unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ? -- KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); -+ /* -+ * Pass through host's Machine Check Enable value to hw_cr4, which -+ * is in force while we are in guest mode. Do not let guests control -+ * this bit, even if host CR4.MCE == 0. -+ */ -+ unsigned long hw_cr4 = -+ (cr4_read_shadow() & X86_CR4_MCE) | -+ (cr4 & ~X86_CR4_MCE) | -+ (to_vmx(vcpu)->rmode.vm86_active ? -+ KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); - - if (cr4 & X86_CR4_VMXE) { - /* -diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c -index 32bf19e..e222ba5 100644 ---- a/arch/x86/kvm/x86.c -+++ b/arch/x86/kvm/x86.c -@@ -5775,7 +5775,6 @@ int kvm_arch_init(void *opaque) - kvm_set_mmio_spte_mask(); - - kvm_x86_ops = ops; -- kvm_init_msr_list(); - - kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, - PT_DIRTY_MASK, PT64_NX_MASK, 0); -@@ -7209,7 +7208,14 @@ void kvm_arch_hardware_disable(void) - - int kvm_arch_hardware_setup(void) - { -- return kvm_x86_ops->hardware_setup(); -+ int r; -+ -+ r = kvm_x86_ops->hardware_setup(); -+ if (r != 0) -+ return r; -+ -+ kvm_init_msr_list(); -+ return 0; - } - - void kvm_arch_hardware_unsetup(void) -diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c -index 1313ae6..85994f5 100644 ---- a/arch/x86/lib/insn.c -+++ b/arch/x86/lib/insn.c -@@ -52,6 +52,13 @@ - */ - void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) - { -+ /* -+ * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid -+ * even if the input buffer is long enough to hold them. -+ */ -+ if (buf_len > MAX_INSN_SIZE) -+ buf_len = MAX_INSN_SIZE; -+ - memset(insn, 0, sizeof(*insn)); - insn->kaddr = kaddr; - insn->end_kaddr = kaddr + buf_len; -diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c -index 1f33b3d..0a42327 100644 ---- a/arch/x86/lib/usercopy_64.c -+++ b/arch/x86/lib/usercopy_64.c -@@ -82,7 +82,7 @@ copy_user_handle_tail(char *to, char *from, unsigned len) - clac(); - - /* If the destination is a kernel buffer, we always clear the end */ -- if ((unsigned long)to >= TASK_SIZE_MAX) -+ if (!__addr_ok(to)) - memset(to, 0, len); - return len; - } -diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c -index 9793322..40d2473 100644 ---- a/arch/x86/vdso/vclock_gettime.c -+++ b/arch/x86/vdso/vclock_gettime.c -@@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) - cycle_t ret; - u64 last; - u32 version; -+ u32 migrate_count; - u8 flags; - unsigned cpu, cpu1; - - - /* -- * Note: hypervisor must guarantee that: -- * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. -- * 2. that per-CPU pvclock time info is updated if the -- * underlying CPU changes. -- * 3. that version is increased whenever underlying CPU -- * changes. -- * -+ * When looping to get a consistent (time-info, tsc) pair, we -+ * also need to deal with the possibility we can switch vcpus, -+ * so make sure we always re-fetch time-info for the current vcpu. - */ - do { - cpu = __getcpu() & VGETCPU_CPU_MASK; -@@ -102,20 +99,27 @@ static notrace cycle_t vread_pvclock(int *mode) - * __getcpu() calls (Gleb). - */ - -- pvti = get_pvti(cpu); -+ /* Make sure migrate_count will change if we leave the VCPU. */ -+ do { -+ pvti = get_pvti(cpu); -+ migrate_count = pvti->migrate_count; -+ -+ cpu1 = cpu; -+ cpu = __getcpu() & VGETCPU_CPU_MASK; -+ } while (unlikely(cpu != cpu1)); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. -- * We could have been migrated just after the first -- * vgetcpu but before fetching the version, so we -- * wouldn't notice a version change. -+ * - We must read TSC of pvti's VCPU. -+ * - KVM doesn't follow the versioning protocol, so data could -+ * change before version if we left the VCPU. - */ -- cpu1 = __getcpu() & VGETCPU_CPU_MASK; -- } while (unlikely(cpu != cpu1 || -- (pvti->pvti.version & 1) || -- pvti->pvti.version != version)); -+ smp_rmb(); -+ } while (unlikely((pvti->pvti.version & 1) || -+ pvti->pvti.version != version || -+ pvti->migrate_count != migrate_count)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; -diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig -index e31d494..87be10e 100644 ---- a/arch/xtensa/Kconfig -+++ b/arch/xtensa/Kconfig -@@ -428,6 +428,36 @@ config DEFAULT_MEM_SIZE - - If unsure, leave the default value here. - -+config XTFPGA_LCD -+ bool "Enable XTFPGA LCD driver" -+ depends on XTENSA_PLATFORM_XTFPGA -+ default n -+ help -+ There's a 2x16 LCD on most of XTFPGA boards, kernel may output -+ progress messages there during bootup/shutdown. It may be useful -+ during board bringup. -+ -+ If unsure, say N. -+ -+config XTFPGA_LCD_BASE_ADDR -+ hex "XTFPGA LCD base address" -+ depends on XTFPGA_LCD -+ default "0x0d0c0000" -+ help -+ Base address of the LCD controller inside KIO region. -+ Different boards from XTFPGA family have LCD controller at different -+ addresses. Please consult prototyping user guide for your board for -+ the correct address. Wrong address here may lead to hardware lockup. -+ -+config XTFPGA_LCD_8BIT_ACCESS -+ bool "Use 8-bit access to XTFPGA LCD" -+ depends on XTFPGA_LCD -+ default n -+ help -+ LCD may be connected with 4- or 8-bit interface, 8-bit access may -+ only be used with 8-bit interface. Please consult prototyping user -+ guide for your board for the correct interface width. -+ - endmenu - - menu "Executable file formats" -diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h -index db5bb72..62d8465 100644 ---- a/arch/xtensa/include/uapi/asm/unistd.h -+++ b/arch/xtensa/include/uapi/asm/unistd.h -@@ -715,7 +715,7 @@ __SYSCALL(323, sys_process_vm_writev, 6) - __SYSCALL(324, sys_name_to_handle_at, 5) - #define __NR_open_by_handle_at 325 - __SYSCALL(325, sys_open_by_handle_at, 3) --#define __NR_sync_file_range 326 -+#define __NR_sync_file_range2 326 - __SYSCALL(326, sys_sync_file_range2, 6) - #define __NR_perf_event_open 327 - __SYSCALL(327, sys_perf_event_open, 5) -diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c -index d05f8fe..17b1ef3 100644 ---- a/arch/xtensa/platforms/iss/network.c -+++ b/arch/xtensa/platforms/iss/network.c -@@ -349,8 +349,8 @@ static void iss_net_timer(unsigned long priv) - { - struct iss_net_private *lp = (struct iss_net_private *)priv; - -- spin_lock(&lp->lock); - iss_net_poll(); -+ spin_lock(&lp->lock); - mod_timer(&lp->timer, jiffies + lp->timer_val); - spin_unlock(&lp->lock); - } -@@ -361,7 +361,7 @@ static int iss_net_open(struct net_device *dev) - struct iss_net_private *lp = netdev_priv(dev); - int err; - -- spin_lock(&lp->lock); -+ spin_lock_bh(&lp->lock); - - err = lp->tp.open(lp); - if (err < 0) -@@ -376,9 +376,11 @@ static int iss_net_open(struct net_device *dev) - while ((err = iss_net_rx(dev)) > 0) - ; - -- spin_lock(&opened_lock); -+ spin_unlock_bh(&lp->lock); -+ spin_lock_bh(&opened_lock); - list_add(&lp->opened_list, &opened); -- spin_unlock(&opened_lock); -+ spin_unlock_bh(&opened_lock); -+ spin_lock_bh(&lp->lock); - - init_timer(&lp->timer); - lp->timer_val = ISS_NET_TIMER_VALUE; -@@ -387,7 +389,7 @@ static int iss_net_open(struct net_device *dev) - mod_timer(&lp->timer, jiffies + lp->timer_val); - - out: -- spin_unlock(&lp->lock); -+ spin_unlock_bh(&lp->lock); - return err; - } - -@@ -395,7 +397,7 @@ static int iss_net_close(struct net_device *dev) - { - struct iss_net_private *lp = netdev_priv(dev); - netif_stop_queue(dev); -- spin_lock(&lp->lock); -+ spin_lock_bh(&lp->lock); - - spin_lock(&opened_lock); - list_del(&opened); -@@ -405,18 +407,17 @@ static int iss_net_close(struct net_device *dev) - - lp->tp.close(lp); - -- spin_unlock(&lp->lock); -+ spin_unlock_bh(&lp->lock); - return 0; - } - - static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) - { - struct iss_net_private *lp = netdev_priv(dev); -- unsigned long flags; - int len; - - netif_stop_queue(dev); -- spin_lock_irqsave(&lp->lock, flags); -+ spin_lock_bh(&lp->lock); - - len = lp->tp.write(lp, &skb); - -@@ -438,7 +439,7 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev) - pr_err("%s: %s failed(%d)\n", dev->name, __func__, len); - } - -- spin_unlock_irqrestore(&lp->lock, flags); -+ spin_unlock_bh(&lp->lock); - - dev_kfree_skb(skb); - return NETDEV_TX_OK; -@@ -466,9 +467,9 @@ static int iss_net_set_mac(struct net_device *dev, void *addr) - - if (!is_valid_ether_addr(hwaddr->sa_data)) - return -EADDRNOTAVAIL; -- spin_lock(&lp->lock); -+ spin_lock_bh(&lp->lock); - memcpy(dev->dev_addr, hwaddr->sa_data, ETH_ALEN); -- spin_unlock(&lp->lock); -+ spin_unlock_bh(&lp->lock); - return 0; - } - -@@ -520,11 +521,11 @@ static int iss_net_configure(int index, char *init) - *lp = (struct iss_net_private) { - .device_list = LIST_HEAD_INIT(lp->device_list), - .opened_list = LIST_HEAD_INIT(lp->opened_list), -- .lock = __SPIN_LOCK_UNLOCKED(lp.lock), - .dev = dev, - .index = index, -- }; -+ }; - -+ spin_lock_init(&lp->lock); - /* - * If this name ends up conflicting with an existing registered - * netdevice, that is OK, register_netdev{,ice}() will notice this -diff --git a/arch/xtensa/platforms/xtfpga/Makefile b/arch/xtensa/platforms/xtfpga/Makefile -index b9ae206..7839d38 100644 ---- a/arch/xtensa/platforms/xtfpga/Makefile -+++ b/arch/xtensa/platforms/xtfpga/Makefile -@@ -6,4 +6,5 @@ - # - # Note 2! The CFLAGS definitions are in the main makefile... - --obj-y = setup.o lcd.o -+obj-y += setup.o -+obj-$(CONFIG_XTFPGA_LCD) += lcd.o -diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h -index 6edd20b..4e0af26 100644 ---- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h -+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h -@@ -40,9 +40,6 @@ - - /* UART */ - #define DUART16552_PADDR (XCHAL_KIO_PADDR + 0x0D050020) --/* LCD instruction and data addresses. */ --#define LCD_INSTR_ADDR ((char *)IOADDR(0x0D040000)) --#define LCD_DATA_ADDR ((char *)IOADDR(0x0D040004)) - - /* Misc. */ - #define XTFPGA_FPGAREGS_VADDR IOADDR(0x0D020000) -diff --git a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h -index 0e43564..4c8541e 100644 ---- a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h -+++ b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h -@@ -11,10 +11,25 @@ - #ifndef __XTENSA_XTAVNET_LCD_H - #define __XTENSA_XTAVNET_LCD_H - -+#ifdef CONFIG_XTFPGA_LCD - /* Display string STR at position POS on the LCD. */ - void lcd_disp_at_pos(char *str, unsigned char pos); - - /* Shift the contents of the LCD display left or right. */ - void lcd_shiftleft(void); - void lcd_shiftright(void); -+#else -+static inline void lcd_disp_at_pos(char *str, unsigned char pos) -+{ -+} -+ -+static inline void lcd_shiftleft(void) -+{ -+} -+ -+static inline void lcd_shiftright(void) -+{ -+} -+#endif -+ - #endif -diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c -index 2872301..4dc0c1b 100644 ---- a/arch/xtensa/platforms/xtfpga/lcd.c -+++ b/arch/xtensa/platforms/xtfpga/lcd.c -@@ -1,50 +1,63 @@ - /* -- * Driver for the LCD display on the Tensilica LX60 Board. -+ * Driver for the LCD display on the Tensilica XTFPGA board family. -+ * http://www.mytechcorp.com/cfdata/productFile/File1/MOC-16216B-B-A0A04.pdf - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001, 2006 Tensilica Inc. -+ * Copyright (C) 2015 Cadence Design Systems Inc. - */ - --/* -- * -- * FIXME: this code is from the examples from the LX60 user guide. -- * -- * The lcd_pause function does busy waiting, which is probably not -- * great. Maybe the code could be changed to use kernel timers, or -- * change the hardware to not need to wait. -- */ -- -+#include - #include - #include - - #include - #include --#include - --#define LCD_PAUSE_ITERATIONS 4000 -+/* LCD instruction and data addresses. */ -+#define LCD_INSTR_ADDR ((char *)IOADDR(CONFIG_XTFPGA_LCD_BASE_ADDR)) -+#define LCD_DATA_ADDR (LCD_INSTR_ADDR + 4) -+ - #define LCD_CLEAR 0x1 - #define LCD_DISPLAY_ON 0xc - - /* 8bit and 2 lines display */ - #define LCD_DISPLAY_MODE8BIT 0x38 -+#define LCD_DISPLAY_MODE4BIT 0x28 - #define LCD_DISPLAY_POS 0x80 - #define LCD_SHIFT_LEFT 0x18 - #define LCD_SHIFT_RIGHT 0x1c - -+static void lcd_put_byte(u8 *addr, u8 data) -+{ -+#ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS -+ ACCESS_ONCE(*addr) = data; -+#else -+ ACCESS_ONCE(*addr) = data & 0xf0; -+ ACCESS_ONCE(*addr) = (data << 4) & 0xf0; -+#endif -+} -+ - static int __init lcd_init(void) - { -- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; -+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; - mdelay(5); -- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; -+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; - udelay(200); -- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT; -+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT; -+ udelay(50); -+#ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS -+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT; -+ udelay(50); -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT); - udelay(50); -- *LCD_INSTR_ADDR = LCD_DISPLAY_ON; -+#endif -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_ON); - udelay(50); -- *LCD_INSTR_ADDR = LCD_CLEAR; -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_CLEAR); - mdelay(10); - lcd_disp_at_pos("XTENSA LINUX", 0); - return 0; -@@ -52,10 +65,10 @@ static int __init lcd_init(void) - - void lcd_disp_at_pos(char *str, unsigned char pos) - { -- *LCD_INSTR_ADDR = LCD_DISPLAY_POS | pos; -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_POS | pos); - udelay(100); - while (*str != 0) { -- *LCD_DATA_ADDR = *str; -+ lcd_put_byte(LCD_DATA_ADDR, *str); - udelay(200); - str++; - } -@@ -63,13 +76,13 @@ void lcd_disp_at_pos(char *str, unsigned char pos) - - void lcd_shiftleft(void) - { -- *LCD_INSTR_ADDR = LCD_SHIFT_LEFT; -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_LEFT); - udelay(50); - } - - void lcd_shiftright(void) - { -- *LCD_INSTR_ADDR = LCD_SHIFT_RIGHT; -+ lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_RIGHT); - udelay(50); - } - -diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c -index 5ed064e..ccf7932 100644 ---- a/drivers/acpi/acpica/evgpe.c -+++ b/drivers/acpi/acpica/evgpe.c -@@ -92,6 +92,7 @@ acpi_ev_update_gpe_enable_mask(struct acpi_gpe_event_info *gpe_event_info) - ACPI_SET_BIT(gpe_register_info->enable_for_run, - (u8)register_bit); - } -+ gpe_register_info->enable_mask = gpe_register_info->enable_for_run; - - return_ACPI_STATUS(AE_OK); - } -@@ -123,7 +124,7 @@ acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info) - - /* Enable the requested GPE */ - -- status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE_SAVE); -+ status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE); - return_ACPI_STATUS(status); - } - -@@ -202,7 +203,7 @@ acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info) - if (ACPI_SUCCESS(status)) { - status = - acpi_hw_low_set_gpe(gpe_event_info, -- ACPI_GPE_DISABLE_SAVE); -+ ACPI_GPE_DISABLE); - } - - if (ACPI_FAILURE(status)) { -diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c -index 84bc550..af6514e 100644 ---- a/drivers/acpi/acpica/hwgpe.c -+++ b/drivers/acpi/acpica/hwgpe.c -@@ -89,6 +89,8 @@ u32 acpi_hw_get_gpe_register_bit(struct acpi_gpe_event_info *gpe_event_info) - * RETURN: Status - * - * DESCRIPTION: Enable or disable a single GPE in the parent enable register. -+ * The enable_mask field of the involved GPE register must be -+ * updated by the caller if necessary. - * - ******************************************************************************/ - -@@ -119,7 +121,7 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action) - /* Set or clear just the bit that corresponds to this GPE */ - - register_bit = acpi_hw_get_gpe_register_bit(gpe_event_info); -- switch (action & ~ACPI_GPE_SAVE_MASK) { -+ switch (action) { - case ACPI_GPE_CONDITIONAL_ENABLE: - - /* Only enable if the corresponding enable_mask bit is set */ -@@ -149,9 +151,6 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action) - /* Write the updated enable mask */ - - status = acpi_hw_write(enable_mask, &gpe_register_info->enable_address); -- if (ACPI_SUCCESS(status) && (action & ACPI_GPE_SAVE_MASK)) { -- gpe_register_info->enable_mask = (u8)enable_mask; -- } - return (status); - } - -@@ -286,10 +285,8 @@ acpi_hw_gpe_enable_write(u8 enable_mask, - { - acpi_status status; - -+ gpe_register_info->enable_mask = enable_mask; - status = acpi_hw_write(enable_mask, &gpe_register_info->enable_address); -- if (ACPI_SUCCESS(status)) { -- gpe_register_info->enable_mask = enable_mask; -- } - return (status); - } - -diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c -index 9bad45e..7fbc2b9 100644 ---- a/drivers/acpi/acpica/tbinstal.c -+++ b/drivers/acpi/acpica/tbinstal.c -@@ -346,7 +346,6 @@ acpi_tb_install_standard_table(acpi_physical_address address, - */ - acpi_tb_uninstall_table(&new_table_desc); - *table_index = i; -- (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); - return_ACPI_STATUS(AE_OK); - } - } -diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c -index bbca783..349f4fd 100644 ---- a/drivers/acpi/scan.c -+++ b/drivers/acpi/scan.c -@@ -298,7 +298,11 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent) - struct acpi_device_physical_node *pn; - bool offline = true; - -- mutex_lock(&adev->physical_node_lock); -+ /* -+ * acpi_container_offline() calls this for all of the container's -+ * children under the container's physical_node_lock lock. -+ */ -+ mutex_lock_nested(&adev->physical_node_lock, SINGLE_DEPTH_NESTING); - - list_for_each_entry(pn, &adev->physical_node_list, node) - if (device_supports_offline(pn->dev) && !pn->dev->offline) { -diff --git a/drivers/base/bus.c b/drivers/base/bus.c -index 876bae5..79bc203 100644 ---- a/drivers/base/bus.c -+++ b/drivers/base/bus.c -@@ -515,11 +515,11 @@ int bus_add_device(struct device *dev) - goto out_put; - error = device_add_groups(dev, bus->dev_groups); - if (error) -- goto out_groups; -+ goto out_id; - error = sysfs_create_link(&bus->p->devices_kset->kobj, - &dev->kobj, dev_name(dev)); - if (error) -- goto out_id; -+ goto out_groups; - error = sysfs_create_link(&dev->kobj, - &dev->bus->p->subsys.kobj, "subsystem"); - if (error) -diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c -index 6e64563..9c2ba1c 100644 ---- a/drivers/base/cacheinfo.c -+++ b/drivers/base/cacheinfo.c -@@ -62,15 +62,21 @@ static int cache_setup_of_node(unsigned int cpu) - return -ENOENT; - } - -- while (np && index < cache_leaves(cpu)) { -+ while (index < cache_leaves(cpu)) { - this_leaf = this_cpu_ci->info_list + index; - if (this_leaf->level != 1) - np = of_find_next_cache_node(np); - else - np = of_node_get(np);/* cpu node itself */ -+ if (!np) -+ break; - this_leaf->of_node = np; - index++; - } -+ -+ if (index != cache_leaves(cpu)) /* not all OF nodes populated */ -+ return -ENOENT; -+ - return 0; - } - -@@ -189,8 +195,11 @@ static int detect_cache_attributes(unsigned int cpu) - * will be set up here only if they are not populated already - */ - ret = cache_shared_cpu_map_setup(cpu); -- if (ret) -+ if (ret) { -+ pr_warn("Unable to detect cache hierarcy from DT for CPU %d\n", -+ cpu); - goto free_ci; -+ } - return 0; - - free_ci: -diff --git a/drivers/base/platform.c b/drivers/base/platform.c -index 9421fed..e68ab79 100644 ---- a/drivers/base/platform.c -+++ b/drivers/base/platform.c -@@ -101,6 +101,15 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) - } - - r = platform_get_resource(dev, IORESOURCE_IRQ, num); -+ /* -+ * The resources may pass trigger flags to the irqs that need -+ * to be set up. It so happens that the trigger flags for -+ * IORESOURCE_BITS correspond 1-to-1 to the IRQF_TRIGGER* -+ * settings. -+ */ -+ if (r && r->flags & IORESOURCE_BITS) -+ irqd_set_trigger_type(irq_get_irq_data(r->start), -+ r->flags & IORESOURCE_BITS); - - return r ? r->start : -ENXIO; - #endif -diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c -index de4c849..288547a 100644 ---- a/drivers/bluetooth/ath3k.c -+++ b/drivers/bluetooth/ath3k.c -@@ -65,6 +65,7 @@ static const struct usb_device_id ath3k_table[] = { - /* Atheros AR3011 with sflash firmware*/ - { USB_DEVICE(0x0489, 0xE027) }, - { USB_DEVICE(0x0489, 0xE03D) }, -+ { USB_DEVICE(0x04F2, 0xAFF1) }, - { USB_DEVICE(0x0930, 0x0215) }, - { USB_DEVICE(0x0CF3, 0x3002) }, - { USB_DEVICE(0x0CF3, 0xE019) }, -diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c -index 8bfc4c2..2c527da 100644 ---- a/drivers/bluetooth/btusb.c -+++ b/drivers/bluetooth/btusb.c -@@ -159,6 +159,7 @@ static const struct usb_device_id blacklist_table[] = { - /* Atheros 3011 with sflash firmware */ - { USB_DEVICE(0x0489, 0xe027), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0489, 0xe03d), .driver_info = BTUSB_IGNORE }, -+ { USB_DEVICE(0x04f2, 0xaff1), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0930, 0x0215), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0cf3, 0x3002), .driver_info = BTUSB_IGNORE }, - { USB_DEVICE(0x0cf3, 0xe019), .driver_info = BTUSB_IGNORE }, -diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c -index e096e9c..283f00a 100644 ---- a/drivers/char/tpm/tpm-chip.c -+++ b/drivers/char/tpm/tpm-chip.c -@@ -170,6 +170,41 @@ static void tpm_dev_del_device(struct tpm_chip *chip) - device_unregister(&chip->dev); - } - -+static int tpm1_chip_register(struct tpm_chip *chip) -+{ -+ int rc; -+ -+ if (chip->flags & TPM_CHIP_FLAG_TPM2) -+ return 0; -+ -+ rc = tpm_sysfs_add_device(chip); -+ if (rc) -+ return rc; -+ -+ rc = tpm_add_ppi(chip); -+ if (rc) { -+ tpm_sysfs_del_device(chip); -+ return rc; -+ } -+ -+ chip->bios_dir = tpm_bios_log_setup(chip->devname); -+ -+ return 0; -+} -+ -+static void tpm1_chip_unregister(struct tpm_chip *chip) -+{ -+ if (chip->flags & TPM_CHIP_FLAG_TPM2) -+ return; -+ -+ if (chip->bios_dir) -+ tpm_bios_log_teardown(chip->bios_dir); -+ -+ tpm_remove_ppi(chip); -+ -+ tpm_sysfs_del_device(chip); -+} -+ - /* - * tpm_chip_register() - create a character device for the TPM chip - * @chip: TPM chip to use. -@@ -185,22 +220,13 @@ int tpm_chip_register(struct tpm_chip *chip) - { - int rc; - -- /* Populate sysfs for TPM1 devices. */ -- if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { -- rc = tpm_sysfs_add_device(chip); -- if (rc) -- goto del_misc; -- -- rc = tpm_add_ppi(chip); -- if (rc) -- goto del_sysfs; -- -- chip->bios_dir = tpm_bios_log_setup(chip->devname); -- } -+ rc = tpm1_chip_register(chip); -+ if (rc) -+ return rc; - - rc = tpm_dev_add_device(chip); - if (rc) -- return rc; -+ goto out_err; - - /* Make the chip available. */ - spin_lock(&driver_lock); -@@ -210,10 +236,8 @@ int tpm_chip_register(struct tpm_chip *chip) - chip->flags |= TPM_CHIP_FLAG_REGISTERED; - - return 0; --del_sysfs: -- tpm_sysfs_del_device(chip); --del_misc: -- tpm_dev_del_device(chip); -+out_err: -+ tpm1_chip_unregister(chip); - return rc; - } - EXPORT_SYMBOL_GPL(tpm_chip_register); -@@ -238,13 +262,7 @@ void tpm_chip_unregister(struct tpm_chip *chip) - spin_unlock(&driver_lock); - synchronize_rcu(); - -- if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { -- if (chip->bios_dir) -- tpm_bios_log_teardown(chip->bios_dir); -- tpm_remove_ppi(chip); -- tpm_sysfs_del_device(chip); -- } -- -+ tpm1_chip_unregister(chip); - tpm_dev_del_device(chip); - } - EXPORT_SYMBOL_GPL(tpm_chip_unregister); -diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c -index a23ac0c..0b7c3e8 100644 ---- a/drivers/clk/at91/clk-usb.c -+++ b/drivers/clk/at91/clk-usb.c -@@ -56,22 +56,55 @@ static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw, - return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1)); - } - --static long at91sam9x5_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate, -- unsigned long *parent_rate) -+static long at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw, -+ unsigned long rate, -+ unsigned long min_rate, -+ unsigned long max_rate, -+ unsigned long *best_parent_rate, -+ struct clk_hw **best_parent_hw) - { -- unsigned long div; -+ struct clk *parent = NULL; -+ long best_rate = -EINVAL; -+ unsigned long tmp_rate; -+ int best_diff = -1; -+ int tmp_diff; -+ int i; - -- if (!rate) -- return -EINVAL; -+ for (i = 0; i < __clk_get_num_parents(hw->clk); i++) { -+ int div; - -- if (rate >= *parent_rate) -- return *parent_rate; -+ parent = clk_get_parent_by_index(hw->clk, i); -+ if (!parent) -+ continue; -+ -+ for (div = 1; div < SAM9X5_USB_MAX_DIV + 2; div++) { -+ unsigned long tmp_parent_rate; -+ -+ tmp_parent_rate = rate * div; -+ tmp_parent_rate = __clk_round_rate(parent, -+ tmp_parent_rate); -+ tmp_rate = DIV_ROUND_CLOSEST(tmp_parent_rate, div); -+ if (tmp_rate < rate) -+ tmp_diff = rate - tmp_rate; -+ else -+ tmp_diff = tmp_rate - rate; -+ -+ if (best_diff < 0 || best_diff > tmp_diff) { -+ best_rate = tmp_rate; -+ best_diff = tmp_diff; -+ *best_parent_rate = tmp_parent_rate; -+ *best_parent_hw = __clk_get_hw(parent); -+ } -+ -+ if (!best_diff || tmp_rate < rate) -+ break; -+ } - -- div = DIV_ROUND_CLOSEST(*parent_rate, rate); -- if (div > SAM9X5_USB_MAX_DIV + 1) -- div = SAM9X5_USB_MAX_DIV + 1; -+ if (!best_diff) -+ break; -+ } - -- return DIV_ROUND_CLOSEST(*parent_rate, div); -+ return best_rate; - } - - static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index) -@@ -121,7 +154,7 @@ static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate, - - static const struct clk_ops at91sam9x5_usb_ops = { - .recalc_rate = at91sam9x5_clk_usb_recalc_rate, -- .round_rate = at91sam9x5_clk_usb_round_rate, -+ .determine_rate = at91sam9x5_clk_usb_determine_rate, - .get_parent = at91sam9x5_clk_usb_get_parent, - .set_parent = at91sam9x5_clk_usb_set_parent, - .set_rate = at91sam9x5_clk_usb_set_rate, -@@ -159,7 +192,7 @@ static const struct clk_ops at91sam9n12_usb_ops = { - .disable = at91sam9n12_clk_usb_disable, - .is_enabled = at91sam9n12_clk_usb_is_enabled, - .recalc_rate = at91sam9x5_clk_usb_recalc_rate, -- .round_rate = at91sam9x5_clk_usb_round_rate, -+ .determine_rate = at91sam9x5_clk_usb_determine_rate, - .set_rate = at91sam9x5_clk_usb_set_rate, - }; - -@@ -179,7 +212,8 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name, - init.ops = &at91sam9x5_usb_ops; - init.parent_names = parent_names; - init.num_parents = num_parents; -- init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE; -+ init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE | -+ CLK_SET_RATE_PARENT; - - usb->hw.init = &init; - usb->pmc = pmc; -@@ -207,7 +241,7 @@ at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name, - init.ops = &at91sam9n12_usb_ops; - init.parent_names = &parent_name; - init.num_parents = 1; -- init.flags = CLK_SET_RATE_GATE; -+ init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT; - - usb->hw.init = &init; - usb->pmc = pmc; -diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c -index 0039bd7..466f30c 100644 ---- a/drivers/clk/qcom/clk-rcg.c -+++ b/drivers/clk/qcom/clk-rcg.c -@@ -495,6 +495,57 @@ static int clk_rcg_bypass_set_rate(struct clk_hw *hw, unsigned long rate, - return __clk_rcg_set_rate(rcg, rcg->freq_tbl); - } - -+/* -+ * This type of clock has a glitch-free mux that switches between the output of -+ * the M/N counter and an always on clock source (XO). When clk_set_rate() is -+ * called we need to make sure that we don't switch to the M/N counter if it -+ * isn't clocking because the mux will get stuck and the clock will stop -+ * outputting a clock. This can happen if the framework isn't aware that this -+ * clock is on and so clk_set_rate() doesn't turn on the new parent. To fix -+ * this we switch the mux in the enable/disable ops and reprogram the M/N -+ * counter in the set_rate op. We also make sure to switch away from the M/N -+ * counter in set_rate if software thinks the clock is off. -+ */ -+static int clk_rcg_lcc_set_rate(struct clk_hw *hw, unsigned long rate, -+ unsigned long parent_rate) -+{ -+ struct clk_rcg *rcg = to_clk_rcg(hw); -+ const struct freq_tbl *f; -+ int ret; -+ u32 gfm = BIT(10); -+ -+ f = qcom_find_freq(rcg->freq_tbl, rate); -+ if (!f) -+ return -EINVAL; -+ -+ /* Switch to XO to avoid glitches */ -+ regmap_update_bits(rcg->clkr.regmap, rcg->ns_reg, gfm, 0); -+ ret = __clk_rcg_set_rate(rcg, f); -+ /* Switch back to M/N if it's clocking */ -+ if (__clk_is_enabled(hw->clk)) -+ regmap_update_bits(rcg->clkr.regmap, rcg->ns_reg, gfm, gfm); -+ -+ return ret; -+} -+ -+static int clk_rcg_lcc_enable(struct clk_hw *hw) -+{ -+ struct clk_rcg *rcg = to_clk_rcg(hw); -+ u32 gfm = BIT(10); -+ -+ /* Use M/N */ -+ return regmap_update_bits(rcg->clkr.regmap, rcg->ns_reg, gfm, gfm); -+} -+ -+static void clk_rcg_lcc_disable(struct clk_hw *hw) -+{ -+ struct clk_rcg *rcg = to_clk_rcg(hw); -+ u32 gfm = BIT(10); -+ -+ /* Use XO */ -+ regmap_update_bits(rcg->clkr.regmap, rcg->ns_reg, gfm, 0); -+} -+ - static int __clk_dyn_rcg_set_rate(struct clk_hw *hw, unsigned long rate) - { - struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw); -@@ -543,6 +594,17 @@ const struct clk_ops clk_rcg_bypass_ops = { - }; - EXPORT_SYMBOL_GPL(clk_rcg_bypass_ops); - -+const struct clk_ops clk_rcg_lcc_ops = { -+ .enable = clk_rcg_lcc_enable, -+ .disable = clk_rcg_lcc_disable, -+ .get_parent = clk_rcg_get_parent, -+ .set_parent = clk_rcg_set_parent, -+ .recalc_rate = clk_rcg_recalc_rate, -+ .determine_rate = clk_rcg_determine_rate, -+ .set_rate = clk_rcg_lcc_set_rate, -+}; -+EXPORT_SYMBOL_GPL(clk_rcg_lcc_ops); -+ - const struct clk_ops clk_dyn_rcg_ops = { - .enable = clk_enable_regmap, - .is_enabled = clk_is_enabled_regmap, -diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h -index 687e41f..d09d06b 100644 ---- a/drivers/clk/qcom/clk-rcg.h -+++ b/drivers/clk/qcom/clk-rcg.h -@@ -96,6 +96,7 @@ struct clk_rcg { - - extern const struct clk_ops clk_rcg_ops; - extern const struct clk_ops clk_rcg_bypass_ops; -+extern const struct clk_ops clk_rcg_lcc_ops; - - #define to_clk_rcg(_hw) container_of(to_clk_regmap(_hw), struct clk_rcg, clkr) - -diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c -index 742acfa..381f274 100644 ---- a/drivers/clk/qcom/clk-rcg2.c -+++ b/drivers/clk/qcom/clk-rcg2.c -@@ -243,7 +243,7 @@ static int clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f) - mask |= CFG_SRC_SEL_MASK | CFG_MODE_MASK; - cfg = f->pre_div << CFG_SRC_DIV_SHIFT; - cfg |= rcg->parent_map[f->src] << CFG_SRC_SEL_SHIFT; -- if (rcg->mnd_width && f->n) -+ if (rcg->mnd_width && f->n && (f->m != f->n)) - cfg |= CFG_MODE_DUAL_EDGE; - ret = regmap_update_bits(rcg->clkr.regmap, - rcg->cmd_rcgr + CFG_REG, mask, cfg); -diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c -index cbdc31d..a015bb0 100644 ---- a/drivers/clk/qcom/gcc-ipq806x.c -+++ b/drivers/clk/qcom/gcc-ipq806x.c -@@ -525,8 +525,8 @@ static struct freq_tbl clk_tbl_gsbi_qup[] = { - { 10800000, P_PXO, 1, 2, 5 }, - { 15060000, P_PLL8, 1, 2, 51 }, - { 24000000, P_PLL8, 4, 1, 4 }, -+ { 25000000, P_PXO, 1, 0, 0 }, - { 25600000, P_PLL8, 1, 1, 15 }, -- { 27000000, P_PXO, 1, 0, 0 }, - { 48000000, P_PLL8, 4, 1, 2 }, - { 51200000, P_PLL8, 1, 2, 15 }, - { } -diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c -index c9ff27b..a6d3a67 100644 ---- a/drivers/clk/qcom/lcc-ipq806x.c -+++ b/drivers/clk/qcom/lcc-ipq806x.c -@@ -294,14 +294,14 @@ static struct clk_regmap_mux pcm_clk = { - }; - - static struct freq_tbl clk_tbl_aif_osr[] = { -- { 22050, P_PLL4, 1, 147, 20480 }, -- { 32000, P_PLL4, 1, 1, 96 }, -- { 44100, P_PLL4, 1, 147, 10240 }, -- { 48000, P_PLL4, 1, 1, 64 }, -- { 88200, P_PLL4, 1, 147, 5120 }, -- { 96000, P_PLL4, 1, 1, 32 }, -- { 176400, P_PLL4, 1, 147, 2560 }, -- { 192000, P_PLL4, 1, 1, 16 }, -+ { 2822400, P_PLL4, 1, 147, 20480 }, -+ { 4096000, P_PLL4, 1, 1, 96 }, -+ { 5644800, P_PLL4, 1, 147, 10240 }, -+ { 6144000, P_PLL4, 1, 1, 64 }, -+ { 11289600, P_PLL4, 1, 147, 5120 }, -+ { 12288000, P_PLL4, 1, 1, 32 }, -+ { 22579200, P_PLL4, 1, 147, 2560 }, -+ { 24576000, P_PLL4, 1, 1, 16 }, - { }, - }; - -@@ -360,7 +360,7 @@ static struct clk_branch spdif_clk = { - }; - - static struct freq_tbl clk_tbl_ahbix[] = { -- { 131072, P_PLL4, 1, 1, 3 }, -+ { 131072000, P_PLL4, 1, 1, 3 }, - { }, - }; - -@@ -386,13 +386,12 @@ static struct clk_rcg ahbix_clk = { - .freq_tbl = clk_tbl_ahbix, - .clkr = { - .enable_reg = 0x38, -- .enable_mask = BIT(10), /* toggle the gfmux to select mn/pxo */ -+ .enable_mask = BIT(11), - .hw.init = &(struct clk_init_data){ - .name = "ahbix", - .parent_names = lcc_pxo_pll4, - .num_parents = 2, -- .ops = &clk_rcg_ops, -- .flags = CLK_SET_RATE_GATE, -+ .ops = &clk_rcg_lcc_ops, - }, - }, - }; -diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c -index 51462e8..714d6ba 100644 ---- a/drivers/clk/samsung/clk-exynos4.c -+++ b/drivers/clk/samsung/clk-exynos4.c -@@ -1354,7 +1354,7 @@ static struct samsung_pll_clock exynos4x12_plls[nr_plls] __initdata = { - VPLL_LOCK, VPLL_CON0, NULL), - }; - --static void __init exynos4_core_down_clock(enum exynos4_soc soc) -+static void __init exynos4x12_core_down_clock(void) - { - unsigned int tmp; - -@@ -1373,11 +1373,9 @@ static void __init exynos4_core_down_clock(enum exynos4_soc soc) - __raw_writel(tmp, reg_base + PWR_CTRL1); - - /* -- * Disable the clock up feature on Exynos4x12, in case it was -- * enabled by bootloader. -+ * Disable the clock up feature in case it was enabled by bootloader. - */ -- if (exynos4_soc == EXYNOS4X12) -- __raw_writel(0x0, reg_base + E4X12_PWR_CTRL2); -+ __raw_writel(0x0, reg_base + E4X12_PWR_CTRL2); - } - - /* register exynos4 clocks */ -@@ -1474,7 +1472,8 @@ static void __init exynos4_clk_init(struct device_node *np, - samsung_clk_register_alias(ctx, exynos4_aliases, - ARRAY_SIZE(exynos4_aliases)); - -- exynos4_core_down_clock(soc); -+ if (soc == EXYNOS4X12) -+ exynos4x12_core_down_clock(); - exynos4_clk_sleep_init(); - - samsung_clk_of_add_provider(np, ctx); -diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c -index 9a893f2..23ce0af 100644 ---- a/drivers/clk/tegra/clk-tegra124.c -+++ b/drivers/clk/tegra/clk-tegra124.c -@@ -1110,16 +1110,18 @@ static __init void tegra124_periph_clk_init(void __iomem *clk_base, - 1, 2); - clks[TEGRA124_CLK_XUSB_SS_DIV2] = clk; - -- clk = clk_register_gate(NULL, "plld_dsi", "plld_out0", 0, -+ clk = clk_register_gate(NULL, "pll_d_dsi_out", "pll_d_out0", 0, - clk_base + PLLD_MISC, 30, 0, &pll_d_lock); -- clks[TEGRA124_CLK_PLLD_DSI] = clk; -+ clks[TEGRA124_CLK_PLL_D_DSI_OUT] = clk; - -- clk = tegra_clk_register_periph_gate("dsia", "plld_dsi", 0, clk_base, -- 0, 48, periph_clk_enb_refcnt); -+ clk = tegra_clk_register_periph_gate("dsia", "pll_d_dsi_out", 0, -+ clk_base, 0, 48, -+ periph_clk_enb_refcnt); - clks[TEGRA124_CLK_DSIA] = clk; - -- clk = tegra_clk_register_periph_gate("dsib", "plld_dsi", 0, clk_base, -- 0, 82, periph_clk_enb_refcnt); -+ clk = tegra_clk_register_periph_gate("dsib", "pll_d_dsi_out", 0, -+ clk_base, 0, 82, -+ periph_clk_enb_refcnt); - clks[TEGRA124_CLK_DSIB] = clk; - - /* emc mux */ -diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c -index 9ddb754..7a1df61 100644 ---- a/drivers/clk/tegra/clk.c -+++ b/drivers/clk/tegra/clk.c -@@ -272,7 +272,7 @@ void __init tegra_add_of_provider(struct device_node *np) - of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data); - - rst_ctlr.of_node = np; -- rst_ctlr.nr_resets = clk_num * 32; -+ rst_ctlr.nr_resets = periph_banks * 32; - reset_controller_register(&rst_ctlr); - } - -diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c -index 42f95a4..9a28b7e 100644 ---- a/drivers/crypto/omap-aes.c -+++ b/drivers/crypto/omap-aes.c -@@ -554,15 +554,23 @@ static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd) - return err; - } - --static int omap_aes_check_aligned(struct scatterlist *sg) -+static int omap_aes_check_aligned(struct scatterlist *sg, int total) - { -+ int len = 0; -+ - while (sg) { - if (!IS_ALIGNED(sg->offset, 4)) - return -1; - if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE)) - return -1; -+ -+ len += sg->length; - sg = sg_next(sg); - } -+ -+ if (len != total) -+ return -1; -+ - return 0; - } - -@@ -633,8 +641,8 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd, - dd->in_sg = req->src; - dd->out_sg = req->dst; - -- if (omap_aes_check_aligned(dd->in_sg) || -- omap_aes_check_aligned(dd->out_sg)) { -+ if (omap_aes_check_aligned(dd->in_sg, dd->total) || -+ omap_aes_check_aligned(dd->out_sg, dd->total)) { - if (omap_aes_copy_sgs(dd)) - pr_err("Failed to copy SGs for unaligned cases\n"); - dd->sgs_copied = 1; -diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c -index d0bc123..1a54205 100644 ---- a/drivers/gpio/gpio-mvebu.c -+++ b/drivers/gpio/gpio-mvebu.c -@@ -320,11 +320,13 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d) - { - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct mvebu_gpio_chip *mvchip = gc->private; -+ struct irq_chip_type *ct = irq_data_get_chip_type(d); - u32 mask = 1 << (d->irq - gc->irq_base); - - irq_gc_lock(gc); -- gc->mask_cache &= ~mask; -- writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip)); -+ ct->mask_cache_priv &= ~mask; -+ -+ writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); - irq_gc_unlock(gc); - } - -@@ -332,11 +334,13 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d) - { - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct mvebu_gpio_chip *mvchip = gc->private; -+ struct irq_chip_type *ct = irq_data_get_chip_type(d); -+ - u32 mask = 1 << (d->irq - gc->irq_base); - - irq_gc_lock(gc); -- gc->mask_cache |= mask; -- writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip)); -+ ct->mask_cache_priv |= mask; -+ writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip)); - irq_gc_unlock(gc); - } - -@@ -344,11 +348,13 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d) - { - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct mvebu_gpio_chip *mvchip = gc->private; -+ struct irq_chip_type *ct = irq_data_get_chip_type(d); -+ - u32 mask = 1 << (d->irq - gc->irq_base); - - irq_gc_lock(gc); -- gc->mask_cache &= ~mask; -- writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip)); -+ ct->mask_cache_priv &= ~mask; -+ writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); - irq_gc_unlock(gc); - } - -@@ -356,11 +362,13 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d) - { - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct mvebu_gpio_chip *mvchip = gc->private; -+ struct irq_chip_type *ct = irq_data_get_chip_type(d); -+ - u32 mask = 1 << (d->irq - gc->irq_base); - - irq_gc_lock(gc); -- gc->mask_cache |= mask; -- writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip)); -+ ct->mask_cache_priv |= mask; -+ writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip)); - irq_gc_unlock(gc); - } - -diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c -index bf17a60..1dbfba5 100644 ---- a/drivers/gpu/drm/exynos/exynos_dp_core.c -+++ b/drivers/gpu/drm/exynos/exynos_dp_core.c -@@ -32,10 +32,16 @@ - #include - - #include "exynos_dp_core.h" -+#include "exynos_drm_fimd.h" - - #define ctx_from_connector(c) container_of(c, struct exynos_dp_device, \ - connector) - -+static inline struct exynos_drm_crtc *dp_to_crtc(struct exynos_dp_device *dp) -+{ -+ return to_exynos_crtc(dp->encoder->crtc); -+} -+ - static inline struct exynos_dp_device * - display_to_dp(struct exynos_drm_display *d) - { -@@ -1070,6 +1076,8 @@ static void exynos_dp_poweron(struct exynos_dp_device *dp) - } - } - -+ fimd_dp_clock_enable(dp_to_crtc(dp), true); -+ - clk_prepare_enable(dp->clock); - exynos_dp_phy_init(dp); - exynos_dp_init_dp(dp); -@@ -1094,6 +1102,8 @@ static void exynos_dp_poweroff(struct exynos_dp_device *dp) - exynos_dp_phy_exit(dp); - clk_disable_unprepare(dp->clock); - -+ fimd_dp_clock_enable(dp_to_crtc(dp), false); -+ - if (dp->panel) { - if (drm_panel_unprepare(dp->panel)) - DRM_ERROR("failed to turnoff the panel\n"); -diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c -index 33a10ce..5d58f6c 100644 ---- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c -+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c -@@ -32,6 +32,7 @@ - #include "exynos_drm_fbdev.h" - #include "exynos_drm_crtc.h" - #include "exynos_drm_iommu.h" -+#include "exynos_drm_fimd.h" - - /* - * FIMD stands for Fully Interactive Mobile Display and -@@ -1233,6 +1234,24 @@ static int fimd_remove(struct platform_device *pdev) - return 0; - } - -+void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable) -+{ -+ struct fimd_context *ctx = crtc->ctx; -+ u32 val; -+ -+ /* -+ * Only Exynos 5250, 5260, 5410 and 542x requires enabling DP/MIE -+ * clock. On these SoCs the bootloader may enable it but any -+ * power domain off/on will reset it to disable state. -+ */ -+ if (ctx->driver_data != &exynos5_fimd_driver_data) -+ return; -+ -+ val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE; -+ writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON); -+} -+EXPORT_SYMBOL_GPL(fimd_dp_clock_enable); -+ - struct platform_driver fimd_driver = { - .probe = fimd_probe, - .remove = fimd_remove, -diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.h b/drivers/gpu/drm/exynos/exynos_drm_fimd.h -new file mode 100644 -index 0000000..b4fcaa5 ---- /dev/null -+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.h -@@ -0,0 +1,15 @@ -+/* -+ * Copyright (c) 2015 Samsung Electronics Co., Ltd. -+ * -+ * This program is free software; you can redistribute it and/or modify it -+ * under the terms of the GNU General Public License as published by the -+ * Free Software Foundation; either version 2 of the License, or (at your -+ * option) any later version. -+ */ -+ -+#ifndef _EXYNOS_DRM_FIMD_H_ -+#define _EXYNOS_DRM_FIMD_H_ -+ -+extern void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable); -+ -+#endif /* _EXYNOS_DRM_FIMD_H_ */ -diff --git a/drivers/gpu/drm/i2c/adv7511.c b/drivers/gpu/drm/i2c/adv7511.c -index fa140e0..60ab1f7 100644 ---- a/drivers/gpu/drm/i2c/adv7511.c -+++ b/drivers/gpu/drm/i2c/adv7511.c -@@ -33,6 +33,7 @@ struct adv7511 { - - unsigned int current_edid_segment; - uint8_t edid_buf[256]; -+ bool edid_read; - - wait_queue_head_t wq; - struct drm_encoder *encoder; -@@ -379,69 +380,71 @@ static bool adv7511_hpd(struct adv7511 *adv7511) - return false; - } - --static irqreturn_t adv7511_irq_handler(int irq, void *devid) --{ -- struct adv7511 *adv7511 = devid; -- -- if (adv7511_hpd(adv7511)) -- drm_helper_hpd_irq_event(adv7511->encoder->dev); -- -- wake_up_all(&adv7511->wq); -- -- return IRQ_HANDLED; --} -- --static unsigned int adv7511_is_interrupt_pending(struct adv7511 *adv7511, -- unsigned int irq) -+static int adv7511_irq_process(struct adv7511 *adv7511) - { - unsigned int irq0, irq1; -- unsigned int pending; - int ret; - - ret = regmap_read(adv7511->regmap, ADV7511_REG_INT(0), &irq0); - if (ret < 0) -- return 0; -+ return ret; -+ - ret = regmap_read(adv7511->regmap, ADV7511_REG_INT(1), &irq1); - if (ret < 0) -- return 0; -+ return ret; -+ -+ regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0); -+ regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1); -+ -+ if (irq0 & ADV7511_INT0_HDP) -+ drm_helper_hpd_irq_event(adv7511->encoder->dev); -+ -+ if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) { -+ adv7511->edid_read = true; -+ -+ if (adv7511->i2c_main->irq) -+ wake_up_all(&adv7511->wq); -+ } -+ -+ return 0; -+} - -- pending = (irq1 << 8) | irq0; -+static irqreturn_t adv7511_irq_handler(int irq, void *devid) -+{ -+ struct adv7511 *adv7511 = devid; -+ int ret; - -- return pending & irq; -+ ret = adv7511_irq_process(adv7511); -+ return ret < 0 ? IRQ_NONE : IRQ_HANDLED; - } - --static int adv7511_wait_for_interrupt(struct adv7511 *adv7511, int irq, -- int timeout) -+/* ----------------------------------------------------------------------------- -+ * EDID retrieval -+ */ -+ -+static int adv7511_wait_for_edid(struct adv7511 *adv7511, int timeout) - { -- unsigned int pending; - int ret; - - if (adv7511->i2c_main->irq) { - ret = wait_event_interruptible_timeout(adv7511->wq, -- adv7511_is_interrupt_pending(adv7511, irq), -- msecs_to_jiffies(timeout)); -- if (ret <= 0) -- return 0; -- pending = adv7511_is_interrupt_pending(adv7511, irq); -+ adv7511->edid_read, msecs_to_jiffies(timeout)); - } else { -- if (timeout < 25) -- timeout = 25; -- do { -- pending = adv7511_is_interrupt_pending(adv7511, irq); -- if (pending) -+ for (; timeout > 0; timeout -= 25) { -+ ret = adv7511_irq_process(adv7511); -+ if (ret < 0) - break; -+ -+ if (adv7511->edid_read) -+ break; -+ - msleep(25); -- timeout -= 25; -- } while (timeout >= 25); -+ } - } - -- return pending; -+ return adv7511->edid_read ? 0 : -EIO; - } - --/* ----------------------------------------------------------------------------- -- * EDID retrieval -- */ -- - static int adv7511_get_edid_block(void *data, u8 *buf, unsigned int block, - size_t len) - { -@@ -463,19 +466,14 @@ static int adv7511_get_edid_block(void *data, u8 *buf, unsigned int block, - return ret; - - if (status != 2) { -+ adv7511->edid_read = false; - regmap_write(adv7511->regmap, ADV7511_REG_EDID_SEGMENT, - block); -- ret = adv7511_wait_for_interrupt(adv7511, -- ADV7511_INT0_EDID_READY | -- ADV7511_INT1_DDC_ERROR, 200); -- -- if (!(ret & ADV7511_INT0_EDID_READY)) -- return -EIO; -+ ret = adv7511_wait_for_edid(adv7511, 200); -+ if (ret < 0) -+ return ret; - } - -- regmap_write(adv7511->regmap, ADV7511_REG_INT(0), -- ADV7511_INT0_EDID_READY | ADV7511_INT1_DDC_ERROR); -- - /* Break this apart, hopefully more I2C controllers will - * support 64 byte transfers than 256 byte transfers - */ -@@ -528,7 +526,9 @@ static int adv7511_get_modes(struct drm_encoder *encoder, - /* Reading the EDID only works if the device is powered */ - if (adv7511->dpms_mode != DRM_MODE_DPMS_ON) { - regmap_write(adv7511->regmap, ADV7511_REG_INT(0), -- ADV7511_INT0_EDID_READY | ADV7511_INT1_DDC_ERROR); -+ ADV7511_INT0_EDID_READY); -+ regmap_write(adv7511->regmap, ADV7511_REG_INT(1), -+ ADV7511_INT1_DDC_ERROR); - regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER, - ADV7511_POWER_POWER_DOWN, 0); - adv7511->current_edid_segment = -1; -@@ -563,7 +563,9 @@ static void adv7511_encoder_dpms(struct drm_encoder *encoder, int mode) - adv7511->current_edid_segment = -1; - - regmap_write(adv7511->regmap, ADV7511_REG_INT(0), -- ADV7511_INT0_EDID_READY | ADV7511_INT1_DDC_ERROR); -+ ADV7511_INT0_EDID_READY); -+ regmap_write(adv7511->regmap, ADV7511_REG_INT(1), -+ ADV7511_INT1_DDC_ERROR); - regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER, - ADV7511_POWER_POWER_DOWN, 0); - /* -diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c -index 5c66b56..ec4d932 100644 ---- a/drivers/gpu/drm/i915/i915_drv.c -+++ b/drivers/gpu/drm/i915/i915_drv.c -@@ -1042,7 +1042,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) - s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4); - - s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); -- s->gfx_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); -+ s->gfx_max_req_count = I915_READ(GEN7_GFX_MAX_REQ_COUNT); - - s->render_hwsp = I915_READ(RENDER_HWS_PGA_GEN7); - s->ecochk = I915_READ(GAM_ECOCHK); -@@ -1124,7 +1124,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) - I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]); - - I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count); -- I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count); -+ I915_WRITE(GEN7_GFX_MAX_REQ_COUNT, s->gfx_max_req_count); - - I915_WRITE(RENDER_HWS_PGA_GEN7, s->render_hwsp); - I915_WRITE(GAM_ECOCHK, s->ecochk); -diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c -index ede5bbb..07320cb 100644 ---- a/drivers/gpu/drm/i915/i915_irq.c -+++ b/drivers/gpu/drm/i915/i915_irq.c -@@ -3718,14 +3718,12 @@ static int i8xx_irq_postinstall(struct drm_device *dev) - ~(I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | - I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | - I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT | -- I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT | -- I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT); -+ I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT); - I915_WRITE16(IMR, dev_priv->irq_mask); - - I915_WRITE16(IER, - I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | - I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | -- I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT | - I915_USER_INTERRUPT); - POSTING_READ16(IER); - -@@ -3887,14 +3885,12 @@ static int i915_irq_postinstall(struct drm_device *dev) - I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | - I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | - I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT | -- I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT | -- I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT); -+ I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT); - - enable_mask = - I915_ASLE_INTERRUPT | - I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | - I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | -- I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT | - I915_USER_INTERRUPT; - - if (I915_HAS_HOTPLUG(dev)) { -diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h -index 33b3d0a2..f536ff2 100644 ---- a/drivers/gpu/drm/i915/i915_reg.h -+++ b/drivers/gpu/drm/i915/i915_reg.h -@@ -1740,6 +1740,7 @@ enum punit_power_well { - #define GMBUS_CYCLE_INDEX (2<<25) - #define GMBUS_CYCLE_STOP (4<<25) - #define GMBUS_BYTE_COUNT_SHIFT 16 -+#define GMBUS_BYTE_COUNT_MAX 256U - #define GMBUS_SLAVE_INDEX_SHIFT 8 - #define GMBUS_SLAVE_ADDR_SHIFT 1 - #define GMBUS_SLAVE_READ (1<<0) -diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c -index b31088a..56e437e 100644 ---- a/drivers/gpu/drm/i915/intel_i2c.c -+++ b/drivers/gpu/drm/i915/intel_i2c.c -@@ -270,18 +270,17 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) - } - - static int --gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, -- u32 gmbus1_index) -+gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, -+ unsigned short addr, u8 *buf, unsigned int len, -+ u32 gmbus1_index) - { - int reg_offset = dev_priv->gpio_mmio_base; -- u16 len = msg->len; -- u8 *buf = msg->buf; - - I915_WRITE(GMBUS1 + reg_offset, - gmbus1_index | - GMBUS_CYCLE_WAIT | - (len << GMBUS_BYTE_COUNT_SHIFT) | -- (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | -+ (addr << GMBUS_SLAVE_ADDR_SHIFT) | - GMBUS_SLAVE_READ | GMBUS_SW_RDY); - while (len) { - int ret; -@@ -303,11 +302,35 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, - } - - static int --gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) -+gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, -+ u32 gmbus1_index) - { -- int reg_offset = dev_priv->gpio_mmio_base; -- u16 len = msg->len; - u8 *buf = msg->buf; -+ unsigned int rx_size = msg->len; -+ unsigned int len; -+ int ret; -+ -+ do { -+ len = min(rx_size, GMBUS_BYTE_COUNT_MAX); -+ -+ ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, -+ buf, len, gmbus1_index); -+ if (ret) -+ return ret; -+ -+ rx_size -= len; -+ buf += len; -+ } while (rx_size != 0); -+ -+ return 0; -+} -+ -+static int -+gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, -+ unsigned short addr, u8 *buf, unsigned int len) -+{ -+ int reg_offset = dev_priv->gpio_mmio_base; -+ unsigned int chunk_size = len; - u32 val, loop; - - val = loop = 0; -@@ -319,8 +342,8 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) - I915_WRITE(GMBUS3 + reg_offset, val); - I915_WRITE(GMBUS1 + reg_offset, - GMBUS_CYCLE_WAIT | -- (msg->len << GMBUS_BYTE_COUNT_SHIFT) | -- (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | -+ (chunk_size << GMBUS_BYTE_COUNT_SHIFT) | -+ (addr << GMBUS_SLAVE_ADDR_SHIFT) | - GMBUS_SLAVE_WRITE | GMBUS_SW_RDY); - while (len) { - int ret; -@@ -337,6 +360,29 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) - if (ret) - return ret; - } -+ -+ return 0; -+} -+ -+static int -+gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) -+{ -+ u8 *buf = msg->buf; -+ unsigned int tx_size = msg->len; -+ unsigned int len; -+ int ret; -+ -+ do { -+ len = min(tx_size, GMBUS_BYTE_COUNT_MAX); -+ -+ ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len); -+ if (ret) -+ return ret; -+ -+ buf += len; -+ tx_size -= len; -+ } while (tx_size != 0); -+ - return 0; - } - -diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c -index 86807ee..9bd5611 100644 ---- a/drivers/gpu/drm/radeon/atombios_crtc.c -+++ b/drivers/gpu/drm/radeon/atombios_crtc.c -@@ -330,8 +330,10 @@ atombios_set_crtc_dtd_timing(struct drm_crtc *crtc, - misc |= ATOM_COMPOSITESYNC; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - misc |= ATOM_INTERLACE; -- if (mode->flags & DRM_MODE_FLAG_DBLSCAN) -+ if (mode->flags & DRM_MODE_FLAG_DBLCLK) - misc |= ATOM_DOUBLE_CLOCK_MODE; -+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN) -+ misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2; - - args.susModeMiscInfo.usAccess = cpu_to_le16(misc); - args.ucCRTC = radeon_crtc->crtc_id; -@@ -374,8 +376,10 @@ static void atombios_crtc_set_timing(struct drm_crtc *crtc, - misc |= ATOM_COMPOSITESYNC; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) - misc |= ATOM_INTERLACE; -- if (mode->flags & DRM_MODE_FLAG_DBLSCAN) -+ if (mode->flags & DRM_MODE_FLAG_DBLCLK) - misc |= ATOM_DOUBLE_CLOCK_MODE; -+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN) -+ misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2; - - args.susModeMiscInfo.usAccess = cpu_to_le16(misc); - args.ucCRTC = radeon_crtc->crtc_id; -diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h -index 9c47867..7fe5590 100644 ---- a/drivers/hid/hid-ids.h -+++ b/drivers/hid/hid-ids.h -@@ -459,6 +459,10 @@ - #define USB_DEVICE_ID_UGCI_FLYING 0x0020 - #define USB_DEVICE_ID_UGCI_FIGHTING 0x0030 - -+#define USB_VENDOR_ID_HP 0x03f0 -+#define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE 0x0a4a -+#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE 0x134a -+ - #define USB_VENDOR_ID_HUION 0x256c - #define USB_DEVICE_ID_HUION_TABLET 0x006e - -diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c -index a821277..4e3ae9f 100644 ---- a/drivers/hid/usbhid/hid-quirks.c -+++ b/drivers/hid/usbhid/hid-quirks.c -@@ -78,6 +78,8 @@ static const struct hid_blacklist { - { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, - { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, - { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, -+ { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, -+ { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL }, - { USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET }, - { USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS }, -diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c -index 2978f5e..00bc30e 100644 ---- a/drivers/hv/channel.c -+++ b/drivers/hv/channel.c -@@ -135,7 +135,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, - GFP_KERNEL); - if (!open_info) { - err = -ENOMEM; -- goto error0; -+ goto error_gpadl; - } - - init_completion(&open_info->waitevent); -@@ -151,7 +151,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, - - if (userdatalen > MAX_USER_DEFINED_BYTES) { - err = -EINVAL; -- goto error0; -+ goto error_gpadl; - } - - if (userdatalen) -@@ -195,6 +195,9 @@ error1: - list_del(&open_info->msglistentry); - spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); - -+error_gpadl: -+ vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle); -+ - error0: - free_pages((unsigned long)out, - get_order(send_ringbuffer_size + recv_ringbuffer_size)); -diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c -index 5f96b1b..019d542 100644 ---- a/drivers/i2c/busses/i2c-rk3x.c -+++ b/drivers/i2c/busses/i2c-rk3x.c -@@ -833,7 +833,7 @@ static int rk3x_i2c_xfer(struct i2c_adapter *adap, - clk_disable(i2c->clk); - spin_unlock_irqrestore(&i2c->lock, flags); - -- return ret; -+ return ret < 0 ? ret : num; - } - - static u32 rk3x_i2c_func(struct i2c_adapter *adap) -diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c -index edf274c..8143162 100644 ---- a/drivers/i2c/i2c-core.c -+++ b/drivers/i2c/i2c-core.c -@@ -596,6 +596,7 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap) - adap->bus_recovery_info->set_scl(adap, 1); - return i2c_generic_recovery(adap); - } -+EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery); - - int i2c_generic_gpio_recovery(struct i2c_adapter *adap) - { -@@ -610,6 +611,7 @@ int i2c_generic_gpio_recovery(struct i2c_adapter *adap) - - return ret; - } -+EXPORT_SYMBOL_GPL(i2c_generic_gpio_recovery); - - int i2c_recover_bus(struct i2c_adapter *adap) - { -@@ -619,6 +621,7 @@ int i2c_recover_bus(struct i2c_adapter *adap) - dev_dbg(&adap->dev, "Trying i2c bus recovery\n"); - return adap->bus_recovery_info->recover_bus(adap); - } -+EXPORT_SYMBOL_GPL(i2c_recover_bus); - - static int i2c_device_probe(struct device *dev) - { -@@ -1410,6 +1413,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) - - dev_dbg(&adap->dev, "adapter [%s] registered\n", adap->name); - -+ pm_runtime_no_callbacks(&adap->dev); -+ - #ifdef CONFIG_I2C_COMPAT - res = class_compat_create_link(i2c_adapter_compat_class, &adap->dev, - adap->dev.parent); -diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c -index 593f7ca..06cc1ff 100644 ---- a/drivers/i2c/i2c-mux.c -+++ b/drivers/i2c/i2c-mux.c -@@ -32,8 +32,9 @@ struct i2c_mux_priv { - struct i2c_algorithm algo; - - struct i2c_adapter *parent; -- void *mux_priv; /* the mux chip/device */ -- u32 chan_id; /* the channel id */ -+ struct device *mux_dev; -+ void *mux_priv; -+ u32 chan_id; - - int (*select)(struct i2c_adapter *, void *mux_priv, u32 chan_id); - int (*deselect)(struct i2c_adapter *, void *mux_priv, u32 chan_id); -@@ -119,6 +120,7 @@ struct i2c_adapter *i2c_add_mux_adapter(struct i2c_adapter *parent, - - /* Set up private adapter data */ - priv->parent = parent; -+ priv->mux_dev = mux_dev; - priv->mux_priv = mux_priv; - priv->chan_id = chan_id; - priv->select = select; -@@ -203,7 +205,7 @@ void i2c_del_mux_adapter(struct i2c_adapter *adap) - char symlink_name[20]; - - snprintf(symlink_name, sizeof(symlink_name), "channel-%u", priv->chan_id); -- sysfs_remove_link(&adap->dev.parent->kobj, symlink_name); -+ sysfs_remove_link(&priv->mux_dev->kobj, symlink_name); - - sysfs_remove_link(&priv->adap.dev.kobj, "mux_device"); - i2c_del_adapter(adap); -diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c -index b0e5852..44d1d79 100644 ---- a/drivers/idle/intel_idle.c -+++ b/drivers/idle/intel_idle.c -@@ -218,18 +218,10 @@ static struct cpuidle_state byt_cstates[] = { - .enter = &intel_idle, - .enter_freeze = intel_idle_freeze, }, - { -- .name = "C1E-BYT", -- .desc = "MWAIT 0x01", -- .flags = MWAIT2flg(0x01), -- .exit_latency = 15, -- .target_residency = 30, -- .enter = &intel_idle, -- .enter_freeze = intel_idle_freeze, }, -- { - .name = "C6N-BYT", - .desc = "MWAIT 0x58", - .flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED, -- .exit_latency = 40, -+ .exit_latency = 300, - .target_residency = 275, - .enter = &intel_idle, - .enter_freeze = intel_idle_freeze, }, -@@ -237,7 +229,7 @@ static struct cpuidle_state byt_cstates[] = { - .name = "C6S-BYT", - .desc = "MWAIT 0x52", - .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, -- .exit_latency = 140, -+ .exit_latency = 500, - .target_residency = 560, - .enter = &intel_idle, - .enter_freeze = intel_idle_freeze, }, -@@ -246,7 +238,7 @@ static struct cpuidle_state byt_cstates[] = { - .desc = "MWAIT 0x60", - .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 1200, -- .target_residency = 1500, -+ .target_residency = 4000, - .enter = &intel_idle, - .enter_freeze = intel_idle_freeze, }, - { -diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c -index 8c014b5..38acb3c 100644 ---- a/drivers/infiniband/core/umem.c -+++ b/drivers/infiniband/core/umem.c -@@ -99,12 +99,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, - if (dmasync) - dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); - -+ if (!size) -+ return ERR_PTR(-EINVAL); -+ - /* - * If the combination of the addr and size requested for this memory - * region causes an integer overflow, return error. - */ -- if ((PAGE_ALIGN(addr + size) <= size) || -- (PAGE_ALIGN(addr + size) <= addr)) -+ if (((addr + size) < addr) || -+ PAGE_ALIGN(addr + size) < (addr + size)) - return ERR_PTR(-EINVAL); - - if (!can_do_mlock()) -diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c -index ed2bd67..fbde33a 100644 ---- a/drivers/infiniband/hw/mlx4/qp.c -+++ b/drivers/infiniband/hw/mlx4/qp.c -@@ -2605,8 +2605,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr, - - memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen); - -- *lso_hdr_sz = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 | -- wr->wr.ud.hlen); -+ *lso_hdr_sz = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen); - *lso_seg_len = halign; - return 0; - } -diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c -index 20e859a..76eb57b 100644 ---- a/drivers/infiniband/ulp/iser/iser_initiator.c -+++ b/drivers/infiniband/ulp/iser/iser_initiator.c -@@ -409,8 +409,8 @@ int iser_send_command(struct iscsi_conn *conn, - if (scsi_prot_sg_count(sc)) { - prot_buf->buf = scsi_prot_sglist(sc); - prot_buf->size = scsi_prot_sg_count(sc); -- prot_buf->data_len = data_buf->data_len >> -- ilog2(sc->device->sector_size) * 8; -+ prot_buf->data_len = (data_buf->data_len >> -+ ilog2(sc->device->sector_size)) * 8; - } - - if (hdr->flags & ISCSI_FLAG_CMD_READ) { -diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c -index 075b19c..147029a 100644 ---- a/drivers/infiniband/ulp/isert/ib_isert.c -+++ b/drivers/infiniband/ulp/isert/ib_isert.c -@@ -222,7 +222,7 @@ fail: - static void - isert_free_rx_descriptors(struct isert_conn *isert_conn) - { -- struct ib_device *ib_dev = isert_conn->conn_cm_id->device; -+ struct ib_device *ib_dev = isert_conn->conn_device->ib_device; - struct iser_rx_desc *rx_desc; - int i; - -@@ -719,8 +719,8 @@ out: - static void - isert_connect_release(struct isert_conn *isert_conn) - { -- struct ib_device *ib_dev = isert_conn->conn_cm_id->device; - struct isert_device *device = isert_conn->conn_device; -+ struct ib_device *ib_dev = device->ib_device; - - isert_dbg("conn %p\n", isert_conn); - -@@ -728,7 +728,8 @@ isert_connect_release(struct isert_conn *isert_conn) - isert_conn_free_fastreg_pool(isert_conn); - - isert_free_rx_descriptors(isert_conn); -- rdma_destroy_id(isert_conn->conn_cm_id); -+ if (isert_conn->conn_cm_id) -+ rdma_destroy_id(isert_conn->conn_cm_id); - - if (isert_conn->conn_qp) { - struct isert_comp *comp = isert_conn->conn_qp->recv_cq->cq_context; -@@ -878,12 +879,15 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id, - return 0; - } - --static void -+static int - isert_connect_error(struct rdma_cm_id *cma_id) - { - struct isert_conn *isert_conn = cma_id->qp->qp_context; - -+ isert_conn->conn_cm_id = NULL; - isert_put_conn(isert_conn); -+ -+ return -1; - } - - static int -@@ -912,7 +916,7 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) - case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ - case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ - case RDMA_CM_EVENT_CONNECT_ERROR: -- isert_connect_error(cma_id); -+ ret = isert_connect_error(cma_id); - break; - default: - isert_err("Unhandled RDMA CMA event: %d\n", event->event); -@@ -1861,11 +1865,13 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc, - cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT; - spin_unlock_bh(&cmd->istate_lock); - -- if (ret) -+ if (ret) { -+ target_put_sess_cmd(se_cmd->se_sess, se_cmd); - transport_send_check_condition_and_sense(se_cmd, - se_cmd->pi_err, 0); -- else -+ } else { - target_execute_cmd(se_cmd); -+ } - } - - static void -diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c -index 27bcdbc..ea6cb64 100644 ---- a/drivers/input/mouse/alps.c -+++ b/drivers/input/mouse/alps.c -@@ -1159,13 +1159,14 @@ static void alps_report_bare_ps2_packet(struct psmouse *psmouse, - bool report_buttons) - { - struct alps_data *priv = psmouse->private; -- struct input_dev *dev; -+ struct input_dev *dev, *dev2 = NULL; - - /* Figure out which device to use to report the bare packet */ - if (priv->proto_version == ALPS_PROTO_V2 && - (priv->flags & ALPS_DUALPOINT)) { - /* On V2 devices the DualPoint Stick reports bare packets */ - dev = priv->dev2; -+ dev2 = psmouse->dev; - } else if (unlikely(IS_ERR_OR_NULL(priv->dev3))) { - /* Register dev3 mouse if we received PS/2 packet first time */ - if (!IS_ERR(priv->dev3)) -@@ -1177,7 +1178,7 @@ static void alps_report_bare_ps2_packet(struct psmouse *psmouse, - } - - if (report_buttons) -- alps_report_buttons(dev, NULL, -+ alps_report_buttons(dev, dev2, - packet[0] & 1, packet[0] & 2, packet[0] & 4); - - input_report_rel(dev, REL_X, -diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c -index 6e22682..991dc6b 100644 ---- a/drivers/input/mouse/elantech.c -+++ b/drivers/input/mouse/elantech.c -@@ -893,6 +893,21 @@ static psmouse_ret_t elantech_process_byte(struct psmouse *psmouse) - } - - /* -+ * This writes the reg_07 value again to the hardware at the end of every -+ * set_rate call because the register loses its value. reg_07 allows setting -+ * absolute mode on v4 hardware -+ */ -+static void elantech_set_rate_restore_reg_07(struct psmouse *psmouse, -+ unsigned int rate) -+{ -+ struct elantech_data *etd = psmouse->private; -+ -+ etd->original_set_rate(psmouse, rate); -+ if (elantech_write_reg(psmouse, 0x07, etd->reg_07)) -+ psmouse_err(psmouse, "restoring reg_07 failed\n"); -+} -+ -+/* - * Put the touchpad into absolute mode - */ - static int elantech_set_absolute_mode(struct psmouse *psmouse) -@@ -1094,6 +1109,8 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, - * Asus K53SV 0x450f01 78, 15, 0c 2 hw buttons - * Asus G46VW 0x460f02 00, 18, 0c 2 hw buttons - * Asus G750JX 0x360f00 00, 16, 0c 2 hw buttons -+ * Asus TP500LN 0x381f17 10, 14, 0e clickpad -+ * Asus X750JN 0x381f17 10, 14, 0e clickpad - * Asus UX31 0x361f00 20, 15, 0e clickpad - * Asus UX32VD 0x361f02 00, 15, 0e clickpad - * Avatar AVIU-145A2 0x361f00 ? clickpad -@@ -1635,6 +1652,11 @@ int elantech_init(struct psmouse *psmouse) - goto init_fail; - } - -+ if (etd->fw_version == 0x381f17) { -+ etd->original_set_rate = psmouse->set_rate; -+ psmouse->set_rate = elantech_set_rate_restore_reg_07; -+ } -+ - if (elantech_set_input_params(psmouse)) { - psmouse_err(psmouse, "failed to query touchpad range.\n"); - goto init_fail; -diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h -index 6f3afec..f965d15 100644 ---- a/drivers/input/mouse/elantech.h -+++ b/drivers/input/mouse/elantech.h -@@ -142,6 +142,7 @@ struct elantech_data { - struct finger_pos mt[ETP_MAX_FINGERS]; - unsigned char parity[256]; - int (*send_cmd)(struct psmouse *psmouse, unsigned char c, unsigned char *param); -+ void (*original_set_rate)(struct psmouse *psmouse, unsigned int rate); - }; - - #ifdef CONFIG_MOUSE_PS2_ELANTECH -diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c -index 713a962..41473929 100644 ---- a/drivers/md/dm-crypt.c -+++ b/drivers/md/dm-crypt.c -@@ -925,11 +925,10 @@ static int crypt_convert(struct crypt_config *cc, - - switch (r) { - /* async */ -+ case -EINPROGRESS: - case -EBUSY: - wait_for_completion(&ctx->restart); - reinit_completion(&ctx->restart); -- /* fall through*/ -- case -EINPROGRESS: - ctx->req = NULL; - ctx->cc_sector++; - continue; -@@ -1346,10 +1345,8 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, - struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); - struct crypt_config *cc = io->cc; - -- if (error == -EINPROGRESS) { -- complete(&ctx->restart); -+ if (error == -EINPROGRESS) - return; -- } - - if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post) - error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq); -@@ -1360,12 +1357,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, - crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio); - - if (!atomic_dec_and_test(&ctx->cc_pending)) -- return; -+ goto done; - - if (bio_data_dir(io->base_bio) == READ) - kcryptd_crypt_read_done(io); - else - kcryptd_crypt_write_io_submit(io, 1); -+done: -+ if (!completion_done(&ctx->restart)) -+ complete(&ctx->restart); - } - - static void kcryptd_crypt(struct work_struct *work) -diff --git a/drivers/md/md.c b/drivers/md/md.c -index 717daad..e617878 100644 ---- a/drivers/md/md.c -+++ b/drivers/md/md.c -@@ -249,6 +249,7 @@ static void md_make_request(struct request_queue *q, struct bio *bio) - const int rw = bio_data_dir(bio); - struct mddev *mddev = q->queuedata; - unsigned int sectors; -+ int cpu; - - if (mddev == NULL || mddev->pers == NULL - || !mddev->ready) { -@@ -284,7 +285,10 @@ static void md_make_request(struct request_queue *q, struct bio *bio) - sectors = bio_sectors(bio); - mddev->pers->make_request(mddev, bio); - -- generic_start_io_acct(rw, sectors, &mddev->gendisk->part0); -+ cpu = part_stat_lock(); -+ part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); -+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); -+ part_stat_unlock(); - - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); -diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c -index 3ed9f42..3b5d7f7 100644 ---- a/drivers/md/raid0.c -+++ b/drivers/md/raid0.c -@@ -313,7 +313,7 @@ static struct strip_zone *find_zone(struct r0conf *conf, - - /* - * remaps the bio to the target device. we separate two flows. -- * power 2 flow and a general flow for the sake of perfromance -+ * power 2 flow and a general flow for the sake of performance - */ - static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, - sector_t sector, sector_t *sector_offset) -@@ -524,6 +524,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) - split = bio; - } - -+ sector = bio->bi_iter.bi_sector; - zone = find_zone(mddev->private, §or); - tmp_dev = map_sector(mddev, zone, sector, §or); - split->bi_bdev = tmp_dev->bdev; -diff --git a/drivers/media/rc/img-ir/img-ir-core.c b/drivers/media/rc/img-ir/img-ir-core.c -index 77c78de..7020659 100644 ---- a/drivers/media/rc/img-ir/img-ir-core.c -+++ b/drivers/media/rc/img-ir/img-ir-core.c -@@ -146,7 +146,7 @@ static int img_ir_remove(struct platform_device *pdev) - { - struct img_ir_priv *priv = platform_get_drvdata(pdev); - -- free_irq(priv->irq, img_ir_isr); -+ free_irq(priv->irq, priv); - img_ir_remove_hw(priv); - img_ir_remove_raw(priv); - -diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c -index 65a326c..749ad56 100644 ---- a/drivers/media/usb/stk1160/stk1160-v4l.c -+++ b/drivers/media/usb/stk1160/stk1160-v4l.c -@@ -240,6 +240,11 @@ static int stk1160_stop_streaming(struct stk1160 *dev) - if (mutex_lock_interruptible(&dev->v4l_lock)) - return -ERESTARTSYS; - -+ /* -+ * Once URBs are cancelled, the URB complete handler -+ * won't be running. This is required to safely release the -+ * current buffer (dev->isoc_ctl.buf). -+ */ - stk1160_cancel_isoc(dev); - - /* -@@ -620,8 +625,16 @@ void stk1160_clear_queue(struct stk1160 *dev) - stk1160_info("buffer [%p/%d] aborted\n", - buf, buf->vb.v4l2_buf.index); - } -- /* It's important to clear current buffer */ -- dev->isoc_ctl.buf = NULL; -+ -+ /* It's important to release the current buffer */ -+ if (dev->isoc_ctl.buf) { -+ buf = dev->isoc_ctl.buf; -+ dev->isoc_ctl.buf = NULL; -+ -+ vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); -+ stk1160_info("buffer [%p/%d] aborted\n", -+ buf, buf->vb.v4l2_buf.index); -+ } - spin_unlock_irqrestore(&dev->buf_lock, flags); - } - -diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c -index fc145d2..922a750 100644 ---- a/drivers/memstick/core/mspro_block.c -+++ b/drivers/memstick/core/mspro_block.c -@@ -758,7 +758,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error) - - if (error || (card->current_mrq.tpc == MSPRO_CMD_STOP)) { - if (msb->data_dir == READ) { -- for (cnt = 0; cnt < msb->current_seg; cnt++) -+ for (cnt = 0; cnt < msb->current_seg; cnt++) { - t_len += msb->req_sg[cnt].length - / msb->page_size; - -@@ -766,6 +766,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error) - t_len += msb->current_page - 1; - - t_len *= msb->page_size; -+ } - } - } else - t_len = blk_rq_bytes(msb->block_req); -diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c -index 2a87f69..1aed3b7 100644 ---- a/drivers/mfd/mfd-core.c -+++ b/drivers/mfd/mfd-core.c -@@ -128,7 +128,7 @@ static int mfd_add_device(struct device *parent, int id, - int platform_id; - int r; - -- if (id < 0) -+ if (id == PLATFORM_DEVID_AUTO) - platform_id = id; - else - platform_id = id + cell->id; -diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c -index e8a4218..459ed1b 100644 ---- a/drivers/mmc/host/sunxi-mmc.c -+++ b/drivers/mmc/host/sunxi-mmc.c -@@ -930,7 +930,9 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host, - return PTR_ERR(host->clk_sample); - } - -- host->reset = devm_reset_control_get(&pdev->dev, "ahb"); -+ host->reset = devm_reset_control_get_optional(&pdev->dev, "ahb"); -+ if (PTR_ERR(host->reset) == -EPROBE_DEFER) -+ return PTR_ERR(host->reset); - - ret = clk_prepare_enable(host->clk_ahb); - if (ret) { -diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c -index a31c357..dba7e1c 100644 ---- a/drivers/mmc/host/tmio_mmc_pio.c -+++ b/drivers/mmc/host/tmio_mmc_pio.c -@@ -1073,8 +1073,6 @@ EXPORT_SYMBOL(tmio_mmc_host_alloc); - void tmio_mmc_host_free(struct tmio_mmc_host *host) - { - mmc_free_host(host->mmc); -- -- host->mmc = NULL; - } - EXPORT_SYMBOL(tmio_mmc_host_free); - -diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c -index 9d2e16f..b5e1548 100644 ---- a/drivers/mtd/ubi/attach.c -+++ b/drivers/mtd/ubi/attach.c -@@ -410,7 +410,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, - second_is_newer = !second_is_newer; - } else { - dbg_bld("PEB %d CRC is OK", pnum); -- bitflips = !!err; -+ bitflips |= !!err; - } - mutex_unlock(&ubi->buf_mutex); - -diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c -index d647e50..d16fccf 100644 ---- a/drivers/mtd/ubi/cdev.c -+++ b/drivers/mtd/ubi/cdev.c -@@ -455,7 +455,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd, - /* Validate the request */ - err = -EINVAL; - if (req.lnum < 0 || req.lnum >= vol->reserved_pebs || -- req.bytes < 0 || req.lnum >= vol->usable_leb_size) -+ req.bytes < 0 || req.bytes > vol->usable_leb_size) - break; - - err = get_exclusive(desc); -diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c -index 16e34b3..8c9a710 100644 ---- a/drivers/mtd/ubi/eba.c -+++ b/drivers/mtd/ubi/eba.c -@@ -1419,7 +1419,8 @@ int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai) - * during re-size. - */ - ubi_move_aeb_to_list(av, aeb, &ai->erase); -- vol->eba_tbl[aeb->lnum] = aeb->pnum; -+ else -+ vol->eba_tbl[aeb->lnum] = aeb->pnum; - } - } - -diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c -index 8f7bde6..0bd92d8 100644 ---- a/drivers/mtd/ubi/wl.c -+++ b/drivers/mtd/ubi/wl.c -@@ -1002,7 +1002,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, - int shutdown) - { - int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; -- int vol_id = -1, uninitialized_var(lnum); -+ int vol_id = -1, lnum = -1; - #ifdef CONFIG_MTD_UBI_FASTMAP - int anchor = wrk->anchor; - #endif -diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c -index 81d4153..77bf133 100644 ---- a/drivers/net/ethernet/cadence/macb.c -+++ b/drivers/net/ethernet/cadence/macb.c -@@ -2165,7 +2165,7 @@ static void macb_configure_caps(struct macb *bp) - } - } - -- if (MACB_BFEXT(IDNUM, macb_readl(bp, MID)) == 0x2) -+ if (MACB_BFEXT(IDNUM, macb_readl(bp, MID)) >= 0x2) - bp->caps |= MACB_CAPS_MACB_IS_GEM; - - if (macb_is_gem(bp)) { -diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c -index 7f997d3..a71c446 100644 ---- a/drivers/net/ethernet/intel/e1000/e1000_main.c -+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c -@@ -144,6 +144,11 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, - static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, - struct e1000_rx_ring *rx_ring, - int *work_done, int work_to_do); -+static void e1000_alloc_dummy_rx_buffers(struct e1000_adapter *adapter, -+ struct e1000_rx_ring *rx_ring, -+ int cleaned_count) -+{ -+} - static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, - struct e1000_rx_ring *rx_ring, - int cleaned_count); -@@ -3552,8 +3557,11 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) - msleep(1); - /* e1000_down has a dependency on max_frame_size */ - hw->max_frame_size = max_frame; -- if (netif_running(netdev)) -+ if (netif_running(netdev)) { -+ /* prevent buffers from being reallocated */ -+ adapter->alloc_rx_buf = e1000_alloc_dummy_rx_buffers; - e1000_down(adapter); -+ } - - /* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN - * means we reserve 2 more, this pushes us to allocate from the next -diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c -index af829c5..7ace07d 100644 ---- a/drivers/net/ethernet/marvell/pxa168_eth.c -+++ b/drivers/net/ethernet/marvell/pxa168_eth.c -@@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev) - np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (!np) { - dev_err(&pdev->dev, "missing phy-handle\n"); -- return -EINVAL; -+ err = -EINVAL; -+ goto err_netdev; - } - of_property_read_u32(np, "reg", &pep->phy_addr); - pep->phy_intf = of_get_phy_mode(pdev->dev.of_node); -@@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) - pep->smi_bus = mdiobus_alloc(); - if (pep->smi_bus == NULL) { - err = -ENOMEM; -- goto err_base; -+ goto err_netdev; - } - pep->smi_bus->priv = pep; - pep->smi_bus->name = "pxa168_eth smi"; -@@ -1551,13 +1552,10 @@ err_mdiobus: - mdiobus_unregister(pep->smi_bus); - err_free_mdio: - mdiobus_free(pep->smi_bus); --err_base: -- iounmap(pep->base); - err_netdev: - free_netdev(dev); - err_clk: -- clk_disable(clk); -- clk_put(clk); -+ clk_disable_unprepare(clk); - return err; - } - -@@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev) - if (pep->phy) - phy_disconnect(pep->phy); - if (pep->clk) { -- clk_disable(pep->clk); -- clk_put(pep->clk); -- pep->clk = NULL; -+ clk_disable_unprepare(pep->clk); - } - -- iounmap(pep->base); -- pep->base = NULL; - mdiobus_unregister(pep->smi_bus); - mdiobus_free(pep->smi_bus); - unregister_netdev(dev); -diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c -index a7b58ba..3dccf01 100644 ---- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c -+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c -@@ -981,20 +981,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc) - struct mlx4_en_priv *priv = netdev_priv(dev); - - /* check if requested function is supported by the device */ -- if ((hfunc == ETH_RSS_HASH_TOP && -- !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) || -- (hfunc == ETH_RSS_HASH_XOR && -- !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))) -- return -EINVAL; -+ if (hfunc == ETH_RSS_HASH_TOP) { -+ if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) -+ return -EINVAL; -+ if (!(dev->features & NETIF_F_RXHASH)) -+ en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); -+ return 0; -+ } else if (hfunc == ETH_RSS_HASH_XOR) { -+ if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)) -+ return -EINVAL; -+ if (dev->features & NETIF_F_RXHASH) -+ en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); -+ return 0; -+ } - -- priv->rss_hash_fn = hfunc; -- if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH)) -- en_warn(priv, -- "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); -- if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH)) -- en_warn(priv, -- "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); -- return 0; -+ return -EINVAL; - } - - static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key, -@@ -1068,6 +1069,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index, - priv->prof->rss_rings = rss_rings; - if (key) - memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE); -+ if (hfunc != ETH_RSS_HASH_NO_CHANGE) -+ priv->rss_hash_fn = hfunc; - - if (port_up) { - err = mlx4_en_start_port(dev); -diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c -index af034db..9d15566 100644 ---- a/drivers/net/ppp/ppp_generic.c -+++ b/drivers/net/ppp/ppp_generic.c -@@ -1716,6 +1716,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) - { - /* note: a 0-length skb is used as an error indication */ - if (skb->len > 0) { -+ skb_checksum_complete_unset(skb); - #ifdef CONFIG_PPP_MULTILINK - /* XXX do channel-level decompression here */ - if (PPP_PROTO(skb) == PPP_MP) -diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c -index 90a714c..23806c2 100644 ---- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c -+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c -@@ -321,6 +321,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { - {RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/ - {RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/ - {RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/ -+ {RTL_USB_DEVICE(0x0b05, 0x17ba, rtl92cu_hal_cfg)}, /*ASUS-Edimax*/ - {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ - {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ - {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ -@@ -377,6 +378,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { - {RTL_USB_DEVICE(0x2001, 0x3307, rtl92cu_hal_cfg)}, /*D-Link-Cameo*/ - {RTL_USB_DEVICE(0x2001, 0x3309, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/ - {RTL_USB_DEVICE(0x2001, 0x330a, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/ -+ {RTL_USB_DEVICE(0x2001, 0x330d, rtl92cu_hal_cfg)}, /*D-Link DWA-131 */ - {RTL_USB_DEVICE(0x2019, 0xab2b, rtl92cu_hal_cfg)}, /*Planex -Abocom*/ - {RTL_USB_DEVICE(0x20f4, 0x624d, rtl92cu_hal_cfg)}, /*TRENDNet*/ - {RTL_USB_DEVICE(0x2357, 0x0100, rtl92cu_hal_cfg)}, /*TP-Link WN8200ND*/ -diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c -index c93fae9..5fbd223 100644 ---- a/drivers/net/wireless/ti/wl18xx/debugfs.c -+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c -@@ -139,7 +139,7 @@ WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, protection_filter, "%u"); - WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, accum_arp_pend_requests, "%u"); - WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, max_arp_queue_dep, "%u"); - --WL18XX_DEBUGFS_FWSTATS_FILE(rx_rate, rx_frames_per_rates, "%u"); -+WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(rx_rate, rx_frames_per_rates, 50); - - WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(aggr_size, tx_agg_vs_rate, - AGGR_STATS_TX_AGG*AGGR_STATS_TX_RATE); -diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h -index 0f2cfb0..bf14676 100644 ---- a/drivers/net/wireless/ti/wlcore/debugfs.h -+++ b/drivers/net/wireless/ti/wlcore/debugfs.h -@@ -26,8 +26,8 @@ - - #include "wlcore.h" - --int wl1271_format_buffer(char __user *userbuf, size_t count, -- loff_t *ppos, char *fmt, ...); -+__printf(4, 5) int wl1271_format_buffer(char __user *userbuf, size_t count, -+ loff_t *ppos, char *fmt, ...); - - int wl1271_debugfs_init(struct wl1271 *wl); - void wl1271_debugfs_exit(struct wl1271 *wl); -diff --git a/drivers/nfc/st21nfcb/i2c.c b/drivers/nfc/st21nfcb/i2c.c -index eb88693..7b53a5c 100644 ---- a/drivers/nfc/st21nfcb/i2c.c -+++ b/drivers/nfc/st21nfcb/i2c.c -@@ -109,7 +109,7 @@ static int st21nfcb_nci_i2c_write(void *phy_id, struct sk_buff *skb) - return phy->ndlc->hard_fault; - - r = i2c_master_send(client, skb->data, skb->len); -- if (r == -EREMOTEIO) { /* Retry, chip was in standby */ -+ if (r < 0) { /* Retry, chip was in standby */ - usleep_range(1000, 4000); - r = i2c_master_send(client, skb->data, skb->len); - } -@@ -148,7 +148,7 @@ static int st21nfcb_nci_i2c_read(struct st21nfcb_i2c_phy *phy, - struct i2c_client *client = phy->i2c_dev; - - r = i2c_master_recv(client, buf, ST21NFCB_NCI_I2C_MIN_SIZE); -- if (r == -EREMOTEIO) { /* Retry, chip was in standby */ -+ if (r < 0) { /* Retry, chip was in standby */ - usleep_range(1000, 4000); - r = i2c_master_recv(client, buf, ST21NFCB_NCI_I2C_MIN_SIZE); - } -diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c -index 15c0fab..bceb30b 100644 ---- a/drivers/platform/x86/compal-laptop.c -+++ b/drivers/platform/x86/compal-laptop.c -@@ -1026,9 +1026,9 @@ static int compal_probe(struct platform_device *pdev) - if (err) - return err; - -- hwmon_dev = hwmon_device_register_with_groups(&pdev->dev, -- "compal", data, -- compal_hwmon_groups); -+ hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev, -+ "compal", data, -+ compal_hwmon_groups); - if (IS_ERR(hwmon_dev)) { - err = PTR_ERR(hwmon_dev); - goto remove; -@@ -1036,7 +1036,9 @@ static int compal_probe(struct platform_device *pdev) - - /* Power supply */ - initialize_power_supply_data(data); -- power_supply_register(&compal_device->dev, &data->psy); -+ err = power_supply_register(&compal_device->dev, &data->psy); -+ if (err < 0) -+ goto remove; - - platform_set_drvdata(pdev, data); - -diff --git a/drivers/power/ipaq_micro_battery.c b/drivers/power/ipaq_micro_battery.c -index 9d69460..96b15e0 100644 ---- a/drivers/power/ipaq_micro_battery.c -+++ b/drivers/power/ipaq_micro_battery.c -@@ -226,6 +226,7 @@ static struct power_supply micro_ac_power = { - static int micro_batt_probe(struct platform_device *pdev) - { - struct micro_battery *mb; -+ int ret; - - mb = devm_kzalloc(&pdev->dev, sizeof(*mb), GFP_KERNEL); - if (!mb) -@@ -233,14 +234,30 @@ static int micro_batt_probe(struct platform_device *pdev) - - mb->micro = dev_get_drvdata(pdev->dev.parent); - mb->wq = create_singlethread_workqueue("ipaq-battery-wq"); -+ if (!mb->wq) -+ return -ENOMEM; -+ - INIT_DELAYED_WORK(&mb->update, micro_battery_work); - platform_set_drvdata(pdev, mb); - queue_delayed_work(mb->wq, &mb->update, 1); -- power_supply_register(&pdev->dev, µ_batt_power); -- power_supply_register(&pdev->dev, µ_ac_power); -+ -+ ret = power_supply_register(&pdev->dev, µ_batt_power); -+ if (ret < 0) -+ goto batt_err; -+ -+ ret = power_supply_register(&pdev->dev, µ_ac_power); -+ if (ret < 0) -+ goto ac_err; - - dev_info(&pdev->dev, "iPAQ micro battery driver\n"); - return 0; -+ -+ac_err: -+ power_supply_unregister(µ_ac_power); -+batt_err: -+ cancel_delayed_work_sync(&mb->update); -+ destroy_workqueue(mb->wq); -+ return ret; - } - - static int micro_batt_remove(struct platform_device *pdev) -@@ -251,6 +268,7 @@ static int micro_batt_remove(struct platform_device *pdev) - power_supply_unregister(µ_ac_power); - power_supply_unregister(µ_batt_power); - cancel_delayed_work_sync(&mb->update); -+ destroy_workqueue(mb->wq); - - return 0; - } -diff --git a/drivers/power/lp8788-charger.c b/drivers/power/lp8788-charger.c -index 21fc233..176dab2 100644 ---- a/drivers/power/lp8788-charger.c -+++ b/drivers/power/lp8788-charger.c -@@ -417,8 +417,10 @@ static int lp8788_psy_register(struct platform_device *pdev, - pchg->battery.num_properties = ARRAY_SIZE(lp8788_battery_prop); - pchg->battery.get_property = lp8788_battery_get_property; - -- if (power_supply_register(&pdev->dev, &pchg->battery)) -+ if (power_supply_register(&pdev->dev, &pchg->battery)) { -+ power_supply_unregister(&pchg->charger); - return -EPERM; -+ } - - return 0; - } -diff --git a/drivers/power/twl4030_madc_battery.c b/drivers/power/twl4030_madc_battery.c -index 7ef445a..cf90760 100644 ---- a/drivers/power/twl4030_madc_battery.c -+++ b/drivers/power/twl4030_madc_battery.c -@@ -192,6 +192,7 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev) - { - struct twl4030_madc_battery *twl4030_madc_bat; - struct twl4030_madc_bat_platform_data *pdata = pdev->dev.platform_data; -+ int ret = 0; - - twl4030_madc_bat = kzalloc(sizeof(*twl4030_madc_bat), GFP_KERNEL); - if (!twl4030_madc_bat) -@@ -216,9 +217,11 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev) - - twl4030_madc_bat->pdata = pdata; - platform_set_drvdata(pdev, twl4030_madc_bat); -- power_supply_register(&pdev->dev, &twl4030_madc_bat->psy); -+ ret = power_supply_register(&pdev->dev, &twl4030_madc_bat->psy); -+ if (ret < 0) -+ kfree(twl4030_madc_bat); - -- return 0; -+ return ret; - } - - static int twl4030_madc_battery_remove(struct platform_device *pdev) -diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c -index 675b5e7..5a0800d 100644 ---- a/drivers/scsi/megaraid/megaraid_sas_fusion.c -+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c -@@ -1584,11 +1584,11 @@ megasas_build_ldio_fusion(struct megasas_instance *instance, - fp_possible = io_info.fpOkForIo; - } - -- /* Use smp_processor_id() for now until cmd->request->cpu is CPU -+ /* Use raw_smp_processor_id() for now until cmd->request->cpu is CPU - id by default, not CPU group id, otherwise all MSI-X queues won't - be utilized */ - cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ? -- smp_processor_id() % instance->msix_vectors : 0; -+ raw_smp_processor_id() % instance->msix_vectors : 0; - - if (fp_possible) { - megasas_set_pd_lba(io_request, scp->cmd_len, &io_info, scp, -@@ -1693,7 +1693,10 @@ megasas_build_dcdb_fusion(struct megasas_instance *instance, - << MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT; - cmd->request_desc->SCSIIO.DevHandle = io_request->DevHandle; - cmd->request_desc->SCSIIO.MSIxIndex = -- instance->msix_vectors ? smp_processor_id() % instance->msix_vectors : 0; -+ instance->msix_vectors ? -+ raw_smp_processor_id() % -+ instance->msix_vectors : -+ 0; - os_timeout_value = scmd->request->timeout / HZ; - - if (instance->secure_jbod_support && -diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c -index 2d5ab6d..454536c 100644 ---- a/drivers/scsi/mvsas/mv_sas.c -+++ b/drivers/scsi/mvsas/mv_sas.c -@@ -441,14 +441,11 @@ static u32 mvs_get_ncq_tag(struct sas_task *task, u32 *tag) - static int mvs_task_prep_ata(struct mvs_info *mvi, - struct mvs_task_exec_info *tei) - { -- struct sas_ha_struct *sha = mvi->sas; - struct sas_task *task = tei->task; - struct domain_device *dev = task->dev; - struct mvs_device *mvi_dev = dev->lldd_dev; - struct mvs_cmd_hdr *hdr = tei->hdr; - struct asd_sas_port *sas_port = dev->port; -- struct sas_phy *sphy = dev->phy; -- struct asd_sas_phy *sas_phy = sha->sas_phy[sphy->number]; - struct mvs_slot_info *slot; - void *buf_prd; - u32 tag = tei->tag, hdr_tag; -@@ -468,7 +465,7 @@ static int mvs_task_prep_ata(struct mvs_info *mvi, - slot->tx = mvi->tx_prod; - del_q = TXQ_MODE_I | tag | - (TXQ_CMD_STP << TXQ_CMD_SHIFT) | -- (MVS_PHY_ID << TXQ_PHY_SHIFT) | -+ ((sas_port->phy_mask & TXQ_PHY_MASK) << TXQ_PHY_SHIFT) | - (mvi_dev->taskfileset << TXQ_SRS_SHIFT); - mvi->tx[mvi->tx_prod] = cpu_to_le32(del_q); - -diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c -index 6b78476..3290a3e 100644 ---- a/drivers/scsi/sd.c -+++ b/drivers/scsi/sd.c -@@ -3100,6 +3100,7 @@ static void scsi_disk_release(struct device *dev) - ida_remove(&sd_index_ida, sdkp->index); - spin_unlock(&sd_index_lock); - -+ blk_integrity_unregister(disk); - disk->private_data = NULL; - put_disk(disk); - put_device(&sdkp->device->sdev_gendev); -diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c -index 14c7d42..5c06d29 100644 ---- a/drivers/scsi/sd_dif.c -+++ b/drivers/scsi/sd_dif.c -@@ -77,7 +77,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp) - - disk->integrity->flags |= BLK_INTEGRITY_DEVICE_CAPABLE; - -- if (!sdkp) -+ if (!sdkp->ATO) - return; - - if (type == SD_DIF_TYPE3_PROTECTION) -diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c -index efc6e44..bf8c5c1 100644 ---- a/drivers/scsi/storvsc_drv.c -+++ b/drivers/scsi/storvsc_drv.c -@@ -746,21 +746,22 @@ static unsigned int copy_to_bounce_buffer(struct scatterlist *orig_sgl, - if (bounce_sgl[j].length == PAGE_SIZE) { - /* full..move to next entry */ - sg_kunmap_atomic(bounce_addr); -+ bounce_addr = 0; - j++; -+ } - -- /* if we need to use another bounce buffer */ -- if (srclen || i != orig_sgl_count - 1) -- bounce_addr = sg_kmap_atomic(bounce_sgl,j); -+ /* if we need to use another bounce buffer */ -+ if (srclen && bounce_addr == 0) -+ bounce_addr = sg_kmap_atomic(bounce_sgl, j); - -- } else if (srclen == 0 && i == orig_sgl_count - 1) { -- /* unmap the last bounce that is < PAGE_SIZE */ -- sg_kunmap_atomic(bounce_addr); -- } - } - - sg_kunmap_atomic(src_addr - orig_sgl[i].offset); - } - -+ if (bounce_addr) -+ sg_kunmap_atomic(bounce_addr); -+ - local_irq_restore(flags); - - return total_copied; -diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c -index 6fea4af..aea3a67 100644 ---- a/drivers/spi/spi-imx.c -+++ b/drivers/spi/spi-imx.c -@@ -370,8 +370,6 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx, - if (spi_imx->dma_is_inited) { - dma = readl(spi_imx->base + MX51_ECSPI_DMA); - -- spi_imx->tx_wml = spi_imx_get_fifosize(spi_imx) / 2; -- spi_imx->rx_wml = spi_imx_get_fifosize(spi_imx) / 2; - spi_imx->rxt_wml = spi_imx_get_fifosize(spi_imx) / 2; - rx_wml_cfg = spi_imx->rx_wml << MX51_ECSPI_DMA_RX_WML_OFFSET; - tx_wml_cfg = spi_imx->tx_wml << MX51_ECSPI_DMA_TX_WML_OFFSET; -@@ -868,6 +866,8 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx, - master->max_dma_len = MAX_SDMA_BD_BYTES; - spi_imx->bitbang.master->flags = SPI_MASTER_MUST_RX | - SPI_MASTER_MUST_TX; -+ spi_imx->tx_wml = spi_imx_get_fifosize(spi_imx) / 2; -+ spi_imx->rx_wml = spi_imx_get_fifosize(spi_imx) / 2; - spi_imx->dma_is_inited = 1; - - return 0; -diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c -index 4eb7a98..7bf5186 100644 ---- a/drivers/spi/spidev.c -+++ b/drivers/spi/spidev.c -@@ -245,7 +245,10 @@ static int spidev_message(struct spidev_data *spidev, - k_tmp->len = u_tmp->len; - - total += k_tmp->len; -- if (total > bufsiz) { -+ /* Check total length of transfers. Also check each -+ * transfer length to avoid arithmetic overflow. -+ */ -+ if (total > bufsiz || k_tmp->len > bufsiz) { - status = -EMSGSIZE; - goto done; - } -diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c -index 7bdb62b..f83e00c 100644 ---- a/drivers/staging/android/sync.c -+++ b/drivers/staging/android/sync.c -@@ -114,7 +114,7 @@ void sync_timeline_signal(struct sync_timeline *obj) - list_for_each_entry_safe(pt, next, &obj->active_list_head, - active_list) { - if (fence_is_signaled_locked(&pt->base)) -- list_del(&pt->active_list); -+ list_del_init(&pt->active_list); - } - - spin_unlock_irqrestore(&obj->child_list_lock, flags); -diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c -index 6ed35b6..04fc217 100644 ---- a/drivers/staging/panel/panel.c -+++ b/drivers/staging/panel/panel.c -@@ -335,11 +335,11 @@ static unsigned char lcd_bits[LCD_PORTS][LCD_BITS][BIT_STATES]; - * LCD types - */ - #define LCD_TYPE_NONE 0 --#define LCD_TYPE_OLD 1 --#define LCD_TYPE_KS0074 2 --#define LCD_TYPE_HANTRONIX 3 --#define LCD_TYPE_NEXCOM 4 --#define LCD_TYPE_CUSTOM 5 -+#define LCD_TYPE_CUSTOM 1 -+#define LCD_TYPE_OLD 2 -+#define LCD_TYPE_KS0074 3 -+#define LCD_TYPE_HANTRONIX 4 -+#define LCD_TYPE_NEXCOM 5 - - /* - * keypad types -@@ -502,7 +502,7 @@ MODULE_PARM_DESC(keypad_type, - static int lcd_type = NOT_SET; - module_param(lcd_type, int, 0000); - MODULE_PARM_DESC(lcd_type, -- "LCD type: 0=none, 1=old //, 2=serial ks0074, 3=hantronix //, 4=nexcom //, 5=compiled-in"); -+ "LCD type: 0=none, 1=compiled-in, 2=old, 3=serial ks0074, 4=hantronix, 5=nexcom"); - - static int lcd_height = NOT_SET; - module_param(lcd_height, int, 0000); -diff --git a/drivers/staging/vt6655/rxtx.c b/drivers/staging/vt6655/rxtx.c -index 07ce3fd..fdf5c56 100644 ---- a/drivers/staging/vt6655/rxtx.c -+++ b/drivers/staging/vt6655/rxtx.c -@@ -1308,10 +1308,18 @@ int vnt_generate_fifo_header(struct vnt_private *priv, u32 dma_idx, - priv->hw->conf.chandef.chan->hw_value); - } - -- if (current_rate > RATE_11M) -- pkt_type = (u8)priv->byPacketType; -- else -+ if (current_rate > RATE_11M) { -+ if (info->band == IEEE80211_BAND_5GHZ) { -+ pkt_type = PK_TYPE_11A; -+ } else { -+ if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT) -+ pkt_type = PK_TYPE_11GB; -+ else -+ pkt_type = PK_TYPE_11GA; -+ } -+ } else { - pkt_type = PK_TYPE_11B; -+ } - - /*Set fifo controls */ - if (pkt_type == PK_TYPE_11A) -diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c -index 77d6425..5e35612 100644 ---- a/drivers/target/iscsi/iscsi_target.c -+++ b/drivers/target/iscsi/iscsi_target.c -@@ -537,7 +537,7 @@ static struct iscsit_transport iscsi_target_transport = { - - static int __init iscsi_target_init_module(void) - { -- int ret = 0; -+ int ret = 0, size; - - pr_debug("iSCSI-Target "ISCSIT_VERSION"\n"); - -@@ -546,6 +546,7 @@ static int __init iscsi_target_init_module(void) - pr_err("Unable to allocate memory for iscsit_global\n"); - return -1; - } -+ spin_lock_init(&iscsit_global->ts_bitmap_lock); - mutex_init(&auth_id_lock); - spin_lock_init(&sess_idr_lock); - idr_init(&tiqn_idr); -@@ -555,15 +556,11 @@ static int __init iscsi_target_init_module(void) - if (ret < 0) - goto out; - -- ret = iscsi_thread_set_init(); -- if (ret < 0) -+ size = BITS_TO_LONGS(ISCSIT_BITMAP_BITS) * sizeof(long); -+ iscsit_global->ts_bitmap = vzalloc(size); -+ if (!iscsit_global->ts_bitmap) { -+ pr_err("Unable to allocate iscsit_global->ts_bitmap\n"); - goto configfs_out; -- -- if (iscsi_allocate_thread_sets(TARGET_THREAD_SET_COUNT) != -- TARGET_THREAD_SET_COUNT) { -- pr_err("iscsi_allocate_thread_sets() returned" -- " unexpected value!\n"); -- goto ts_out1; - } - - lio_qr_cache = kmem_cache_create("lio_qr_cache", -@@ -572,7 +569,7 @@ static int __init iscsi_target_init_module(void) - if (!lio_qr_cache) { - pr_err("nable to kmem_cache_create() for" - " lio_qr_cache\n"); -- goto ts_out2; -+ goto bitmap_out; - } - - lio_dr_cache = kmem_cache_create("lio_dr_cache", -@@ -617,10 +614,8 @@ dr_out: - kmem_cache_destroy(lio_dr_cache); - qr_out: - kmem_cache_destroy(lio_qr_cache); --ts_out2: -- iscsi_deallocate_thread_sets(); --ts_out1: -- iscsi_thread_set_free(); -+bitmap_out: -+ vfree(iscsit_global->ts_bitmap); - configfs_out: - iscsi_target_deregister_configfs(); - out: -@@ -630,8 +625,6 @@ out: - - static void __exit iscsi_target_cleanup_module(void) - { -- iscsi_deallocate_thread_sets(); -- iscsi_thread_set_free(); - iscsit_release_discovery_tpg(); - iscsit_unregister_transport(&iscsi_target_transport); - kmem_cache_destroy(lio_qr_cache); -@@ -641,6 +634,7 @@ static void __exit iscsi_target_cleanup_module(void) - - iscsi_target_deregister_configfs(); - -+ vfree(iscsit_global->ts_bitmap); - kfree(iscsit_global); - } - -@@ -3715,17 +3709,16 @@ static int iscsit_send_reject( - - void iscsit_thread_get_cpumask(struct iscsi_conn *conn) - { -- struct iscsi_thread_set *ts = conn->thread_set; - int ord, cpu; - /* -- * thread_id is assigned from iscsit_global->ts_bitmap from -- * within iscsi_thread_set.c:iscsi_allocate_thread_sets() -+ * bitmap_id is assigned from iscsit_global->ts_bitmap from -+ * within iscsit_start_kthreads() - * -- * Here we use thread_id to determine which CPU that this -- * iSCSI connection's iscsi_thread_set will be scheduled to -+ * Here we use bitmap_id to determine which CPU that this -+ * iSCSI connection's RX/TX threads will be scheduled to - * execute upon. - */ -- ord = ts->thread_id % cpumask_weight(cpu_online_mask); -+ ord = conn->bitmap_id % cpumask_weight(cpu_online_mask); - for_each_online_cpu(cpu) { - if (ord-- == 0) { - cpumask_set_cpu(cpu, conn->conn_cpumask); -@@ -3914,7 +3907,7 @@ check_rsp_state: - switch (state) { - case ISTATE_SEND_LOGOUTRSP: - if (!iscsit_logout_post_handler(cmd, conn)) -- goto restart; -+ return -ECONNRESET; - /* fall through */ - case ISTATE_SEND_STATUS: - case ISTATE_SEND_ASYNCMSG: -@@ -3942,8 +3935,6 @@ check_rsp_state: - - err: - return -1; --restart: -- return -EAGAIN; - } - - static int iscsit_handle_response_queue(struct iscsi_conn *conn) -@@ -3970,21 +3961,13 @@ static int iscsit_handle_response_queue(struct iscsi_conn *conn) - int iscsi_target_tx_thread(void *arg) - { - int ret = 0; -- struct iscsi_conn *conn; -- struct iscsi_thread_set *ts = arg; -+ struct iscsi_conn *conn = arg; - /* - * Allow ourselves to be interrupted by SIGINT so that a - * connection recovery / failure event can be triggered externally. - */ - allow_signal(SIGINT); - --restart: -- conn = iscsi_tx_thread_pre_handler(ts); -- if (!conn) -- goto out; -- -- ret = 0; -- - while (!kthread_should_stop()) { - /* - * Ensure that both TX and RX per connection kthreads -@@ -3993,11 +3976,9 @@ restart: - iscsit_thread_check_cpumask(conn, current, 1); - - wait_event_interruptible(conn->queues_wq, -- !iscsit_conn_all_queues_empty(conn) || -- ts->status == ISCSI_THREAD_SET_RESET); -+ !iscsit_conn_all_queues_empty(conn)); - -- if ((ts->status == ISCSI_THREAD_SET_RESET) || -- signal_pending(current)) -+ if (signal_pending(current)) - goto transport_err; - - get_immediate: -@@ -4008,15 +3989,14 @@ get_immediate: - ret = iscsit_handle_response_queue(conn); - if (ret == 1) - goto get_immediate; -- else if (ret == -EAGAIN) -- goto restart; -+ else if (ret == -ECONNRESET) -+ goto out; - else if (ret < 0) - goto transport_err; - } - - transport_err: - iscsit_take_action_for_connection_exit(conn); -- goto restart; - out: - return 0; - } -@@ -4111,8 +4091,7 @@ int iscsi_target_rx_thread(void *arg) - int ret; - u8 buffer[ISCSI_HDR_LEN], opcode; - u32 checksum = 0, digest = 0; -- struct iscsi_conn *conn = NULL; -- struct iscsi_thread_set *ts = arg; -+ struct iscsi_conn *conn = arg; - struct kvec iov; - /* - * Allow ourselves to be interrupted by SIGINT so that a -@@ -4120,11 +4099,6 @@ int iscsi_target_rx_thread(void *arg) - */ - allow_signal(SIGINT); - --restart: -- conn = iscsi_rx_thread_pre_handler(ts); -- if (!conn) -- goto out; -- - if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) { - struct completion comp; - int rc; -@@ -4134,7 +4108,7 @@ restart: - if (rc < 0) - goto transport_err; - -- goto out; -+ goto transport_err; - } - - while (!kthread_should_stop()) { -@@ -4210,8 +4184,6 @@ transport_err: - if (!signal_pending(current)) - atomic_set(&conn->transport_failed, 1); - iscsit_take_action_for_connection_exit(conn); -- goto restart; --out: - return 0; - } - -@@ -4273,7 +4245,24 @@ int iscsit_close_connection( - if (conn->conn_transport->transport_type == ISCSI_TCP) - complete(&conn->conn_logout_comp); - -- iscsi_release_thread_set(conn); -+ if (!strcmp(current->comm, ISCSI_RX_THREAD_NAME)) { -+ if (conn->tx_thread && -+ cmpxchg(&conn->tx_thread_active, true, false)) { -+ send_sig(SIGINT, conn->tx_thread, 1); -+ kthread_stop(conn->tx_thread); -+ } -+ } else if (!strcmp(current->comm, ISCSI_TX_THREAD_NAME)) { -+ if (conn->rx_thread && -+ cmpxchg(&conn->rx_thread_active, true, false)) { -+ send_sig(SIGINT, conn->rx_thread, 1); -+ kthread_stop(conn->rx_thread); -+ } -+ } -+ -+ spin_lock(&iscsit_global->ts_bitmap_lock); -+ bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, -+ get_order(1)); -+ spin_unlock(&iscsit_global->ts_bitmap_lock); - - iscsit_stop_timers_for_cmds(conn); - iscsit_stop_nopin_response_timer(conn); -@@ -4551,15 +4540,13 @@ static void iscsit_logout_post_handler_closesession( - struct iscsi_conn *conn) - { - struct iscsi_session *sess = conn->sess; -- -- iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); -- iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); -+ int sleep = cmpxchg(&conn->tx_thread_active, true, false); - - atomic_set(&conn->conn_logout_remove, 0); - complete(&conn->conn_logout_comp); - - iscsit_dec_conn_usage_count(conn); -- iscsit_stop_session(sess, 1, 1); -+ iscsit_stop_session(sess, sleep, sleep); - iscsit_dec_session_usage_count(sess); - target_put_session(sess->se_sess); - } -@@ -4567,13 +4554,12 @@ static void iscsit_logout_post_handler_closesession( - static void iscsit_logout_post_handler_samecid( - struct iscsi_conn *conn) - { -- iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); -- iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); -+ int sleep = cmpxchg(&conn->tx_thread_active, true, false); - - atomic_set(&conn->conn_logout_remove, 0); - complete(&conn->conn_logout_comp); - -- iscsit_cause_connection_reinstatement(conn, 1); -+ iscsit_cause_connection_reinstatement(conn, sleep); - iscsit_dec_conn_usage_count(conn); - } - -diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c -index bdd8731..e008ed2 100644 ---- a/drivers/target/iscsi/iscsi_target_erl0.c -+++ b/drivers/target/iscsi/iscsi_target_erl0.c -@@ -860,7 +860,10 @@ void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *conn) - } - spin_unlock_bh(&conn->state_lock); - -- iscsi_thread_set_force_reinstatement(conn); -+ if (conn->tx_thread && conn->tx_thread_active) -+ send_sig(SIGINT, conn->tx_thread, 1); -+ if (conn->rx_thread && conn->rx_thread_active) -+ send_sig(SIGINT, conn->rx_thread, 1); - - sleep: - wait_for_completion(&conn->conn_wait_rcfr_comp); -@@ -885,10 +888,10 @@ void iscsit_cause_connection_reinstatement(struct iscsi_conn *conn, int sleep) - return; - } - -- if (iscsi_thread_set_force_reinstatement(conn) < 0) { -- spin_unlock_bh(&conn->state_lock); -- return; -- } -+ if (conn->tx_thread && conn->tx_thread_active) -+ send_sig(SIGINT, conn->tx_thread, 1); -+ if (conn->rx_thread && conn->rx_thread_active) -+ send_sig(SIGINT, conn->rx_thread, 1); - - atomic_set(&conn->connection_reinstatement, 1); - if (!sleep) { -diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c -index 153fb66..345f073 100644 ---- a/drivers/target/iscsi/iscsi_target_login.c -+++ b/drivers/target/iscsi/iscsi_target_login.c -@@ -699,6 +699,51 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn) - iscsit_start_nopin_timer(conn); - } - -+int iscsit_start_kthreads(struct iscsi_conn *conn) -+{ -+ int ret = 0; -+ -+ spin_lock(&iscsit_global->ts_bitmap_lock); -+ conn->bitmap_id = bitmap_find_free_region(iscsit_global->ts_bitmap, -+ ISCSIT_BITMAP_BITS, get_order(1)); -+ spin_unlock(&iscsit_global->ts_bitmap_lock); -+ -+ if (conn->bitmap_id < 0) { -+ pr_err("bitmap_find_free_region() failed for" -+ " iscsit_start_kthreads()\n"); -+ return -ENOMEM; -+ } -+ -+ conn->tx_thread = kthread_run(iscsi_target_tx_thread, conn, -+ "%s", ISCSI_TX_THREAD_NAME); -+ if (IS_ERR(conn->tx_thread)) { -+ pr_err("Unable to start iscsi_target_tx_thread\n"); -+ ret = PTR_ERR(conn->tx_thread); -+ goto out_bitmap; -+ } -+ conn->tx_thread_active = true; -+ -+ conn->rx_thread = kthread_run(iscsi_target_rx_thread, conn, -+ "%s", ISCSI_RX_THREAD_NAME); -+ if (IS_ERR(conn->rx_thread)) { -+ pr_err("Unable to start iscsi_target_rx_thread\n"); -+ ret = PTR_ERR(conn->rx_thread); -+ goto out_tx; -+ } -+ conn->rx_thread_active = true; -+ -+ return 0; -+out_tx: -+ kthread_stop(conn->tx_thread); -+ conn->tx_thread_active = false; -+out_bitmap: -+ spin_lock(&iscsit_global->ts_bitmap_lock); -+ bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, -+ get_order(1)); -+ spin_unlock(&iscsit_global->ts_bitmap_lock); -+ return ret; -+} -+ - int iscsi_post_login_handler( - struct iscsi_np *np, - struct iscsi_conn *conn, -@@ -709,7 +754,7 @@ int iscsi_post_login_handler( - struct se_session *se_sess = sess->se_sess; - struct iscsi_portal_group *tpg = sess->tpg; - struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; -- struct iscsi_thread_set *ts; -+ int rc; - - iscsit_inc_conn_usage_count(conn); - -@@ -724,7 +769,6 @@ int iscsi_post_login_handler( - /* - * SCSI Initiator -> SCSI Target Port Mapping - */ -- ts = iscsi_get_thread_set(); - if (!zero_tsih) { - iscsi_set_session_parameters(sess->sess_ops, - conn->param_list, 0); -@@ -751,9 +795,11 @@ int iscsi_post_login_handler( - sess->sess_ops->InitiatorName); - spin_unlock_bh(&sess->conn_lock); - -- iscsi_post_login_start_timers(conn); -+ rc = iscsit_start_kthreads(conn); -+ if (rc) -+ return rc; - -- iscsi_activate_thread_set(conn, ts); -+ iscsi_post_login_start_timers(conn); - /* - * Determine CPU mask to ensure connection's RX and TX kthreads - * are scheduled on the same CPU. -@@ -810,8 +856,11 @@ int iscsi_post_login_handler( - " iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt); - spin_unlock_bh(&se_tpg->session_lock); - -+ rc = iscsit_start_kthreads(conn); -+ if (rc) -+ return rc; -+ - iscsi_post_login_start_timers(conn); -- iscsi_activate_thread_set(conn, ts); - /* - * Determine CPU mask to ensure connection's RX and TX kthreads - * are scheduled on the same CPU. -diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c -index 44620fb..cbb0cc2 100644 ---- a/drivers/target/target_core_file.c -+++ b/drivers/target/target_core_file.c -@@ -264,40 +264,32 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, - struct se_device *se_dev = cmd->se_dev; - struct fd_dev *dev = FD_DEV(se_dev); - struct file *prot_fd = dev->fd_prot_file; -- struct scatterlist *sg; - loff_t pos = (cmd->t_task_lba * se_dev->prot_length); - unsigned char *buf; -- u32 prot_size, len, size; -- int rc, ret = 1, i; -+ u32 prot_size; -+ int rc, ret = 1; - - prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) * - se_dev->prot_length; - - if (!is_write) { -- fd_prot->prot_buf = vzalloc(prot_size); -+ fd_prot->prot_buf = kzalloc(prot_size, GFP_KERNEL); - if (!fd_prot->prot_buf) { - pr_err("Unable to allocate fd_prot->prot_buf\n"); - return -ENOMEM; - } - buf = fd_prot->prot_buf; - -- fd_prot->prot_sg_nents = cmd->t_prot_nents; -- fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist) * -- fd_prot->prot_sg_nents, GFP_KERNEL); -+ fd_prot->prot_sg_nents = 1; -+ fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist), -+ GFP_KERNEL); - if (!fd_prot->prot_sg) { - pr_err("Unable to allocate fd_prot->prot_sg\n"); -- vfree(fd_prot->prot_buf); -+ kfree(fd_prot->prot_buf); - return -ENOMEM; - } -- size = prot_size; -- -- for_each_sg(fd_prot->prot_sg, sg, fd_prot->prot_sg_nents, i) { -- -- len = min_t(u32, PAGE_SIZE, size); -- sg_set_buf(sg, buf, len); -- size -= len; -- buf += len; -- } -+ sg_init_table(fd_prot->prot_sg, fd_prot->prot_sg_nents); -+ sg_set_buf(fd_prot->prot_sg, buf, prot_size); - } - - if (is_write) { -@@ -318,7 +310,7 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, - - if (is_write || ret < 0) { - kfree(fd_prot->prot_sg); -- vfree(fd_prot->prot_buf); -+ kfree(fd_prot->prot_buf); - } - - return ret; -@@ -549,6 +541,56 @@ fd_execute_write_same(struct se_cmd *cmd) - return 0; - } - -+static int -+fd_do_prot_fill(struct se_device *se_dev, sector_t lba, sector_t nolb, -+ void *buf, size_t bufsize) -+{ -+ struct fd_dev *fd_dev = FD_DEV(se_dev); -+ struct file *prot_fd = fd_dev->fd_prot_file; -+ sector_t prot_length, prot; -+ loff_t pos = lba * se_dev->prot_length; -+ -+ if (!prot_fd) { -+ pr_err("Unable to locate fd_dev->fd_prot_file\n"); -+ return -ENODEV; -+ } -+ -+ prot_length = nolb * se_dev->prot_length; -+ -+ for (prot = 0; prot < prot_length;) { -+ sector_t len = min_t(sector_t, bufsize, prot_length - prot); -+ ssize_t ret = kernel_write(prot_fd, buf, len, pos + prot); -+ -+ if (ret != len) { -+ pr_err("vfs_write to prot file failed: %zd\n", ret); -+ return ret < 0 ? ret : -ENODEV; -+ } -+ prot += ret; -+ } -+ -+ return 0; -+} -+ -+static int -+fd_do_prot_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) -+{ -+ void *buf; -+ int rc; -+ -+ buf = (void *)__get_free_page(GFP_KERNEL); -+ if (!buf) { -+ pr_err("Unable to allocate FILEIO prot buf\n"); -+ return -ENOMEM; -+ } -+ memset(buf, 0xff, PAGE_SIZE); -+ -+ rc = fd_do_prot_fill(cmd->se_dev, lba, nolb, buf, PAGE_SIZE); -+ -+ free_page((unsigned long)buf); -+ -+ return rc; -+} -+ - static sense_reason_t - fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb) - { -@@ -556,6 +598,12 @@ fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb) - struct inode *inode = file->f_mapping->host; - int ret; - -+ if (cmd->se_dev->dev_attrib.pi_prot_type) { -+ ret = fd_do_prot_unmap(cmd, lba, nolb); -+ if (ret) -+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; -+ } -+ - if (S_ISBLK(inode->i_mode)) { - /* The backend is block device, use discard */ - struct block_device *bdev = inode->i_bdev; -@@ -658,11 +706,11 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, - 0, fd_prot.prot_sg, 0); - if (rc) { - kfree(fd_prot.prot_sg); -- vfree(fd_prot.prot_buf); -+ kfree(fd_prot.prot_buf); - return rc; - } - kfree(fd_prot.prot_sg); -- vfree(fd_prot.prot_buf); -+ kfree(fd_prot.prot_buf); - } - } else { - memset(&fd_prot, 0, sizeof(struct fd_prot)); -@@ -678,7 +726,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, - 0, fd_prot.prot_sg, 0); - if (rc) { - kfree(fd_prot.prot_sg); -- vfree(fd_prot.prot_buf); -+ kfree(fd_prot.prot_buf); - return rc; - } - } -@@ -714,7 +762,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, - - if (ret < 0) { - kfree(fd_prot.prot_sg); -- vfree(fd_prot.prot_buf); -+ kfree(fd_prot.prot_buf); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } - -@@ -878,48 +926,28 @@ static int fd_init_prot(struct se_device *dev) - - static int fd_format_prot(struct se_device *dev) - { -- struct fd_dev *fd_dev = FD_DEV(dev); -- struct file *prot_fd = fd_dev->fd_prot_file; -- sector_t prot_length, prot; - unsigned char *buf; -- loff_t pos = 0; - int unit_size = FDBD_FORMAT_UNIT_SIZE * dev->dev_attrib.block_size; -- int rc, ret = 0, size, len; -+ int ret; - - if (!dev->dev_attrib.pi_prot_type) { - pr_err("Unable to format_prot while pi_prot_type == 0\n"); - return -ENODEV; - } -- if (!prot_fd) { -- pr_err("Unable to locate fd_dev->fd_prot_file\n"); -- return -ENODEV; -- } - - buf = vzalloc(unit_size); - if (!buf) { - pr_err("Unable to allocate FILEIO prot buf\n"); - return -ENOMEM; - } -- prot_length = (dev->transport->get_blocks(dev) + 1) * dev->prot_length; -- size = prot_length; - - pr_debug("Using FILEIO prot_length: %llu\n", -- (unsigned long long)prot_length); -+ (unsigned long long)(dev->transport->get_blocks(dev) + 1) * -+ dev->prot_length); - - memset(buf, 0xff, unit_size); -- for (prot = 0; prot < prot_length; prot += unit_size) { -- len = min(unit_size, size); -- rc = kernel_write(prot_fd, buf, len, pos); -- if (rc != len) { -- pr_err("vfs_write to prot file failed: %d\n", rc); -- ret = -ENODEV; -- goto out; -- } -- pos += len; -- size -= len; -- } -- --out: -+ ret = fd_do_prot_fill(dev, 0, dev->transport->get_blocks(dev) + 1, -+ buf, unit_size); - vfree(buf); - return ret; - } -diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c -index 3e72974..755bd9b3 100644 ---- a/drivers/target/target_core_sbc.c -+++ b/drivers/target/target_core_sbc.c -@@ -312,7 +312,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o - return 0; - } - --static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd) -+static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success) - { - unsigned char *buf, *addr; - struct scatterlist *sg; -@@ -376,7 +376,7 @@ sbc_execute_rw(struct se_cmd *cmd) - cmd->data_direction); - } - --static sense_reason_t compare_and_write_post(struct se_cmd *cmd) -+static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success) - { - struct se_device *dev = cmd->se_dev; - -@@ -399,7 +399,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd) - return TCM_NO_SENSE; - } - --static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) -+static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success) - { - struct se_device *dev = cmd->se_dev; - struct scatterlist *write_sg = NULL, *sg; -@@ -414,11 +414,16 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) - - /* - * Handle early failure in transport_generic_request_failure(), -- * which will not have taken ->caw_mutex yet.. -+ * which will not have taken ->caw_sem yet.. - */ -- if (!cmd->t_data_sg || !cmd->t_bidi_data_sg) -+ if (!success && (!cmd->t_data_sg || !cmd->t_bidi_data_sg)) - return TCM_NO_SENSE; - /* -+ * Handle special case for zero-length COMPARE_AND_WRITE -+ */ -+ if (!cmd->data_length) -+ goto out; -+ /* - * Immediately exit + release dev->caw_sem if command has already - * been failed with a non-zero SCSI status. - */ -diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c -index ac3cbab..f786de0 100644 ---- a/drivers/target/target_core_transport.c -+++ b/drivers/target/target_core_transport.c -@@ -1615,11 +1615,11 @@ void transport_generic_request_failure(struct se_cmd *cmd, - transport_complete_task_attr(cmd); - /* - * Handle special case for COMPARE_AND_WRITE failure, where the -- * callback is expected to drop the per device ->caw_mutex. -+ * callback is expected to drop the per device ->caw_sem. - */ - if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && - cmd->transport_complete_callback) -- cmd->transport_complete_callback(cmd); -+ cmd->transport_complete_callback(cmd, false); - - switch (sense_reason) { - case TCM_NON_EXISTENT_LUN: -@@ -1975,8 +1975,12 @@ static void target_complete_ok_work(struct work_struct *work) - if (cmd->transport_complete_callback) { - sense_reason_t rc; - -- rc = cmd->transport_complete_callback(cmd); -+ rc = cmd->transport_complete_callback(cmd, true); - if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) { -+ if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && -+ !cmd->data_length) -+ goto queue_rsp; -+ - return; - } else if (rc) { - ret = transport_send_check_condition_and_sense(cmd, -@@ -1990,6 +1994,7 @@ static void target_complete_ok_work(struct work_struct *work) - } - } - -+queue_rsp: - switch (cmd->data_direction) { - case DMA_FROM_DEVICE: - spin_lock(&cmd->se_lun->lun_sep_lock); -@@ -2094,6 +2099,16 @@ static inline void transport_reset_sgl_orig(struct se_cmd *cmd) - static inline void transport_free_pages(struct se_cmd *cmd) - { - if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) { -+ /* -+ * Release special case READ buffer payload required for -+ * SG_TO_MEM_NOALLOC to function with COMPARE_AND_WRITE -+ */ -+ if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) { -+ transport_free_sgl(cmd->t_bidi_data_sg, -+ cmd->t_bidi_data_nents); -+ cmd->t_bidi_data_sg = NULL; -+ cmd->t_bidi_data_nents = 0; -+ } - transport_reset_sgl_orig(cmd); - return; - } -@@ -2246,6 +2261,7 @@ sense_reason_t - transport_generic_new_cmd(struct se_cmd *cmd) - { - int ret = 0; -+ bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); - - /* - * Determine is the TCM fabric module has already allocated physical -@@ -2254,7 +2270,6 @@ transport_generic_new_cmd(struct se_cmd *cmd) - */ - if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) && - cmd->data_length) { -- bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); - - if ((cmd->se_cmd_flags & SCF_BIDI) || - (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) { -@@ -2285,6 +2300,20 @@ transport_generic_new_cmd(struct se_cmd *cmd) - cmd->data_length, zero_flag); - if (ret < 0) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; -+ } else if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && -+ cmd->data_length) { -+ /* -+ * Special case for COMPARE_AND_WRITE with fabrics -+ * using SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC. -+ */ -+ u32 caw_length = cmd->t_task_nolb * -+ cmd->se_dev->dev_attrib.block_size; -+ -+ ret = target_alloc_sgl(&cmd->t_bidi_data_sg, -+ &cmd->t_bidi_data_nents, -+ caw_length, zero_flag); -+ if (ret < 0) -+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } - /* - * If this command is not a write we can execute it right here, -diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c -index deae122..d465ace 100644 ---- a/drivers/tty/serial/8250/8250_core.c -+++ b/drivers/tty/serial/8250/8250_core.c -@@ -3444,7 +3444,8 @@ void serial8250_suspend_port(int line) - port->type != PORT_8250) { - unsigned char canary = 0xa5; - serial_out(up, UART_SCR, canary); -- up->canary = canary; -+ if (serial_in(up, UART_SCR) == canary) -+ up->canary = canary; - } - - uart_suspend_port(&serial8250_reg, port); -diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c -index 6ae5b85..7a80250 100644 ---- a/drivers/tty/serial/8250/8250_dw.c -+++ b/drivers/tty/serial/8250/8250_dw.c -@@ -629,6 +629,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = { - { "80860F0A", 0 }, - { "8086228A", 0 }, - { "APMC0D08", 0}, -+ { "AMD0020", 0 }, - { }, - }; - MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match); -diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c -index 0eb29b1..2306191 100644 ---- a/drivers/tty/serial/imx.c -+++ b/drivers/tty/serial/imx.c -@@ -818,7 +818,7 @@ static irqreturn_t imx_int(int irq, void *dev_id) - if (sts2 & USR2_ORE) { - dev_err(sport->port.dev, "Rx FIFO overrun\n"); - sport->port.icount.overrun++; -- writel(sts2 | USR2_ORE, sport->port.membase + USR2); -+ writel(USR2_ORE, sport->port.membase + USR2); - } - - return IRQ_HANDLED; -@@ -1181,10 +1181,12 @@ static int imx_startup(struct uart_port *port) - imx_uart_dma_init(sport); - - spin_lock_irqsave(&sport->port.lock, flags); -+ - /* - * Finally, clear and enable interrupts - */ - writel(USR1_RTSD, sport->port.membase + USR1); -+ writel(USR2_ORE, sport->port.membase + USR2); - - if (sport->dma_is_inited && !sport->dma_is_enabled) - imx_enable_dma(sport); -@@ -1199,10 +1201,6 @@ static int imx_startup(struct uart_port *port) - - writel(temp, sport->port.membase + UCR1); - -- /* Clear any pending ORE flag before enabling interrupt */ -- temp = readl(sport->port.membase + USR2); -- writel(temp | USR2_ORE, sport->port.membase + USR2); -- - temp = readl(sport->port.membase + UCR4); - temp |= UCR4_OREN; - writel(temp, sport->port.membase + UCR4); -diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c -index a051a7a..a81f9dd 100644 ---- a/drivers/usb/class/cdc-wdm.c -+++ b/drivers/usb/class/cdc-wdm.c -@@ -245,7 +245,7 @@ static void wdm_int_callback(struct urb *urb) - case USB_CDC_NOTIFY_RESPONSE_AVAILABLE: - dev_dbg(&desc->intf->dev, - "NOTIFY_RESPONSE_AVAILABLE received: index %d len %d", -- dr->wIndex, dr->wLength); -+ le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength)); - break; - - case USB_CDC_NOTIFY_NETWORK_CONNECTION: -@@ -262,7 +262,9 @@ static void wdm_int_callback(struct urb *urb) - clear_bit(WDM_POLL_RUNNING, &desc->flags); - dev_err(&desc->intf->dev, - "unknown notification %d received: index %d len %d\n", -- dr->bNotificationType, dr->wIndex, dr->wLength); -+ dr->bNotificationType, -+ le16_to_cpu(dr->wIndex), -+ le16_to_cpu(dr->wLength)); - goto exit; - } - -@@ -408,7 +410,7 @@ static ssize_t wdm_write - USB_RECIP_INTERFACE); - req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; - req->wValue = 0; -- req->wIndex = desc->inum; -+ req->wIndex = desc->inum; /* already converted */ - req->wLength = cpu_to_le16(count); - set_bit(WDM_IN_USE, &desc->flags); - desc->outbuf = buf; -@@ -422,7 +424,7 @@ static ssize_t wdm_write - rv = usb_translate_errors(rv); - } else { - dev_dbg(&desc->intf->dev, "Tx URB has been submitted index=%d", -- req->wIndex); -+ le16_to_cpu(req->wIndex)); - } - out: - usb_autopm_put_interface(desc->intf); -@@ -820,7 +822,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor - desc->irq->bRequestType = (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE); - desc->irq->bRequest = USB_CDC_GET_ENCAPSULATED_RESPONSE; - desc->irq->wValue = 0; -- desc->irq->wIndex = desc->inum; -+ desc->irq->wIndex = desc->inum; /* already converted */ - desc->irq->wLength = cpu_to_le16(desc->wMaxCommand); - - usb_fill_control_urb( -diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c -index d7c3d5a..3b71516 100644 ---- a/drivers/usb/core/hub.c -+++ b/drivers/usb/core/hub.c -@@ -3406,10 +3406,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) - if (status) { - dev_dbg(&port_dev->dev, "can't resume, status %d\n", status); - } else { -- /* drive resume for at least 20 msec */ -+ /* drive resume for USB_RESUME_TIMEOUT msec */ - dev_dbg(&udev->dev, "usb %sresume\n", - (PMSG_IS_AUTO(msg) ? "auto-" : "")); -- msleep(25); -+ msleep(USB_RESUME_TIMEOUT); - - /* Virtual root hubs can trigger on GET_PORT_STATUS to - * stop resume signaling. Then finish the resume -diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c -index c78c874..758b7e0 100644 ---- a/drivers/usb/dwc2/hcd.c -+++ b/drivers/usb/dwc2/hcd.c -@@ -1521,7 +1521,7 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, - dev_dbg(hsotg->dev, - "ClearPortFeature USB_PORT_FEAT_SUSPEND\n"); - writel(0, hsotg->regs + PCGCTL); -- usleep_range(20000, 40000); -+ msleep(USB_RESUME_TIMEOUT); - - hprt0 = dwc2_read_hprt0(hsotg); - hprt0 |= HPRT0_RES; -diff --git a/drivers/usb/gadget/legacy/printer.c b/drivers/usb/gadget/legacy/printer.c -index 9054598..6385c19 100644 ---- a/drivers/usb/gadget/legacy/printer.c -+++ b/drivers/usb/gadget/legacy/printer.c -@@ -1031,6 +1031,15 @@ unknown: - break; - } - /* host either stalls (value < 0) or reports success */ -+ if (value >= 0) { -+ req->length = value; -+ req->zero = value < wLength; -+ value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC); -+ if (value < 0) { -+ ERROR(dev, "%s:%d Error!\n", __func__, __LINE__); -+ req->status = 0; -+ } -+ } - return value; - } - -diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c -index 85e56d1..f4d88df 100644 ---- a/drivers/usb/host/ehci-hcd.c -+++ b/drivers/usb/host/ehci-hcd.c -@@ -792,12 +792,12 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) - ehci->reset_done[i] == 0)) - continue; - -- /* start 20 msec resume signaling from this port, -- * and make hub_wq collect PORT_STAT_C_SUSPEND to -- * stop that signaling. Use 5 ms extra for safety, -- * like usb_port_resume() does. -+ /* start USB_RESUME_TIMEOUT msec resume signaling from -+ * this port, and make hub_wq collect -+ * PORT_STAT_C_SUSPEND to stop that signaling. - */ -- ehci->reset_done[i] = jiffies + msecs_to_jiffies(25); -+ ehci->reset_done[i] = jiffies + -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - set_bit(i, &ehci->resuming_ports); - ehci_dbg (ehci, "port %d remote wakeup\n", i + 1); - usb_hcd_start_port_resume(&hcd->self, i); -diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c -index 87cf86f..7354d01 100644 ---- a/drivers/usb/host/ehci-hub.c -+++ b/drivers/usb/host/ehci-hub.c -@@ -471,10 +471,13 @@ static int ehci_bus_resume (struct usb_hcd *hcd) - ehci_writel(ehci, temp, &ehci->regs->port_status [i]); - } - -- /* msleep for 20ms only if code is trying to resume port */ -+ /* -+ * msleep for USB_RESUME_TIMEOUT ms only if code is trying to resume -+ * port -+ */ - if (resume_needed) { - spin_unlock_irq(&ehci->lock); -- msleep(20); -+ msleep(USB_RESUME_TIMEOUT); - spin_lock_irq(&ehci->lock); - if (ehci->shutdown) - goto shutdown; -@@ -942,7 +945,7 @@ int ehci_hub_control( - temp &= ~PORT_WAKE_BITS; - ehci_writel(ehci, temp | PORT_RESUME, status_reg); - ehci->reset_done[wIndex] = jiffies -- + msecs_to_jiffies(20); -+ + msecs_to_jiffies(USB_RESUME_TIMEOUT); - set_bit(wIndex, &ehci->resuming_ports); - usb_hcd_start_port_resume(&hcd->self, wIndex); - break; -diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c -index 475b21f..7a6681f 100644 ---- a/drivers/usb/host/fotg210-hcd.c -+++ b/drivers/usb/host/fotg210-hcd.c -@@ -1595,7 +1595,7 @@ static int fotg210_hub_control( - /* resume signaling for 20 msec */ - fotg210_writel(fotg210, temp | PORT_RESUME, status_reg); - fotg210->reset_done[wIndex] = jiffies -- + msecs_to_jiffies(20); -+ + msecs_to_jiffies(USB_RESUME_TIMEOUT); - break; - case USB_PORT_FEAT_C_SUSPEND: - clear_bit(wIndex, &fotg210->port_c_suspend); -diff --git a/drivers/usb/host/fusbh200-hcd.c b/drivers/usb/host/fusbh200-hcd.c -index a83eefe..ba77e2e 100644 ---- a/drivers/usb/host/fusbh200-hcd.c -+++ b/drivers/usb/host/fusbh200-hcd.c -@@ -1550,10 +1550,9 @@ static int fusbh200_hub_control ( - if ((temp & PORT_PE) == 0) - goto error; - -- /* resume signaling for 20 msec */ - fusbh200_writel(fusbh200, temp | PORT_RESUME, status_reg); - fusbh200->reset_done[wIndex] = jiffies -- + msecs_to_jiffies(20); -+ + msecs_to_jiffies(USB_RESUME_TIMEOUT); - break; - case USB_PORT_FEAT_C_SUSPEND: - clear_bit(wIndex, &fusbh200->port_c_suspend); -diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c -index 113d0cc..9ef5644 100644 ---- a/drivers/usb/host/isp116x-hcd.c -+++ b/drivers/usb/host/isp116x-hcd.c -@@ -1490,7 +1490,7 @@ static int isp116x_bus_resume(struct usb_hcd *hcd) - spin_unlock_irq(&isp116x->lock); - - hcd->state = HC_STATE_RESUMING; -- msleep(20); -+ msleep(USB_RESUME_TIMEOUT); - - /* Go operational */ - spin_lock_irq(&isp116x->lock); -diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c -index ef7efb2..28a2866 100644 ---- a/drivers/usb/host/oxu210hp-hcd.c -+++ b/drivers/usb/host/oxu210hp-hcd.c -@@ -2500,11 +2500,12 @@ static irqreturn_t oxu210_hcd_irq(struct usb_hcd *hcd) - || oxu->reset_done[i] != 0) - continue; - -- /* start 20 msec resume signaling from this port, -- * and make hub_wq collect PORT_STAT_C_SUSPEND to -+ /* start USB_RESUME_TIMEOUT resume signaling from this -+ * port, and make hub_wq collect PORT_STAT_C_SUSPEND to - * stop that signaling. - */ -- oxu->reset_done[i] = jiffies + msecs_to_jiffies(20); -+ oxu->reset_done[i] = jiffies + -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - oxu_dbg(oxu, "port %d remote wakeup\n", i + 1); - mod_timer(&hcd->rh_timer, oxu->reset_done[i]); - } -diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c -index bdc82fe..54a4170 100644 ---- a/drivers/usb/host/r8a66597-hcd.c -+++ b/drivers/usb/host/r8a66597-hcd.c -@@ -2301,7 +2301,7 @@ static int r8a66597_bus_resume(struct usb_hcd *hcd) - rh->port &= ~USB_PORT_STAT_SUSPEND; - rh->port |= USB_PORT_STAT_C_SUSPEND << 16; - r8a66597_mdfy(r8a66597, RESUME, RESUME | UACT, dvstctr_reg); -- msleep(50); -+ msleep(USB_RESUME_TIMEOUT); - r8a66597_mdfy(r8a66597, UACT, RESUME | UACT, dvstctr_reg); - } - -diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c -index 4f4ba1e..9118cd8 100644 ---- a/drivers/usb/host/sl811-hcd.c -+++ b/drivers/usb/host/sl811-hcd.c -@@ -1259,7 +1259,7 @@ sl811h_hub_control( - sl811_write(sl811, SL11H_CTLREG1, sl811->ctrl1); - - mod_timer(&sl811->timer, jiffies -- + msecs_to_jiffies(20)); -+ + msecs_to_jiffies(USB_RESUME_TIMEOUT)); - break; - case USB_PORT_FEAT_POWER: - port_power(sl811, 0); -diff --git a/drivers/usb/host/uhci-hub.c b/drivers/usb/host/uhci-hub.c -index 19ba5ea..7b3d1af 100644 ---- a/drivers/usb/host/uhci-hub.c -+++ b/drivers/usb/host/uhci-hub.c -@@ -166,7 +166,7 @@ static void uhci_check_ports(struct uhci_hcd *uhci) - /* Port received a wakeup request */ - set_bit(port, &uhci->resuming_ports); - uhci->ports_timeout = jiffies + -- msecs_to_jiffies(25); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - usb_hcd_start_port_resume( - &uhci_to_hcd(uhci)->self, port); - -@@ -338,7 +338,8 @@ static int uhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, - uhci_finish_suspend(uhci, port, port_addr); - - /* USB v2.0 7.1.7.5 */ -- uhci->ports_timeout = jiffies + msecs_to_jiffies(50); -+ uhci->ports_timeout = jiffies + -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - break; - case USB_PORT_FEAT_POWER: - /* UHCI has no power switching */ -diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c -index 73485fa..eeedde8 100644 ---- a/drivers/usb/host/xhci-ring.c -+++ b/drivers/usb/host/xhci-ring.c -@@ -1574,7 +1574,7 @@ static void handle_port_status(struct xhci_hcd *xhci, - } else { - xhci_dbg(xhci, "resume HS port %d\n", port_id); - bus_state->resume_done[faked_port_index] = jiffies + -- msecs_to_jiffies(20); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - set_bit(faked_port_index, &bus_state->resuming_ports); - mod_timer(&hcd->rh_timer, - bus_state->resume_done[faked_port_index]); -diff --git a/drivers/usb/isp1760/isp1760-hcd.c b/drivers/usb/isp1760/isp1760-hcd.c -index 3cb98b1..7911b6b 100644 ---- a/drivers/usb/isp1760/isp1760-hcd.c -+++ b/drivers/usb/isp1760/isp1760-hcd.c -@@ -1869,7 +1869,7 @@ static int isp1760_hub_control(struct usb_hcd *hcd, u16 typeReq, - reg_write32(hcd->regs, HC_PORTSC1, - temp | PORT_RESUME); - priv->reset_done = jiffies + -- msecs_to_jiffies(20); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT); - } - break; - case USB_PORT_FEAT_C_SUSPEND: -diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c -index 067920f..ec0ee3b 100644 ---- a/drivers/usb/musb/musb_core.c -+++ b/drivers/usb/musb/musb_core.c -@@ -99,6 +99,7 @@ - #include - #include - #include -+#include - - #include "musb_core.h" - -@@ -562,7 +563,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, - (USB_PORT_STAT_C_SUSPEND << 16) - | MUSB_PORT_STAT_RESUME; - musb->rh_timer = jiffies -- + msecs_to_jiffies(20); -+ + msecs_to_jiffies(USB_RESUME_TIMEOUT); - musb->need_finish_resume = 1; - - musb->xceiv->otg->state = OTG_STATE_A_HOST; -@@ -1597,16 +1598,30 @@ irqreturn_t musb_interrupt(struct musb *musb) - is_host_active(musb) ? "host" : "peripheral", - musb->int_usb, musb->int_tx, musb->int_rx); - -- /* the core can interrupt us for multiple reasons; docs have -- * a generic interrupt flowchart to follow -+ /** -+ * According to Mentor Graphics' documentation, flowchart on page 98, -+ * IRQ should be handled as follows: -+ * -+ * . Resume IRQ -+ * . Session Request IRQ -+ * . VBUS Error IRQ -+ * . Suspend IRQ -+ * . Connect IRQ -+ * . Disconnect IRQ -+ * . Reset/Babble IRQ -+ * . SOF IRQ (we're not using this one) -+ * . Endpoint 0 IRQ -+ * . TX Endpoints -+ * . RX Endpoints -+ * -+ * We will be following that flowchart in order to avoid any problems -+ * that might arise with internal Finite State Machine. - */ -+ - if (musb->int_usb) - retval |= musb_stage0_irq(musb, musb->int_usb, - devctl); - -- /* "stage 1" is handling endpoint irqs */ -- -- /* handle endpoint 0 first */ - if (musb->int_tx & 1) { - if (is_host_active(musb)) - retval |= musb_h_ep0_irq(musb); -@@ -1614,37 +1629,31 @@ irqreturn_t musb_interrupt(struct musb *musb) - retval |= musb_g_ep0_irq(musb); - } - -- /* RX on endpoints 1-15 */ -- reg = musb->int_rx >> 1; -+ reg = musb->int_tx >> 1; - ep_num = 1; - while (reg) { - if (reg & 1) { -- /* musb_ep_select(musb->mregs, ep_num); */ -- /* REVISIT just retval = ep->rx_irq(...) */ - retval = IRQ_HANDLED; - if (is_host_active(musb)) -- musb_host_rx(musb, ep_num); -+ musb_host_tx(musb, ep_num); - else -- musb_g_rx(musb, ep_num); -+ musb_g_tx(musb, ep_num); - } -- - reg >>= 1; - ep_num++; - } - -- /* TX on endpoints 1-15 */ -- reg = musb->int_tx >> 1; -+ reg = musb->int_rx >> 1; - ep_num = 1; - while (reg) { - if (reg & 1) { -- /* musb_ep_select(musb->mregs, ep_num); */ -- /* REVISIT just retval |= ep->tx_irq(...) */ - retval = IRQ_HANDLED; - if (is_host_active(musb)) -- musb_host_tx(musb, ep_num); -+ musb_host_rx(musb, ep_num); - else -- musb_g_tx(musb, ep_num); -+ musb_g_rx(musb, ep_num); - } -+ - reg >>= 1; - ep_num++; - } -@@ -2463,7 +2472,7 @@ static int musb_resume(struct device *dev) - if (musb->need_finish_resume) { - musb->need_finish_resume = 0; - schedule_delayed_work(&musb->finish_resume_work, -- msecs_to_jiffies(20)); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT)); - } - - /* -@@ -2506,7 +2515,7 @@ static int musb_runtime_resume(struct device *dev) - if (musb->need_finish_resume) { - musb->need_finish_resume = 0; - schedule_delayed_work(&musb->finish_resume_work, -- msecs_to_jiffies(20)); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT)); - } - - return 0; -diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c -index 294e159..5428ed1 100644 ---- a/drivers/usb/musb/musb_virthub.c -+++ b/drivers/usb/musb/musb_virthub.c -@@ -136,7 +136,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend) - /* later, GetPortStatus will stop RESUME signaling */ - musb->port1_status |= MUSB_PORT_STAT_RESUME; - schedule_delayed_work(&musb->finish_resume_work, -- msecs_to_jiffies(20)); -+ msecs_to_jiffies(USB_RESUME_TIMEOUT)); - } - } - -diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c -index 2f9735b..d1cd6b5 100644 ---- a/drivers/usb/phy/phy.c -+++ b/drivers/usb/phy/phy.c -@@ -81,7 +81,9 @@ static void devm_usb_phy_release(struct device *dev, void *res) - - static int devm_usb_phy_match(struct device *dev, void *res, void *match_data) - { -- return res == match_data; -+ struct usb_phy **phy = res; -+ -+ return *phy == match_data; - } - - /** -diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c -index 995986b..d925f55 100644 ---- a/fs/binfmt_elf.c -+++ b/fs/binfmt_elf.c -@@ -862,6 +862,7 @@ static int load_elf_binary(struct linux_binprm *bprm) - i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot = 0, elf_flags; - unsigned long k, vaddr; -+ unsigned long total_size = 0; - - if (elf_ppnt->p_type != PT_LOAD) - continue; -@@ -924,10 +925,16 @@ static int load_elf_binary(struct linux_binprm *bprm) - #else - load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr); - #endif -+ total_size = total_mapping_size(elf_phdata, -+ loc->elf_ex.e_phnum); -+ if (!total_size) { -+ error = -EINVAL; -+ goto out_free_dentry; -+ } - } - - error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, -- elf_prot, elf_flags, 0); -+ elf_prot, elf_flags, total_size); - if (BAD_ADDR(error)) { - retval = IS_ERR((void *)error) ? - PTR_ERR((void*)error) : -EINVAL; -diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c -index 8b353ad..0a795c9 100644 ---- a/fs/btrfs/extent-tree.c -+++ b/fs/btrfs/extent-tree.c -@@ -6956,12 +6956,11 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, - return -ENOSPC; - } - -- if (btrfs_test_opt(root, DISCARD)) -- ret = btrfs_discard_extent(root, start, len, NULL); -- - if (pin) - pin_down_extent(root, cache, start, len, 1); - else { -+ if (btrfs_test_opt(root, DISCARD)) -+ ret = btrfs_discard_extent(root, start, len, NULL); - btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); - } -diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c -index 74609b9..f23d4be 100644 ---- a/fs/btrfs/ioctl.c -+++ b/fs/btrfs/ioctl.c -@@ -2897,6 +2897,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 len, - if (src == dst) - return -EINVAL; - -+ if (len == 0) -+ return 0; -+ - btrfs_double_lock(src, loff, dst, dst_loff, len); - - ret = extent_same_check_offsets(src, loff, len); -@@ -3626,6 +3629,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, - if (off + len == src->i_size) - len = ALIGN(src->i_size, bs) - off; - -+ if (len == 0) { -+ ret = 0; -+ goto out_unlock; -+ } -+ - /* verify the end result is block aligned */ - if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || - !IS_ALIGNED(destoff, bs)) -diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c -index 883b936..45ea704 100644 ---- a/fs/btrfs/xattr.c -+++ b/fs/btrfs/xattr.c -@@ -364,22 +364,42 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { - /* - * Check if the attribute is in a supported namespace. - * -- * This applied after the check for the synthetic attributes in the system -+ * This is applied after the check for the synthetic attributes in the system - * namespace. - */ --static bool btrfs_is_valid_xattr(const char *name) -+static int btrfs_is_valid_xattr(const char *name) - { -- return !strncmp(name, XATTR_SECURITY_PREFIX, -- XATTR_SECURITY_PREFIX_LEN) || -- !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) || -- !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || -- !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) || -- !strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN); -+ int len = strlen(name); -+ int prefixlen = 0; -+ -+ if (!strncmp(name, XATTR_SECURITY_PREFIX, -+ XATTR_SECURITY_PREFIX_LEN)) -+ prefixlen = XATTR_SECURITY_PREFIX_LEN; -+ else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) -+ prefixlen = XATTR_SYSTEM_PREFIX_LEN; -+ else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) -+ prefixlen = XATTR_TRUSTED_PREFIX_LEN; -+ else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) -+ prefixlen = XATTR_USER_PREFIX_LEN; -+ else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) -+ prefixlen = XATTR_BTRFS_PREFIX_LEN; -+ else -+ return -EOPNOTSUPP; -+ -+ /* -+ * The name cannot consist of just prefix -+ */ -+ if (len <= prefixlen) -+ return -EINVAL; -+ -+ return 0; - } - - ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) - { -+ int ret; -+ - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler -@@ -388,8 +408,9 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, buffer, size); - -- if (!btrfs_is_valid_xattr(name)) -- return -EOPNOTSUPP; -+ ret = btrfs_is_valid_xattr(name); -+ if (ret) -+ return ret; - return __btrfs_getxattr(dentry->d_inode, name, buffer, size); - } - -@@ -397,6 +418,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) - { - struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; -+ int ret; - - /* - * The permission on security.* and system.* is not checked -@@ -413,8 +435,9 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, size, flags); - -- if (!btrfs_is_valid_xattr(name)) -- return -EOPNOTSUPP; -+ ret = btrfs_is_valid_xattr(name); -+ if (ret) -+ return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(dentry->d_inode, name, -@@ -430,6 +453,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, - int btrfs_removexattr(struct dentry *dentry, const char *name) - { - struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root; -+ int ret; - - /* - * The permission on security.* and system.* is not checked -@@ -446,8 +470,9 @@ int btrfs_removexattr(struct dentry *dentry, const char *name) - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); - -- if (!btrfs_is_valid_xattr(name)) -- return -EOPNOTSUPP; -+ ret = btrfs_is_valid_xattr(name); -+ if (ret) -+ return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(dentry->d_inode, name, -diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c -index 28fe71a..aae7011 100644 ---- a/fs/ext4/namei.c -+++ b/fs/ext4/namei.c -@@ -1865,7 +1865,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, - struct inode *inode) - { - struct inode *dir = dentry->d_parent->d_inode; -- struct buffer_head *bh; -+ struct buffer_head *bh = NULL; - struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; - struct super_block *sb; -@@ -1889,14 +1889,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, - return retval; - if (retval == 1) { - retval = 0; -- return retval; -+ goto out; - } - } - - if (is_dx(dir)) { - retval = ext4_dx_add_entry(handle, dentry, inode); - if (!retval || (retval != ERR_BAD_DX_DIR)) -- return retval; -+ goto out; - ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); - dx_fallback++; - ext4_mark_inode_dirty(handle, dir); -@@ -1908,14 +1908,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, - return PTR_ERR(bh); - - retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); -- if (retval != -ENOSPC) { -- brelse(bh); -- return retval; -- } -+ if (retval != -ENOSPC) -+ goto out; - - if (blocks == 1 && !dx_fallback && -- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) -- return make_indexed_dir(handle, dentry, inode, bh); -+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { -+ retval = make_indexed_dir(handle, dentry, inode, bh); -+ bh = NULL; /* make_indexed_dir releases bh */ -+ goto out; -+ } - brelse(bh); - } - bh = ext4_append(handle, dir, &block); -@@ -1931,6 +1932,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, - } - - retval = add_dirent_to_buf(handle, dentry, inode, de, bh); -+out: - brelse(bh); - if (retval == 0) - ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY); -diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c -index 665ef5a..a563ddb 100644 ---- a/fs/lockd/svcsubs.c -+++ b/fs/lockd/svcsubs.c -@@ -31,7 +31,7 @@ - static struct hlist_head nlm_files[FILE_NRHASH]; - static DEFINE_MUTEX(nlm_file_mutex); - --#ifdef NFSD_DEBUG -+#ifdef CONFIG_SUNRPC_DEBUG - static inline void nlm_debug_print_fh(char *msg, struct nfs_fh *f) - { - u32 *fhp = (u32*)f->data; -diff --git a/fs/namei.c b/fs/namei.c -index c83145a..caa38a2 100644 ---- a/fs/namei.c -+++ b/fs/namei.c -@@ -1591,7 +1591,8 @@ static inline int walk_component(struct nameidata *nd, struct path *path, - - if (should_follow_link(path->dentry, follow)) { - if (nd->flags & LOOKUP_RCU) { -- if (unlikely(unlazy_walk(nd, path->dentry))) { -+ if (unlikely(nd->path.mnt != path->mnt || -+ unlazy_walk(nd, path->dentry))) { - err = -ECHILD; - goto out_err; - } -@@ -3047,7 +3048,8 @@ finish_lookup: - - if (should_follow_link(path->dentry, !symlink_ok)) { - if (nd->flags & LOOKUP_RCU) { -- if (unlikely(unlazy_walk(nd, path->dentry))) { -+ if (unlikely(nd->path.mnt != path->mnt || -+ unlazy_walk(nd, path->dentry))) { - error = -ECHILD; - goto out; - } -diff --git a/fs/namespace.c b/fs/namespace.c -index 82ef140..4622ee3 100644 ---- a/fs/namespace.c -+++ b/fs/namespace.c -@@ -632,14 +632,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) - */ - struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) - { -- struct mount *p, *res; -- res = p = __lookup_mnt(mnt, dentry); -+ struct mount *p, *res = NULL; -+ p = __lookup_mnt(mnt, dentry); - if (!p) - goto out; -+ if (!(p->mnt.mnt_flags & MNT_UMOUNT)) -+ res = p; - hlist_for_each_entry_continue(p, mnt_hash) { - if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) - break; -- res = p; -+ if (!(p->mnt.mnt_flags & MNT_UMOUNT)) -+ res = p; - } - out: - return res; -@@ -795,10 +798,8 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns) - /* - * vfsmount lock must be held for write - */ --static void detach_mnt(struct mount *mnt, struct path *old_path) -+static void unhash_mnt(struct mount *mnt) - { -- old_path->dentry = mnt->mnt_mountpoint; -- old_path->mnt = &mnt->mnt_parent->mnt; - mnt->mnt_parent = mnt; - mnt->mnt_mountpoint = mnt->mnt.mnt_root; - list_del_init(&mnt->mnt_child); -@@ -811,6 +812,26 @@ static void detach_mnt(struct mount *mnt, struct path *old_path) - /* - * vfsmount lock must be held for write - */ -+static void detach_mnt(struct mount *mnt, struct path *old_path) -+{ -+ old_path->dentry = mnt->mnt_mountpoint; -+ old_path->mnt = &mnt->mnt_parent->mnt; -+ unhash_mnt(mnt); -+} -+ -+/* -+ * vfsmount lock must be held for write -+ */ -+static void umount_mnt(struct mount *mnt) -+{ -+ /* old mountpoint will be dropped when we can do that */ -+ mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint; -+ unhash_mnt(mnt); -+} -+ -+/* -+ * vfsmount lock must be held for write -+ */ - void mnt_set_mountpoint(struct mount *mnt, - struct mountpoint *mp, - struct mount *child_mnt) -@@ -1078,6 +1099,13 @@ static void mntput_no_expire(struct mount *mnt) - rcu_read_unlock(); - - list_del(&mnt->mnt_instance); -+ -+ if (unlikely(!list_empty(&mnt->mnt_mounts))) { -+ struct mount *p, *tmp; -+ list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { -+ umount_mnt(p); -+ } -+ } - unlock_mount_hash(); - - if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { -@@ -1319,49 +1347,63 @@ static inline void namespace_lock(void) - down_write(&namespace_sem); - } - -+enum umount_tree_flags { -+ UMOUNT_SYNC = 1, -+ UMOUNT_PROPAGATE = 2, -+ UMOUNT_CONNECTED = 4, -+}; - /* - * mount_lock must be held - * namespace_sem must be held for write -- * how = 0 => just this tree, don't propagate -- * how = 1 => propagate; we know that nobody else has reference to any victims -- * how = 2 => lazy umount - */ --void umount_tree(struct mount *mnt, int how) -+static void umount_tree(struct mount *mnt, enum umount_tree_flags how) - { -- HLIST_HEAD(tmp_list); -+ LIST_HEAD(tmp_list); - struct mount *p; - -+ if (how & UMOUNT_PROPAGATE) -+ propagate_mount_unlock(mnt); -+ -+ /* Gather the mounts to umount */ - for (p = mnt; p; p = next_mnt(p, mnt)) { -- hlist_del_init_rcu(&p->mnt_hash); -- hlist_add_head(&p->mnt_hash, &tmp_list); -+ p->mnt.mnt_flags |= MNT_UMOUNT; -+ list_move(&p->mnt_list, &tmp_list); - } - -- hlist_for_each_entry(p, &tmp_list, mnt_hash) -+ /* Hide the mounts from mnt_mounts */ -+ list_for_each_entry(p, &tmp_list, mnt_list) { - list_del_init(&p->mnt_child); -+ } - -- if (how) -+ /* Add propogated mounts to the tmp_list */ -+ if (how & UMOUNT_PROPAGATE) - propagate_umount(&tmp_list); - -- while (!hlist_empty(&tmp_list)) { -- p = hlist_entry(tmp_list.first, struct mount, mnt_hash); -- hlist_del_init_rcu(&p->mnt_hash); -+ while (!list_empty(&tmp_list)) { -+ bool disconnect; -+ p = list_first_entry(&tmp_list, struct mount, mnt_list); - list_del_init(&p->mnt_expire); - list_del_init(&p->mnt_list); - __touch_mnt_namespace(p->mnt_ns); - p->mnt_ns = NULL; -- if (how < 2) -+ if (how & UMOUNT_SYNC) - p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; - -- pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, &unmounted); -+ disconnect = !(((how & UMOUNT_CONNECTED) && -+ mnt_has_parent(p) && -+ (p->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) || -+ IS_MNT_LOCKED_AND_LAZY(p)); -+ -+ pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, -+ disconnect ? &unmounted : NULL); - if (mnt_has_parent(p)) { -- hlist_del_init(&p->mnt_mp_list); -- put_mountpoint(p->mnt_mp); - mnt_add_count(p->mnt_parent, -1); -- /* old mountpoint will be dropped when we can do that */ -- p->mnt_ex_mountpoint = p->mnt_mountpoint; -- p->mnt_mountpoint = p->mnt.mnt_root; -- p->mnt_parent = p; -- p->mnt_mp = NULL; -+ if (!disconnect) { -+ /* Don't forget about p */ -+ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); -+ } else { -+ umount_mnt(p); -+ } - } - change_mnt_propagation(p, MS_PRIVATE); - } -@@ -1447,14 +1489,14 @@ static int do_umount(struct mount *mnt, int flags) - - if (flags & MNT_DETACH) { - if (!list_empty(&mnt->mnt_list)) -- umount_tree(mnt, 2); -+ umount_tree(mnt, UMOUNT_PROPAGATE); - retval = 0; - } else { - shrink_submounts(mnt); - retval = -EBUSY; - if (!propagate_mount_busy(mnt, 2)) { - if (!list_empty(&mnt->mnt_list)) -- umount_tree(mnt, 1); -+ umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); - retval = 0; - } - } -@@ -1480,13 +1522,20 @@ void __detach_mounts(struct dentry *dentry) - - namespace_lock(); - mp = lookup_mountpoint(dentry); -- if (!mp) -+ if (IS_ERR_OR_NULL(mp)) - goto out_unlock; - - lock_mount_hash(); - while (!hlist_empty(&mp->m_list)) { - mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); -- umount_tree(mnt, 2); -+ if (mnt->mnt.mnt_flags & MNT_UMOUNT) { -+ struct mount *p, *tmp; -+ list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { -+ hlist_add_head(&p->mnt_umount.s_list, &unmounted); -+ umount_mnt(p); -+ } -+ } -+ else umount_tree(mnt, UMOUNT_CONNECTED); - } - unlock_mount_hash(); - put_mountpoint(mp); -@@ -1648,7 +1697,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, - out: - if (res) { - lock_mount_hash(); -- umount_tree(res, 0); -+ umount_tree(res, UMOUNT_SYNC); - unlock_mount_hash(); - } - return q; -@@ -1672,7 +1721,7 @@ void drop_collected_mounts(struct vfsmount *mnt) - { - namespace_lock(); - lock_mount_hash(); -- umount_tree(real_mount(mnt), 0); -+ umount_tree(real_mount(mnt), UMOUNT_SYNC); - unlock_mount_hash(); - namespace_unlock(); - } -@@ -1855,7 +1904,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, - out_cleanup_ids: - while (!hlist_empty(&tree_list)) { - child = hlist_entry(tree_list.first, struct mount, mnt_hash); -- umount_tree(child, 0); -+ umount_tree(child, UMOUNT_SYNC); - } - unlock_mount_hash(); - cleanup_group_ids(source_mnt, NULL); -@@ -2035,7 +2084,7 @@ static int do_loopback(struct path *path, const char *old_name, - err = graft_tree(mnt, parent, mp); - if (err) { - lock_mount_hash(); -- umount_tree(mnt, 0); -+ umount_tree(mnt, UMOUNT_SYNC); - unlock_mount_hash(); - } - out2: -@@ -2406,7 +2455,7 @@ void mark_mounts_for_expiry(struct list_head *mounts) - while (!list_empty(&graveyard)) { - mnt = list_first_entry(&graveyard, struct mount, mnt_expire); - touch_mnt_namespace(mnt->mnt_ns); -- umount_tree(mnt, 1); -+ umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); - } - unlock_mount_hash(); - namespace_unlock(); -@@ -2477,7 +2526,7 @@ static void shrink_submounts(struct mount *mnt) - m = list_first_entry(&graveyard, struct mount, - mnt_expire); - touch_mnt_namespace(m->mnt_ns); -- umount_tree(m, 1); -+ umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); - } - } - } -diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c -index 351be920..8d129bb 100644 ---- a/fs/nfs/callback.c -+++ b/fs/nfs/callback.c -@@ -128,7 +128,7 @@ nfs41_callback_svc(void *vrqstp) - if (try_to_freeze()) - continue; - -- prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE); -+ prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); - spin_lock_bh(&serv->sv_cb_lock); - if (!list_empty(&serv->sv_cb_list)) { - req = list_first_entry(&serv->sv_cb_list, -@@ -142,10 +142,10 @@ nfs41_callback_svc(void *vrqstp) - error); - } else { - spin_unlock_bh(&serv->sv_cb_lock); -- /* schedule_timeout to game the hung task watchdog */ -- schedule_timeout(60 * HZ); -+ schedule(); - finish_wait(&serv->sv_cb_waitq, &wq); - } -+ flush_signals(current); - } - return 0; - } -diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c -index e907c8c..ab21ef1 100644 ---- a/fs/nfs/direct.c -+++ b/fs/nfs/direct.c -@@ -129,22 +129,25 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) - int i; - ssize_t count; - -- WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count); -- -- count = dreq->mirrors[hdr->pgio_mirror_idx].count; -- if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) { -- count = hdr->io_start + hdr->good_bytes - dreq->io_start; -- dreq->mirrors[hdr->pgio_mirror_idx].count = count; -- } -- -- /* update the dreq->count by finding the minimum agreed count from all -- * mirrors */ -- count = dreq->mirrors[0].count; -+ if (dreq->mirror_count == 1) { -+ dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes; -+ dreq->count += hdr->good_bytes; -+ } else { -+ /* mirrored writes */ -+ count = dreq->mirrors[hdr->pgio_mirror_idx].count; -+ if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) { -+ count = hdr->io_start + hdr->good_bytes - dreq->io_start; -+ dreq->mirrors[hdr->pgio_mirror_idx].count = count; -+ } -+ /* update the dreq->count by finding the minimum agreed count from all -+ * mirrors */ -+ count = dreq->mirrors[0].count; - -- for (i = 1; i < dreq->mirror_count; i++) -- count = min(count, dreq->mirrors[i].count); -+ for (i = 1; i < dreq->mirror_count; i++) -+ count = min(count, dreq->mirrors[i].count); - -- dreq->count = count; -+ dreq->count = count; -+ } - } - - /* -diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c -index 5c399ec..d494ea2 100644 ---- a/fs/nfs/nfs4xdr.c -+++ b/fs/nfs/nfs4xdr.c -@@ -7365,6 +7365,11 @@ nfs4_stat_to_errno(int stat) - .p_name = #proc, \ - } - -+#define STUB(proc) \ -+[NFSPROC4_CLNT_##proc] = { \ -+ .p_name = #proc, \ -+} -+ - struct rpc_procinfo nfs4_procedures[] = { - PROC(READ, enc_read, dec_read), - PROC(WRITE, enc_write, dec_write), -@@ -7417,6 +7422,7 @@ struct rpc_procinfo nfs4_procedures[] = { - PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name), - PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), - PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), -+ STUB(GETDEVICELIST), - PROC(BIND_CONN_TO_SESSION, - enc_bind_conn_to_session, dec_bind_conn_to_session), - PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), -diff --git a/fs/nfs/read.c b/fs/nfs/read.c -index 568ecf0..848d8b1 100644 ---- a/fs/nfs/read.c -+++ b/fs/nfs/read.c -@@ -284,7 +284,7 @@ int nfs_readpage(struct file *file, struct page *page) - dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_CACHE_SIZE, page_file_index(page)); - nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); -- nfs_inc_stats(inode, NFSIOS_READPAGES); -+ nfs_add_stats(inode, NFSIOS_READPAGES, 1); - - /* - * Try to flush any pending writes to the file.. -diff --git a/fs/nfs/write.c b/fs/nfs/write.c -index 849ed78..41b3f1096 100644 ---- a/fs/nfs/write.c -+++ b/fs/nfs/write.c -@@ -580,7 +580,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st - int ret; - - nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); -- nfs_inc_stats(inode, NFSIOS_WRITEPAGES); -+ nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - - nfs_pageio_cond_complete(pgio, page_file_index(page)); - ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); -diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c -index 92b9d97..5416968 100644 ---- a/fs/nfsd/nfs4proc.c -+++ b/fs/nfsd/nfs4proc.c -@@ -1030,6 +1030,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); - return status; - } -+ if (!file) -+ return nfserr_bad_stateid; - - status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file, - fallocate->falloc_offset, -@@ -1069,6 +1071,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); - return status; - } -+ if (!file) -+ return nfserr_bad_stateid; - - switch (seek->seek_whence) { - case NFS4_CONTENT_DATA: -diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c -index 8ba1d88..ee1cccd 100644 ---- a/fs/nfsd/nfs4state.c -+++ b/fs/nfsd/nfs4state.c -@@ -1139,7 +1139,7 @@ hash_sessionid(struct nfs4_sessionid *sessionid) - return sid->sequence % SESSION_HASH_SIZE; - } - --#ifdef NFSD_DEBUG -+#ifdef CONFIG_SUNRPC_DEBUG - static inline void - dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) - { -diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c -index 5fb7e78..5b33ce1 100644 ---- a/fs/nfsd/nfs4xdr.c -+++ b/fs/nfsd/nfs4xdr.c -@@ -3422,6 +3422,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - unsigned long maxcount; - struct xdr_stream *xdr = &resp->xdr; - struct file *file = read->rd_filp; -+ struct svc_fh *fhp = read->rd_fhp; - int starting_len = xdr->buf->len; - struct raparms *ra; - __be32 *p; -@@ -3445,12 +3446,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - maxcount = min_t(unsigned long, maxcount, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); - -- if (!read->rd_filp) { -+ if (read->rd_filp) -+ err = nfsd_permission(resp->rqstp, fhp->fh_export, -+ fhp->fh_dentry, -+ NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); -+ else - err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp, - &file, &ra); -- if (err) -- goto err_truncate; -- } -+ if (err) -+ goto err_truncate; - - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) - err = nfsd4_encode_splice_read(resp, read, file, maxcount); -diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c -index aa47d75..9690cb4 100644 ---- a/fs/nfsd/nfsctl.c -+++ b/fs/nfsd/nfsctl.c -@@ -1250,15 +1250,15 @@ static int __init init_nfsd(void) - int retval; - printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); - -- retval = register_cld_notifier(); -- if (retval) -- return retval; - retval = register_pernet_subsys(&nfsd_net_ops); - if (retval < 0) -- goto out_unregister_notifier; -- retval = nfsd4_init_slabs(); -+ return retval; -+ retval = register_cld_notifier(); - if (retval) - goto out_unregister_pernet; -+ retval = nfsd4_init_slabs(); -+ if (retval) -+ goto out_unregister_notifier; - retval = nfsd4_init_pnfs(); - if (retval) - goto out_free_slabs; -@@ -1290,10 +1290,10 @@ out_exit_pnfs: - nfsd4_exit_pnfs(); - out_free_slabs: - nfsd4_free_slabs(); --out_unregister_pernet: -- unregister_pernet_subsys(&nfsd_net_ops); - out_unregister_notifier: - unregister_cld_notifier(); -+out_unregister_pernet: -+ unregister_pernet_subsys(&nfsd_net_ops); - return retval; - } - -@@ -1308,8 +1308,8 @@ static void __exit exit_nfsd(void) - nfsd4_exit_pnfs(); - nfsd_fault_inject_cleanup(); - unregister_filesystem(&nfsd_fs_type); -- unregister_pernet_subsys(&nfsd_net_ops); - unregister_cld_notifier(); -+ unregister_pernet_subsys(&nfsd_net_ops); - } - - MODULE_AUTHOR("Olaf Kirch "); -diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h -index 565c4da..cf98052 100644 ---- a/fs/nfsd/nfsd.h -+++ b/fs/nfsd/nfsd.h -@@ -24,7 +24,7 @@ - #include "export.h" - - #undef ifdebug --#ifdef NFSD_DEBUG -+#ifdef CONFIG_SUNRPC_DEBUG - # define ifdebug(flag) if (nfsd_debug & NFSDDBG_##flag) - #else - # define ifdebug(flag) if (0) -diff --git a/fs/open.c b/fs/open.c -index 33f9cbf..44a3be1 100644 ---- a/fs/open.c -+++ b/fs/open.c -@@ -570,6 +570,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group) - uid = make_kuid(current_user_ns(), user); - gid = make_kgid(current_user_ns(), group); - -+retry_deleg: - newattrs.ia_valid = ATTR_CTIME; - if (user != (uid_t) -1) { - if (!uid_valid(uid)) -@@ -586,7 +587,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) - if (!S_ISDIR(inode->i_mode)) - newattrs.ia_valid |= - ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; --retry_deleg: - mutex_lock(&inode->i_mutex); - error = security_path_chown(path, uid, gid); - if (!error) -diff --git a/fs/pnode.c b/fs/pnode.c -index 260ac8f..6367e1e 100644 ---- a/fs/pnode.c -+++ b/fs/pnode.c -@@ -362,6 +362,46 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) - } - - /* -+ * Clear MNT_LOCKED when it can be shown to be safe. -+ * -+ * mount_lock lock must be held for write -+ */ -+void propagate_mount_unlock(struct mount *mnt) -+{ -+ struct mount *parent = mnt->mnt_parent; -+ struct mount *m, *child; -+ -+ BUG_ON(parent == mnt); -+ -+ for (m = propagation_next(parent, parent); m; -+ m = propagation_next(m, parent)) { -+ child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); -+ if (child) -+ child->mnt.mnt_flags &= ~MNT_LOCKED; -+ } -+} -+ -+/* -+ * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. -+ */ -+static void mark_umount_candidates(struct mount *mnt) -+{ -+ struct mount *parent = mnt->mnt_parent; -+ struct mount *m; -+ -+ BUG_ON(parent == mnt); -+ -+ for (m = propagation_next(parent, parent); m; -+ m = propagation_next(m, parent)) { -+ struct mount *child = __lookup_mnt_last(&m->mnt, -+ mnt->mnt_mountpoint); -+ if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { -+ SET_MNT_MARK(child); -+ } -+ } -+} -+ -+/* - * NOTE: unmounting 'mnt' naturally propagates to all other mounts its - * parent propagates to. - */ -@@ -378,13 +418,16 @@ static void __propagate_umount(struct mount *mnt) - struct mount *child = __lookup_mnt_last(&m->mnt, - mnt->mnt_mountpoint); - /* -- * umount the child only if the child has no -- * other children -+ * umount the child only if the child has no children -+ * and the child is marked safe to unmount. - */ -- if (child && list_empty(&child->mnt_mounts)) { -+ if (!child || !IS_MNT_MARKED(child)) -+ continue; -+ CLEAR_MNT_MARK(child); -+ if (list_empty(&child->mnt_mounts)) { - list_del_init(&child->mnt_child); -- hlist_del_init_rcu(&child->mnt_hash); -- hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash); -+ child->mnt.mnt_flags |= MNT_UMOUNT; -+ list_move_tail(&child->mnt_list, &mnt->mnt_list); - } - } - } -@@ -396,11 +439,14 @@ static void __propagate_umount(struct mount *mnt) - * - * vfsmount lock must be held for write - */ --int propagate_umount(struct hlist_head *list) -+int propagate_umount(struct list_head *list) - { - struct mount *mnt; - -- hlist_for_each_entry(mnt, list, mnt_hash) -+ list_for_each_entry_reverse(mnt, list, mnt_list) -+ mark_umount_candidates(mnt); -+ -+ list_for_each_entry(mnt, list, mnt_list) - __propagate_umount(mnt); - return 0; - } -diff --git a/fs/pnode.h b/fs/pnode.h -index 4a24635..7114ce6 100644 ---- a/fs/pnode.h -+++ b/fs/pnode.h -@@ -19,6 +19,9 @@ - #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) - #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED) - #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED) -+#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED) -+#define IS_MNT_LOCKED_AND_LAZY(m) \ -+ (((m)->mnt.mnt_flags & (MNT_LOCKED|MNT_SYNC_UMOUNT)) == MNT_LOCKED) - - #define CL_EXPIRE 0x01 - #define CL_SLAVE 0x02 -@@ -40,14 +43,14 @@ static inline void set_mnt_shared(struct mount *mnt) - void change_mnt_propagation(struct mount *, int); - int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, - struct hlist_head *); --int propagate_umount(struct hlist_head *); -+int propagate_umount(struct list_head *); - int propagate_mount_busy(struct mount *, int); -+void propagate_mount_unlock(struct mount *); - void mnt_release_group_id(struct mount *); - int get_dominating_id(struct mount *mnt, const struct path *root); - unsigned int mnt_get_count(struct mount *mnt); - void mnt_set_mountpoint(struct mount *, struct mountpoint *, - struct mount *); --void umount_tree(struct mount *, int); - struct mount *copy_tree(struct mount *, struct dentry *, int); - bool is_path_reachable(struct mount *, struct dentry *, - const struct path *root); -diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h -index b034f10..0d58525 100644 ---- a/include/acpi/actypes.h -+++ b/include/acpi/actypes.h -@@ -199,9 +199,29 @@ typedef int s32; - typedef s32 acpi_native_int; - - typedef u32 acpi_size; -+ -+#ifdef ACPI_32BIT_PHYSICAL_ADDRESS -+ -+/* -+ * OSPMs can define this to shrink the size of the structures for 32-bit -+ * none PAE environment. ASL compiler may always define this to generate -+ * 32-bit OSPM compliant tables. -+ */ - typedef u32 acpi_io_address; - typedef u32 acpi_physical_address; - -+#else /* ACPI_32BIT_PHYSICAL_ADDRESS */ -+ -+/* -+ * It is reported that, after some calculations, the physical addresses can -+ * wrap over the 32-bit boundary on 32-bit PAE environment. -+ * https://bugzilla.kernel.org/show_bug.cgi?id=87971 -+ */ -+typedef u64 acpi_io_address; -+typedef u64 acpi_physical_address; -+ -+#endif /* ACPI_32BIT_PHYSICAL_ADDRESS */ -+ - #define ACPI_MAX_PTR ACPI_UINT32_MAX - #define ACPI_SIZE_MAX ACPI_UINT32_MAX - -@@ -736,10 +756,6 @@ typedef u32 acpi_event_status; - #define ACPI_GPE_ENABLE 0 - #define ACPI_GPE_DISABLE 1 - #define ACPI_GPE_CONDITIONAL_ENABLE 2 --#define ACPI_GPE_SAVE_MASK 4 -- --#define ACPI_GPE_ENABLE_SAVE (ACPI_GPE_ENABLE | ACPI_GPE_SAVE_MASK) --#define ACPI_GPE_DISABLE_SAVE (ACPI_GPE_DISABLE | ACPI_GPE_SAVE_MASK) - - /* - * GPE info flags - Per GPE -diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h -index ad74dc5..ecdf940 100644 ---- a/include/acpi/platform/acenv.h -+++ b/include/acpi/platform/acenv.h -@@ -76,6 +76,7 @@ - #define ACPI_LARGE_NAMESPACE_NODE - #define ACPI_DATA_TABLE_DISASSEMBLY - #define ACPI_SINGLE_THREADED -+#define ACPI_32BIT_PHYSICAL_ADDRESS - #endif - - /* acpi_exec configuration. Multithreaded with full AML debugger */ -diff --git a/include/dt-bindings/clock/tegra124-car-common.h b/include/dt-bindings/clock/tegra124-car-common.h -index ae2eb17..a215609 100644 ---- a/include/dt-bindings/clock/tegra124-car-common.h -+++ b/include/dt-bindings/clock/tegra124-car-common.h -@@ -297,7 +297,7 @@ - #define TEGRA124_CLK_PLL_C4 270 - #define TEGRA124_CLK_PLL_DP 271 - #define TEGRA124_CLK_PLL_E_MUX 272 --#define TEGRA124_CLK_PLLD_DSI 273 -+#define TEGRA124_CLK_PLL_D_DSI_OUT 273 - /* 274 */ - /* 275 */ - /* 276 */ -diff --git a/include/linux/bpf.h b/include/linux/bpf.h -index bbfceb7..33b52fb 100644 ---- a/include/linux/bpf.h -+++ b/include/linux/bpf.h -@@ -48,7 +48,7 @@ struct bpf_map *bpf_map_get(struct fd f); - - /* function argument constraints */ - enum bpf_arg_type { -- ARG_ANYTHING = 0, /* any argument is ok */ -+ ARG_DONTCARE = 0, /* unused argument in helper function */ - - /* the following constraints used to prototype - * bpf_map_lookup/update/delete_elem() functions -@@ -62,6 +62,8 @@ enum bpf_arg_type { - */ - ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ - ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ -+ -+ ARG_ANYTHING, /* any (initialized) argument is ok */ - }; - - /* type of values returned from helper functions */ -diff --git a/include/linux/mount.h b/include/linux/mount.h -index c2c561d..564beee 100644 ---- a/include/linux/mount.h -+++ b/include/linux/mount.h -@@ -61,6 +61,7 @@ struct mnt_namespace; - #define MNT_DOOMED 0x1000000 - #define MNT_SYNC_UMOUNT 0x2000000 - #define MNT_MARKED 0x4000000 -+#define MNT_UMOUNT 0x8000000 - - struct vfsmount { - struct dentry *mnt_root; /* root of the mounted tree */ -diff --git a/include/linux/sched.h b/include/linux/sched.h -index a419b65..51348f7 100644 ---- a/include/linux/sched.h -+++ b/include/linux/sched.h -@@ -176,6 +176,14 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); - extern void calc_global_load(unsigned long ticks); - extern void update_cpu_load_nohz(void); - -+/* Notifier for when a task gets migrated to a new CPU */ -+struct task_migration_notifier { -+ struct task_struct *task; -+ int from_cpu; -+ int to_cpu; -+}; -+extern void register_task_migration_notifier(struct notifier_block *n); -+ - extern unsigned long get_parent_ip(unsigned long addr); - - extern void dump_cpu_task(int cpu); -diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h -index f54d665..bdccc4b 100644 ---- a/include/linux/skbuff.h -+++ b/include/linux/skbuff.h -@@ -769,6 +769,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, - - struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, - int node); -+struct sk_buff *__build_skb(void *data, unsigned int frag_size); - struct sk_buff *build_skb(void *data, unsigned int frag_size); - static inline struct sk_buff *alloc_skb(unsigned int size, - gfp_t priority) -@@ -3013,6 +3014,18 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, - */ - #define CHECKSUM_BREAK 76 - -+/* Unset checksum-complete -+ * -+ * Unset checksum complete can be done when packet is being modified -+ * (uncompressed for instance) and checksum-complete value is -+ * invalidated. -+ */ -+static inline void skb_checksum_complete_unset(struct sk_buff *skb) -+{ -+ if (skb->ip_summed == CHECKSUM_COMPLETE) -+ skb->ip_summed = CHECKSUM_NONE; -+} -+ - /* Validate (init) checksum based on checksum complete. - * - * Return values: -diff --git a/include/linux/usb.h b/include/linux/usb.h -index 7ee1b5c..447fe29 100644 ---- a/include/linux/usb.h -+++ b/include/linux/usb.h -@@ -205,6 +205,32 @@ void usb_put_intf(struct usb_interface *intf); - #define USB_MAXINTERFACES 32 - #define USB_MAXIADS (USB_MAXINTERFACES/2) - -+/* -+ * USB Resume Timer: Every Host controller driver should drive the resume -+ * signalling on the bus for the amount of time defined by this macro. -+ * -+ * That way we will have a 'stable' behavior among all HCDs supported by Linux. -+ * -+ * Note that the USB Specification states we should drive resume for *at least* -+ * 20 ms, but it doesn't give an upper bound. This creates two possible -+ * situations which we want to avoid: -+ * -+ * (a) sometimes an msleep(20) might expire slightly before 20 ms, which causes -+ * us to fail USB Electrical Tests, thus failing Certification -+ * -+ * (b) Some (many) devices actually need more than 20 ms of resume signalling, -+ * and while we can argue that's against the USB Specification, we don't have -+ * control over which devices a certification laboratory will be using for -+ * certification. If CertLab uses a device which was tested against Windows and -+ * that happens to have relaxed resume signalling rules, we might fall into -+ * situations where we fail interoperability and electrical tests. -+ * -+ * In order to avoid both conditions, we're using a 40 ms resume timeout, which -+ * should cope with both LPJ calibration errors and devices not following every -+ * detail of the USB Specification. -+ */ -+#define USB_RESUME_TIMEOUT 40 /* ms */ -+ - /** - * struct usb_interface_cache - long-term representation of a device interface - * @num_altsetting: number of altsettings defined. -diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h -index d3583d3..dd0f3ab 100644 ---- a/include/target/iscsi/iscsi_target_core.h -+++ b/include/target/iscsi/iscsi_target_core.h -@@ -602,6 +602,11 @@ struct iscsi_conn { - struct iscsi_session *sess; - /* Pointer to thread_set in use for this conn's threads */ - struct iscsi_thread_set *thread_set; -+ int bitmap_id; -+ int rx_thread_active; -+ struct task_struct *rx_thread; -+ int tx_thread_active; -+ struct task_struct *tx_thread; - /* list_head for session connection list */ - struct list_head conn_list; - } ____cacheline_aligned; -@@ -871,10 +876,12 @@ struct iscsit_global { - /* Unique identifier used for the authentication daemon */ - u32 auth_id; - u32 inactive_ts; -+#define ISCSIT_BITMAP_BITS 262144 - /* Thread Set bitmap count */ - int ts_bitmap_count; - /* Thread Set bitmap pointer */ - unsigned long *ts_bitmap; -+ spinlock_t ts_bitmap_lock; - /* Used for iSCSI discovery session authentication */ - struct iscsi_node_acl discovery_acl; - struct iscsi_portal_group *discovery_tpg; -diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h -index 672150b..985ca4c 100644 ---- a/include/target/target_core_base.h -+++ b/include/target/target_core_base.h -@@ -524,7 +524,7 @@ struct se_cmd { - sense_reason_t (*execute_cmd)(struct se_cmd *); - sense_reason_t (*execute_rw)(struct se_cmd *, struct scatterlist *, - u32, enum dma_data_direction); -- sense_reason_t (*transport_complete_callback)(struct se_cmd *); -+ sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool); - - unsigned char *t_task_cdb; - unsigned char __t_task_cdb[TCM_MAX_COMMAND_SIZE]; -diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h -index 0bf130a..28ec6c9 100644 ---- a/include/uapi/linux/nfsd/debug.h -+++ b/include/uapi/linux/nfsd/debug.h -@@ -12,14 +12,6 @@ - #include - - /* -- * Enable debugging for nfsd. -- * Requires RPC_DEBUG. -- */ --#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) --# define NFSD_DEBUG 1 --#endif -- --/* - * knfsd debug flags - */ - #define NFSDDBG_SOCK 0x0001 -diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h -index a20e4a3..847a0a2 100644 ---- a/include/video/samsung_fimd.h -+++ b/include/video/samsung_fimd.h -@@ -436,6 +436,12 @@ - #define BLENDCON_NEW_8BIT_ALPHA_VALUE (1 << 0) - #define BLENDCON_NEW_4BIT_ALPHA_VALUE (0 << 0) - -+/* Display port clock control */ -+#define DP_MIE_CLKCON 0x27c -+#define DP_MIE_CLK_DISABLE 0x0 -+#define DP_MIE_CLK_DP_ENABLE 0x2 -+#define DP_MIE_CLK_MIE_ENABLE 0x3 -+ - /* Notes on per-window bpp settings - * - * Value Win0 Win1 Win2 Win3 Win 4 -diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c -index 36508e6..5d8ea3d 100644 ---- a/kernel/bpf/verifier.c -+++ b/kernel/bpf/verifier.c -@@ -755,7 +755,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno, - enum bpf_reg_type expected_type; - int err = 0; - -- if (arg_type == ARG_ANYTHING) -+ if (arg_type == ARG_DONTCARE) - return 0; - - if (reg->type == NOT_INIT) { -@@ -763,6 +763,9 @@ static int check_func_arg(struct verifier_env *env, u32 regno, - return -EACCES; - } - -+ if (arg_type == ARG_ANYTHING) -+ return 0; -+ - if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || - arg_type == ARG_PTR_TO_MAP_VALUE) { - expected_type = PTR_TO_STACK; -diff --git a/kernel/ptrace.c b/kernel/ptrace.c -index 227fec3..9a34bd8 100644 ---- a/kernel/ptrace.c -+++ b/kernel/ptrace.c -@@ -697,6 +697,8 @@ static int ptrace_peek_siginfo(struct task_struct *child, - static int ptrace_resume(struct task_struct *child, long request, - unsigned long data) - { -+ bool need_siglock; -+ - if (!valid_signal(data)) - return -EIO; - -@@ -724,8 +726,26 @@ static int ptrace_resume(struct task_struct *child, long request, - user_disable_single_step(child); - } - -+ /* -+ * Change ->exit_code and ->state under siglock to avoid the race -+ * with wait_task_stopped() in between; a non-zero ->exit_code will -+ * wrongly look like another report from tracee. -+ * -+ * Note that we need siglock even if ->exit_code == data and/or this -+ * status was not reported yet, the new status must not be cleared by -+ * wait_task_stopped() after resume. -+ * -+ * If data == 0 we do not care if wait_task_stopped() reports the old -+ * status and clears the code too; this can't race with the tracee, it -+ * takes siglock after resume. -+ */ -+ need_siglock = data && !thread_group_empty(current); -+ if (need_siglock) -+ spin_lock_irq(&child->sighand->siglock); - child->exit_code = data; - wake_up_state(child, __TASK_TRACED); -+ if (need_siglock) -+ spin_unlock_irq(&child->sighand->siglock); - - return 0; - } -diff --git a/kernel/sched/core.c b/kernel/sched/core.c -index 62671f5..3d5f6f6 100644 ---- a/kernel/sched/core.c -+++ b/kernel/sched/core.c -@@ -996,6 +996,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) - rq_clock_skip_update(rq, true); - } - -+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); -+ -+void register_task_migration_notifier(struct notifier_block *n) -+{ -+ atomic_notifier_chain_register(&task_migration_notifier, n); -+} -+ - #ifdef CONFIG_SMP - void set_task_cpu(struct task_struct *p, unsigned int new_cpu) - { -@@ -1026,10 +1033,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) - trace_sched_migrate_task(p, new_cpu); - - if (task_cpu(p) != new_cpu) { -+ struct task_migration_notifier tmn; -+ - if (p->sched_class->migrate_task_rq) - p->sched_class->migrate_task_rq(p, new_cpu); - p->se.nr_migrations++; - perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); -+ -+ tmn.task = p; -+ tmn.from_cpu = task_cpu(p); -+ tmn.to_cpu = new_cpu; -+ -+ atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); - } - - __set_task_cpu(p, new_cpu); -diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c -index 3fa8fa6..f670cbb 100644 ---- a/kernel/sched/deadline.c -+++ b/kernel/sched/deadline.c -@@ -514,7 +514,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) - unsigned long flags; - struct rq *rq; - -- rq = task_rq_lock(current, &flags); -+ rq = task_rq_lock(p, &flags); - - /* - * We need to take care of several possible races here: -@@ -569,7 +569,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) - push_dl_task(rq); - #endif - unlock: -- task_rq_unlock(rq, current, &flags); -+ task_rq_unlock(rq, p, &flags); - - return HRTIMER_NORESTART; - } -diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c -index 5040d44..922048a 100644 ---- a/kernel/trace/ring_buffer.c -+++ b/kernel/trace/ring_buffer.c -@@ -2679,7 +2679,7 @@ static DEFINE_PER_CPU(unsigned int, current_context); - - static __always_inline int trace_recursive_lock(void) - { -- unsigned int val = this_cpu_read(current_context); -+ unsigned int val = __this_cpu_read(current_context); - int bit; - - if (in_interrupt()) { -@@ -2696,18 +2696,17 @@ static __always_inline int trace_recursive_lock(void) - return 1; - - val |= (1 << bit); -- this_cpu_write(current_context, val); -+ __this_cpu_write(current_context, val); - - return 0; - } - - static __always_inline void trace_recursive_unlock(void) - { -- unsigned int val = this_cpu_read(current_context); -+ unsigned int val = __this_cpu_read(current_context); - -- val--; -- val &= this_cpu_read(current_context); -- this_cpu_write(current_context, val); -+ val &= val & (val - 1); -+ __this_cpu_write(current_context, val); - } - - #else -diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c -index db54dda..a9c10a3 100644 ---- a/kernel/trace/trace_events.c -+++ b/kernel/trace/trace_events.c -@@ -565,6 +565,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, - static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) - { - char *event = NULL, *sub = NULL, *match; -+ int ret; - - /* - * The buf format can be : -@@ -590,7 +591,13 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) - event = NULL; - } - -- return __ftrace_set_clr_event(tr, match, sub, event, set); -+ ret = __ftrace_set_clr_event(tr, match, sub, event, set); -+ -+ /* Put back the colon to allow this to be called again */ -+ if (buf) -+ *(buf - 1) = ':'; -+ -+ return ret; - } - - /** -diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c -index 2d25ad1..b6fce36 100644 ---- a/kernel/trace/trace_functions_graph.c -+++ b/kernel/trace/trace_functions_graph.c -@@ -1309,15 +1309,19 @@ void graph_trace_open(struct trace_iterator *iter) - { - /* pid and depth on the last trace processed */ - struct fgraph_data *data; -+ gfp_t gfpflags; - int cpu; - - iter->private = NULL; - -- data = kzalloc(sizeof(*data), GFP_KERNEL); -+ /* We can be called in atomic context via ftrace_dump() */ -+ gfpflags = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL; -+ -+ data = kzalloc(sizeof(*data), gfpflags); - if (!data) - goto out_err; - -- data->cpu_data = alloc_percpu(struct fgraph_cpu_data); -+ data->cpu_data = alloc_percpu_gfp(struct fgraph_cpu_data, gfpflags); - if (!data->cpu_data) - goto out_err_free; - -diff --git a/lib/string.c b/lib/string.c -index ce81aae..a579201 100644 ---- a/lib/string.c -+++ b/lib/string.c -@@ -607,7 +607,7 @@ EXPORT_SYMBOL(memset); - void memzero_explicit(void *s, size_t count) - { - memset(s, 0, count); -- OPTIMIZER_HIDE_VAR(s); -+ barrier(); - } - EXPORT_SYMBOL(memzero_explicit); - -diff --git a/mm/huge_memory.c b/mm/huge_memory.c -index 6817b03..956d4db 100644 ---- a/mm/huge_memory.c -+++ b/mm/huge_memory.c -@@ -2316,8 +2316,14 @@ static struct page - struct vm_area_struct *vma, unsigned long address, - int node) - { -+ gfp_t flags; -+ - VM_BUG_ON_PAGE(*hpage, *hpage); - -+ /* Only allocate from the target node */ -+ flags = alloc_hugepage_gfpmask(khugepaged_defrag(), __GFP_OTHER_NODE) | -+ __GFP_THISNODE; -+ - /* - * Before allocating the hugepage, release the mmap_sem read lock. - * The allocation can take potentially a long time if it involves -@@ -2326,8 +2332,7 @@ static struct page - */ - up_read(&mm->mmap_sem); - -- *hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask( -- khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER); -+ *hpage = alloc_pages_exact_node(node, flags, HPAGE_PMD_ORDER); - if (unlikely(!*hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - *hpage = ERR_PTR(-ENOMEM); -diff --git a/mm/hugetlb.c b/mm/hugetlb.c -index c41b2a0..caad3c5 100644 ---- a/mm/hugetlb.c -+++ b/mm/hugetlb.c -@@ -3735,8 +3735,7 @@ retry: - if (!pmd_huge(*pmd)) - goto out; - if (pmd_present(*pmd)) { -- page = pte_page(*(pte_t *)pmd) + -- ((address & ~PMD_MASK) >> PAGE_SHIFT); -+ page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); - if (flags & FOLL_GET) - get_page(page); - } else { -diff --git a/mm/mempolicy.c b/mm/mempolicy.c -index 4721046..de5dc5e 100644 ---- a/mm/mempolicy.c -+++ b/mm/mempolicy.c -@@ -1985,7 +1985,8 @@ retry_cpuset: - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(node, *nmask)) { - mpol_cond_put(pol); -- page = alloc_pages_exact_node(node, gfp, order); -+ page = alloc_pages_exact_node(node, -+ gfp | __GFP_THISNODE, order); - goto out; - } - } -diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c -index 0ee453f..f371cbf 100644 ---- a/net/bridge/br_netfilter.c -+++ b/net/bridge/br_netfilter.c -@@ -651,6 +651,13 @@ static int br_nf_forward_finish(struct sk_buff *skb) - struct net_device *in; - - if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { -+ int frag_max_size; -+ -+ if (skb->protocol == htons(ETH_P_IP)) { -+ frag_max_size = IPCB(skb)->frag_max_size; -+ BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size; -+ } -+ - in = nf_bridge->physindev; - if (nf_bridge->mask & BRNF_PKT_TYPE) { - skb->pkt_type = PACKET_OTHERHOST; -@@ -710,8 +717,14 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, - nf_bridge->mask |= BRNF_PKT_TYPE; - } - -- if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) -- return NF_DROP; -+ if (pf == NFPROTO_IPV4) { -+ int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size; -+ -+ if (br_parse_ip_options(skb)) -+ return NF_DROP; -+ -+ IPCB(skb)->frag_max_size = frag_max; -+ } - - /* The physdev module checks on this */ - nf_bridge->mask |= BRNF_BRIDGED; -diff --git a/net/core/dev.c b/net/core/dev.c -index 45109b7..22a53ac 100644 ---- a/net/core/dev.c -+++ b/net/core/dev.c -@@ -3041,7 +3041,7 @@ static struct rps_dev_flow * - set_rps_cpu(struct net_device *dev, struct sk_buff *skb, - struct rps_dev_flow *rflow, u16 next_cpu) - { -- if (next_cpu != RPS_NO_CPU) { -+ if (next_cpu < nr_cpu_ids) { - #ifdef CONFIG_RFS_ACCEL - struct netdev_rx_queue *rxqueue; - struct rps_dev_flow_table *flow_table; -@@ -3146,7 +3146,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, - * If the desired CPU (where last recvmsg was done) is - * different from current CPU (one in the rx-queue flow - * table entry), switch if one of the following holds: -- * - Current CPU is unset (equal to RPS_NO_CPU). -+ * - Current CPU is unset (>= nr_cpu_ids). - * - Current CPU is offline. - * - The current CPU's queue tail has advanced beyond the - * last packet that was enqueued using this table entry. -@@ -3154,14 +3154,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, - * have been dequeued, thus preserving in order delivery. - */ - if (unlikely(tcpu != next_cpu) && -- (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || -+ (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || - ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) { - tcpu = next_cpu; - rflow = set_rps_cpu(dev, skb, rflow, next_cpu); - } - -- if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { -+ if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { - *rflowp = rflow; - cpu = tcpu; - goto done; -@@ -3202,14 +3202,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, - struct rps_dev_flow_table *flow_table; - struct rps_dev_flow *rflow; - bool expire = true; -- int cpu; -+ unsigned int cpu; - - rcu_read_lock(); - flow_table = rcu_dereference(rxqueue->rps_flow_table); - if (flow_table && flow_id <= flow_table->mask) { - rflow = &flow_table->flows[flow_id]; - cpu = ACCESS_ONCE(rflow->cpu); -- if (rflow->filter == filter_id && cpu != RPS_NO_CPU && -+ if (rflow->filter == filter_id && cpu < nr_cpu_ids && - ((int)(per_cpu(softnet_data, cpu).input_queue_head - - rflow->last_qtail) < - (int)(10 * flow_table->mask))) -diff --git a/net/core/skbuff.c b/net/core/skbuff.c -index 98d45fe..e9f9a15 100644 ---- a/net/core/skbuff.c -+++ b/net/core/skbuff.c -@@ -280,13 +280,14 @@ nodata: - EXPORT_SYMBOL(__alloc_skb); - - /** -- * build_skb - build a network buffer -+ * __build_skb - build a network buffer - * @data: data buffer provided by caller -- * @frag_size: size of fragment, or 0 if head was kmalloced -+ * @frag_size: size of data, or 0 if head was kmalloced - * - * Allocate a new &sk_buff. Caller provides space holding head and - * skb_shared_info. @data must have been allocated by kmalloc() only if -- * @frag_size is 0, otherwise data should come from the page allocator. -+ * @frag_size is 0, otherwise data should come from the page allocator -+ * or vmalloc() - * The return is the new skb buffer. - * On a failure the return is %NULL, and @data is not freed. - * Notes : -@@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); - * before giving packet to stack. - * RX rings only contains data buffers, not full skbs. - */ --struct sk_buff *build_skb(void *data, unsigned int frag_size) -+struct sk_buff *__build_skb(void *data, unsigned int frag_size) - { - struct skb_shared_info *shinfo; - struct sk_buff *skb; -@@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) - - memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->truesize = SKB_TRUESIZE(size); -- skb->head_frag = frag_size != 0; - atomic_set(&skb->users, 1); - skb->head = data; - skb->data = data; -@@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) - - return skb; - } -+ -+/* build_skb() is wrapper over __build_skb(), that specifically -+ * takes care of skb->head and skb->pfmemalloc -+ * This means that if @frag_size is not zero, then @data must be backed -+ * by a page fragment, not kmalloc() or vmalloc() -+ */ -+struct sk_buff *build_skb(void *data, unsigned int frag_size) -+{ -+ struct sk_buff *skb = __build_skb(data, frag_size); -+ -+ if (skb && frag_size) { -+ skb->head_frag = 1; -+ if (virt_to_head_page(data)->pfmemalloc) -+ skb->pfmemalloc = 1; -+ } -+ return skb; -+} - EXPORT_SYMBOL(build_skb); - - struct netdev_alloc_cache { -@@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, - gfp_t gfp = gfp_mask; - - if (order) { -- gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; -+ gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | -+ __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); - nc->frag.size = PAGE_SIZE << (page ? order : 0); - } -diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c -index d9bc28a..53bd53f 100644 ---- a/net/ipv4/ip_forward.c -+++ b/net/ipv4/ip_forward.c -@@ -82,6 +82,9 @@ int ip_forward(struct sk_buff *skb) - if (skb->pkt_type != PACKET_HOST) - goto drop; - -+ if (unlikely(skb->sk)) -+ goto drop; -+ - if (skb_warn_if_lro(skb)) - goto drop; - -diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c -index d520492..9d48dc4 100644 ---- a/net/ipv4/tcp_output.c -+++ b/net/ipv4/tcp_output.c -@@ -2751,39 +2751,65 @@ begin_fwd: - } - } - --/* Send a fin. The caller locks the socket for us. This cannot be -- * allowed to fail queueing a FIN frame under any circumstances. -+/* We allow to exceed memory limits for FIN packets to expedite -+ * connection tear down and (memory) recovery. -+ * Otherwise tcp_send_fin() could be tempted to either delay FIN -+ * or even be forced to close flow without any FIN. -+ */ -+static void sk_forced_wmem_schedule(struct sock *sk, int size) -+{ -+ int amt, status; -+ -+ if (size <= sk->sk_forward_alloc) -+ return; -+ amt = sk_mem_pages(size); -+ sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; -+ sk_memory_allocated_add(sk, amt, &status); -+} -+ -+/* Send a FIN. The caller locks the socket for us. -+ * We should try to send a FIN packet really hard, but eventually give up. - */ - void tcp_send_fin(struct sock *sk) - { -+ struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); - struct tcp_sock *tp = tcp_sk(sk); -- struct sk_buff *skb = tcp_write_queue_tail(sk); -- int mss_now; - -- /* Optimization, tack on the FIN if we have a queue of -- * unsent frames. But be careful about outgoing SACKS -- * and IP options. -+ /* Optimization, tack on the FIN if we have one skb in write queue and -+ * this skb was not yet sent, or we are under memory pressure. -+ * Note: in the latter case, FIN packet will be sent after a timeout, -+ * as TCP stack thinks it has already been transmitted. - */ -- mss_now = tcp_current_mss(sk); -- -- if (tcp_send_head(sk) != NULL) { -- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; -- TCP_SKB_CB(skb)->end_seq++; -+ if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { -+coalesce: -+ TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; -+ TCP_SKB_CB(tskb)->end_seq++; - tp->write_seq++; -+ if (!tcp_send_head(sk)) { -+ /* This means tskb was already sent. -+ * Pretend we included the FIN on previous transmit. -+ * We need to set tp->snd_nxt to the value it would have -+ * if FIN had been sent. This is because retransmit path -+ * does not change tp->snd_nxt. -+ */ -+ tp->snd_nxt++; -+ return; -+ } - } else { -- /* Socket is locked, keep trying until memory is available. */ -- for (;;) { -- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); -- if (skb) -- break; -- yield(); -+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); -+ if (unlikely(!skb)) { -+ if (tskb) -+ goto coalesce; -+ return; - } -+ skb_reserve(skb, MAX_TCP_HEADER); -+ sk_forced_wmem_schedule(sk, skb->truesize); - /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ - tcp_init_nondata_skb(skb, tp->write_seq, - TCPHDR_ACK | TCPHDR_FIN); - tcp_queue_skb(sk, skb); - } -- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); -+ __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); - } - - /* We get here when a process closes a file descriptor (either due to -diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c -index 142f66a..0ca013d 100644 ---- a/net/mac80211/mlme.c -+++ b/net/mac80211/mlme.c -@@ -2260,7 +2260,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) - else - ssid_len = ssid[1]; - -- ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL, -+ ieee80211_send_probe_req(sdata, sdata->vif.addr, dst, - ssid + 2, ssid_len, NULL, - 0, (u32) -1, true, 0, - ifmgd->associated->channel, false); -diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c -index 05919bf..d1d7a81 100644 ---- a/net/netlink/af_netlink.c -+++ b/net/netlink/af_netlink.c -@@ -1616,13 +1616,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, - if (data == NULL) - return NULL; - -- skb = build_skb(data, size); -+ skb = __build_skb(data, size); - if (skb == NULL) - vfree(data); -- else { -- skb->head_frag = 0; -+ else - skb->destructor = netlink_skb_destructor; -- } - - return skb; - } -diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c -index 2ca9f2e..53745f4 100644 ---- a/sound/pci/emu10k1/emuproc.c -+++ b/sound/pci/emu10k1/emuproc.c -@@ -241,31 +241,22 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, - struct snd_emu10k1 *emu = entry->private_data; - u32 value; - u32 value2; -- unsigned long flags; - u32 rate; - - if (emu->card_capabilities->emu_model) { -- spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read(emu, 0x38, &value); -- spin_unlock_irqrestore(&emu->emu_lock, flags); - if ((value & 0x1) == 0) { -- spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read(emu, 0x2a, &value); - snd_emu1010_fpga_read(emu, 0x2b, &value2); -- spin_unlock_irqrestore(&emu->emu_lock, flags); - rate = 0x1770000 / (((value << 5) | value2)+1); - snd_iprintf(buffer, "ADAT Locked : %u\n", rate); - } else { - snd_iprintf(buffer, "ADAT Unlocked\n"); - } -- spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read(emu, 0x20, &value); -- spin_unlock_irqrestore(&emu->emu_lock, flags); - if ((value & 0x4) == 0) { -- spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read(emu, 0x28, &value); - snd_emu1010_fpga_read(emu, 0x29, &value2); -- spin_unlock_irqrestore(&emu->emu_lock, flags); - rate = 0x1770000 / (((value << 5) | value2)+1); - snd_iprintf(buffer, "SPDIF Locked : %d\n", rate); - } else { -@@ -410,14 +401,11 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, - { - struct snd_emu10k1 *emu = entry->private_data; - u32 value; -- unsigned long flags; - int i; - snd_iprintf(buffer, "EMU1010 Registers:\n\n"); - - for(i = 0; i < 0x40; i+=1) { -- spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read(emu, i, &value); -- spin_unlock_irqrestore(&emu->emu_lock, flags); - snd_iprintf(buffer, "%02X: %08X, %02X\n", i, value, (value >> 8) & 0x7f); - } - } -diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c -index f9d12c0..2fd490b 100644 ---- a/sound/pci/hda/patch_realtek.c -+++ b/sound/pci/hda/patch_realtek.c -@@ -5047,12 +5047,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { - SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), -+ SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), - SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), - SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), - SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), -+ SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), -@@ -5142,6 +5144,16 @@ static const struct hda_model_fixup alc269_fixup_models[] = { - {0x1b, 0x411111f0}, \ - {0x1e, 0x411111f0} - -+#define ALC256_STANDARD_PINS \ -+ {0x12, 0x90a60140}, \ -+ {0x14, 0x90170110}, \ -+ {0x19, 0x411111f0}, \ -+ {0x1a, 0x411111f0}, \ -+ {0x1b, 0x411111f0}, \ -+ {0x1d, 0x40700001}, \ -+ {0x1e, 0x411111f0}, \ -+ {0x21, 0x02211020} -+ - #define ALC282_STANDARD_PINS \ - {0x14, 0x90170110}, \ - {0x18, 0x411111f0}, \ -@@ -5235,15 +5247,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { - {0x1d, 0x40700001}, - {0x21, 0x02211050}), - SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, -- {0x12, 0x90a60140}, -- {0x13, 0x40000000}, -- {0x14, 0x90170110}, -- {0x19, 0x411111f0}, -- {0x1a, 0x411111f0}, -- {0x1b, 0x411111f0}, -- {0x1d, 0x40700001}, -- {0x1e, 0x411111f0}, -- {0x21, 0x02211020}), -+ ALC256_STANDARD_PINS, -+ {0x13, 0x40000000}), -+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, -+ ALC256_STANDARD_PINS, -+ {0x13, 0x411111f0}), - SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4, - {0x12, 0x90a60130}, - {0x13, 0x40000000}, -@@ -5563,6 +5571,8 @@ static int patch_alc269(struct hda_codec *codec) - break; - case 0x10ec0256: - spec->codec_variant = ALC269_TYPE_ALC256; -+ spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ -+ alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/ - break; - } - -@@ -5576,8 +5586,8 @@ static int patch_alc269(struct hda_codec *codec) - if (err < 0) - goto error; - -- if (!spec->gen.no_analog && spec->gen.beep_nid) -- set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT); -+ if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid) -+ set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT); - - codec->patch_ops = alc_patch_ops; - #ifdef CONFIG_PM -diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c -index 7d3a6ac..e770ee6 100644 ---- a/sound/soc/codecs/cs4271.c -+++ b/sound/soc/codecs/cs4271.c -@@ -561,10 +561,10 @@ static int cs4271_codec_probe(struct snd_soc_codec *codec) - if (gpio_is_valid(cs4271->gpio_nreset)) { - /* Reset codec */ - gpio_direction_output(cs4271->gpio_nreset, 0); -- udelay(1); -+ mdelay(1); - gpio_set_value(cs4271->gpio_nreset, 1); - /* Give the codec time to wake up */ -- udelay(1); -+ mdelay(1); - } - - ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2, -diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c -index 474cae8..8c09e3f 100644 ---- a/sound/soc/codecs/pcm512x.c -+++ b/sound/soc/codecs/pcm512x.c -@@ -304,9 +304,9 @@ static const struct soc_enum pcm512x_veds = - static const struct snd_kcontrol_new pcm512x_controls[] = { - SOC_DOUBLE_R_TLV("Digital Playback Volume", PCM512x_DIGITAL_VOLUME_2, - PCM512x_DIGITAL_VOLUME_3, 0, 255, 1, digital_tlv), --SOC_DOUBLE_TLV("Playback Volume", PCM512x_ANALOG_GAIN_CTRL, -+SOC_DOUBLE_TLV("Analogue Playback Volume", PCM512x_ANALOG_GAIN_CTRL, - PCM512x_LAGN_SHIFT, PCM512x_RAGN_SHIFT, 1, 1, analog_tlv), --SOC_DOUBLE_TLV("Playback Boost Volume", PCM512x_ANALOG_GAIN_BOOST, -+SOC_DOUBLE_TLV("Analogue Playback Boost Volume", PCM512x_ANALOG_GAIN_BOOST, - PCM512x_AGBL_SHIFT, PCM512x_AGBR_SHIFT, 1, 0, boost_tlv), - SOC_DOUBLE("Digital Playback Switch", PCM512x_MUTE, PCM512x_RQML_SHIFT, - PCM512x_RQMR_SHIFT, 1, 1), -@@ -576,8 +576,8 @@ static int pcm512x_find_pll_coeff(struct snd_soc_dai *dai, - - /* pllin_rate / P (or here, den) cannot be greater than 20 MHz */ - if (pllin_rate / den > 20000000 && num < 8) { -- num *= 20000000 / (pllin_rate / den); -- den *= 20000000 / (pllin_rate / den); -+ num *= DIV_ROUND_UP(pllin_rate / den, 20000000); -+ den *= DIV_ROUND_UP(pllin_rate / den, 20000000); - } - dev_dbg(dev, "num / den = %lu / %lu\n", num, den); - -diff --git a/sound/soc/codecs/wm8741.c b/sound/soc/codecs/wm8741.c -index 31bb480..9e71c76 100644 ---- a/sound/soc/codecs/wm8741.c -+++ b/sound/soc/codecs/wm8741.c -@@ -123,7 +123,7 @@ static struct { - }; - - static const unsigned int rates_11289[] = { -- 44100, 88235, -+ 44100, 88200, - }; - - static const struct snd_pcm_hw_constraint_list constraints_11289 = { -@@ -150,7 +150,7 @@ static const struct snd_pcm_hw_constraint_list constraints_16384 = { - }; - - static const unsigned int rates_16934[] = { -- 44100, 88235, -+ 44100, 88200, - }; - - static const struct snd_pcm_hw_constraint_list constraints_16934 = { -@@ -168,7 +168,7 @@ static const struct snd_pcm_hw_constraint_list constraints_18432 = { - }; - - static const unsigned int rates_22579[] = { -- 44100, 88235, 1764000 -+ 44100, 88200, 176400 - }; - - static const struct snd_pcm_hw_constraint_list constraints_22579 = { -@@ -186,7 +186,7 @@ static const struct snd_pcm_hw_constraint_list constraints_24576 = { - }; - - static const unsigned int rates_36864[] = { -- 48000, 96000, 19200 -+ 48000, 96000, 192000 - }; - - static const struct snd_pcm_hw_constraint_list constraints_36864 = { -diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c -index b6bb594..8c2b9be 100644 ---- a/sound/soc/davinci/davinci-evm.c -+++ b/sound/soc/davinci/davinci-evm.c -@@ -425,18 +425,8 @@ static int davinci_evm_probe(struct platform_device *pdev) - return ret; - } - --static int davinci_evm_remove(struct platform_device *pdev) --{ -- struct snd_soc_card *card = platform_get_drvdata(pdev); -- -- snd_soc_unregister_card(card); -- -- return 0; --} -- - static struct platform_driver davinci_evm_driver = { - .probe = davinci_evm_probe, -- .remove = davinci_evm_remove, - .driver = { - .name = "davinci_evm", - .pm = &snd_soc_pm_ops, -diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c -index 9a28365..32631a8 100644 ---- a/sound/usb/quirks.c -+++ b/sound/usb/quirks.c -@@ -1115,6 +1115,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) - { - /* devices which do not support reading the sample rate. */ - switch (chip->usb_id) { -+ case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ - case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ - case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ - return true; -diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c -index dcc6652..deb3569 100644 ---- a/tools/lib/traceevent/kbuffer-parse.c -+++ b/tools/lib/traceevent/kbuffer-parse.c -@@ -372,7 +372,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, - switch (type_len) { - case KBUFFER_TYPE_PADDING: - *length = read_4(kbuf, data); -- data += *length; - break; - - case KBUFFER_TYPE_TIME_EXTEND: -diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile -index cc22408..0884d31 100644 ---- a/tools/perf/config/Makefile -+++ b/tools/perf/config/Makefile -@@ -651,7 +651,7 @@ ifeq (${IS_64_BIT}, 1) - NO_PERF_READ_VDSO32 := 1 - endif - endif -- ifneq (${IS_X86_64}, 1) -+ ifneq ($(ARCH), x86) - NO_PERF_READ_VDSOX32 := 1 - endif - ifndef NO_PERF_READ_VDSOX32 -@@ -699,7 +699,7 @@ sysconfdir = $(prefix)/etc - ETC_PERFCONFIG = etc/perfconfig - endif - ifndef lib --ifeq ($(IS_X86_64),1) -+ifeq ($(ARCH)$(IS_64_BIT), x861) - lib = lib64 - else - lib = lib -diff --git a/tools/perf/tests/make b/tools/perf/tests/make -index 75709d2..bff8532 100644 ---- a/tools/perf/tests/make -+++ b/tools/perf/tests/make -@@ -5,7 +5,7 @@ include config/Makefile.arch - - # FIXME looks like x86 is the only arch running tests ;-) - # we need some IS_(32/64) flag to make this generic --ifeq ($(IS_X86_64),1) -+ifeq ($(ARCH)$(IS_64_BIT), x861) - lib = lib64 - else - lib = lib -diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c -index 6da965b..85b5238 100644 ---- a/tools/perf/util/cloexec.c -+++ b/tools/perf/util/cloexec.c -@@ -7,6 +7,12 @@ - - static unsigned long flag = PERF_FLAG_FD_CLOEXEC; - -+int __weak sched_getcpu(void) -+{ -+ errno = ENOSYS; -+ return -1; -+} -+ - static int perf_flag_probe(void) - { - /* use 'safest' configuration as used in perf_evsel__fallback() */ -diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h -index 94a5a7d..68888c2 100644 ---- a/tools/perf/util/cloexec.h -+++ b/tools/perf/util/cloexec.h -@@ -3,4 +3,10 @@ - - unsigned long perf_event_open_cloexec_flag(void); - -+#ifdef __GLIBC_PREREQ -+#if !__GLIBC_PREREQ(2, 6) -+extern int sched_getcpu(void) __THROW; -+#endif -+#endif -+ - #endif /* __PERF_CLOEXEC_H */ -diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c -index 33b7a2a..9bdf007 100644 ---- a/tools/perf/util/symbol-elf.c -+++ b/tools/perf/util/symbol-elf.c -@@ -74,6 +74,10 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) - return GELF_ST_TYPE(sym->st_info); - } - -+#ifndef STT_GNU_IFUNC -+#define STT_GNU_IFUNC 10 -+#endif -+ - static inline int elf_sym__is_function(const GElf_Sym *sym) - { - return (elf_sym__type(sym) == STT_FUNC || -diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile -index d1b3a36..4039854 100644 ---- a/tools/power/x86/turbostat/Makefile -+++ b/tools/power/x86/turbostat/Makefile -@@ -1,8 +1,12 @@ - CC = $(CROSS_COMPILE)gcc --BUILD_OUTPUT := $(PWD) -+BUILD_OUTPUT := $(CURDIR) - PREFIX := /usr - DESTDIR := - -+ifeq ("$(origin O)", "command line") -+ BUILD_OUTPUT := $(O) -+endif -+ - turbostat : turbostat.c - CFLAGS += -Wall - CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"' -diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c -index c9f60f5..e5abe7c 100644 ---- a/virt/kvm/arm/vgic.c -+++ b/virt/kvm/arm/vgic.c -@@ -1371,6 +1371,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, - goto out; - } - -+ if (irq_num >= kvm->arch.vgic.nr_irqs) -+ return -EINVAL; -+ - vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level); - if (vcpu_id >= 0) { - /* kick the specified vcpu */ -diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c -index cc6a25d..f8f3f5f 100644 ---- a/virt/kvm/kvm_main.c -+++ b/virt/kvm/kvm_main.c -@@ -1653,8 +1653,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - ghc->generation = slots->generation; - ghc->len = len; - ghc->memslot = gfn_to_memslot(kvm, start_gfn); -- ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); -- if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { -+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL); -+ if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) { - ghc->hva += offset; - } else { - /* diff --git a/1002_linux-4.0.3.patch b/1002_linux-4.0.3.patch deleted file mode 100644 index d137bf26..00000000 --- a/1002_linux-4.0.3.patch +++ /dev/null @@ -1,2827 +0,0 @@ -diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt -index bfcb1a62a7b4..4d68ec841304 100644 ---- a/Documentation/kernel-parameters.txt -+++ b/Documentation/kernel-parameters.txt -@@ -3746,6 +3746,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. - READ_CAPACITY_16 command); - f = NO_REPORT_OPCODES (don't use report opcodes - command, uas only); -+ g = MAX_SECTORS_240 (don't transfer more than -+ 240 sectors at a time, uas only); - h = CAPACITY_HEURISTICS (decrease the - reported device capacity by one - sector if the number is odd); -diff --git a/Makefile b/Makefile -index 0649a6011a76..dc9f43a019d6 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 0 --SUBLEVEL = 2 -+SUBLEVEL = 3 - EXTRAVERSION = - NAME = Hurr durr I'ma sheep - -diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c -index ef7d112f5ce0..b0bd4e5fd5cf 100644 ---- a/arch/arm64/mm/dma-mapping.c -+++ b/arch/arm64/mm/dma-mapping.c -@@ -67,8 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) - - *ret_page = phys_to_page(phys); - ptr = (void *)val; -- if (flags & __GFP_ZERO) -- memset(ptr, 0, size); -+ memset(ptr, 0, size); - } - - return ptr; -@@ -105,7 +104,6 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, - struct page *page; - void *addr; - -- size = PAGE_ALIGN(size); - page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, - get_order(size)); - if (!page) -@@ -113,8 +111,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, - - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - addr = page_address(page); -- if (flags & __GFP_ZERO) -- memset(addr, 0, size); -+ memset(addr, 0, size); - return addr; - } else { - return swiotlb_alloc_coherent(dev, size, dma_handle, flags); -@@ -195,6 +192,8 @@ static void __dma_free(struct device *dev, size_t size, - { - void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); - -+ size = PAGE_ALIGN(size); -+ - if (!is_device_dma_coherent(dev)) { - if (__free_from_pool(vaddr, size)) - return; -diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig -index c7a16904cd03..1a313c468d65 100644 ---- a/arch/mips/Kconfig -+++ b/arch/mips/Kconfig -@@ -2072,7 +2072,7 @@ config MIPSR2_TO_R6_EMULATOR - help - Choose this option if you want to run non-R6 MIPS userland code. - Even if you say 'Y' here, the emulator will still be disabled by -- default. You can enable it using the 'mipsr2emul' kernel option. -+ default. You can enable it using the 'mipsr2emu' kernel option. - The only reason this is a build-time option is to save ~14K from the - final kernel image. - comment "MIPS R2-to-R6 emulator is only available for UP kernels" -@@ -2142,7 +2142,7 @@ config MIPS_CMP - - config MIPS_CPS - bool "MIPS Coherent Processing System support" -- depends on SYS_SUPPORTS_MIPS_CPS -+ depends on SYS_SUPPORTS_MIPS_CPS && !64BIT - select MIPS_CM - select MIPS_CPC - select MIPS_CPS_PM if HOTPLUG_CPU -diff --git a/arch/mips/Makefile b/arch/mips/Makefile -index 8f57fc72d62c..1b4dab1e6ab8 100644 ---- a/arch/mips/Makefile -+++ b/arch/mips/Makefile -@@ -197,11 +197,17 @@ endif - # Warning: the 64-bit MIPS architecture does not support the `smartmips' extension - # Pass -Wa,--no-warn to disable all assembler warnings until the kernel code has - # been fixed properly. --mips-cflags := "$(cflags-y)" --cflags-$(CONFIG_CPU_HAS_SMARTMIPS) += $(call cc-option,$(mips-cflags),-msmartmips) -Wa,--no-warn --cflags-$(CONFIG_CPU_MICROMIPS) += $(call cc-option,$(mips-cflags),-mmicromips) -+mips-cflags := $(cflags-y) -+ifeq ($(CONFIG_CPU_HAS_SMARTMIPS),y) -+smartmips-ase := $(call cc-option-yn,$(mips-cflags) -msmartmips) -+cflags-$(smartmips-ase) += -msmartmips -Wa,--no-warn -+endif -+ifeq ($(CONFIG_CPU_MICROMIPS),y) -+micromips-ase := $(call cc-option-yn,$(mips-cflags) -mmicromips) -+cflags-$(micromips-ase) += -mmicromips -+endif - ifeq ($(CONFIG_CPU_HAS_MSA),y) --toolchain-msa := $(call cc-option-yn,-$(mips-cflags),mhard-float -mfp64 -Wa$(comma)-mmsa) -+toolchain-msa := $(call cc-option-yn,$(mips-cflags) -mhard-float -mfp64 -Wa$(comma)-mmsa) - cflags-$(toolchain-msa) += -DTOOLCHAIN_SUPPORTS_MSA - endif - -diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c -index b3ae068ca4fa..3fd369d74444 100644 ---- a/arch/mips/bcm47xx/board.c -+++ b/arch/mips/bcm47xx/board.c -@@ -247,8 +247,8 @@ static __init const struct bcm47xx_board_type *bcm47xx_board_get_nvram(void) - } - - if (bcm47xx_nvram_getenv("hardware_version", buf1, sizeof(buf1)) >= 0 && -- bcm47xx_nvram_getenv("boardtype", buf2, sizeof(buf2)) >= 0) { -- for (e2 = bcm47xx_board_list_boot_hw; e2->value1; e2++) { -+ bcm47xx_nvram_getenv("boardnum", buf2, sizeof(buf2)) >= 0) { -+ for (e2 = bcm47xx_board_list_hw_version_num; e2->value1; e2++) { - if (!strstarts(buf1, e2->value1) && - !strcmp(buf2, e2->value2)) - return &e2->board; -diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c -index e1f27d653f60..7019e2967009 100644 ---- a/arch/mips/bcm63xx/prom.c -+++ b/arch/mips/bcm63xx/prom.c -@@ -17,7 +17,6 @@ - #include - #include - #include --#include - - void __init prom_init(void) - { -@@ -53,9 +52,6 @@ void __init prom_init(void) - reg &= ~mask; - bcm_perf_writel(reg, PERF_CKCTL_REG); - -- /* register gpiochip */ -- bcm63xx_gpio_init(); -- - /* do low level board init */ - board_prom_init(); - -diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c -index 6660c7ddf87b..240fb4ffa55c 100644 ---- a/arch/mips/bcm63xx/setup.c -+++ b/arch/mips/bcm63xx/setup.c -@@ -20,6 +20,7 @@ - #include - #include - #include -+#include - - void bcm63xx_machine_halt(void) - { -@@ -160,6 +161,9 @@ void __init plat_mem_setup(void) - - int __init bcm63xx_register_devices(void) - { -+ /* register gpiochip */ -+ bcm63xx_gpio_init(); -+ - return board_register_devices(); - } - -diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c -index 7d8987818ccf..d8960d46417b 100644 ---- a/arch/mips/cavium-octeon/dma-octeon.c -+++ b/arch/mips/cavium-octeon/dma-octeon.c -@@ -306,7 +306,7 @@ void __init plat_swiotlb_setup(void) - swiotlbsize = 64 * (1<<20); - } - #endif --#ifdef CONFIG_USB_OCTEON_OHCI -+#ifdef CONFIG_USB_OHCI_HCD_PLATFORM - /* OCTEON II ohci is only 32-bit. */ - if (OCTEON_IS_OCTEON2() && max_addr >= 0x100000000ul) - swiotlbsize = 64 * (1<<20); -diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c -index a42110e7edbc..a7f40820e567 100644 ---- a/arch/mips/cavium-octeon/setup.c -+++ b/arch/mips/cavium-octeon/setup.c -@@ -413,7 +413,10 @@ static void octeon_restart(char *command) - - mb(); - while (1) -- cvmx_write_csr(CVMX_CIU_SOFT_RST, 1); -+ if (OCTEON_IS_OCTEON3()) -+ cvmx_write_csr(CVMX_RST_SOFT_RST, 1); -+ else -+ cvmx_write_csr(CVMX_CIU_SOFT_RST, 1); - } - - -diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h -index e08381a37f8b..723229f4cf27 100644 ---- a/arch/mips/include/asm/cacheflush.h -+++ b/arch/mips/include/asm/cacheflush.h -@@ -29,6 +29,20 @@ - * - flush_icache_all() flush the entire instruction cache - * - flush_data_cache_page() flushes a page from the data cache - */ -+ -+ /* -+ * This flag is used to indicate that the page pointed to by a pte -+ * is dirty and requires cleaning before returning it to the user. -+ */ -+#define PG_dcache_dirty PG_arch_1 -+ -+#define Page_dcache_dirty(page) \ -+ test_bit(PG_dcache_dirty, &(page)->flags) -+#define SetPageDcacheDirty(page) \ -+ set_bit(PG_dcache_dirty, &(page)->flags) -+#define ClearPageDcacheDirty(page) \ -+ clear_bit(PG_dcache_dirty, &(page)->flags) -+ - extern void (*flush_cache_all)(void); - extern void (*__flush_cache_all)(void); - extern void (*flush_cache_mm)(struct mm_struct *mm); -@@ -37,13 +51,15 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma, - unsigned long start, unsigned long end); - extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn); - extern void __flush_dcache_page(struct page *page); -+extern void __flush_icache_page(struct vm_area_struct *vma, struct page *page); - - #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 - static inline void flush_dcache_page(struct page *page) - { -- if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) -+ if (cpu_has_dc_aliases) - __flush_dcache_page(page); -- -+ else if (!cpu_has_ic_fills_f_dc) -+ SetPageDcacheDirty(page); - } - - #define flush_dcache_mmap_lock(mapping) do { } while (0) -@@ -61,6 +77,11 @@ static inline void flush_anon_page(struct vm_area_struct *vma, - static inline void flush_icache_page(struct vm_area_struct *vma, - struct page *page) - { -+ if (!cpu_has_ic_fills_f_dc && (vma->vm_flags & VM_EXEC) && -+ Page_dcache_dirty(page)) { -+ __flush_icache_page(vma, page); -+ ClearPageDcacheDirty(page); -+ } - } - - extern void (*flush_icache_range)(unsigned long start, unsigned long end); -@@ -95,19 +116,6 @@ extern void (*flush_icache_all)(void); - extern void (*local_flush_data_cache_page)(void * addr); - extern void (*flush_data_cache_page)(unsigned long addr); - --/* -- * This flag is used to indicate that the page pointed to by a pte -- * is dirty and requires cleaning before returning it to the user. -- */ --#define PG_dcache_dirty PG_arch_1 -- --#define Page_dcache_dirty(page) \ -- test_bit(PG_dcache_dirty, &(page)->flags) --#define SetPageDcacheDirty(page) \ -- set_bit(PG_dcache_dirty, &(page)->flags) --#define ClearPageDcacheDirty(page) \ -- clear_bit(PG_dcache_dirty, &(page)->flags) -- - /* Run kernel code uncached, useful for cache probing functions. */ - unsigned long run_uncached(void *func); - -diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h -index 0d8208de9a3f..345fd7f80730 100644 ---- a/arch/mips/include/asm/cpu-features.h -+++ b/arch/mips/include/asm/cpu-features.h -@@ -235,8 +235,39 @@ - /* MIPSR2 and MIPSR6 have a lot of similarities */ - #define cpu_has_mips_r2_r6 (cpu_has_mips_r2 | cpu_has_mips_r6) - -+/* -+ * cpu_has_mips_r2_exec_hazard - return if IHB is required on current processor -+ * -+ * Returns non-zero value if the current processor implementation requires -+ * an IHB instruction to deal with an instruction hazard as per MIPS R2 -+ * architecture specification, zero otherwise. -+ */ - #ifndef cpu_has_mips_r2_exec_hazard --#define cpu_has_mips_r2_exec_hazard (cpu_has_mips_r2 | cpu_has_mips_r6) -+#define cpu_has_mips_r2_exec_hazard \ -+({ \ -+ int __res; \ -+ \ -+ switch (current_cpu_type()) { \ -+ case CPU_M14KC: \ -+ case CPU_74K: \ -+ case CPU_1074K: \ -+ case CPU_PROAPTIV: \ -+ case CPU_P5600: \ -+ case CPU_M5150: \ -+ case CPU_QEMU_GENERIC: \ -+ case CPU_CAVIUM_OCTEON: \ -+ case CPU_CAVIUM_OCTEON_PLUS: \ -+ case CPU_CAVIUM_OCTEON2: \ -+ case CPU_CAVIUM_OCTEON3: \ -+ __res = 0; \ -+ break; \ -+ \ -+ default: \ -+ __res = 1; \ -+ } \ -+ \ -+ __res; \ -+}) - #endif - - /* -diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h -index 535f196ffe02..694925a26924 100644 ---- a/arch/mips/include/asm/elf.h -+++ b/arch/mips/include/asm/elf.h -@@ -294,6 +294,9 @@ do { \ - if (personality(current->personality) != PER_LINUX) \ - set_personality(PER_LINUX); \ - \ -+ clear_thread_flag(TIF_HYBRID_FPREGS); \ -+ set_thread_flag(TIF_32BIT_FPREGS); \ -+ \ - mips_set_personality_fp(state); \ - \ - current->thread.abi = &mips_abi; \ -@@ -319,6 +322,8 @@ do { \ - do { \ - set_thread_flag(TIF_32BIT_REGS); \ - set_thread_flag(TIF_32BIT_ADDR); \ -+ clear_thread_flag(TIF_HYBRID_FPREGS); \ -+ set_thread_flag(TIF_32BIT_FPREGS); \ - \ - mips_set_personality_fp(state); \ - \ -diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h -index fa1f3cfbae8d..d68e685cde60 100644 ---- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h -+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h -@@ -50,7 +50,6 @@ - #define cpu_has_mips32r2 0 - #define cpu_has_mips64r1 0 - #define cpu_has_mips64r2 1 --#define cpu_has_mips_r2_exec_hazard 0 - #define cpu_has_dsp 0 - #define cpu_has_dsp2 0 - #define cpu_has_mipsmt 0 -diff --git a/arch/mips/include/asm/octeon/cvmx.h b/arch/mips/include/asm/octeon/cvmx.h -index 33db1c806b01..774bb45834cb 100644 ---- a/arch/mips/include/asm/octeon/cvmx.h -+++ b/arch/mips/include/asm/octeon/cvmx.h -@@ -436,14 +436,6 @@ static inline uint64_t cvmx_get_cycle_global(void) - - /***************************************************************************/ - --static inline void cvmx_reset_octeon(void) --{ -- union cvmx_ciu_soft_rst ciu_soft_rst; -- ciu_soft_rst.u64 = 0; -- ciu_soft_rst.s.soft_rst = 1; -- cvmx_write_csr(CVMX_CIU_SOFT_RST, ciu_soft_rst.u64); --} -- - /* Return the number of cores available in the chip */ - static inline uint32_t cvmx_octeon_num_cores(void) - { -diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h -index 64ba56a02843..1884609741a8 100644 ---- a/arch/mips/include/asm/octeon/pci-octeon.h -+++ b/arch/mips/include/asm/octeon/pci-octeon.h -@@ -11,9 +11,6 @@ - - #include - --/* Some PCI cards require delays when accessing config space. */ --#define PCI_CONFIG_SPACE_DELAY 10000 -- - /* - * The physical memory base mapped by BAR1. 256MB at the end of the - * first 4GB. -diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h -index bef782c4a44b..f8f809fd6c6d 100644 ---- a/arch/mips/include/asm/pgtable.h -+++ b/arch/mips/include/asm/pgtable.h -@@ -127,10 +127,6 @@ do { \ - } \ - } while(0) - -- --extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, -- pte_t pteval); -- - #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) - - #define pte_none(pte) (!(((pte).pte_low | (pte).pte_high) & ~_PAGE_GLOBAL)) -@@ -154,6 +150,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) - } - } - } -+#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) - - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) - { -@@ -192,6 +189,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) - } - #endif - } -+#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) - - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) - { -@@ -407,12 +405,15 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) - - extern void __update_tlb(struct vm_area_struct *vma, unsigned long address, - pte_t pte); -+extern void __update_cache(struct vm_area_struct *vma, unsigned long address, -+ pte_t pte); - - static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) - { - pte_t pte = *ptep; - __update_tlb(vma, address, pte); -+ __update_cache(vma, address, pte); - } - - static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, -diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h -index 1b22d2da88a1..38902bf97adc 100644 ---- a/arch/mips/include/asm/r4kcache.h -+++ b/arch/mips/include/asm/r4kcache.h -@@ -12,6 +12,8 @@ - #ifndef _ASM_R4KCACHE_H - #define _ASM_R4KCACHE_H - -+#include -+ - #include - #include - #include -@@ -344,7 +346,7 @@ static inline void invalidate_tcache_page(unsigned long addr) - " cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n" \ - " cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n" \ -- " addiu $1, $0, 0x100 \n" \ -+ " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x010($1)\n" \ - " cache %1, 0x020($1); cache %1, 0x030($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x050($1)\n" \ -@@ -368,17 +370,17 @@ static inline void invalidate_tcache_page(unsigned long addr) - " cache %1, 0x040(%0); cache %1, 0x060(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n" \ - " cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ -- " addiu $1, $1, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ - " cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n" \ -- " addiu $1, $1, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100\n" \ - " cache %1, 0x000($1); cache %1, 0x020($1)\n" \ - " cache %1, 0x040($1); cache %1, 0x060($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0a0($1)\n" \ -@@ -396,25 +398,25 @@ static inline void invalidate_tcache_page(unsigned long addr) - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x040(%0)\n" \ - " cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ - " cache %1, 0x000($1); cache %1, 0x040($1)\n" \ - " cache %1, 0x080($1); cache %1, 0x0c0($1)\n" \ - " .set pop\n" \ -@@ -429,39 +431,38 @@ static inline void invalidate_tcache_page(unsigned long addr) - " .set mips64r6\n" \ - " .set noat\n" \ - " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -- " cache %1, 0x000(%0); cache %1, 0x080(%0)\n" \ -- " addiu $1, %0, 0x100\n" \ -+ " "__stringify(LONG_ADDIU)" $1, %0, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ -+ " "__stringify(LONG_ADDIU)" $1, $1, 0x100 \n" \ -+ " cache %1, 0x000($1); cache %1, 0x080($1)\n" \ - " .set pop\n" \ - : \ - : "r" (base), \ -diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h -index b4548690ade9..1fca2e0793dc 100644 ---- a/arch/mips/include/asm/spinlock.h -+++ b/arch/mips/include/asm/spinlock.h -@@ -263,7 +263,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_unlock \n" -- " addiu %1, 1 \n" -+ " addiu %1, -1 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) -diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S -index af41ba6db960..7791840cf22c 100644 ---- a/arch/mips/kernel/entry.S -+++ b/arch/mips/kernel/entry.S -@@ -10,6 +10,7 @@ - - #include - #include -+#include - #include - #include - #include -@@ -185,7 +186,7 @@ syscall_exit_work: - * For C code use the inline version named instruction_hazard(). - */ - LEAF(mips_ihb) -- .set mips32r2 -+ .set MIPS_ISA_LEVEL_RAW - jr.hb ra - nop - END(mips_ihb) -diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c -index bed7590e475f..d5589bedd0a4 100644 ---- a/arch/mips/kernel/smp-cps.c -+++ b/arch/mips/kernel/smp-cps.c -@@ -88,6 +88,12 @@ static void __init cps_smp_setup(void) - - /* Make core 0 coherent with everything */ - write_gcr_cl_coherence(0xff); -+ -+#ifdef CONFIG_MIPS_MT_FPAFF -+ /* If we have an FPU, enroll ourselves in the FPU-full mask */ -+ if (cpu_has_fpu) -+ cpu_set(0, mt_fpu_cpumask); -+#endif /* CONFIG_MIPS_MT_FPAFF */ - } - - static void __init cps_prepare_cpus(unsigned int max_cpus) -diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c -index 7e3ea7766822..77d96db8253c 100644 ---- a/arch/mips/mm/cache.c -+++ b/arch/mips/mm/cache.c -@@ -119,36 +119,37 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) - - EXPORT_SYMBOL(__flush_anon_page); - --static void mips_flush_dcache_from_pte(pte_t pteval, unsigned long address) -+void __flush_icache_page(struct vm_area_struct *vma, struct page *page) -+{ -+ unsigned long addr; -+ -+ if (PageHighMem(page)) -+ return; -+ -+ addr = (unsigned long) page_address(page); -+ flush_data_cache_page(addr); -+} -+EXPORT_SYMBOL_GPL(__flush_icache_page); -+ -+void __update_cache(struct vm_area_struct *vma, unsigned long address, -+ pte_t pte) - { - struct page *page; -- unsigned long pfn = pte_pfn(pteval); -+ unsigned long pfn, addr; -+ int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc; - -+ pfn = pte_pfn(pte); - if (unlikely(!pfn_valid(pfn))) - return; -- - page = pfn_to_page(pfn); - if (page_mapping(page) && Page_dcache_dirty(page)) { -- unsigned long page_addr = (unsigned long) page_address(page); -- -- if (!cpu_has_ic_fills_f_dc || -- pages_do_alias(page_addr, address & PAGE_MASK)) -- flush_data_cache_page(page_addr); -+ addr = (unsigned long) page_address(page); -+ if (exec || pages_do_alias(addr, address & PAGE_MASK)) -+ flush_data_cache_page(addr); - ClearPageDcacheDirty(page); - } - } - --void set_pte_at(struct mm_struct *mm, unsigned long addr, -- pte_t *ptep, pte_t pteval) --{ -- if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) { -- if (pte_present(pteval)) -- mips_flush_dcache_from_pte(pteval, addr); -- } -- -- set_pte(ptep, pteval); --} -- - unsigned long _page_cachable_default; - EXPORT_SYMBOL(_page_cachable_default); - -diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c -index d75ff73a2012..a79fd0af0224 100644 ---- a/arch/mips/mm/tlbex.c -+++ b/arch/mips/mm/tlbex.c -@@ -501,26 +501,9 @@ static void build_tlb_write_entry(u32 **p, struct uasm_label **l, - case tlb_indexed: tlbw = uasm_i_tlbwi; break; - } - -- if (cpu_has_mips_r2_exec_hazard) { -- /* -- * The architecture spec says an ehb is required here, -- * but a number of cores do not have the hazard and -- * using an ehb causes an expensive pipeline stall. -- */ -- switch (current_cpu_type()) { -- case CPU_M14KC: -- case CPU_74K: -- case CPU_1074K: -- case CPU_PROAPTIV: -- case CPU_P5600: -- case CPU_M5150: -- case CPU_QEMU_GENERIC: -- break; -- -- default: -+ if (cpu_has_mips_r2_r6) { -+ if (cpu_has_mips_r2_exec_hazard) - uasm_i_ehb(p); -- break; -- } - tlbw(p); - return; - } -diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c -index c83dbf3689e2..7b066a44e679 100644 ---- a/arch/mips/netlogic/xlp/ahci-init-xlp2.c -+++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c -@@ -203,6 +203,7 @@ static u8 read_phy_reg(u64 regbase, u32 addr, u32 physel) - static void config_sata_phy(u64 regbase) - { - u32 port, i, reg; -+ u8 val; - - for (port = 0; port < 2; port++) { - for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++) -@@ -210,6 +211,18 @@ static void config_sata_phy(u64 regbase) - - for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++) - write_phy_reg(regbase, reg, port, sata_phy_config2[i]); -+ -+ /* Fix for PHY link up failures at lower temperatures */ -+ write_phy_reg(regbase, 0x800F, port, 0x1f); -+ -+ val = read_phy_reg(regbase, 0x0029, port); -+ write_phy_reg(regbase, 0x0029, port, val | (0x7 << 1)); -+ -+ val = read_phy_reg(regbase, 0x0056, port); -+ write_phy_reg(regbase, 0x0056, port, val & ~(1 << 3)); -+ -+ val = read_phy_reg(regbase, 0x0018, port); -+ write_phy_reg(regbase, 0x0018, port, val & ~(0x7 << 0)); - } - } - -diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile -index 300591c6278d..2eda01e6e08f 100644 ---- a/arch/mips/pci/Makefile -+++ b/arch/mips/pci/Makefile -@@ -43,7 +43,7 @@ obj-$(CONFIG_SIBYTE_BCM1x80) += pci-bcm1480.o pci-bcm1480ht.o - obj-$(CONFIG_SNI_RM) += fixup-sni.o ops-sni.o - obj-$(CONFIG_LANTIQ) += fixup-lantiq.o - obj-$(CONFIG_PCI_LANTIQ) += pci-lantiq.o ops-lantiq.o --obj-$(CONFIG_SOC_RT2880) += pci-rt2880.o -+obj-$(CONFIG_SOC_RT288X) += pci-rt2880.o - obj-$(CONFIG_SOC_RT3883) += pci-rt3883.o - obj-$(CONFIG_TANBAC_TB0219) += fixup-tb0219.o - obj-$(CONFIG_TANBAC_TB0226) += fixup-tb0226.o -diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c -index a04af55d89f1..c258cd406fbb 100644 ---- a/arch/mips/pci/pci-octeon.c -+++ b/arch/mips/pci/pci-octeon.c -@@ -214,6 +214,8 @@ const char *octeon_get_pci_interrupts(void) - return "AAABAAAAAAAAAAAAAAAAAAAAAAAAAAAA"; - case CVMX_BOARD_TYPE_BBGW_REF: - return "AABCD"; -+ case CVMX_BOARD_TYPE_CUST_DSR1000N: -+ return "CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC"; - case CVMX_BOARD_TYPE_THUNDER: - case CVMX_BOARD_TYPE_EBH3000: - default: -@@ -271,9 +273,6 @@ static int octeon_read_config(struct pci_bus *bus, unsigned int devfn, - pci_addr.s.func = devfn & 0x7; - pci_addr.s.reg = reg; - --#if PCI_CONFIG_SPACE_DELAY -- udelay(PCI_CONFIG_SPACE_DELAY); --#endif - switch (size) { - case 4: - *val = le32_to_cpu(cvmx_read64_uint32(pci_addr.u64)); -@@ -308,9 +307,6 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn, - pci_addr.s.func = devfn & 0x7; - pci_addr.s.reg = reg; - --#if PCI_CONFIG_SPACE_DELAY -- udelay(PCI_CONFIG_SPACE_DELAY); --#endif - switch (size) { - case 4: - cvmx_write64_uint32(pci_addr.u64, cpu_to_le32(val)); -diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c -index 1bb0b2bf8d6e..99f3db4f0a9b 100644 ---- a/arch/mips/pci/pcie-octeon.c -+++ b/arch/mips/pci/pcie-octeon.c -@@ -1762,14 +1762,6 @@ static int octeon_pcie_write_config(unsigned int pcie_port, struct pci_bus *bus, - default: - return PCIBIOS_FUNC_NOT_SUPPORTED; - } --#if PCI_CONFIG_SPACE_DELAY -- /* -- * Delay on writes so that devices have time to come up. Some -- * bridges need this to allow time for the secondary busses to -- * work -- */ -- udelay(PCI_CONFIG_SPACE_DELAY); --#endif - return PCIBIOS_SUCCESSFUL; - } - -diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig -index b1c52ca580f9..e9bc8c96174e 100644 ---- a/arch/mips/ralink/Kconfig -+++ b/arch/mips/ralink/Kconfig -@@ -7,6 +7,11 @@ config CLKEVT_RT3352 - select CLKSRC_OF - select CLKSRC_MMIO - -+config RALINK_ILL_ACC -+ bool -+ depends on SOC_RT305X -+ default y -+ - choice - prompt "Ralink SoC selection" - default SOC_RT305X -diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c -index a7a3edd28beb..f23179e84128 100644 ---- a/drivers/acpi/sbs.c -+++ b/drivers/acpi/sbs.c -@@ -670,7 +670,7 @@ static int acpi_sbs_add(struct acpi_device *device) - if (!sbs_manager_broken) { - result = acpi_manager_get_info(sbs); - if (!result) { -- sbs->manager_present = 0; -+ sbs->manager_present = 1; - for (id = 0; id < MAX_SBS_BAT; ++id) - if ((sbs->batteries_supported & (1 << id))) - acpi_battery_add(sbs, id); -diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c -index b40af3203089..b67066d0d9a6 100644 ---- a/drivers/block/rbd.c -+++ b/drivers/block/rbd.c -@@ -2264,6 +2264,11 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request) - result, xferred); - if (!img_request->result) - img_request->result = result; -+ /* -+ * Need to end I/O on the entire obj_request worth of -+ * bytes in case of error. -+ */ -+ xferred = obj_request->length; - } - - /* Image object requests don't own their page array */ -diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c -index 9bd56116fd5a..1afc0b419da2 100644 ---- a/drivers/gpu/drm/radeon/atombios_crtc.c -+++ b/drivers/gpu/drm/radeon/atombios_crtc.c -@@ -580,6 +580,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, - else - radeon_crtc->pll_flags |= RADEON_PLL_PREFER_LOW_REF_DIV; - -+ /* if there is no audio, set MINM_OVER_MAXP */ -+ if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) -+ radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP; - if (rdev->family < CHIP_RV770) - radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP; - /* use frac fb div on APUs */ -diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c -index c39c1d0d9d4e..f20eb32406d1 100644 ---- a/drivers/gpu/drm/radeon/atombios_encoders.c -+++ b/drivers/gpu/drm/radeon/atombios_encoders.c -@@ -1729,17 +1729,15 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) - struct drm_device *dev = encoder->dev; - struct radeon_device *rdev = dev->dev_private; - struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); -- struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - int encoder_mode = atombios_get_encoder_mode(encoder); - - DRM_DEBUG_KMS("encoder dpms %d to mode %d, devices %08x, active_devices %08x\n", - radeon_encoder->encoder_id, mode, radeon_encoder->devices, - radeon_encoder->active_device); - -- if (connector && (radeon_audio != 0) && -+ if ((radeon_audio != 0) && - ((encoder_mode == ATOM_ENCODER_MODE_HDMI) || -- (ENCODER_MODE_IS_DP(encoder_mode) && -- drm_detect_monitor_audio(radeon_connector_edid(connector))))) -+ ENCODER_MODE_IS_DP(encoder_mode))) - radeon_audio_dpms(encoder, mode); - - switch (radeon_encoder->encoder_id) { -diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c -index 3adc2afe32aa..68fd9fc677e3 100644 ---- a/drivers/gpu/drm/radeon/dce6_afmt.c -+++ b/drivers/gpu/drm/radeon/dce6_afmt.c -@@ -295,28 +295,3 @@ void dce6_dp_audio_set_dto(struct radeon_device *rdev, - WREG32(DCCG_AUDIO_DTO1_MODULE, clock); - } - } -- --void dce6_dp_enable(struct drm_encoder *encoder, bool enable) --{ -- struct drm_device *dev = encoder->dev; -- struct radeon_device *rdev = dev->dev_private; -- struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); -- struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; -- -- if (!dig || !dig->afmt) -- return; -- -- if (enable) { -- WREG32(EVERGREEN_DP_SEC_TIMESTAMP + dig->afmt->offset, -- EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); -- WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, -- EVERGREEN_DP_SEC_ASP_ENABLE | /* Audio packet transmission */ -- EVERGREEN_DP_SEC_ATP_ENABLE | /* Audio timestamp packet transmission */ -- EVERGREEN_DP_SEC_AIP_ENABLE | /* Audio infoframe packet transmission */ -- EVERGREEN_DP_SEC_STREAM_ENABLE); /* Master enable for secondary stream engine */ -- } else { -- WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, 0); -- } -- -- dig->afmt->enabled = enable; --} -diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c -index c18d4ecbd95d..0926739c9fa7 100644 ---- a/drivers/gpu/drm/radeon/evergreen_hdmi.c -+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c -@@ -219,13 +219,9 @@ void evergreen_set_avi_packet(struct radeon_device *rdev, u32 offset, - WREG32(AFMT_AVI_INFO3 + offset, - frame[0xC] | (frame[0xD] << 8) | (buffer[1] << 24)); - -- WREG32_OR(HDMI_INFOFRAME_CONTROL0 + offset, -- HDMI_AVI_INFO_SEND | /* enable AVI info frames */ -- HDMI_AVI_INFO_CONT); /* required for audio info values to be updated */ -- - WREG32_P(HDMI_INFOFRAME_CONTROL1 + offset, -- HDMI_AVI_INFO_LINE(2), /* anything other than 0 */ -- ~HDMI_AVI_INFO_LINE_MASK); -+ HDMI_AVI_INFO_LINE(2), /* anything other than 0 */ -+ ~HDMI_AVI_INFO_LINE_MASK); - } - - void dce4_hdmi_audio_set_dto(struct radeon_device *rdev, -@@ -370,9 +366,13 @@ void dce4_set_audio_packet(struct drm_encoder *encoder, u32 offset) - WREG32(AFMT_AUDIO_PACKET_CONTROL2 + offset, - AFMT_AUDIO_CHANNEL_ENABLE(0xff)); - -+ WREG32(HDMI_AUDIO_PACKET_CONTROL + offset, -+ HDMI_AUDIO_DELAY_EN(1) | /* set the default audio delay */ -+ HDMI_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */ -+ - /* allow 60958 channel status and send audio packets fields to be updated */ -- WREG32(AFMT_AUDIO_PACKET_CONTROL + offset, -- AFMT_AUDIO_SAMPLE_SEND | AFMT_RESET_FIFO_WHEN_AUDIO_DIS | AFMT_60958_CS_UPDATE); -+ WREG32_OR(AFMT_AUDIO_PACKET_CONTROL + offset, -+ AFMT_RESET_FIFO_WHEN_AUDIO_DIS | AFMT_60958_CS_UPDATE); - } - - -@@ -398,17 +398,26 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) - return; - - if (enable) { -- WREG32(HDMI_INFOFRAME_CONTROL1 + dig->afmt->offset, -- HDMI_AUDIO_INFO_LINE(2)); /* anything other than 0 */ -- -- WREG32(HDMI_AUDIO_PACKET_CONTROL + dig->afmt->offset, -- HDMI_AUDIO_DELAY_EN(1) | /* set the default audio delay */ -- HDMI_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */ -+ struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - -- WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, -- HDMI_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */ -- HDMI_AUDIO_INFO_CONT); /* required for audio info values to be updated */ -+ if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { -+ WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, -+ HDMI_AVI_INFO_SEND | /* enable AVI info frames */ -+ HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */ -+ HDMI_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */ -+ HDMI_AUDIO_INFO_CONT); /* required for audio info values to be updated */ -+ WREG32_OR(AFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, -+ AFMT_AUDIO_SAMPLE_SEND); -+ } else { -+ WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, -+ HDMI_AVI_INFO_SEND | /* enable AVI info frames */ -+ HDMI_AVI_INFO_CONT); /* required for audio info values to be updated */ -+ WREG32_AND(AFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, -+ ~AFMT_AUDIO_SAMPLE_SEND); -+ } - } else { -+ WREG32_AND(AFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, -+ ~AFMT_AUDIO_SAMPLE_SEND); - WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, 0); - } - -@@ -424,20 +433,24 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable) - struct radeon_device *rdev = dev->dev_private; - struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; -+ struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - - if (!dig || !dig->afmt) - return; - -- if (enable) { -+ if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) { - struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector; - uint32_t val; - -+ WREG32_OR(AFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, -+ AFMT_AUDIO_SAMPLE_SEND); -+ - WREG32(EVERGREEN_DP_SEC_TIMESTAMP + dig->afmt->offset, - EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); - -- if (radeon_connector->con_priv) { -+ if (!ASIC_IS_DCE6(rdev) && radeon_connector->con_priv) { - dig_connector = radeon_connector->con_priv; - val = RREG32(EVERGREEN_DP_SEC_AUD_N + dig->afmt->offset); - val &= ~EVERGREEN_DP_SEC_N_BASE_MULTIPLE(0xf); -@@ -457,6 +470,8 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable) - EVERGREEN_DP_SEC_STREAM_ENABLE); /* Master enable for secondary stream engine */ - } else { - WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, 0); -+ WREG32_AND(AFMT_AUDIO_PACKET_CONTROL + dig->afmt->offset, -+ ~AFMT_AUDIO_SAMPLE_SEND); - } - - dig->afmt->enabled = enable; -diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c -index dd6606b8e23c..e85894ade95c 100644 ---- a/drivers/gpu/drm/radeon/r600_hdmi.c -+++ b/drivers/gpu/drm/radeon/r600_hdmi.c -@@ -228,12 +228,13 @@ void r600_set_avi_packet(struct radeon_device *rdev, u32 offset, - WREG32(HDMI0_AVI_INFO3 + offset, - frame[0xC] | (frame[0xD] << 8) | (buffer[1] << 24)); - -+ WREG32_OR(HDMI0_INFOFRAME_CONTROL1 + offset, -+ HDMI0_AVI_INFO_LINE(2)); /* anything other than 0 */ -+ - WREG32_OR(HDMI0_INFOFRAME_CONTROL0 + offset, -- HDMI0_AVI_INFO_SEND | /* enable AVI info frames */ -- HDMI0_AVI_INFO_CONT); /* send AVI info frames every frame/field */ -+ HDMI0_AVI_INFO_SEND | /* enable AVI info frames */ -+ HDMI0_AVI_INFO_CONT); /* send AVI info frames every frame/field */ - -- WREG32_OR(HDMI0_INFOFRAME_CONTROL1 + offset, -- HDMI0_AVI_INFO_LINE(2)); /* anything other than 0 */ - } - - /* -diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c -index b21ef69a34ac..b7d33a13db9f 100644 ---- a/drivers/gpu/drm/radeon/radeon_audio.c -+++ b/drivers/gpu/drm/radeon/radeon_audio.c -@@ -102,7 +102,6 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, - void r600_hdmi_enable(struct drm_encoder *encoder, bool enable); - void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable); - void evergreen_dp_enable(struct drm_encoder *encoder, bool enable); --void dce6_dp_enable(struct drm_encoder *encoder, bool enable); - - static const u32 pin_offsets[7] = - { -@@ -240,7 +239,7 @@ static struct radeon_audio_funcs dce6_dp_funcs = { - .set_avi_packet = evergreen_set_avi_packet, - .set_audio_packet = dce4_set_audio_packet, - .mode_set = radeon_audio_dp_mode_set, -- .dpms = dce6_dp_enable, -+ .dpms = evergreen_dp_enable, - }; - - static void radeon_audio_interface_init(struct radeon_device *rdev) -@@ -461,30 +460,33 @@ void radeon_audio_detect(struct drm_connector *connector, - if (!connector || !connector->encoder) - return; - -+ if (!radeon_encoder_is_digital(connector->encoder)) -+ return; -+ - rdev = connector->encoder->dev->dev_private; - radeon_encoder = to_radeon_encoder(connector->encoder); - dig = radeon_encoder->enc_priv; - -- if (status == connector_status_connected) { -- struct radeon_connector *radeon_connector; -- int sink_type; -- -- if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) { -- radeon_encoder->audio = NULL; -- return; -- } -+ if (!dig->afmt) -+ return; - -- radeon_connector = to_radeon_connector(connector); -- sink_type = radeon_dp_getsinktype(radeon_connector); -+ if (status == connector_status_connected) { -+ struct radeon_connector *radeon_connector = to_radeon_connector(connector); - - if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort && -- sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) -+ radeon_dp_getsinktype(radeon_connector) == -+ CONNECTOR_OBJECT_ID_DISPLAYPORT) - radeon_encoder->audio = rdev->audio.dp_funcs; - else - radeon_encoder->audio = rdev->audio.hdmi_funcs; - - dig->afmt->pin = radeon_audio_get_pin(connector->encoder); -- radeon_audio_enable(rdev, dig->afmt->pin, 0xf); -+ if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { -+ radeon_audio_enable(rdev, dig->afmt->pin, 0xf); -+ } else { -+ radeon_audio_enable(rdev, dig->afmt->pin, 0); -+ dig->afmt->pin = NULL; -+ } - } else { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; -diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c -index 27def67cb6be..27973e3faf0e 100644 ---- a/drivers/gpu/drm/radeon/radeon_connectors.c -+++ b/drivers/gpu/drm/radeon/radeon_connectors.c -@@ -1333,8 +1333,10 @@ out: - /* updated in get modes as well since we need to know if it's analog or digital */ - radeon_connector_update_scratch_regs(connector, ret); - -- if (radeon_audio != 0) -+ if (radeon_audio != 0) { -+ radeon_connector_get_edid(connector); - radeon_audio_detect(connector, ret); -+ } - - exit: - pm_runtime_mark_last_busy(connector->dev->dev); -@@ -1659,8 +1661,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force) - - radeon_connector_update_scratch_regs(connector, ret); - -- if (radeon_audio != 0) -+ if (radeon_audio != 0) { -+ radeon_connector_get_edid(connector); - radeon_audio_detect(connector, ret); -+ } - - out: - pm_runtime_mark_last_busy(connector->dev->dev); -diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c -index 4d0f96cc3da4..ab39b85e0f76 100644 ---- a/drivers/gpu/drm/radeon/radeon_cs.c -+++ b/drivers/gpu/drm/radeon/radeon_cs.c -@@ -88,7 +88,7 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) - p->dma_reloc_idx = 0; - /* FIXME: we assume that each relocs use 4 dwords */ - p->nrelocs = chunk->length_dw / 4; -- p->relocs = kcalloc(p->nrelocs, sizeof(struct radeon_bo_list), GFP_KERNEL); -+ p->relocs = drm_calloc_large(p->nrelocs, sizeof(struct radeon_bo_list)); - if (p->relocs == NULL) { - return -ENOMEM; - } -@@ -428,7 +428,7 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo - } - } - kfree(parser->track); -- kfree(parser->relocs); -+ drm_free_large(parser->relocs); - drm_free_large(parser->vm_bos); - for (i = 0; i < parser->nchunks; i++) - drm_free_large(parser->chunks[i].kdata); -diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c -index 2a5a4a9e772d..de42fc4a22b8 100644 ---- a/drivers/gpu/drm/radeon/radeon_vm.c -+++ b/drivers/gpu/drm/radeon/radeon_vm.c -@@ -473,6 +473,23 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, - } - - mutex_lock(&vm->mutex); -+ soffset /= RADEON_GPU_PAGE_SIZE; -+ eoffset /= RADEON_GPU_PAGE_SIZE; -+ if (soffset || eoffset) { -+ struct interval_tree_node *it; -+ it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1); -+ if (it && it != &bo_va->it) { -+ struct radeon_bo_va *tmp; -+ tmp = container_of(it, struct radeon_bo_va, it); -+ /* bo and tmp overlap, invalid offset */ -+ dev_err(rdev->dev, "bo %p va 0x%010Lx conflict with " -+ "(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo, -+ soffset, tmp->bo, tmp->it.start, tmp->it.last); -+ mutex_unlock(&vm->mutex); -+ return -EINVAL; -+ } -+ } -+ - if (bo_va->it.start || bo_va->it.last) { - if (bo_va->addr) { - /* add a clone of the bo_va to clear the old address */ -@@ -490,6 +507,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, - spin_lock(&vm->status_lock); - list_add(&tmp->vm_status, &vm->freed); - spin_unlock(&vm->status_lock); -+ -+ bo_va->addr = 0; - } - - interval_tree_remove(&bo_va->it, &vm->va); -@@ -497,21 +516,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, - bo_va->it.last = 0; - } - -- soffset /= RADEON_GPU_PAGE_SIZE; -- eoffset /= RADEON_GPU_PAGE_SIZE; - if (soffset || eoffset) { -- struct interval_tree_node *it; -- it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1); -- if (it) { -- struct radeon_bo_va *tmp; -- tmp = container_of(it, struct radeon_bo_va, it); -- /* bo and tmp overlap, invalid offset */ -- dev_err(rdev->dev, "bo %p va 0x%010Lx conflict with " -- "(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo, -- soffset, tmp->bo, tmp->it.start, tmp->it.last); -- mutex_unlock(&vm->mutex); -- return -EINVAL; -- } - bo_va->it.start = soffset; - bo_va->it.last = eoffset - 1; - interval_tree_insert(&bo_va->it, &vm->va); -@@ -1107,7 +1112,8 @@ void radeon_vm_bo_rmv(struct radeon_device *rdev, - list_del(&bo_va->bo_list); - - mutex_lock(&vm->mutex); -- interval_tree_remove(&bo_va->it, &vm->va); -+ if (bo_va->it.start || bo_va->it.last) -+ interval_tree_remove(&bo_va->it, &vm->va); - spin_lock(&vm->status_lock); - list_del(&bo_va->vm_status); - -diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c -index 7be11651b7e6..9dbb3154d559 100644 ---- a/drivers/gpu/drm/radeon/si_dpm.c -+++ b/drivers/gpu/drm/radeon/si_dpm.c -@@ -2924,6 +2924,7 @@ struct si_dpm_quirk { - static struct si_dpm_quirk si_dpm_quirk_list[] = { - /* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */ - { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, -+ { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, - { 0, 0, 0, 0 }, - }; - -diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c -index 3736f71bdec5..18def3022f6e 100644 ---- a/drivers/hv/channel_mgmt.c -+++ b/drivers/hv/channel_mgmt.c -@@ -787,7 +787,7 @@ int vmbus_request_offers(void) - { - struct vmbus_channel_message_header *msg; - struct vmbus_channel_msginfo *msginfo; -- int ret, t; -+ int ret; - - msginfo = kmalloc(sizeof(*msginfo) + - sizeof(struct vmbus_channel_message_header), -@@ -795,8 +795,6 @@ int vmbus_request_offers(void) - if (!msginfo) - return -ENOMEM; - -- init_completion(&msginfo->waitevent); -- - msg = (struct vmbus_channel_message_header *)msginfo->msg; - - msg->msgtype = CHANNELMSG_REQUESTOFFERS; -@@ -810,14 +808,6 @@ int vmbus_request_offers(void) - goto cleanup; - } - -- t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); -- if (t == 0) { -- ret = -ETIMEDOUT; -- goto cleanup; -- } -- -- -- - cleanup: - kfree(msginfo); - -diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c -index ee394dc68303..ec1ea8ba7aac 100644 ---- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c -+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c -@@ -492,7 +492,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, - memoffset = (mtype * (edc_size * 1024 * 1024)); - else { - mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, -- MA_EXT_MEMORY1_BAR_A)); -+ MA_EXT_MEMORY0_BAR_A)); - memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; - } - -diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c -index 3485acf03014..2f1324bed7b3 100644 ---- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c -+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c -@@ -1467,6 +1467,7 @@ static void mlx4_en_service_task(struct work_struct *work) - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_ptp_overflow_check(mdev); - -+ mlx4_en_recover_from_oom(priv); - queue_delayed_work(mdev->workqueue, &priv->service_task, - SERVICE_TASK_DELAY); - } -diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c -index 698d60de1255..05ec5e151ded 100644 ---- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c -+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c -@@ -244,6 +244,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, - return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); - } - -+static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) -+{ -+ BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size); -+ return ring->prod == ring->cons; -+} -+ - static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring) - { - *ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff); -@@ -315,8 +321,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, - ring->cons, ring->prod); - - /* Unmap and free Rx buffers */ -- BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size); -- while (ring->cons != ring->prod) { -+ while (!mlx4_en_is_ring_empty(ring)) { - index = ring->cons & ring->size_mask; - en_dbg(DRV, priv, "Processing descriptor:%d\n", index); - mlx4_en_free_rx_desc(priv, ring, index); -@@ -491,6 +496,23 @@ err_allocator: - return err; - } - -+/* We recover from out of memory by scheduling our napi poll -+ * function (mlx4_en_process_cq), which tries to allocate -+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers). -+ */ -+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) -+{ -+ int ring; -+ -+ if (!priv->port_up) -+ return; -+ -+ for (ring = 0; ring < priv->rx_ring_num; ring++) { -+ if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) -+ napi_reschedule(&priv->rx_cq[ring]->napi); -+ } -+} -+ - void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring **pring, - u32 size, u16 stride) -diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c -index 55f9f5c5344e..8c234ec1d8aa 100644 ---- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c -+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c -@@ -143,8 +143,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, - ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type; - ring->queue_index = queue_index; - -- if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index)) -- cpumask_set_cpu(queue_index, &ring->affinity_mask); -+ if (queue_index < priv->num_tx_rings_p_up) -+ cpumask_set_cpu_local_first(queue_index, -+ priv->mdev->dev->numa_node, -+ &ring->affinity_mask); - - *pring = ring; - return 0; -@@ -213,7 +215,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, - - err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context, - &ring->qp, &ring->qp_state); -- if (!user_prio && cpu_online(ring->queue_index)) -+ if (!cpumask_empty(&ring->affinity_mask)) - netif_set_xps_queue(priv->dev, &ring->affinity_mask, - ring->queue_index); - -diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h -index ebbe244e80dd..8687c8d54227 100644 ---- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h -+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h -@@ -790,6 +790,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, - void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv, - struct mlx4_en_tx_ring *ring); - void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev); -+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv); - int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, - struct mlx4_en_rx_ring **pring, - u32 size, u16 stride, int node); -diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c -index 7600639db4c4..add419d6ff34 100644 ---- a/drivers/scsi/3w-9xxx.c -+++ b/drivers/scsi/3w-9xxx.c -@@ -149,7 +149,6 @@ static int twa_reset_sequence(TW_Device_Extension *tw_dev, int soft_reset); - static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg); - static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int request_id); - static char *twa_string_lookup(twa_message_type *table, unsigned int aen_code); --static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id); - - /* Functions */ - -@@ -1340,11 +1339,11 @@ static irqreturn_t twa_interrupt(int irq, void *dev_instance) - } - - /* Now complete the io */ -+ scsi_dma_unmap(cmd); -+ cmd->scsi_done(cmd); - tw_dev->state[request_id] = TW_S_COMPLETED; - twa_free_request_id(tw_dev, request_id); - tw_dev->posted_request_count--; -- tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); -- twa_unmap_scsi_data(tw_dev, request_id); - } - - /* Check for valid status after each drain */ -@@ -1402,26 +1401,6 @@ static void twa_load_sgl(TW_Device_Extension *tw_dev, TW_Command_Full *full_comm - } - } /* End twa_load_sgl() */ - --/* This function will perform a pci-dma mapping for a scatter gather list */ --static int twa_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id) --{ -- int use_sg; -- struct scsi_cmnd *cmd = tw_dev->srb[request_id]; -- -- use_sg = scsi_dma_map(cmd); -- if (!use_sg) -- return 0; -- else if (use_sg < 0) { -- TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1c, "Failed to map scatter gather list"); -- return 0; -- } -- -- cmd->SCp.phase = TW_PHASE_SGLIST; -- cmd->SCp.have_data_in = use_sg; -- -- return use_sg; --} /* End twa_map_scsi_sg_data() */ -- - /* This function will poll for a response interrupt of a request */ - static int twa_poll_response(TW_Device_Extension *tw_dev, int request_id, int seconds) - { -@@ -1600,9 +1579,11 @@ static int twa_reset_device_extension(TW_Device_Extension *tw_dev) - (tw_dev->state[i] != TW_S_INITIAL) && - (tw_dev->state[i] != TW_S_COMPLETED)) { - if (tw_dev->srb[i]) { -- tw_dev->srb[i]->result = (DID_RESET << 16); -- tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); -- twa_unmap_scsi_data(tw_dev, i); -+ struct scsi_cmnd *cmd = tw_dev->srb[i]; -+ -+ cmd->result = (DID_RESET << 16); -+ scsi_dma_unmap(cmd); -+ cmd->scsi_done(cmd); - } - } - } -@@ -1781,21 +1762,18 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_ - /* Save the scsi command for use by the ISR */ - tw_dev->srb[request_id] = SCpnt; - -- /* Initialize phase to zero */ -- SCpnt->SCp.phase = TW_PHASE_INITIAL; -- - retval = twa_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL); - switch (retval) { - case SCSI_MLQUEUE_HOST_BUSY: -+ scsi_dma_unmap(SCpnt); - twa_free_request_id(tw_dev, request_id); -- twa_unmap_scsi_data(tw_dev, request_id); - break; - case 1: -- tw_dev->state[request_id] = TW_S_COMPLETED; -- twa_free_request_id(tw_dev, request_id); -- twa_unmap_scsi_data(tw_dev, request_id); - SCpnt->result = (DID_ERROR << 16); -+ scsi_dma_unmap(SCpnt); - done(SCpnt); -+ tw_dev->state[request_id] = TW_S_COMPLETED; -+ twa_free_request_id(tw_dev, request_id); - retval = 0; - } - out: -@@ -1863,8 +1841,8 @@ static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, - command_packet->sg_list[0].address = TW_CPU_TO_SGL(tw_dev->generic_buffer_phys[request_id]); - command_packet->sg_list[0].length = cpu_to_le32(TW_MIN_SGL_LENGTH); - } else { -- sg_count = twa_map_scsi_sg_data(tw_dev, request_id); -- if (sg_count == 0) -+ sg_count = scsi_dma_map(srb); -+ if (sg_count < 0) - goto out; - - scsi_for_each_sg(srb, sg, sg_count, i) { -@@ -1979,15 +1957,6 @@ static char *twa_string_lookup(twa_message_type *table, unsigned int code) - return(table[index].text); - } /* End twa_string_lookup() */ - --/* This function will perform a pci-dma unmap */ --static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id) --{ -- struct scsi_cmnd *cmd = tw_dev->srb[request_id]; -- -- if (cmd->SCp.phase == TW_PHASE_SGLIST) -- scsi_dma_unmap(cmd); --} /* End twa_unmap_scsi_data() */ -- - /* This function gets called when a disk is coming on-line */ - static int twa_slave_configure(struct scsi_device *sdev) - { -diff --git a/drivers/scsi/3w-9xxx.h b/drivers/scsi/3w-9xxx.h -index 040f7214e5b7..0fdc83cfa0e1 100644 ---- a/drivers/scsi/3w-9xxx.h -+++ b/drivers/scsi/3w-9xxx.h -@@ -324,11 +324,6 @@ static twa_message_type twa_error_table[] = { - #define TW_CURRENT_DRIVER_BUILD 0 - #define TW_CURRENT_DRIVER_BRANCH 0 - --/* Phase defines */ --#define TW_PHASE_INITIAL 0 --#define TW_PHASE_SINGLE 1 --#define TW_PHASE_SGLIST 2 -- - /* Misc defines */ - #define TW_9550SX_DRAIN_COMPLETED 0xFFFF - #define TW_SECTOR_SIZE 512 -diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c -index 2361772d5909..f8374850f714 100644 ---- a/drivers/scsi/3w-sas.c -+++ b/drivers/scsi/3w-sas.c -@@ -290,26 +290,6 @@ static int twl_post_command_packet(TW_Device_Extension *tw_dev, int request_id) - return 0; - } /* End twl_post_command_packet() */ - --/* This function will perform a pci-dma mapping for a scatter gather list */ --static int twl_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id) --{ -- int use_sg; -- struct scsi_cmnd *cmd = tw_dev->srb[request_id]; -- -- use_sg = scsi_dma_map(cmd); -- if (!use_sg) -- return 0; -- else if (use_sg < 0) { -- TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1, "Failed to map scatter gather list"); -- return 0; -- } -- -- cmd->SCp.phase = TW_PHASE_SGLIST; -- cmd->SCp.have_data_in = use_sg; -- -- return use_sg; --} /* End twl_map_scsi_sg_data() */ -- - /* This function hands scsi cdb's to the firmware */ - static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry_ISO *sglistarg) - { -@@ -357,8 +337,8 @@ static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, - if (!sglistarg) { - /* Map sglist from scsi layer to cmd packet */ - if (scsi_sg_count(srb)) { -- sg_count = twl_map_scsi_sg_data(tw_dev, request_id); -- if (sg_count == 0) -+ sg_count = scsi_dma_map(srb); -+ if (sg_count <= 0) - goto out; - - scsi_for_each_sg(srb, sg, sg_count, i) { -@@ -1102,15 +1082,6 @@ out: - return retval; - } /* End twl_initialize_device_extension() */ - --/* This function will perform a pci-dma unmap */ --static void twl_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id) --{ -- struct scsi_cmnd *cmd = tw_dev->srb[request_id]; -- -- if (cmd->SCp.phase == TW_PHASE_SGLIST) -- scsi_dma_unmap(cmd); --} /* End twl_unmap_scsi_data() */ -- - /* This function will handle attention interrupts */ - static int twl_handle_attention_interrupt(TW_Device_Extension *tw_dev) - { -@@ -1251,11 +1222,11 @@ static irqreturn_t twl_interrupt(int irq, void *dev_instance) - } - - /* Now complete the io */ -+ scsi_dma_unmap(cmd); -+ cmd->scsi_done(cmd); - tw_dev->state[request_id] = TW_S_COMPLETED; - twl_free_request_id(tw_dev, request_id); - tw_dev->posted_request_count--; -- tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); -- twl_unmap_scsi_data(tw_dev, request_id); - } - - /* Check for another response interrupt */ -@@ -1400,10 +1371,12 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res - if ((tw_dev->state[i] != TW_S_FINISHED) && - (tw_dev->state[i] != TW_S_INITIAL) && - (tw_dev->state[i] != TW_S_COMPLETED)) { -- if (tw_dev->srb[i]) { -- tw_dev->srb[i]->result = (DID_RESET << 16); -- tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); -- twl_unmap_scsi_data(tw_dev, i); -+ struct scsi_cmnd *cmd = tw_dev->srb[i]; -+ -+ if (cmd) { -+ cmd->result = (DID_RESET << 16); -+ scsi_dma_unmap(cmd); -+ cmd->scsi_done(cmd); - } - } - } -@@ -1507,9 +1480,6 @@ static int twl_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_ - /* Save the scsi command for use by the ISR */ - tw_dev->srb[request_id] = SCpnt; - -- /* Initialize phase to zero */ -- SCpnt->SCp.phase = TW_PHASE_INITIAL; -- - retval = twl_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL); - if (retval) { - tw_dev->state[request_id] = TW_S_COMPLETED; -diff --git a/drivers/scsi/3w-sas.h b/drivers/scsi/3w-sas.h -index d474892701d4..fec6449c7595 100644 ---- a/drivers/scsi/3w-sas.h -+++ b/drivers/scsi/3w-sas.h -@@ -103,10 +103,6 @@ static char *twl_aen_severity_table[] = - #define TW_CURRENT_DRIVER_BUILD 0 - #define TW_CURRENT_DRIVER_BRANCH 0 - --/* Phase defines */ --#define TW_PHASE_INITIAL 0 --#define TW_PHASE_SGLIST 2 -- - /* Misc defines */ - #define TW_SECTOR_SIZE 512 - #define TW_MAX_UNITS 32 -diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c -index c75f2048319f..2940bd769936 100644 ---- a/drivers/scsi/3w-xxxx.c -+++ b/drivers/scsi/3w-xxxx.c -@@ -1271,32 +1271,6 @@ static int tw_initialize_device_extension(TW_Device_Extension *tw_dev) - return 0; - } /* End tw_initialize_device_extension() */ - --static int tw_map_scsi_sg_data(struct pci_dev *pdev, struct scsi_cmnd *cmd) --{ -- int use_sg; -- -- dprintk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data()\n"); -- -- use_sg = scsi_dma_map(cmd); -- if (use_sg < 0) { -- printk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data(): pci_map_sg() failed.\n"); -- return 0; -- } -- -- cmd->SCp.phase = TW_PHASE_SGLIST; -- cmd->SCp.have_data_in = use_sg; -- -- return use_sg; --} /* End tw_map_scsi_sg_data() */ -- --static void tw_unmap_scsi_data(struct pci_dev *pdev, struct scsi_cmnd *cmd) --{ -- dprintk(KERN_WARNING "3w-xxxx: tw_unmap_scsi_data()\n"); -- -- if (cmd->SCp.phase == TW_PHASE_SGLIST) -- scsi_dma_unmap(cmd); --} /* End tw_unmap_scsi_data() */ -- - /* This function will reset a device extension */ - static int tw_reset_device_extension(TW_Device_Extension *tw_dev) - { -@@ -1319,8 +1293,8 @@ static int tw_reset_device_extension(TW_Device_Extension *tw_dev) - srb = tw_dev->srb[i]; - if (srb != NULL) { - srb->result = (DID_RESET << 16); -- tw_dev->srb[i]->scsi_done(tw_dev->srb[i]); -- tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[i]); -+ scsi_dma_unmap(srb); -+ srb->scsi_done(srb); - } - } - } -@@ -1767,8 +1741,8 @@ static int tw_scsiop_read_write(TW_Device_Extension *tw_dev, int request_id) - command_packet->byte8.io.lba = lba; - command_packet->byte6.block_count = num_sectors; - -- use_sg = tw_map_scsi_sg_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]); -- if (!use_sg) -+ use_sg = scsi_dma_map(srb); -+ if (use_sg <= 0) - return 1; - - scsi_for_each_sg(tw_dev->srb[request_id], sg, use_sg, i) { -@@ -1955,9 +1929,6 @@ static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_c - /* Save the scsi command for use by the ISR */ - tw_dev->srb[request_id] = SCpnt; - -- /* Initialize phase to zero */ -- SCpnt->SCp.phase = TW_PHASE_INITIAL; -- - switch (*command) { - case READ_10: - case READ_6: -@@ -2185,12 +2156,11 @@ static irqreturn_t tw_interrupt(int irq, void *dev_instance) - - /* Now complete the io */ - if ((error != TW_ISR_DONT_COMPLETE)) { -+ scsi_dma_unmap(tw_dev->srb[request_id]); -+ tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); - tw_dev->state[request_id] = TW_S_COMPLETED; - tw_state_request_finish(tw_dev, request_id); - tw_dev->posted_request_count--; -- tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]); -- -- tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]); - } - } - -diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h -index 29b0b84ed69e..6f65e663d393 100644 ---- a/drivers/scsi/3w-xxxx.h -+++ b/drivers/scsi/3w-xxxx.h -@@ -195,11 +195,6 @@ static unsigned char tw_sense_table[][4] = - #define TW_AEN_SMART_FAIL 0x000F - #define TW_AEN_SBUF_FAIL 0x0024 - --/* Phase defines */ --#define TW_PHASE_INITIAL 0 --#define TW_PHASE_SINGLE 1 --#define TW_PHASE_SGLIST 2 -- - /* Misc defines */ - #define TW_ALIGNMENT_6000 64 /* 64 bytes */ - #define TW_ALIGNMENT_7000 4 /* 4 bytes */ -diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c -index 262ab837a704..9f77d23239a2 100644 ---- a/drivers/scsi/scsi_devinfo.c -+++ b/drivers/scsi/scsi_devinfo.c -@@ -226,6 +226,7 @@ static struct { - {"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, - {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, - {"Promise", "", NULL, BLIST_SPARSELUN}, -+ {"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024}, - {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, - {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, - {"SanDisk", "ImageMate CF-SD1", NULL, BLIST_FORCELUN}, -diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c -index 9c0a520d933c..3e6142f61499 100644 ---- a/drivers/scsi/scsi_scan.c -+++ b/drivers/scsi/scsi_scan.c -@@ -897,6 +897,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, - */ - if (*bflags & BLIST_MAX_512) - blk_queue_max_hw_sectors(sdev->request_queue, 512); -+ /* -+ * Max 1024 sector transfer length for targets that report incorrect -+ * max/optimal lengths and relied on the old block layer safe default -+ */ -+ else if (*bflags & BLIST_MAX_1024) -+ blk_queue_max_hw_sectors(sdev->request_queue, 1024); - - /* - * Some devices may not want to have a start command automatically -diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig -index 75b3603906c1..f0d22cdb51cd 100644 ---- a/drivers/ssb/Kconfig -+++ b/drivers/ssb/Kconfig -@@ -130,6 +130,7 @@ config SSB_DRIVER_MIPS - bool "SSB Broadcom MIPS core driver" - depends on SSB && MIPS - select SSB_SERIAL -+ select SSB_SFLASH - help - Driver for the Sonics Silicon Backplane attached - Broadcom MIPS core. -diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c -index 4e959c43f680..6afce7eb3d74 100644 ---- a/drivers/tty/serial/atmel_serial.c -+++ b/drivers/tty/serial/atmel_serial.c -@@ -880,6 +880,7 @@ static int atmel_prepare_tx_dma(struct uart_port *port) - config.direction = DMA_MEM_TO_DEV; - config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - config.dst_addr = port->mapbase + ATMEL_US_THR; -+ config.dst_maxburst = 1; - - ret = dmaengine_slave_config(atmel_port->chan_tx, - &config); -@@ -1059,6 +1060,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port) - config.direction = DMA_DEV_TO_MEM; - config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - config.src_addr = port->mapbase + ATMEL_US_RHR; -+ config.src_maxburst = 1; - - ret = dmaengine_slave_config(atmel_port->chan_rx, - &config); -diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c -index 33fb94f78967..0a52c8b55a5f 100644 ---- a/drivers/tty/serial/of_serial.c -+++ b/drivers/tty/serial/of_serial.c -@@ -344,7 +344,6 @@ static struct of_device_id of_platform_serial_table[] = { - { .compatible = "ibm,qpace-nwp-serial", - .data = (void *)PORT_NWPSERIAL, }, - #endif -- { .type = "serial", .data = (void *)PORT_UNKNOWN, }, - { /* end of list */ }, - }; - -diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c -index 189f52e3111f..a0099a7f60d4 100644 ---- a/drivers/tty/serial/uartlite.c -+++ b/drivers/tty/serial/uartlite.c -@@ -632,7 +632,8 @@ MODULE_DEVICE_TABLE(of, ulite_of_match); - - static int ulite_probe(struct platform_device *pdev) - { -- struct resource *res, *res2; -+ struct resource *res; -+ int irq; - int id = pdev->id; - #ifdef CONFIG_OF - const __be32 *prop; -@@ -646,11 +647,11 @@ static int ulite_probe(struct platform_device *pdev) - if (!res) - return -ENODEV; - -- res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0); -- if (!res2) -- return -ENODEV; -+ irq = platform_get_irq(pdev, 0); -+ if (irq <= 0) -+ return -ENXIO; - -- return ulite_assign(&pdev->dev, id, res->start, res2->start); -+ return ulite_assign(&pdev->dev, id, res->start, irq); - } - - static int ulite_remove(struct platform_device *pdev) -diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c -index cff531a51a78..54853a02ce9e 100644 ---- a/drivers/tty/serial/xilinx_uartps.c -+++ b/drivers/tty/serial/xilinx_uartps.c -@@ -1325,9 +1325,9 @@ static SIMPLE_DEV_PM_OPS(cdns_uart_dev_pm_ops, cdns_uart_suspend, - */ - static int cdns_uart_probe(struct platform_device *pdev) - { -- int rc, id; -+ int rc, id, irq; - struct uart_port *port; -- struct resource *res, *res2; -+ struct resource *res; - struct cdns_uart *cdns_uart_data; - - cdns_uart_data = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_data), -@@ -1374,9 +1374,9 @@ static int cdns_uart_probe(struct platform_device *pdev) - goto err_out_clk_disable; - } - -- res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0); -- if (!res2) { -- rc = -ENODEV; -+ irq = platform_get_irq(pdev, 0); -+ if (irq <= 0) { -+ rc = -ENXIO; - goto err_out_clk_disable; - } - -@@ -1405,7 +1405,7 @@ static int cdns_uart_probe(struct platform_device *pdev) - * and triggers invocation of the config_port() entry point. - */ - port->mapbase = res->start; -- port->irq = res2->start; -+ port->irq = irq; - port->dev = &pdev->dev; - port->uartclk = clk_get_rate(cdns_uart_data->uartclk); - port->private_data = cdns_uart_data; -diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c -index 562e581f6765..3770330a2201 100644 ---- a/drivers/usb/chipidea/otg_fsm.c -+++ b/drivers/usb/chipidea/otg_fsm.c -@@ -537,7 +537,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on) - { - struct ci_hdrc *ci = container_of(fsm, struct ci_hdrc, fsm); - -- mutex_unlock(&fsm->lock); - if (on) { - ci_role_stop(ci); - ci_role_start(ci, CI_ROLE_HOST); -@@ -546,7 +545,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on) - hw_device_reset(ci); - ci_role_start(ci, CI_ROLE_GADGET); - } -- mutex_lock(&fsm->lock); - return 0; - } - -@@ -554,12 +552,10 @@ static int ci_otg_start_gadget(struct otg_fsm *fsm, int on) - { - struct ci_hdrc *ci = container_of(fsm, struct ci_hdrc, fsm); - -- mutex_unlock(&fsm->lock); - if (on) - usb_gadget_vbus_connect(&ci->gadget); - else - usb_gadget_vbus_disconnect(&ci->gadget); -- mutex_lock(&fsm->lock); - - return 0; - } -diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c -index 683617714e7c..220c0fd059bb 100644 ---- a/drivers/usb/class/cdc-acm.c -+++ b/drivers/usb/class/cdc-acm.c -@@ -1133,11 +1133,16 @@ static int acm_probe(struct usb_interface *intf, - } - - while (buflen > 0) { -+ elength = buffer[0]; -+ if (!elength) { -+ dev_err(&intf->dev, "skipping garbage byte\n"); -+ elength = 1; -+ goto next_desc; -+ } - if (buffer[1] != USB_DT_CS_INTERFACE) { - dev_err(&intf->dev, "skipping garbage\n"); - goto next_desc; - } -- elength = buffer[0]; - - switch (buffer[2]) { - case USB_CDC_UNION_TYPE: /* we've found it */ -diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h -index 9893d696fc97..f58caa9e6a27 100644 ---- a/drivers/usb/storage/uas-detect.h -+++ b/drivers/usb/storage/uas-detect.h -@@ -51,7 +51,8 @@ static int uas_find_endpoints(struct usb_host_interface *alt, - } - - static int uas_use_uas_driver(struct usb_interface *intf, -- const struct usb_device_id *id) -+ const struct usb_device_id *id, -+ unsigned long *flags_ret) - { - struct usb_host_endpoint *eps[4] = { }; - struct usb_device *udev = interface_to_usbdev(intf); -@@ -73,7 +74,7 @@ static int uas_use_uas_driver(struct usb_interface *intf, - * this writing the following versions exist: - * ASM1051 - no uas support version - * ASM1051 - with broken (*) uas support -- * ASM1053 - with working uas support -+ * ASM1053 - with working uas support, but problems with large xfers - * ASM1153 - with working uas support - * - * Devices with these chips re-use a number of device-ids over the -@@ -103,6 +104,9 @@ static int uas_use_uas_driver(struct usb_interface *intf, - } else if (usb_ss_max_streams(&eps[1]->ss_ep_comp) == 32) { - /* Possibly an ASM1051, disable uas */ - flags |= US_FL_IGNORE_UAS; -+ } else { -+ /* ASM1053, these have issues with large transfers */ -+ flags |= US_FL_MAX_SECTORS_240; - } - } - -@@ -132,5 +136,8 @@ static int uas_use_uas_driver(struct usb_interface *intf, - return 0; - } - -+ if (flags_ret) -+ *flags_ret = flags; -+ - return 1; - } -diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c -index 6cdabdc119a7..6d3122afeed3 100644 ---- a/drivers/usb/storage/uas.c -+++ b/drivers/usb/storage/uas.c -@@ -759,7 +759,10 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd) - - static int uas_slave_alloc(struct scsi_device *sdev) - { -- sdev->hostdata = (void *)sdev->host->hostdata; -+ struct uas_dev_info *devinfo = -+ (struct uas_dev_info *)sdev->host->hostdata; -+ -+ sdev->hostdata = devinfo; - - /* USB has unusual DMA-alignment requirements: Although the - * starting address of each scatter-gather element doesn't matter, -@@ -778,6 +781,11 @@ static int uas_slave_alloc(struct scsi_device *sdev) - */ - blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); - -+ if (devinfo->flags & US_FL_MAX_SECTORS_64) -+ blk_queue_max_hw_sectors(sdev->request_queue, 64); -+ else if (devinfo->flags & US_FL_MAX_SECTORS_240) -+ blk_queue_max_hw_sectors(sdev->request_queue, 240); -+ - return 0; - } - -@@ -887,8 +895,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) - struct Scsi_Host *shost = NULL; - struct uas_dev_info *devinfo; - struct usb_device *udev = interface_to_usbdev(intf); -+ unsigned long dev_flags; - -- if (!uas_use_uas_driver(intf, id)) -+ if (!uas_use_uas_driver(intf, id, &dev_flags)) - return -ENODEV; - - if (uas_switch_interface(udev, intf)) -@@ -910,8 +919,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) - devinfo->udev = udev; - devinfo->resetting = 0; - devinfo->shutdown = 0; -- devinfo->flags = id->driver_info; -- usb_stor_adjust_quirks(udev, &devinfo->flags); -+ devinfo->flags = dev_flags; - init_usb_anchor(&devinfo->cmd_urbs); - init_usb_anchor(&devinfo->sense_urbs); - init_usb_anchor(&devinfo->data_urbs); -diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c -index 5600c33fcadb..6c10c888f35f 100644 ---- a/drivers/usb/storage/usb.c -+++ b/drivers/usb/storage/usb.c -@@ -479,7 +479,8 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) - US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT | - US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 | - US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE | -- US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES); -+ US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES | -+ US_FL_MAX_SECTORS_240); - - p = quirks; - while (*p) { -@@ -520,6 +521,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) - case 'f': - f |= US_FL_NO_REPORT_OPCODES; - break; -+ case 'g': -+ f |= US_FL_MAX_SECTORS_240; -+ break; - case 'h': - f |= US_FL_CAPACITY_HEURISTICS; - break; -@@ -1080,7 +1084,7 @@ static int storage_probe(struct usb_interface *intf, - - /* If uas is enabled and this device can do uas then ignore it. */ - #if IS_ENABLED(CONFIG_USB_UAS) -- if (uas_use_uas_driver(intf, id)) -+ if (uas_use_uas_driver(intf, id, NULL)) - return -ENXIO; - #endif - -diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c -index f23d4be3280e..2b4c5423672d 100644 ---- a/fs/btrfs/ioctl.c -+++ b/fs/btrfs/ioctl.c -@@ -2403,7 +2403,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, - "Attempt to delete subvolume %llu during send", - dest->root_key.objectid); - err = -EPERM; -- goto out_dput; -+ goto out_unlock_inode; - } - - d_invalidate(dentry); -@@ -2498,6 +2498,7 @@ out_up_write: - root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); - spin_unlock(&dest->root_item_lock); - } -+out_unlock_inode: - mutex_unlock(&inode->i_mutex); - if (!err) { - shrink_dcache_sb(root->fs_info->sb); -diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c -index bed43081720f..16f6365f65e7 100644 ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -4934,13 +4934,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) - if (ret) - return ret; - -- /* -- * currently supporting (pre)allocate mode for extent-based -- * files _only_ -- */ -- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) -- return -EOPNOTSUPP; -- - if (mode & FALLOC_FL_COLLAPSE_RANGE) - return ext4_collapse_range(inode, offset, len); - -@@ -4962,6 +4955,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) - - mutex_lock(&inode->i_mutex); - -+ /* -+ * We only support preallocation for extent-based files only -+ */ -+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { -+ ret = -EOPNOTSUPP; -+ goto out; -+ } -+ - if (!(mode & FALLOC_FL_KEEP_SIZE) && - offset + len > i_size_read(inode)) { - new_size = offset + len; -diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c -index e04d45733976..9a0121376358 100644 ---- a/fs/ext4/extents_status.c -+++ b/fs/ext4/extents_status.c -@@ -705,6 +705,14 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, - - BUG_ON(end < lblk); - -+ if ((status & EXTENT_STATUS_DELAYED) && -+ (status & EXTENT_STATUS_WRITTEN)) { -+ ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as " -+ " delayed and written which can potentially " -+ " cause data loss.\n", lblk, len); -+ WARN_ON(1); -+ } -+ - newes.es_lblk = lblk; - newes.es_len = len; - ext4_es_store_pblock_status(&newes, pblk, status); -diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c -index 5cb9a212b86f..852cc521f327 100644 ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -534,6 +534,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && -+ !(status & EXTENT_STATUS_WRITTEN) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) - status |= EXTENT_STATUS_DELAYED; -@@ -638,6 +639,7 @@ found: - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && -+ !(status & EXTENT_STATUS_WRITTEN) && - ext4_find_delalloc_range(inode, map->m_lblk, - map->m_lblk + map->m_len - 1)) - status |= EXTENT_STATUS_DELAYED; -diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c -index d98094a9f476..ff10f3decbc9 100644 ---- a/fs/hfsplus/xattr.c -+++ b/fs/hfsplus/xattr.c -@@ -806,9 +806,6 @@ end_removexattr: - static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size, int type) - { -- char *xattr_name; -- int res; -- - if (!strcmp(name, "")) - return -EINVAL; - -@@ -818,24 +815,19 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, - */ - if (is_known_namespace(name)) - return -EOPNOTSUPP; -- xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN -- + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL); -- if (!xattr_name) -- return -ENOMEM; -- strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); -- strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); - -- res = hfsplus_getxattr(dentry, xattr_name, buffer, size); -- kfree(xattr_name); -- return res; -+ /* -+ * osx is the namespace we use to indicate an unprefixed -+ * attribute on the filesystem (like the ones that OS X -+ * creates), so we pass the name through unmodified (after -+ * ensuring it doesn't conflict with another namespace). -+ */ -+ return hfsplus_getxattr(dentry, name, buffer, size); - } - - static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, - const void *buffer, size_t size, int flags, int type) - { -- char *xattr_name; -- int res; -- - if (!strcmp(name, "")) - return -EINVAL; - -@@ -845,16 +837,14 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, - */ - if (is_known_namespace(name)) - return -EOPNOTSUPP; -- xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN -- + XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL); -- if (!xattr_name) -- return -ENOMEM; -- strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); -- strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); - -- res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); -- kfree(xattr_name); -- return res; -+ /* -+ * osx is the namespace we use to indicate an unprefixed -+ * attribute on the filesystem (like the ones that OS X -+ * creates), so we pass the name through unmodified (after -+ * ensuring it doesn't conflict with another namespace). -+ */ -+ return hfsplus_setxattr(dentry, name, buffer, size, flags); - } - - static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list, -diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h -index a7f2604c5f25..7f5f78bd15ad 100644 ---- a/include/linux/usb_usual.h -+++ b/include/linux/usb_usual.h -@@ -77,6 +77,8 @@ - /* Cannot handle ATA_12 or ATA_16 CDBs */ \ - US_FLAG(NO_REPORT_OPCODES, 0x04000000) \ - /* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */ \ -+ US_FLAG(MAX_SECTORS_240, 0x08000000) \ -+ /* Sets max_sectors to 240 */ \ - - #define US_FLAG(name, value) US_FL_##name = value , - enum { US_DO_ALL_FLAGS }; -diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h -index 183eaab7c380..96e3f56519e7 100644 ---- a/include/scsi/scsi_devinfo.h -+++ b/include/scsi/scsi_devinfo.h -@@ -36,5 +36,6 @@ - for sequential scan */ - #define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ - #define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ -+#define BLIST_MAX_1024 0x40000000 /* maximum 1024 sector cdb length */ - - #endif -diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h -index 0de95ccb92cf..5bd134651f5e 100644 ---- a/include/sound/emu10k1.h -+++ b/include/sound/emu10k1.h -@@ -41,7 +41,8 @@ - - #define EMUPAGESIZE 4096 - #define MAXREQVOICES 8 --#define MAXPAGES 8192 -+#define MAXPAGES0 4096 /* 32 bit mode */ -+#define MAXPAGES1 8192 /* 31 bit mode */ - #define RESERVED 0 - #define NUM_MIDI 16 - #define NUM_G 64 /* use all channels */ -@@ -50,8 +51,7 @@ - - /* FIXME? - according to the OSS driver the EMU10K1 needs a 29 bit DMA mask */ - #define EMU10K1_DMA_MASK 0x7fffffffUL /* 31bit */ --#define AUDIGY_DMA_MASK 0x7fffffffUL /* 31bit FIXME - 32 should work? */ -- /* See ALSA bug #1276 - rlrevell */ -+#define AUDIGY_DMA_MASK 0xffffffffUL /* 32bit mode */ - - #define TMEMSIZE 256*1024 - #define TMEMSIZEREG 4 -@@ -466,8 +466,11 @@ - - #define MAPB 0x0d /* Cache map B */ - --#define MAP_PTE_MASK 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ --#define MAP_PTI_MASK 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ -+#define MAP_PTE_MASK0 0xfffff000 /* The 20 MSBs of the PTE indexed by the PTI */ -+#define MAP_PTI_MASK0 0x00000fff /* The 12 bit index to one of the 4096 PTE dwords */ -+ -+#define MAP_PTE_MASK1 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ -+#define MAP_PTI_MASK1 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ - - /* 0x0e, 0x0f: Not used */ - -@@ -1704,6 +1707,7 @@ struct snd_emu10k1 { - unsigned short model; /* subsystem id */ - unsigned int card_type; /* EMU10K1_CARD_* */ - unsigned int ecard_ctrl; /* ecard control bits */ -+ unsigned int address_mode; /* address mode */ - unsigned long dma_mask; /* PCI DMA mask */ - unsigned int delay_pcm_irq; /* in samples */ - int max_cache_pages; /* max memory size / PAGE_SIZE */ -diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h -index 8d7416e46861..15355892a0ff 100644 ---- a/include/sound/soc-dapm.h -+++ b/include/sound/soc-dapm.h -@@ -287,7 +287,7 @@ struct device; - .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | SNDRV_CTL_ELEM_ACCESS_READWRITE,\ - .tlv.p = (tlv_array), \ - .get = snd_soc_dapm_get_volsw, .put = snd_soc_dapm_put_volsw, \ -- .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 0) } -+ .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 1) } - #define SOC_DAPM_SINGLE_TLV_VIRT(xname, max, tlv_array) \ - SOC_DAPM_SINGLE(xname, SND_SOC_NOPM, 0, max, 0, tlv_array) - #define SOC_DAPM_ENUM(xname, xenum) \ -diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c -index a64e7a207d2b..0c5796eadae1 100644 ---- a/kernel/bpf/core.c -+++ b/kernel/bpf/core.c -@@ -357,8 +357,8 @@ select_insn: - ALU64_MOD_X: - if (unlikely(SRC == 0)) - return 0; -- tmp = DST; -- DST = do_div(tmp, SRC); -+ div64_u64_rem(DST, SRC, &tmp); -+ DST = tmp; - CONT; - ALU_MOD_X: - if (unlikely(SRC == 0)) -@@ -367,8 +367,8 @@ select_insn: - DST = do_div(tmp, (u32) SRC); - CONT; - ALU64_MOD_K: -- tmp = DST; -- DST = do_div(tmp, IMM); -+ div64_u64_rem(DST, IMM, &tmp); -+ DST = tmp; - CONT; - ALU_MOD_K: - tmp = (u32) DST; -@@ -377,7 +377,7 @@ select_insn: - ALU64_DIV_X: - if (unlikely(SRC == 0)) - return 0; -- do_div(DST, SRC); -+ DST = div64_u64(DST, SRC); - CONT; - ALU_DIV_X: - if (unlikely(SRC == 0)) -@@ -387,7 +387,7 @@ select_insn: - DST = (u32) tmp; - CONT; - ALU64_DIV_K: -- do_div(DST, IMM); -+ DST = div64_u64(DST, IMM); - CONT; - ALU_DIV_K: - tmp = (u32) DST; -diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c -index 208d5439e59b..787b0d699969 100644 ---- a/net/ipv4/ping.c -+++ b/net/ipv4/ping.c -@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk) - if (sk_hashed(sk)) { - write_lock_bh(&ping_table.lock); - hlist_nulls_del(&sk->sk_nulls_node); -+ sk_nulls_node_init(&sk->sk_nulls_node); - sock_put(sk); - isk->inet_num = 0; - isk->inet_sport = 0; -diff --git a/net/ipv4/route.c b/net/ipv4/route.c -index ad5064362c5c..20fc0202cbbe 100644 ---- a/net/ipv4/route.c -+++ b/net/ipv4/route.c -@@ -963,10 +963,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) - if (dst_metric_locked(dst, RTAX_MTU)) - return; - -- if (dst->dev->mtu < mtu) -- return; -- -- if (rt->rt_pmtu && rt->rt_pmtu < mtu) -+ if (ipv4_mtu(dst) < mtu) - return; - - if (mtu < ip_rt_min_pmtu) -diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c -index 37d0220a094c..db7a2e5e4a14 100644 ---- a/sound/pci/emu10k1/emu10k1.c -+++ b/sound/pci/emu10k1/emu10k1.c -@@ -183,8 +183,10 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci, - } - #endif - -- strcpy(card->driver, emu->card_capabilities->driver); -- strcpy(card->shortname, emu->card_capabilities->name); -+ strlcpy(card->driver, emu->card_capabilities->driver, -+ sizeof(card->driver)); -+ strlcpy(card->shortname, emu->card_capabilities->name, -+ sizeof(card->shortname)); - snprintf(card->longname, sizeof(card->longname), - "%s (rev.%d, serial:0x%x) at 0x%lx, irq %i", - card->shortname, emu->revision, emu->serial, emu->port, emu->irq); -diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c -index 874cd76c7b7f..d2c7ea3a7610 100644 ---- a/sound/pci/emu10k1/emu10k1_callback.c -+++ b/sound/pci/emu10k1/emu10k1_callback.c -@@ -415,7 +415,7 @@ start_voice(struct snd_emux_voice *vp) - snd_emu10k1_ptr_write(hw, Z2, ch, 0); - - /* invalidate maps */ -- temp = (hw->silent_page.addr << 1) | MAP_PTI_MASK; -+ temp = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - snd_emu10k1_ptr_write(hw, MAPA, ch, temp); - snd_emu10k1_ptr_write(hw, MAPB, ch, temp); - #if 0 -@@ -436,7 +436,7 @@ start_voice(struct snd_emux_voice *vp) - snd_emu10k1_ptr_write(hw, CDF, ch, sample); - - /* invalidate maps */ -- temp = ((unsigned int)hw->silent_page.addr << 1) | MAP_PTI_MASK; -+ temp = ((unsigned int)hw->silent_page.addr << hw_address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - snd_emu10k1_ptr_write(hw, MAPA, ch, temp); - snd_emu10k1_ptr_write(hw, MAPB, ch, temp); - -diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c -index b4458a630a7c..df9f5c7c9c77 100644 ---- a/sound/pci/emu10k1/emu10k1_main.c -+++ b/sound/pci/emu10k1/emu10k1_main.c -@@ -282,7 +282,7 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) - snd_emu10k1_ptr_write(emu, TCB, 0, 0); /* taken from original driver */ - snd_emu10k1_ptr_write(emu, TCBS, 0, 4); /* taken from original driver */ - -- silent_page = (emu->silent_page.addr << 1) | MAP_PTI_MASK; -+ silent_page = (emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - for (ch = 0; ch < NUM_G; ch++) { - snd_emu10k1_ptr_write(emu, MAPA, ch, silent_page); - snd_emu10k1_ptr_write(emu, MAPB, ch, silent_page); -@@ -348,6 +348,11 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) - outl(reg | A_IOCFG_GPOUT0, emu->port + A_IOCFG); - } - -+ if (emu->address_mode == 0) { -+ /* use 16M in 4G */ -+ outl(inl(emu->port + HCFG) | HCFG_EXPANDED_MEM, emu->port + HCFG); -+ } -+ - return 0; - } - -@@ -1421,7 +1426,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { - * - */ - {.vendor = 0x1102, .device = 0x0008, .subsystem = 0x20011102, -- .driver = "Audigy2", .name = "SB Audigy 2 ZS Notebook [SB0530]", -+ .driver = "Audigy2", .name = "Audigy 2 ZS Notebook [SB0530]", - .id = "Audigy2", - .emu10k2_chip = 1, - .ca0108_chip = 1, -@@ -1571,7 +1576,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { - .adc_1361t = 1, /* 24 bit capture instead of 16bit */ - .ac97_chip = 1} , - {.vendor = 0x1102, .device = 0x0004, .subsystem = 0x10051102, -- .driver = "Audigy2", .name = "SB Audigy 2 Platinum EX [SB0280]", -+ .driver = "Audigy2", .name = "Audigy 2 Platinum EX [SB0280]", - .id = "Audigy2", - .emu10k2_chip = 1, - .ca0102_chip = 1, -@@ -1877,8 +1882,10 @@ int snd_emu10k1_create(struct snd_card *card, - - is_audigy = emu->audigy = c->emu10k2_chip; - -+ /* set addressing mode */ -+ emu->address_mode = is_audigy ? 0 : 1; - /* set the DMA transfer mask */ -- emu->dma_mask = is_audigy ? AUDIGY_DMA_MASK : EMU10K1_DMA_MASK; -+ emu->dma_mask = emu->address_mode ? EMU10K1_DMA_MASK : AUDIGY_DMA_MASK; - if (pci_set_dma_mask(pci, emu->dma_mask) < 0 || - pci_set_consistent_dma_mask(pci, emu->dma_mask) < 0) { - dev_err(card->dev, -@@ -1903,7 +1910,7 @@ int snd_emu10k1_create(struct snd_card *card, - - emu->max_cache_pages = max_cache_bytes >> PAGE_SHIFT; - if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci), -- 32 * 1024, &emu->ptb_pages) < 0) { -+ (emu->address_mode ? 32 : 16) * 1024, &emu->ptb_pages) < 0) { - err = -ENOMEM; - goto error; - } -@@ -2002,8 +2009,8 @@ int snd_emu10k1_create(struct snd_card *card, - - /* Clear silent pages and set up pointers */ - memset(emu->silent_page.area, 0, PAGE_SIZE); -- silent_page = emu->silent_page.addr << 1; -- for (idx = 0; idx < MAXPAGES; idx++) -+ silent_page = emu->silent_page.addr << emu->address_mode; -+ for (idx = 0; idx < (emu->address_mode ? MAXPAGES1 : MAXPAGES0); idx++) - ((u32 *)emu->ptb_pages.area)[idx] = cpu_to_le32(silent_page | idx); - - /* set up voice indices */ -diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c -index 0dc07385af0e..14a305bd8a98 100644 ---- a/sound/pci/emu10k1/emupcm.c -+++ b/sound/pci/emu10k1/emupcm.c -@@ -380,7 +380,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu, - snd_emu10k1_ptr_write(emu, Z1, voice, 0); - snd_emu10k1_ptr_write(emu, Z2, voice, 0); - /* invalidate maps */ -- silent_page = ((unsigned int)emu->silent_page.addr << 1) | MAP_PTI_MASK; -+ silent_page = ((unsigned int)emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - snd_emu10k1_ptr_write(emu, MAPA, voice, silent_page); - snd_emu10k1_ptr_write(emu, MAPB, voice, silent_page); - /* modulation envelope */ -diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c -index c68e6dd2fa67..4f1f69be1865 100644 ---- a/sound/pci/emu10k1/memory.c -+++ b/sound/pci/emu10k1/memory.c -@@ -34,10 +34,11 @@ - * aligned pages in others - */ - #define __set_ptb_entry(emu,page,addr) \ -- (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << 1) | (page))) -+ (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << (emu->address_mode)) | (page))) - - #define UNIT_PAGES (PAGE_SIZE / EMUPAGESIZE) --#define MAX_ALIGN_PAGES (MAXPAGES / UNIT_PAGES) -+#define MAX_ALIGN_PAGES0 (MAXPAGES0 / UNIT_PAGES) -+#define MAX_ALIGN_PAGES1 (MAXPAGES1 / UNIT_PAGES) - /* get aligned page from offset address */ - #define get_aligned_page(offset) ((offset) >> PAGE_SHIFT) - /* get offset address from aligned page */ -@@ -124,7 +125,7 @@ static int search_empty_map_area(struct snd_emu10k1 *emu, int npages, struct lis - } - page = blk->mapped_page + blk->pages; - } -- size = MAX_ALIGN_PAGES - page; -+ size = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0) - page; - if (size >= max_size) { - *nextp = pos; - return page; -@@ -181,7 +182,7 @@ static int unmap_memblk(struct snd_emu10k1 *emu, struct snd_emu10k1_memblk *blk) - q = get_emu10k1_memblk(p, mapped_link); - end_page = q->mapped_page; - } else -- end_page = MAX_ALIGN_PAGES; -+ end_page = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0); - - /* remove links */ - list_del(&blk->mapped_link); -@@ -307,7 +308,7 @@ snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *subst - if (snd_BUG_ON(!emu)) - return NULL; - if (snd_BUG_ON(runtime->dma_bytes <= 0 || -- runtime->dma_bytes >= MAXPAGES * EMUPAGESIZE)) -+ runtime->dma_bytes >= (emu->address_mode ? MAXPAGES1 : MAXPAGES0) * EMUPAGESIZE)) - return NULL; - hdr = emu->memhdr; - if (snd_BUG_ON(!hdr)) -diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c -index 2fe86d2e1b09..a63a86332deb 100644 ---- a/sound/pci/hda/hda_codec.c -+++ b/sound/pci/hda/hda_codec.c -@@ -3027,6 +3027,16 @@ static struct snd_kcontrol_new vmaster_mute_mode = { - .put = vmaster_mute_mode_put, - }; - -+/* meta hook to call each driver's vmaster hook */ -+static void vmaster_hook(void *private_data, int enabled) -+{ -+ struct hda_vmaster_mute_hook *hook = private_data; -+ -+ if (hook->mute_mode != HDA_VMUTE_FOLLOW_MASTER) -+ enabled = hook->mute_mode; -+ hook->hook(hook->codec, enabled); -+} -+ - /** - * snd_hda_add_vmaster_hook - Add a vmaster hook for mute-LED - * @codec: the HDA codec -@@ -3045,9 +3055,9 @@ int snd_hda_add_vmaster_hook(struct hda_codec *codec, - - if (!hook->hook || !hook->sw_kctl) - return 0; -- snd_ctl_add_vmaster_hook(hook->sw_kctl, hook->hook, codec); - hook->codec = codec; - hook->mute_mode = HDA_VMUTE_FOLLOW_MASTER; -+ snd_ctl_add_vmaster_hook(hook->sw_kctl, vmaster_hook, hook); - if (!expose_enum_ctl) - return 0; - kctl = snd_ctl_new1(&vmaster_mute_mode, hook); -@@ -3073,14 +3083,7 @@ void snd_hda_sync_vmaster_hook(struct hda_vmaster_mute_hook *hook) - */ - if (hook->codec->bus->shutdown) - return; -- switch (hook->mute_mode) { -- case HDA_VMUTE_FOLLOW_MASTER: -- snd_ctl_sync_vmaster_hook(hook->sw_kctl); -- break; -- default: -- hook->hook(hook->codec, hook->mute_mode); -- break; -- } -+ snd_ctl_sync_vmaster_hook(hook->sw_kctl); - } - EXPORT_SYMBOL_GPL(snd_hda_sync_vmaster_hook); - -diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c -index 6ba0b5517c40..2341fc334163 100644 ---- a/sound/pci/hda/thinkpad_helper.c -+++ b/sound/pci/hda/thinkpad_helper.c -@@ -72,6 +72,7 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, - if (led_set_func(TPACPI_LED_MUTE, false) >= 0) { - old_vmaster_hook = spec->vmaster_mute.hook; - spec->vmaster_mute.hook = update_tpacpi_mute_led; -+ spec->vmaster_mute_enum = 1; - removefunc = false; - } - if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) { -diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c -index fb9c20eace3f..97b33e96439a 100644 ---- a/sound/soc/codecs/rt5677.c -+++ b/sound/soc/codecs/rt5677.c -@@ -62,6 +62,9 @@ static const struct reg_default init_list[] = { - {RT5677_PR_BASE + 0x1e, 0x0000}, - {RT5677_PR_BASE + 0x12, 0x0eaa}, - {RT5677_PR_BASE + 0x14, 0x018a}, -+ {RT5677_PR_BASE + 0x15, 0x0490}, -+ {RT5677_PR_BASE + 0x38, 0x0f71}, -+ {RT5677_PR_BASE + 0x39, 0x0f71}, - }; - #define RT5677_INIT_REG_LEN ARRAY_SIZE(init_list) - -@@ -901,7 +904,7 @@ static int set_dmic_clk(struct snd_soc_dapm_widget *w, - { - struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm); - struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec); -- int idx = rl6231_calc_dmic_clk(rt5677->sysclk); -+ int idx = rl6231_calc_dmic_clk(rt5677->lrck[RT5677_AIF1] << 8); - - if (idx < 0) - dev_err(codec->dev, "Failed to set DMIC clock\n"); -diff --git a/sound/soc/codecs/tfa9879.c b/sound/soc/codecs/tfa9879.c -index 16f1b71edb55..aab0af681e8c 100644 ---- a/sound/soc/codecs/tfa9879.c -+++ b/sound/soc/codecs/tfa9879.c -@@ -280,8 +280,8 @@ static int tfa9879_i2c_probe(struct i2c_client *i2c, - int i; - - tfa9879 = devm_kzalloc(&i2c->dev, sizeof(*tfa9879), GFP_KERNEL); -- if (IS_ERR(tfa9879)) -- return PTR_ERR(tfa9879); -+ if (!tfa9879) -+ return -ENOMEM; - - i2c_set_clientdata(i2c, tfa9879); - -diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c -index 326d3c3804e3..5bf723689692 100644 ---- a/sound/soc/samsung/s3c24xx-i2s.c -+++ b/sound/soc/samsung/s3c24xx-i2s.c -@@ -461,8 +461,8 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev) - return -ENOENT; - } - s3c24xx_i2s.regs = devm_ioremap_resource(&pdev->dev, res); -- if (s3c24xx_i2s.regs == NULL) -- return -ENXIO; -+ if (IS_ERR(s3c24xx_i2s.regs)) -+ return PTR_ERR(s3c24xx_i2s.regs); - - s3c24xx_i2s_pcm_stereo_out.dma_addr = res->start + S3C2410_IISFIFO; - s3c24xx_i2s_pcm_stereo_in.dma_addr = res->start + S3C2410_IISFIFO; -diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c -index ab37add269ae..82e350e9501c 100644 ---- a/sound/synth/emux/emux_oss.c -+++ b/sound/synth/emux/emux_oss.c -@@ -118,12 +118,8 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) - if (snd_BUG_ON(!arg || !emu)) - return -ENXIO; - -- mutex_lock(&emu->register_mutex); -- -- if (!snd_emux_inc_count(emu)) { -- mutex_unlock(&emu->register_mutex); -+ if (!snd_emux_inc_count(emu)) - return -EFAULT; -- } - - memset(&callback, 0, sizeof(callback)); - callback.owner = THIS_MODULE; -@@ -135,7 +131,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) - if (p == NULL) { - snd_printk(KERN_ERR "can't create port\n"); - snd_emux_dec_count(emu); -- mutex_unlock(&emu->register_mutex); - return -ENOMEM; - } - -@@ -148,8 +143,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) - reset_port_mode(p, arg->seq_mode); - - snd_emux_reset_port(p); -- -- mutex_unlock(&emu->register_mutex); - return 0; - } - -@@ -195,13 +188,11 @@ snd_emux_close_seq_oss(struct snd_seq_oss_arg *arg) - if (snd_BUG_ON(!emu)) - return -ENXIO; - -- mutex_lock(&emu->register_mutex); - snd_emux_sounds_off_all(p); - snd_soundfont_close_check(emu->sflist, SF_CLIENT_NO(p->chset.port)); - snd_seq_event_port_detach(p->chset.client, p->chset.port); - snd_emux_dec_count(emu); - -- mutex_unlock(&emu->register_mutex); - return 0; - } - -diff --git a/sound/synth/emux/emux_seq.c b/sound/synth/emux/emux_seq.c -index 7778b8e19782..a0209204ae48 100644 ---- a/sound/synth/emux/emux_seq.c -+++ b/sound/synth/emux/emux_seq.c -@@ -124,12 +124,10 @@ snd_emux_detach_seq(struct snd_emux *emu) - if (emu->voices) - snd_emux_terminate_all(emu); - -- mutex_lock(&emu->register_mutex); - if (emu->client >= 0) { - snd_seq_delete_kernel_client(emu->client); - emu->client = -1; - } -- mutex_unlock(&emu->register_mutex); - } - - -@@ -269,8 +267,8 @@ snd_emux_event_input(struct snd_seq_event *ev, int direct, void *private_data, - /* - * increment usage count - */ --int --snd_emux_inc_count(struct snd_emux *emu) -+static int -+__snd_emux_inc_count(struct snd_emux *emu) - { - emu->used++; - if (!try_module_get(emu->ops.owner)) -@@ -284,12 +282,21 @@ snd_emux_inc_count(struct snd_emux *emu) - return 1; - } - -+int snd_emux_inc_count(struct snd_emux *emu) -+{ -+ int ret; -+ -+ mutex_lock(&emu->register_mutex); -+ ret = __snd_emux_inc_count(emu); -+ mutex_unlock(&emu->register_mutex); -+ return ret; -+} - - /* - * decrease usage count - */ --void --snd_emux_dec_count(struct snd_emux *emu) -+static void -+__snd_emux_dec_count(struct snd_emux *emu) - { - module_put(emu->card->module); - emu->used--; -@@ -298,6 +305,12 @@ snd_emux_dec_count(struct snd_emux *emu) - module_put(emu->ops.owner); - } - -+void snd_emux_dec_count(struct snd_emux *emu) -+{ -+ mutex_lock(&emu->register_mutex); -+ __snd_emux_dec_count(emu); -+ mutex_unlock(&emu->register_mutex); -+} - - /* - * Routine that is called upon a first use of a particular port -@@ -317,7 +330,7 @@ snd_emux_use(void *private_data, struct snd_seq_port_subscribe *info) - - mutex_lock(&emu->register_mutex); - snd_emux_init_port(p); -- snd_emux_inc_count(emu); -+ __snd_emux_inc_count(emu); - mutex_unlock(&emu->register_mutex); - return 0; - } -@@ -340,7 +353,7 @@ snd_emux_unuse(void *private_data, struct snd_seq_port_subscribe *info) - - mutex_lock(&emu->register_mutex); - snd_emux_sounds_off_all(p); -- snd_emux_dec_count(emu); -+ __snd_emux_dec_count(emu); - mutex_unlock(&emu->register_mutex); - return 0; - } diff --git a/1003_linux-4.0.4.patch b/1003_linux-4.0.4.patch deleted file mode 100644 index e5c793a4..00000000 --- a/1003_linux-4.0.4.patch +++ /dev/null @@ -1,2713 +0,0 @@ -diff --git a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt -index a4873e5e3e36..e30e184f50c7 100644 ---- a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt -+++ b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt -@@ -38,7 +38,7 @@ dma_apbx: dma-apbx@80024000 { - 80 81 68 69 - 70 71 72 73 - 74 75 76 77>; -- interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", -+ interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", - "saif0", "saif1", "i2c0", "i2c1", - "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", - "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; -diff --git a/Makefile b/Makefile -index dc9f43a019d6..3d16bcc87585 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 0 --SUBLEVEL = 3 -+SUBLEVEL = 4 - EXTRAVERSION = - NAME = Hurr durr I'ma sheep - -diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts -index 0c76d9f05fd0..f4838ebd918b 100644 ---- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts -+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts -@@ -105,6 +105,10 @@ - }; - - internal-regs { -+ rtc@10300 { -+ /* No crystal connected to the internal RTC */ -+ status = "disabled"; -+ }; - serial@12000 { - status = "okay"; - }; -diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts -index 7e6eef2488e8..82045398bf1f 100644 ---- a/arch/arm/boot/dts/imx23-olinuxino.dts -+++ b/arch/arm/boot/dts/imx23-olinuxino.dts -@@ -12,6 +12,7 @@ - */ - - /dts-v1/; -+#include - #include "imx23.dtsi" - - / { -@@ -93,6 +94,7 @@ - - ahb@80080000 { - usb0: usb@80080000 { -+ dr_mode = "host"; - vbus-supply = <®_usb0_vbus>; - status = "okay"; - }; -@@ -122,7 +124,7 @@ - - user { - label = "green"; -- gpios = <&gpio2 1 1>; -+ gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; - }; - }; - }; -diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi -index e4d3aecc4ed2..677f81d9dcd5 100644 ---- a/arch/arm/boot/dts/imx25.dtsi -+++ b/arch/arm/boot/dts/imx25.dtsi -@@ -428,6 +428,7 @@ - - pwm4: pwm@53fc8000 { - compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; -+ #pwm-cells = <2>; - reg = <0x53fc8000 0x4000>; - clocks = <&clks 108>, <&clks 52>; - clock-names = "ipg", "per"; -diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi -index 47f68ac868d4..5ed245a3f9ac 100644 ---- a/arch/arm/boot/dts/imx28.dtsi -+++ b/arch/arm/boot/dts/imx28.dtsi -@@ -900,7 +900,7 @@ - 80 81 68 69 - 70 71 72 73 - 74 75 76 77>; -- interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", -+ interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", - "saif0", "saif1", "i2c0", "i2c1", - "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", - "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; -diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -index 19cc269a08d4..1ce6133b67f5 100644 ---- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi -@@ -31,6 +31,7 @@ - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio4 15 0>; -+ enable-active-high; - }; - - reg_usb_h1_vbus: regulator@1 { -@@ -40,6 +41,7 @@ - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio1 0 0>; -+ enable-active-high; - }; - }; - -diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts -index db80f9d376fa..9c8bdf2c93a1 100644 ---- a/arch/arm/boot/dts/omap3-n900.dts -+++ b/arch/arm/boot/dts/omap3-n900.dts -@@ -484,6 +484,8 @@ - DRVDD-supply = <&vmmc2>; - IOVDD-supply = <&vio>; - DVDD-supply = <&vio>; -+ -+ ai3x-micbias-vg = <1>; - }; - - tlv320aic3x_aux: tlv320aic3x@19 { -@@ -495,6 +497,8 @@ - DRVDD-supply = <&vmmc2>; - IOVDD-supply = <&vio>; - DVDD-supply = <&vio>; -+ -+ ai3x-micbias-vg = <2>; - }; - - tsl2563: tsl2563@29 { -diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi -index bfd3f1c734b8..2201cd5da3bb 100644 ---- a/arch/arm/boot/dts/ste-dbx5x0.dtsi -+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi -@@ -1017,23 +1017,6 @@ - status = "disabled"; - }; - -- vmmci: regulator-gpio { -- compatible = "regulator-gpio"; -- -- regulator-min-microvolt = <1800000>; -- regulator-max-microvolt = <2900000>; -- regulator-name = "mmci-reg"; -- regulator-type = "voltage"; -- -- startup-delay-us = <100>; -- enable-active-high; -- -- states = <1800000 0x1 -- 2900000 0x0>; -- -- status = "disabled"; -- }; -- - mcde@a0350000 { - compatible = "stericsson,mcde"; - reg = <0xa0350000 0x1000>, /* MCDE */ -diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi -index bf8f0eddc2c0..744c1e3a744d 100644 ---- a/arch/arm/boot/dts/ste-href.dtsi -+++ b/arch/arm/boot/dts/ste-href.dtsi -@@ -111,6 +111,21 @@ - pinctrl-1 = <&i2c3_sleep_mode>; - }; - -+ vmmci: regulator-gpio { -+ compatible = "regulator-gpio"; -+ -+ regulator-min-microvolt = <1800000>; -+ regulator-max-microvolt = <2900000>; -+ regulator-name = "mmci-reg"; -+ regulator-type = "voltage"; -+ -+ startup-delay-us = <100>; -+ enable-active-high; -+ -+ states = <1800000 0x1 -+ 2900000 0x0>; -+ }; -+ - // External Micro SD slot - sdi0_per1@80126000 { - arm,primecell-periphid = <0x10480180>; -diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts -index 206826a855c0..1bc84ebdccaa 100644 ---- a/arch/arm/boot/dts/ste-snowball.dts -+++ b/arch/arm/boot/dts/ste-snowball.dts -@@ -146,8 +146,21 @@ - }; - - vmmci: regulator-gpio { -+ compatible = "regulator-gpio"; -+ - gpios = <&gpio7 4 0x4>; - enable-gpio = <&gpio6 25 0x4>; -+ -+ regulator-min-microvolt = <1800000>; -+ regulator-max-microvolt = <2900000>; -+ regulator-name = "mmci-reg"; -+ regulator-type = "voltage"; -+ -+ startup-delay-us = <100>; -+ enable-active-high; -+ -+ states = <1800000 0x1 -+ 2900000 0x0>; - }; - - // External Micro SD slot -diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile -index 902397dd1000..1c1cdfa566ac 100644 ---- a/arch/arm/kernel/Makefile -+++ b/arch/arm/kernel/Makefile -@@ -86,7 +86,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o - - obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o - ifeq ($(CONFIG_ARM_PSCI),y) --obj-y += psci.o -+obj-y += psci.o psci-call.o - obj-$(CONFIG_SMP) += psci_smp.o - endif - -diff --git a/arch/arm/kernel/psci-call.S b/arch/arm/kernel/psci-call.S -new file mode 100644 -index 000000000000..a78e9e1e206d ---- /dev/null -+++ b/arch/arm/kernel/psci-call.S -@@ -0,0 +1,31 @@ -+/* -+ * This program is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License version 2 as -+ * published by the Free Software Foundation. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * Copyright (C) 2015 ARM Limited -+ * -+ * Author: Mark Rutland -+ */ -+ -+#include -+ -+#include -+#include -+ -+/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */ -+ENTRY(__invoke_psci_fn_hvc) -+ __HVC(0) -+ bx lr -+ENDPROC(__invoke_psci_fn_hvc) -+ -+/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */ -+ENTRY(__invoke_psci_fn_smc) -+ __SMC(0) -+ bx lr -+ENDPROC(__invoke_psci_fn_smc) -diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c -index f73891b6b730..f90fdf4ce7c7 100644 ---- a/arch/arm/kernel/psci.c -+++ b/arch/arm/kernel/psci.c -@@ -23,8 +23,6 @@ - - #include - #include --#include --#include - #include - #include - -@@ -33,6 +31,9 @@ struct psci_operations psci_ops; - static int (*invoke_psci_fn)(u32, u32, u32, u32); - typedef int (*psci_initcall_t)(const struct device_node *); - -+asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32); -+asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32); -+ - enum psci_function { - PSCI_FN_CPU_SUSPEND, - PSCI_FN_CPU_ON, -@@ -71,40 +72,6 @@ static u32 psci_power_state_pack(struct psci_power_state state) - & PSCI_0_2_POWER_STATE_AFFL_MASK); - } - --/* -- * The following two functions are invoked via the invoke_psci_fn pointer -- * and will not be inlined, allowing us to piggyback on the AAPCS. -- */ --static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, -- u32 arg2) --{ -- asm volatile( -- __asmeq("%0", "r0") -- __asmeq("%1", "r1") -- __asmeq("%2", "r2") -- __asmeq("%3", "r3") -- __HVC(0) -- : "+r" (function_id) -- : "r" (arg0), "r" (arg1), "r" (arg2)); -- -- return function_id; --} -- --static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, -- u32 arg2) --{ -- asm volatile( -- __asmeq("%0", "r0") -- __asmeq("%1", "r1") -- __asmeq("%2", "r2") -- __asmeq("%3", "r3") -- __SMC(0) -- : "+r" (function_id) -- : "r" (arg0), "r" (arg1), "r" (arg2)); -- -- return function_id; --} -- - static int psci_get_version(void) - { - int err; -diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h -index cbefbd7cfdb5..661d753df584 100644 ---- a/arch/arm/mach-omap2/prm-regbits-34xx.h -+++ b/arch/arm/mach-omap2/prm-regbits-34xx.h -@@ -112,6 +112,7 @@ - #define OMAP3430_VC_CMD_ONLP_SHIFT 16 - #define OMAP3430_VC_CMD_RET_SHIFT 8 - #define OMAP3430_VC_CMD_OFF_SHIFT 0 -+#define OMAP3430_SREN_MASK (1 << 4) - #define OMAP3430_HSEN_MASK (1 << 3) - #define OMAP3430_MCODE_MASK (0x7 << 0) - #define OMAP3430_VALID_MASK (1 << 24) -diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h -index b1c7a33e00e7..e794828dee55 100644 ---- a/arch/arm/mach-omap2/prm-regbits-44xx.h -+++ b/arch/arm/mach-omap2/prm-regbits-44xx.h -@@ -35,6 +35,7 @@ - #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT 1 - #define OMAP4430_GLOBAL_WUEN_MASK (1 << 16) - #define OMAP4430_HSMCODE_MASK (0x7 << 0) -+#define OMAP4430_SRMODEEN_MASK (1 << 4) - #define OMAP4430_HSMODEEN_MASK (1 << 3) - #define OMAP4430_HSSCLL_SHIFT 24 - #define OMAP4430_ICEPICK_RST_SHIFT 9 -diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c -index be9ef834fa81..076fd20d7e5a 100644 ---- a/arch/arm/mach-omap2/vc.c -+++ b/arch/arm/mach-omap2/vc.c -@@ -316,7 +316,8 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm) - * idle. And we can also scale voltages to zero for off-idle. - * Note that no actual voltage scaling during off-idle will - * happen unless the board specific twl4030 PMIC scripts are -- * loaded. -+ * loaded. See also omap_vc_i2c_init for comments regarding -+ * erratum i531. - */ - val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET); - if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) { -@@ -704,9 +705,16 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm) - return; - } - -+ /* -+ * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around -+ * erratum i531 "Extra Power Consumed When Repeated Start Operation -+ * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)". -+ * Otherwise I2C4 eventually leads into about 23mW extra power being -+ * consumed even during off idle using VMODE. -+ */ - i2c_high_speed = voltdm->pmic->i2c_high_speed; - if (i2c_high_speed) -- voltdm->rmw(vc->common->i2c_cfg_hsen_mask, -+ voltdm->rmw(vc->common->i2c_cfg_clear_mask, - vc->common->i2c_cfg_hsen_mask, - vc->common->i2c_cfg_reg); - -diff --git a/arch/arm/mach-omap2/vc.h b/arch/arm/mach-omap2/vc.h -index cdbdd78e755e..89b83b7ff3ec 100644 ---- a/arch/arm/mach-omap2/vc.h -+++ b/arch/arm/mach-omap2/vc.h -@@ -34,6 +34,7 @@ struct voltagedomain; - * @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register - * @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register - * @i2c_cfg_reg: I2C configuration register offset -+ * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register - * @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register - * @i2c_mcode_mask: MCODE field mask for I2C config register - * -@@ -52,6 +53,7 @@ struct omap_vc_common { - u8 cmd_ret_shift; - u8 cmd_off_shift; - u8 i2c_cfg_reg; -+ u8 i2c_cfg_clear_mask; - u8 i2c_cfg_hsen_mask; - u8 i2c_mcode_mask; - }; -diff --git a/arch/arm/mach-omap2/vc3xxx_data.c b/arch/arm/mach-omap2/vc3xxx_data.c -index 75bc4aa22b3a..71d74c9172c1 100644 ---- a/arch/arm/mach-omap2/vc3xxx_data.c -+++ b/arch/arm/mach-omap2/vc3xxx_data.c -@@ -40,6 +40,7 @@ static struct omap_vc_common omap3_vc_common = { - .cmd_onlp_shift = OMAP3430_VC_CMD_ONLP_SHIFT, - .cmd_ret_shift = OMAP3430_VC_CMD_RET_SHIFT, - .cmd_off_shift = OMAP3430_VC_CMD_OFF_SHIFT, -+ .i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK, - .i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK, - .i2c_cfg_reg = OMAP3_PRM_VC_I2C_CFG_OFFSET, - .i2c_mcode_mask = OMAP3430_MCODE_MASK, -diff --git a/arch/arm/mach-omap2/vc44xx_data.c b/arch/arm/mach-omap2/vc44xx_data.c -index 085e5d6a04fd..2abd5fa8a697 100644 ---- a/arch/arm/mach-omap2/vc44xx_data.c -+++ b/arch/arm/mach-omap2/vc44xx_data.c -@@ -42,6 +42,7 @@ static const struct omap_vc_common omap4_vc_common = { - .cmd_ret_shift = OMAP4430_RET_SHIFT, - .cmd_off_shift = OMAP4430_OFF_SHIFT, - .i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET, -+ .i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK, - .i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK, - .i2c_mcode_mask = OMAP4430_HSMCODE_MASK, - }; -diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c -index e1268f905026..f412b53ed268 100644 ---- a/arch/arm/net/bpf_jit_32.c -+++ b/arch/arm/net/bpf_jit_32.c -@@ -449,10 +449,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) - return; - } - #endif -- if (rm != ARM_R0) -- emit(ARM_MOV_R(ARM_R0, rm), ctx); -+ -+ /* -+ * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 -+ * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into -+ * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm -+ * before using it as a source for ARM_R1. -+ * -+ * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is -+ * ARM_R5 (r_X) so there is no particular register overlap -+ * issues. -+ */ - if (rn != ARM_R1) - emit(ARM_MOV_R(ARM_R1, rn), ctx); -+ if (rm != ARM_R0) -+ emit(ARM_MOV_R(ARM_R0, rm), ctx); - - ctx->seen |= SEEN_CALL; - emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); -diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h -index cf87de3fc390..64b611782ef0 100644 ---- a/arch/x86/include/asm/spinlock.h -+++ b/arch/x86/include/asm/spinlock.h -@@ -169,7 +169,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock) - struct __raw_tickets tmp = READ_ONCE(lock->tickets); - - tmp.head &= ~TICKET_SLOWPATH_FLAG; -- return (tmp.tail - tmp.head) > TICKET_LOCK_INC; -+ return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; - } - #define arch_spin_is_contended arch_spin_is_contended - -diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c -index e4695985f9de..d93963340c3c 100644 ---- a/arch/x86/pci/acpi.c -+++ b/arch/x86/pci/acpi.c -@@ -325,6 +325,26 @@ static void release_pci_root_info(struct pci_host_bridge *bridge) - kfree(info); - } - -+/* -+ * An IO port or MMIO resource assigned to a PCI host bridge may be -+ * consumed by the host bridge itself or available to its child -+ * bus/devices. The ACPI specification defines a bit (Producer/Consumer) -+ * to tell whether the resource is consumed by the host bridge itself, -+ * but firmware hasn't used that bit consistently, so we can't rely on it. -+ * -+ * On x86 and IA64 platforms, all IO port and MMIO resources are assumed -+ * to be available to child bus/devices except one special case: -+ * IO port [0xCF8-0xCFF] is consumed by the host bridge itself -+ * to access PCI configuration space. -+ * -+ * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF]. -+ */ -+static bool resource_is_pcicfg_ioport(struct resource *res) -+{ -+ return (res->flags & IORESOURCE_IO) && -+ res->start == 0xCF8 && res->end == 0xCFF; -+} -+ - static void probe_pci_root_info(struct pci_root_info *info, - struct acpi_device *device, - int busnum, int domain, -@@ -346,8 +366,8 @@ static void probe_pci_root_info(struct pci_root_info *info, - "no IO and memory resources present in _CRS\n"); - else - resource_list_for_each_entry_safe(entry, tmp, list) { -- if ((entry->res->flags & IORESOURCE_WINDOW) == 0 || -- (entry->res->flags & IORESOURCE_DISABLED)) -+ if ((entry->res->flags & IORESOURCE_DISABLED) || -+ resource_is_pcicfg_ioport(entry->res)) - resource_list_destroy_entry(entry); - else - entry->res->name = info->name; -diff --git a/block/blk-core.c b/block/blk-core.c -index 794c3e7f01cf..66406474f0c4 100644 ---- a/block/blk-core.c -+++ b/block/blk-core.c -@@ -552,6 +552,8 @@ void blk_cleanup_queue(struct request_queue *q) - q->queue_lock = &q->__queue_lock; - spin_unlock_irq(lock); - -+ bdi_destroy(&q->backing_dev_info); -+ - /* @q is and will stay empty, shutdown and put */ - blk_put_queue(q); - } -diff --git a/block/blk-mq.c b/block/blk-mq.c -index 33c428530193..5c39703e644f 100644 ---- a/block/blk-mq.c -+++ b/block/blk-mq.c -@@ -675,8 +675,11 @@ static void blk_mq_rq_timer(unsigned long priv) - data.next = blk_rq_timeout(round_jiffies_up(data.next)); - mod_timer(&q->timeout, data.next); - } else { -- queue_for_each_hw_ctx(q, hctx, i) -- blk_mq_tag_idle(hctx); -+ queue_for_each_hw_ctx(q, hctx, i) { -+ /* the hctx may be unmapped, so check it here */ -+ if (blk_mq_hw_queue_mapped(hctx)) -+ blk_mq_tag_idle(hctx); -+ } - } - } - -@@ -1570,22 +1573,6 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) - return NOTIFY_OK; - } - --static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu) --{ -- struct request_queue *q = hctx->queue; -- struct blk_mq_tag_set *set = q->tag_set; -- -- if (set->tags[hctx->queue_num]) -- return NOTIFY_OK; -- -- set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num); -- if (!set->tags[hctx->queue_num]) -- return NOTIFY_STOP; -- -- hctx->tags = set->tags[hctx->queue_num]; -- return NOTIFY_OK; --} -- - static int blk_mq_hctx_notify(void *data, unsigned long action, - unsigned int cpu) - { -@@ -1593,8 +1580,11 @@ static int blk_mq_hctx_notify(void *data, unsigned long action, - - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) - return blk_mq_hctx_cpu_offline(hctx, cpu); -- else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) -- return blk_mq_hctx_cpu_online(hctx, cpu); -+ -+ /* -+ * In case of CPU online, tags may be reallocated -+ * in blk_mq_map_swqueue() after mapping is updated. -+ */ - - return NOTIFY_OK; - } -@@ -1776,6 +1766,7 @@ static void blk_mq_map_swqueue(struct request_queue *q) - unsigned int i; - struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx; -+ struct blk_mq_tag_set *set = q->tag_set; - - queue_for_each_hw_ctx(q, hctx, i) { - cpumask_clear(hctx->cpumask); -@@ -1802,16 +1793,20 @@ static void blk_mq_map_swqueue(struct request_queue *q) - * disable it and free the request entries. - */ - if (!hctx->nr_ctx) { -- struct blk_mq_tag_set *set = q->tag_set; -- - if (set->tags[i]) { - blk_mq_free_rq_map(set, set->tags[i], i); - set->tags[i] = NULL; -- hctx->tags = NULL; - } -+ hctx->tags = NULL; - continue; - } - -+ /* unmapped hw queue can be remapped after CPU topo changed */ -+ if (!set->tags[i]) -+ set->tags[i] = blk_mq_init_rq_map(set, i); -+ hctx->tags = set->tags[i]; -+ WARN_ON(!hctx->tags); -+ - /* - * Initialize batch roundrobin counts - */ -@@ -2075,9 +2070,16 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb, - */ - list_for_each_entry(q, &all_q_list, all_q_node) - blk_mq_freeze_queue_start(q); -- list_for_each_entry(q, &all_q_list, all_q_node) -+ list_for_each_entry(q, &all_q_list, all_q_node) { - blk_mq_freeze_queue_wait(q); - -+ /* -+ * timeout handler can't touch hw queue during the -+ * reinitialization -+ */ -+ del_timer_sync(&q->timeout); -+ } -+ - list_for_each_entry(q, &all_q_list, all_q_node) - blk_mq_queue_reinit(q); - -diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c -index faaf36ade7eb..2b8fd302f677 100644 ---- a/block/blk-sysfs.c -+++ b/block/blk-sysfs.c -@@ -522,8 +522,6 @@ static void blk_release_queue(struct kobject *kobj) - - blk_trace_shutdown(q); - -- bdi_destroy(&q->backing_dev_info); -- - ida_simple_remove(&blk_queue_ida, q->id); - call_rcu(&q->rcu_head, blk_free_queue_rcu); - } -diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c -index b193f8425999..ff6d8adc9cda 100644 ---- a/drivers/acpi/acpi_pnp.c -+++ b/drivers/acpi/acpi_pnp.c -@@ -304,6 +304,8 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = { - {"PNPb006"}, - /* cs423x-pnpbios */ - {"CSC0100"}, -+ {"CSC0103"}, -+ {"CSC0110"}, - {"CSC0000"}, - {"GIM0100"}, /* Guillemot Turtlebeach something appears to be cs4232 compatible */ - /* es18xx-pnpbios */ -diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h -index cf607fe69dbd..c240bdf824f2 100644 ---- a/drivers/acpi/acpica/acmacros.h -+++ b/drivers/acpi/acpica/acmacros.h -@@ -63,23 +63,12 @@ - #define ACPI_SET64(ptr, val) (*ACPI_CAST64 (ptr) = (u64) (val)) - - /* -- * printf() format helpers. These macros are workarounds for the difficulties -+ * printf() format helper. This macros is a workaround for the difficulties - * with emitting 64-bit integers and 64-bit pointers with the same code - * for both 32-bit and 64-bit hosts. - */ - #define ACPI_FORMAT_UINT64(i) ACPI_HIDWORD(i), ACPI_LODWORD(i) - --#if ACPI_MACHINE_WIDTH == 64 --#define ACPI_FORMAT_NATIVE_UINT(i) ACPI_FORMAT_UINT64(i) --#define ACPI_FORMAT_TO_UINT(i) ACPI_FORMAT_UINT64(i) --#define ACPI_PRINTF_UINT "0x%8.8X%8.8X" -- --#else --#define ACPI_FORMAT_NATIVE_UINT(i) 0, (u32) (i) --#define ACPI_FORMAT_TO_UINT(i) (u32) (i) --#define ACPI_PRINTF_UINT "0x%8.8X" --#endif -- - /* - * Macros for moving data around to/from buffers that are possibly unaligned. - * If the hardware supports the transfer of unaligned data, just do the store. -diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c -index 77244182ff02..ea0cc4e08f80 100644 ---- a/drivers/acpi/acpica/dsopcode.c -+++ b/drivers/acpi/acpica/dsopcode.c -@@ -446,7 +446,7 @@ acpi_ds_eval_region_operands(struct acpi_walk_state *walk_state, - - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n", - obj_desc, -- ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address), -+ ACPI_FORMAT_UINT64(obj_desc->region.address), - obj_desc->region.length)); - - /* Now the address and length are valid for this opregion */ -@@ -539,13 +539,12 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state, - return_ACPI_STATUS(AE_NOT_EXIST); - } - -- obj_desc->region.address = -- (acpi_physical_address) ACPI_TO_INTEGER(table); -+ obj_desc->region.address = ACPI_PTR_TO_PHYSADDR(table); - obj_desc->region.length = table->length; - - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n", - obj_desc, -- ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address), -+ ACPI_FORMAT_UINT64(obj_desc->region.address), - obj_desc->region.length)); - - /* Now the address and length are valid for this opregion */ -diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c -index 9abace3401f9..2ba28a63fb68 100644 ---- a/drivers/acpi/acpica/evregion.c -+++ b/drivers/acpi/acpica/evregion.c -@@ -272,7 +272,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, - ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, - "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", - ®ion_obj->region.handler->address_space, handler, -- ACPI_FORMAT_NATIVE_UINT(address), -+ ACPI_FORMAT_UINT64(address), - acpi_ut_get_region_name(region_obj->region. - space_id))); - -diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c -index 7c213b6b6472..1da52bef632e 100644 ---- a/drivers/acpi/acpica/exdump.c -+++ b/drivers/acpi/acpica/exdump.c -@@ -767,8 +767,8 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth) - acpi_os_printf("\n"); - } else { - acpi_os_printf(" base %8.8X%8.8X Length %X\n", -- ACPI_FORMAT_NATIVE_UINT(obj_desc->region. -- address), -+ ACPI_FORMAT_UINT64(obj_desc->region. -+ address), - obj_desc->region.length); - } - break; -diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c -index 49479927e7f7..725a3746a2df 100644 ---- a/drivers/acpi/acpica/exfldio.c -+++ b/drivers/acpi/acpica/exfldio.c -@@ -263,17 +263,15 @@ acpi_ex_access_region(union acpi_operand_object *obj_desc, - } - - ACPI_DEBUG_PRINT_RAW((ACPI_DB_BFIELD, -- " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %p\n", -+ " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %8.8X%8.8X\n", - acpi_ut_get_region_name(rgn_desc->region. - space_id), - rgn_desc->region.space_id, - obj_desc->common_field.access_byte_width, - obj_desc->common_field.base_byte_offset, -- field_datum_byte_offset, ACPI_CAST_PTR(void, -- (rgn_desc-> -- region. -- address + -- region_offset)))); -+ field_datum_byte_offset, -+ ACPI_FORMAT_UINT64(rgn_desc->region.address + -+ region_offset))); - - /* Invoke the appropriate address_space/op_region handler */ - -diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c -index 0fe188e238ef..b4bbf3150bc1 100644 ---- a/drivers/acpi/acpica/exregion.c -+++ b/drivers/acpi/acpica/exregion.c -@@ -181,7 +181,7 @@ acpi_ex_system_memory_space_handler(u32 function, - if (!mem_info->mapped_logical_address) { - ACPI_ERROR((AE_INFO, - "Could not map memory at 0x%8.8X%8.8X, size %u", -- ACPI_FORMAT_NATIVE_UINT(address), -+ ACPI_FORMAT_UINT64(address), - (u32) map_length)); - mem_info->mapped_length = 0; - return_ACPI_STATUS(AE_NO_MEMORY); -@@ -202,8 +202,7 @@ acpi_ex_system_memory_space_handler(u32 function, - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "System-Memory (width %u) R/W %u Address=%8.8X%8.8X\n", -- bit_width, function, -- ACPI_FORMAT_NATIVE_UINT(address))); -+ bit_width, function, ACPI_FORMAT_UINT64(address))); - - /* - * Perform the memory read or write -@@ -318,8 +317,7 @@ acpi_ex_system_io_space_handler(u32 function, - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "System-IO (width %u) R/W %u Address=%8.8X%8.8X\n", -- bit_width, function, -- ACPI_FORMAT_NATIVE_UINT(address))); -+ bit_width, function, ACPI_FORMAT_UINT64(address))); - - /* Decode the function parameter */ - -diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c -index 2bd33fe56cb3..29033d71417b 100644 ---- a/drivers/acpi/acpica/hwvalid.c -+++ b/drivers/acpi/acpica/hwvalid.c -@@ -142,17 +142,17 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) - byte_width = ACPI_DIV_8(bit_width); - last_address = address + byte_width - 1; - -- ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %p LastAddress %p Length %X", -- ACPI_CAST_PTR(void, address), ACPI_CAST_PTR(void, -- last_address), -- byte_width)); -+ ACPI_DEBUG_PRINT((ACPI_DB_IO, -+ "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X", -+ ACPI_FORMAT_UINT64(address), -+ ACPI_FORMAT_UINT64(last_address), byte_width)); - - /* Maximum 16-bit address in I/O space */ - - if (last_address > ACPI_UINT16_MAX) { - ACPI_ERROR((AE_INFO, -- "Illegal I/O port address/length above 64K: %p/0x%X", -- ACPI_CAST_PTR(void, address), byte_width)); -+ "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X", -+ ACPI_FORMAT_UINT64(address), byte_width)); - return_ACPI_STATUS(AE_LIMIT); - } - -@@ -181,8 +181,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) - - if (acpi_gbl_osi_data >= port_info->osi_dependency) { - ACPI_DEBUG_PRINT((ACPI_DB_IO, -- "Denied AML access to port 0x%p/%X (%s 0x%.4X-0x%.4X)", -- ACPI_CAST_PTR(void, address), -+ "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)", -+ ACPI_FORMAT_UINT64(address), - byte_width, port_info->name, - port_info->start, - port_info->end)); -diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c -index 80f097eb7381..d259393505fa 100644 ---- a/drivers/acpi/acpica/nsdump.c -+++ b/drivers/acpi/acpica/nsdump.c -@@ -271,12 +271,11 @@ acpi_ns_dump_one_object(acpi_handle obj_handle, - switch (type) { - case ACPI_TYPE_PROCESSOR: - -- acpi_os_printf("ID %02X Len %02X Addr %p\n", -+ acpi_os_printf("ID %02X Len %02X Addr %8.8X%8.8X\n", - obj_desc->processor.proc_id, - obj_desc->processor.length, -- ACPI_CAST_PTR(void, -- obj_desc->processor. -- address)); -+ ACPI_FORMAT_UINT64(obj_desc->processor. -+ address)); - break; - - case ACPI_TYPE_DEVICE: -@@ -347,8 +346,9 @@ acpi_ns_dump_one_object(acpi_handle obj_handle, - space_id)); - if (obj_desc->region.flags & AOPOBJ_DATA_VALID) { - acpi_os_printf(" Addr %8.8X%8.8X Len %.4X\n", -- ACPI_FORMAT_NATIVE_UINT -- (obj_desc->region.address), -+ ACPI_FORMAT_UINT64(obj_desc-> -+ region. -+ address), - obj_desc->region.length); - } else { - acpi_os_printf -diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c -index 6a144957aadd..fd5998b2b46b 100644 ---- a/drivers/acpi/acpica/tbdata.c -+++ b/drivers/acpi/acpica/tbdata.c -@@ -113,9 +113,9 @@ acpi_tb_acquire_table(struct acpi_table_desc *table_desc, - case ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL: - case ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL: - -- table = -- ACPI_CAST_PTR(struct acpi_table_header, -- table_desc->address); -+ table = ACPI_CAST_PTR(struct acpi_table_header, -+ ACPI_PHYSADDR_TO_PTR(table_desc-> -+ address)); - break; - - default: -@@ -214,7 +214,8 @@ acpi_tb_acquire_temp_table(struct acpi_table_desc *table_desc, - case ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL: - case ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL: - -- table_header = ACPI_CAST_PTR(struct acpi_table_header, address); -+ table_header = ACPI_CAST_PTR(struct acpi_table_header, -+ ACPI_PHYSADDR_TO_PTR(address)); - if (!table_header) { - return (AE_NO_MEMORY); - } -@@ -398,14 +399,14 @@ acpi_tb_verify_temp_table(struct acpi_table_desc * table_desc, char *signature) - table_desc->length); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, AE_NO_MEMORY, -- "%4.4s " ACPI_PRINTF_UINT -+ "%4.4s 0x%8.8X%8.8X" - " Attempted table install failed", - acpi_ut_valid_acpi_name(table_desc-> - signature. - ascii) ? - table_desc->signature.ascii : "????", -- ACPI_FORMAT_TO_UINT(table_desc-> -- address))); -+ ACPI_FORMAT_UINT64(table_desc-> -+ address))); - goto invalidate_and_exit; - } - } -diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c -index 7fbc2b9dcbbb..7e69bc73bd16 100644 ---- a/drivers/acpi/acpica/tbinstal.c -+++ b/drivers/acpi/acpica/tbinstal.c -@@ -187,8 +187,9 @@ acpi_tb_install_fixed_table(acpi_physical_address address, - status = acpi_tb_acquire_temp_table(&new_table_desc, address, - ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL); - if (ACPI_FAILURE(status)) { -- ACPI_ERROR((AE_INFO, "Could not acquire table length at %p", -- ACPI_CAST_PTR(void, address))); -+ ACPI_ERROR((AE_INFO, -+ "Could not acquire table length at %8.8X%8.8X", -+ ACPI_FORMAT_UINT64(address))); - return_ACPI_STATUS(status); - } - -@@ -246,8 +247,9 @@ acpi_tb_install_standard_table(acpi_physical_address address, - - status = acpi_tb_acquire_temp_table(&new_table_desc, address, flags); - if (ACPI_FAILURE(status)) { -- ACPI_ERROR((AE_INFO, "Could not acquire table length at %p", -- ACPI_CAST_PTR(void, address))); -+ ACPI_ERROR((AE_INFO, -+ "Could not acquire table length at %8.8X%8.8X", -+ ACPI_FORMAT_UINT64(address))); - return_ACPI_STATUS(status); - } - -@@ -258,9 +260,10 @@ acpi_tb_install_standard_table(acpi_physical_address address, - if (!reload && - acpi_gbl_disable_ssdt_table_install && - ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) { -- ACPI_INFO((AE_INFO, "Ignoring installation of %4.4s at %p", -- new_table_desc.signature.ascii, ACPI_CAST_PTR(void, -- address))); -+ ACPI_INFO((AE_INFO, -+ "Ignoring installation of %4.4s at %8.8X%8.8X", -+ new_table_desc.signature.ascii, -+ ACPI_FORMAT_UINT64(address))); - goto release_and_exit; - } - -@@ -428,11 +431,11 @@ finish_override: - return; - } - -- ACPI_INFO((AE_INFO, "%4.4s " ACPI_PRINTF_UINT -- " %s table override, new table: " ACPI_PRINTF_UINT, -+ ACPI_INFO((AE_INFO, "%4.4s 0x%8.8X%8.8X" -+ " %s table override, new table: 0x%8.8X%8.8X", - old_table_desc->signature.ascii, -- ACPI_FORMAT_TO_UINT(old_table_desc->address), -- override_type, ACPI_FORMAT_TO_UINT(new_table_desc.address))); -+ ACPI_FORMAT_UINT64(old_table_desc->address), -+ override_type, ACPI_FORMAT_UINT64(new_table_desc.address))); - - /* We can now uninstall the original table */ - -@@ -516,7 +519,7 @@ void acpi_tb_uninstall_table(struct acpi_table_desc *table_desc) - - if ((table_desc->flags & ACPI_TABLE_ORIGIN_MASK) == - ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL) { -- ACPI_FREE(ACPI_CAST_PTR(void, table_desc->address)); -+ ACPI_FREE(ACPI_PHYSADDR_TO_PTR(table_desc->address)); - } - - table_desc->address = ACPI_PTR_TO_PHYSADDR(NULL); -diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c -index ef16c06e5091..77ba5c71c6e7 100644 ---- a/drivers/acpi/acpica/tbprint.c -+++ b/drivers/acpi/acpica/tbprint.c -@@ -127,18 +127,12 @@ acpi_tb_print_table_header(acpi_physical_address address, - { - struct acpi_table_header local_header; - -- /* -- * The reason that we use ACPI_PRINTF_UINT and ACPI_FORMAT_TO_UINT is to -- * support both 32-bit and 64-bit hosts/addresses in a consistent manner. -- * The %p specifier does not emit uniform output on all hosts. On some, -- * leading zeros are not supported. -- */ - if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) { - - /* FACS only has signature and length fields */ - -- ACPI_INFO((AE_INFO, "%-4.4s " ACPI_PRINTF_UINT " %06X", -- header->signature, ACPI_FORMAT_TO_UINT(address), -+ ACPI_INFO((AE_INFO, "%-4.4s 0x%8.8X%8.8X %06X", -+ header->signature, ACPI_FORMAT_UINT64(address), - header->length)); - } else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) { - -@@ -149,9 +143,8 @@ acpi_tb_print_table_header(acpi_physical_address address, - header)->oem_id, ACPI_OEM_ID_SIZE); - acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE); - -- ACPI_INFO((AE_INFO, -- "RSDP " ACPI_PRINTF_UINT " %06X (v%.2d %-6.6s)", -- ACPI_FORMAT_TO_UINT(address), -+ ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)", -+ ACPI_FORMAT_UINT64(address), - (ACPI_CAST_PTR(struct acpi_table_rsdp, header)-> - revision > - 0) ? ACPI_CAST_PTR(struct acpi_table_rsdp, -@@ -165,9 +158,9 @@ acpi_tb_print_table_header(acpi_physical_address address, - acpi_tb_cleanup_table_header(&local_header, header); - - ACPI_INFO((AE_INFO, -- "%-4.4s " ACPI_PRINTF_UINT -+ "%-4.4s 0x%8.8X%8.8X" - " %06X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)", -- local_header.signature, ACPI_FORMAT_TO_UINT(address), -+ local_header.signature, ACPI_FORMAT_UINT64(address), - local_header.length, local_header.revision, - local_header.oem_id, local_header.oem_table_id, - local_header.oem_revision, -diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c -index eac52cf14f1a..fa76a3603aa1 100644 ---- a/drivers/acpi/acpica/tbxfroot.c -+++ b/drivers/acpi/acpica/tbxfroot.c -@@ -142,7 +142,7 @@ acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp * rsdp) - * - ******************************************************************************/ - --acpi_status __init acpi_find_root_pointer(acpi_size *table_address) -+acpi_status __init acpi_find_root_pointer(acpi_physical_address * table_address) - { - u8 *table_ptr; - u8 *mem_rover; -@@ -200,7 +200,8 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address) - physical_address += - (u32) ACPI_PTR_DIFF(mem_rover, table_ptr); - -- *table_address = physical_address; -+ *table_address = -+ (acpi_physical_address) physical_address; - return_ACPI_STATUS(AE_OK); - } - } -@@ -233,7 +234,7 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address) - (ACPI_HI_RSDP_WINDOW_BASE + - ACPI_PTR_DIFF(mem_rover, table_ptr)); - -- *table_address = physical_address; -+ *table_address = (acpi_physical_address) physical_address; - return_ACPI_STATUS(AE_OK); - } - -diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c -index 1279f50da757..911ea8e7fe87 100644 ---- a/drivers/acpi/acpica/utaddress.c -+++ b/drivers/acpi/acpica/utaddress.c -@@ -107,10 +107,10 @@ acpi_ut_add_address_range(acpi_adr_space_type space_id, - acpi_gbl_address_range_list[space_id] = range_info; - - ACPI_DEBUG_PRINT((ACPI_DB_NAMES, -- "\nAdded [%4.4s] address range: 0x%p-0x%p\n", -+ "\nAdded [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n", - acpi_ut_get_node_name(range_info->region_node), -- ACPI_CAST_PTR(void, address), -- ACPI_CAST_PTR(void, range_info->end_address))); -+ ACPI_FORMAT_UINT64(address), -+ ACPI_FORMAT_UINT64(range_info->end_address))); - - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return_ACPI_STATUS(AE_OK); -@@ -160,15 +160,13 @@ acpi_ut_remove_address_range(acpi_adr_space_type space_id, - } - - ACPI_DEBUG_PRINT((ACPI_DB_NAMES, -- "\nRemoved [%4.4s] address range: 0x%p-0x%p\n", -+ "\nRemoved [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n", - acpi_ut_get_node_name(range_info-> - region_node), -- ACPI_CAST_PTR(void, -- range_info-> -- start_address), -- ACPI_CAST_PTR(void, -- range_info-> -- end_address))); -+ ACPI_FORMAT_UINT64(range_info-> -+ start_address), -+ ACPI_FORMAT_UINT64(range_info-> -+ end_address))); - - ACPI_FREE(range_info); - return_VOID; -@@ -245,16 +243,14 @@ acpi_ut_check_address_range(acpi_adr_space_type space_id, - region_node); - - ACPI_WARNING((AE_INFO, -- "%s range 0x%p-0x%p conflicts with OpRegion 0x%p-0x%p (%s)", -+ "%s range 0x%8.8X%8.8X-0x%8.8X%8.8X conflicts with OpRegion 0x%8.8X%8.8X-0x%8.8X%8.8X (%s)", - acpi_ut_get_region_name(space_id), -- ACPI_CAST_PTR(void, address), -- ACPI_CAST_PTR(void, end_address), -- ACPI_CAST_PTR(void, -- range_info-> -- start_address), -- ACPI_CAST_PTR(void, -- range_info-> -- end_address), -+ ACPI_FORMAT_UINT64(address), -+ ACPI_FORMAT_UINT64(end_address), -+ ACPI_FORMAT_UINT64(range_info-> -+ start_address), -+ ACPI_FORMAT_UINT64(range_info-> -+ end_address), - pathname)); - ACPI_FREE(pathname); - } -diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c -index 5589a6e2a023..8244f013f210 100644 ---- a/drivers/acpi/resource.c -+++ b/drivers/acpi/resource.c -@@ -573,7 +573,7 @@ EXPORT_SYMBOL_GPL(acpi_dev_get_resources); - * @ares: Input ACPI resource object. - * @types: Valid resource types of IORESOURCE_XXX - * -- * This is a hepler function to support acpi_dev_get_resources(), which filters -+ * This is a helper function to support acpi_dev_get_resources(), which filters - * ACPI resource objects according to resource types. - */ - int acpi_dev_filter_resource_type(struct acpi_resource *ares, -diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c -index 26e5b5060523..bf034f8b7c1a 100644 ---- a/drivers/acpi/sbshc.c -+++ b/drivers/acpi/sbshc.c -@@ -14,6 +14,7 @@ - #include - #include - #include -+#include - #include "sbshc.h" - - #define PREFIX "ACPI: " -@@ -87,6 +88,8 @@ enum acpi_smb_offset { - ACPI_SMB_ALARM_DATA = 0x26, /* 2 bytes alarm data */ - }; - -+static bool macbook; -+ - static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data) - { - return ec_read(hc->offset + address, data); -@@ -132,6 +135,8 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol, - } - - mutex_lock(&hc->lock); -+ if (macbook) -+ udelay(5); - if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp)) - goto end; - if (temp) { -@@ -257,12 +262,29 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, - acpi_handle handle, acpi_ec_query_func func, - void *data); - -+static int macbook_dmi_match(const struct dmi_system_id *d) -+{ -+ pr_debug("Detected MacBook, enabling workaround\n"); -+ macbook = true; -+ return 0; -+} -+ -+static struct dmi_system_id acpi_smbus_dmi_table[] = { -+ { macbook_dmi_match, "Apple MacBook", { -+ DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), -+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") }, -+ }, -+ { }, -+}; -+ - static int acpi_smbus_hc_add(struct acpi_device *device) - { - int status; - unsigned long long val; - struct acpi_smb_hc *hc; - -+ dmi_check_system(acpi_smbus_dmi_table); -+ - if (!device) - return -EINVAL; - -diff --git a/drivers/block/loop.c b/drivers/block/loop.c -index d1f168b73634..773e964f14d9 100644 ---- a/drivers/block/loop.c -+++ b/drivers/block/loop.c -@@ -1672,8 +1672,8 @@ out: - - static void loop_remove(struct loop_device *lo) - { -- del_gendisk(lo->lo_disk); - blk_cleanup_queue(lo->lo_queue); -+ del_gendisk(lo->lo_disk); - blk_mq_free_tag_set(&lo->tag_set); - put_disk(lo->lo_disk); - kfree(lo); -diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c -index 7722ed53bd65..af3bc7a8033b 100644 ---- a/drivers/gpio/gpiolib-sysfs.c -+++ b/drivers/gpio/gpiolib-sysfs.c -@@ -551,6 +551,7 @@ static struct class gpio_class = { - */ - int gpiod_export(struct gpio_desc *desc, bool direction_may_change) - { -+ struct gpio_chip *chip; - unsigned long flags; - int status; - const char *ioname = NULL; -@@ -568,8 +569,16 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) - return -EINVAL; - } - -+ chip = desc->chip; -+ - mutex_lock(&sysfs_lock); - -+ /* check if chip is being removed */ -+ if (!chip || !chip->exported) { -+ status = -ENODEV; -+ goto fail_unlock; -+ } -+ - spin_lock_irqsave(&gpio_lock, flags); - if (!test_bit(FLAG_REQUESTED, &desc->flags) || - test_bit(FLAG_EXPORT, &desc->flags)) { -@@ -783,12 +792,15 @@ void gpiochip_unexport(struct gpio_chip *chip) - { - int status; - struct device *dev; -+ struct gpio_desc *desc; -+ unsigned int i; - - mutex_lock(&sysfs_lock); - dev = class_find_device(&gpio_class, NULL, chip, match_export); - if (dev) { - put_device(dev); - device_unregister(dev); -+ /* prevent further gpiod exports */ - chip->exported = false; - status = 0; - } else -@@ -797,6 +809,13 @@ void gpiochip_unexport(struct gpio_chip *chip) - - if (status) - chip_dbg(chip, "%s: status %d\n", __func__, status); -+ -+ /* unregister gpiod class devices owned by sysfs */ -+ for (i = 0; i < chip->ngpio; i++) { -+ desc = &chip->desc[i]; -+ if (test_and_clear_bit(FLAG_SYSFS, &desc->flags)) -+ gpiod_free(desc); -+ } - } - - static int __init gpiolib_sysfs_init(void) -diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c -index d8135adb2238..39762a7d2ec7 100644 ---- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c -+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c -@@ -429,9 +429,10 @@ static int unregister_process_nocpsch(struct device_queue_manager *dqm, - - BUG_ON(!dqm || !qpd); - -- BUG_ON(!list_empty(&qpd->queues_list)); -+ pr_debug("In func %s\n", __func__); - -- pr_debug("kfd: In func %s\n", __func__); -+ pr_debug("qpd->queues_list is %s\n", -+ list_empty(&qpd->queues_list) ? "empty" : "not empty"); - - retval = 0; - mutex_lock(&dqm->lock); -@@ -878,6 +879,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, - return -ENOMEM; - } - -+ init_sdma_vm(dqm, q, qpd); -+ - retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, - &q->gart_mqd_addr, &q->properties); - if (retval != 0) -diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c -index 10574a0c3a55..5769db4f51f3 100644 ---- a/drivers/gpu/drm/drm_irq.c -+++ b/drivers/gpu/drm/drm_irq.c -@@ -131,12 +131,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) - - /* Reinitialize corresponding vblank timestamp if high-precision query - * available. Skip this step if query unsupported or failed. Will -- * reinitialize delayed at next vblank interrupt in that case. -+ * reinitialize delayed at next vblank interrupt in that case and -+ * assign 0 for now, to mark the vblanktimestamp as invalid. - */ -- if (rc) { -- tslot = atomic_read(&vblank->count) + diff; -- vblanktimestamp(dev, crtc, tslot) = t_vblank; -- } -+ tslot = atomic_read(&vblank->count) + diff; -+ vblanktimestamp(dev, crtc, tslot) = rc ? t_vblank : (struct timeval) {0, 0}; - - smp_mb__before_atomic(); - atomic_add(diff, &vblank->count); -diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c -index a74aaf9242b9..88b36a9173c9 100644 ---- a/drivers/gpu/drm/i915/intel_dp.c -+++ b/drivers/gpu/drm/i915/intel_dp.c -@@ -1176,7 +1176,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, - - pipe_config->has_dp_encoder = true; - pipe_config->has_drrs = false; -- pipe_config->has_audio = intel_dp->has_audio; -+ pipe_config->has_audio = intel_dp->has_audio && port != PORT_A; - - if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) { - intel_fixed_panel_mode(intel_connector->panel.fixed_mode, -@@ -2026,8 +2026,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder, - int dotclock; - - tmp = I915_READ(intel_dp->output_reg); -- if (tmp & DP_AUDIO_OUTPUT_ENABLE) -- pipe_config->has_audio = true; -+ -+ pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A; - - if ((port == PORT_A) || !HAS_PCH_CPT(dev)) { - if (tmp & DP_SYNC_HS_HIGH) -diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c -index 071b96d6e146..fbc2a83795fa 100644 ---- a/drivers/gpu/drm/i915/intel_lvds.c -+++ b/drivers/gpu/drm/i915/intel_lvds.c -@@ -812,12 +812,28 @@ static int intel_dual_link_lvds_callback(const struct dmi_system_id *id) - static const struct dmi_system_id intel_dual_link_lvds[] = { - { - .callback = intel_dual_link_lvds_callback, -- .ident = "Apple MacBook Pro (Core i5/i7 Series)", -+ .ident = "Apple MacBook Pro 15\" (2010)", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), -+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro6,2"), -+ }, -+ }, -+ { -+ .callback = intel_dual_link_lvds_callback, -+ .ident = "Apple MacBook Pro 15\" (2011)", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro8,2"), - }, - }, -+ { -+ .callback = intel_dual_link_lvds_callback, -+ .ident = "Apple MacBook Pro 15\" (2012)", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), -+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,1"), -+ }, -+ }, - { } /* terminating entry */ - }; - -@@ -847,6 +863,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder) - if (i915.lvds_channel_mode > 0) - return i915.lvds_channel_mode == 2; - -+ /* single channel LVDS is limited to 112 MHz */ -+ if (lvds_encoder->attached_connector->base.panel.fixed_mode->clock -+ > 112999) -+ return true; -+ - if (dmi_check_system(intel_dual_link_lvds)) - return true; - -@@ -1104,6 +1125,8 @@ void intel_lvds_init(struct drm_device *dev) - out: - mutex_unlock(&dev->mode_config.mutex); - -+ intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode); -+ - lvds_encoder->is_dual_link = compute_is_dual_link_lvds(lvds_encoder); - DRM_DEBUG_KMS("detected %s-link lvds configuration\n", - lvds_encoder->is_dual_link ? "dual" : "single"); -@@ -1118,7 +1141,6 @@ out: - } - drm_connector_register(connector); - -- intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode); - intel_panel_setup_backlight(connector, INVALID_PIPE); - - return; -diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c -index c0ecd128b14b..7348f222684d 100644 ---- a/drivers/gpu/drm/radeon/radeon_asic.c -+++ b/drivers/gpu/drm/radeon/radeon_asic.c -@@ -1180,7 +1180,7 @@ static struct radeon_asic rs780_asic = { - static struct radeon_asic_ring rv770_uvd_ring = { - .ib_execute = &uvd_v1_0_ib_execute, - .emit_fence = &uvd_v2_2_fence_emit, -- .emit_semaphore = &uvd_v1_0_semaphore_emit, -+ .emit_semaphore = &uvd_v2_2_semaphore_emit, - .cs_parse = &radeon_uvd_cs_parse, - .ring_test = &uvd_v1_0_ring_test, - .ib_test = &uvd_v1_0_ib_test, -diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h -index 72bdd3bf0d8e..c2fd3a5e6c55 100644 ---- a/drivers/gpu/drm/radeon/radeon_asic.h -+++ b/drivers/gpu/drm/radeon/radeon_asic.h -@@ -919,6 +919,10 @@ void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib); - int uvd_v2_2_resume(struct radeon_device *rdev); - void uvd_v2_2_fence_emit(struct radeon_device *rdev, - struct radeon_fence *fence); -+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev, -+ struct radeon_ring *ring, -+ struct radeon_semaphore *semaphore, -+ bool emit_wait); - - /* uvd v3.1 */ - bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev, -diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c -index b7d33a13db9f..b7c6bb69f3c7 100644 ---- a/drivers/gpu/drm/radeon/radeon_audio.c -+++ b/drivers/gpu/drm/radeon/radeon_audio.c -@@ -464,6 +464,10 @@ void radeon_audio_detect(struct drm_connector *connector, - return; - - rdev = connector->encoder->dev->dev_private; -+ -+ if (!radeon_audio_chipset_supported(rdev)) -+ return; -+ - radeon_encoder = to_radeon_encoder(connector->encoder); - dig = radeon_encoder->enc_priv; - -diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c -index b292aca0f342..edafd3c2b170 100644 ---- a/drivers/gpu/drm/radeon/radeon_ttm.c -+++ b/drivers/gpu/drm/radeon/radeon_ttm.c -@@ -591,8 +591,7 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm) - { - struct radeon_device *rdev = radeon_get_rdev(ttm->bdev); - struct radeon_ttm_tt *gtt = (void *)ttm; -- struct scatterlist *sg; -- int i; -+ struct sg_page_iter sg_iter; - - int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY); - enum dma_data_direction direction = write ? -@@ -605,9 +604,8 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm) - /* free the sg table and pages again */ - dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction); - -- for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) { -- struct page *page = sg_page(sg); -- -+ for_each_sg_page(ttm->sg->sgl, &sg_iter, ttm->sg->nents, 0) { -+ struct page *page = sg_page_iter_page(&sg_iter); - if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY)) - set_page_dirty(page); - -diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c -index c10b2aec6450..cd630287cf0a 100644 ---- a/drivers/gpu/drm/radeon/radeon_uvd.c -+++ b/drivers/gpu/drm/radeon/radeon_uvd.c -@@ -396,6 +396,29 @@ static int radeon_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[]) - return 0; - } - -+static int radeon_uvd_validate_codec(struct radeon_cs_parser *p, -+ unsigned stream_type) -+{ -+ switch (stream_type) { -+ case 0: /* H264 */ -+ case 1: /* VC1 */ -+ /* always supported */ -+ return 0; -+ -+ case 3: /* MPEG2 */ -+ case 4: /* MPEG4 */ -+ /* only since UVD 3 */ -+ if (p->rdev->family >= CHIP_PALM) -+ return 0; -+ -+ /* fall through */ -+ default: -+ DRM_ERROR("UVD codec not supported by hardware %d!\n", -+ stream_type); -+ return -EINVAL; -+ } -+} -+ - static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, - unsigned offset, unsigned buf_sizes[]) - { -@@ -436,50 +459,70 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, - return -EINVAL; - } - -- if (msg_type == 1) { -- /* it's a decode msg, calc buffer sizes */ -- r = radeon_uvd_cs_msg_decode(msg, buf_sizes); -- /* calc image size (width * height) */ -- img_size = msg[6] * msg[7]; -+ switch (msg_type) { -+ case 0: -+ /* it's a create msg, calc image size (width * height) */ -+ img_size = msg[7] * msg[8]; -+ -+ r = radeon_uvd_validate_codec(p, msg[4]); -+ radeon_bo_kunmap(bo); -+ if (r) -+ return r; -+ -+ /* try to alloc a new handle */ -+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { -+ if (atomic_read(&p->rdev->uvd.handles[i]) == handle) { -+ DRM_ERROR("Handle 0x%x already in use!\n", handle); -+ return -EINVAL; -+ } -+ -+ if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) { -+ p->rdev->uvd.filp[i] = p->filp; -+ p->rdev->uvd.img_size[i] = img_size; -+ return 0; -+ } -+ } -+ -+ DRM_ERROR("No more free UVD handles!\n"); -+ return -EINVAL; -+ -+ case 1: -+ /* it's a decode msg, validate codec and calc buffer sizes */ -+ r = radeon_uvd_validate_codec(p, msg[4]); -+ if (!r) -+ r = radeon_uvd_cs_msg_decode(msg, buf_sizes); - radeon_bo_kunmap(bo); - if (r) - return r; - -- } else if (msg_type == 2) { -+ /* validate the handle */ -+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { -+ if (atomic_read(&p->rdev->uvd.handles[i]) == handle) { -+ if (p->rdev->uvd.filp[i] != p->filp) { -+ DRM_ERROR("UVD handle collision detected!\n"); -+ return -EINVAL; -+ } -+ return 0; -+ } -+ } -+ -+ DRM_ERROR("Invalid UVD handle 0x%x!\n", handle); -+ return -ENOENT; -+ -+ case 2: - /* it's a destroy msg, free the handle */ - for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) - atomic_cmpxchg(&p->rdev->uvd.handles[i], handle, 0); - radeon_bo_kunmap(bo); - return 0; -- } else { -- /* it's a create msg, calc image size (width * height) */ -- img_size = msg[7] * msg[8]; -- radeon_bo_kunmap(bo); - -- if (msg_type != 0) { -- DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type); -- return -EINVAL; -- } -- -- /* it's a create msg, no special handling needed */ -- } -- -- /* create or decode, validate the handle */ -- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { -- if (atomic_read(&p->rdev->uvd.handles[i]) == handle) -- return 0; -- } -+ default: - -- /* handle not found try to alloc a new one */ -- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { -- if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) { -- p->rdev->uvd.filp[i] = p->filp; -- p->rdev->uvd.img_size[i] = img_size; -- return 0; -- } -+ DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type); -+ return -EINVAL; - } - -- DRM_ERROR("No more free UVD handles!\n"); -+ BUG(); - return -EINVAL; - } - -diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c -index 976fe432f4e2..7ed561225007 100644 ---- a/drivers/gpu/drm/radeon/radeon_vce.c -+++ b/drivers/gpu/drm/radeon/radeon_vce.c -@@ -493,18 +493,27 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi, - * - * @p: parser context - * @handle: handle to validate -+ * @allocated: allocated a new handle? - * - * Validates the handle and return the found session index or -EINVAL - * we we don't have another free session index. - */ --int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle) -+static int radeon_vce_validate_handle(struct radeon_cs_parser *p, -+ uint32_t handle, bool *allocated) - { - unsigned i; - -+ *allocated = false; -+ - /* validate the handle */ - for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) { -- if (atomic_read(&p->rdev->vce.handles[i]) == handle) -+ if (atomic_read(&p->rdev->vce.handles[i]) == handle) { -+ if (p->rdev->vce.filp[i] != p->filp) { -+ DRM_ERROR("VCE handle collision detected!\n"); -+ return -EINVAL; -+ } - return i; -+ } - } - - /* handle not found try to alloc a new one */ -@@ -512,6 +521,7 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle) - if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) { - p->rdev->vce.filp[i] = p->filp; - p->rdev->vce.img_size[i] = 0; -+ *allocated = true; - return i; - } - } -@@ -529,10 +539,10 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle) - int radeon_vce_cs_parse(struct radeon_cs_parser *p) - { - int session_idx = -1; -- bool destroyed = false; -+ bool destroyed = false, created = false, allocated = false; - uint32_t tmp, handle = 0; - uint32_t *size = &tmp; -- int i, r; -+ int i, r = 0; - - while (p->idx < p->chunk_ib->length_dw) { - uint32_t len = radeon_get_ib_value(p, p->idx); -@@ -540,18 +550,21 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) - - if ((len < 8) || (len & 3)) { - DRM_ERROR("invalid VCE command length (%d)!\n", len); -- return -EINVAL; -+ r = -EINVAL; -+ goto out; - } - - if (destroyed) { - DRM_ERROR("No other command allowed after destroy!\n"); -- return -EINVAL; -+ r = -EINVAL; -+ goto out; - } - - switch (cmd) { - case 0x00000001: // session - handle = radeon_get_ib_value(p, p->idx + 2); -- session_idx = radeon_vce_validate_handle(p, handle); -+ session_idx = radeon_vce_validate_handle(p, handle, -+ &allocated); - if (session_idx < 0) - return session_idx; - size = &p->rdev->vce.img_size[session_idx]; -@@ -561,6 +574,13 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) - break; - - case 0x01000001: // create -+ created = true; -+ if (!allocated) { -+ DRM_ERROR("Handle already in use!\n"); -+ r = -EINVAL; -+ goto out; -+ } -+ - *size = radeon_get_ib_value(p, p->idx + 8) * - radeon_get_ib_value(p, p->idx + 10) * - 8 * 3 / 2; -@@ -577,12 +597,12 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) - r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9, - *size); - if (r) -- return r; -+ goto out; - - r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11, - *size / 3); - if (r) -- return r; -+ goto out; - break; - - case 0x02000001: // destroy -@@ -593,7 +613,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) - r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2, - *size * 2); - if (r) -- return r; -+ goto out; - break; - - case 0x05000004: // video bitstream buffer -@@ -601,36 +621,47 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) - r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2, - tmp); - if (r) -- return r; -+ goto out; - break; - - case 0x05000005: // feedback buffer - r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2, - 4096); - if (r) -- return r; -+ goto out; - break; - - default: - DRM_ERROR("invalid VCE command (0x%x)!\n", cmd); -- return -EINVAL; -+ r = -EINVAL; -+ goto out; - } - - if (session_idx == -1) { - DRM_ERROR("no session command at start of IB\n"); -- return -EINVAL; -+ r = -EINVAL; -+ goto out; - } - - p->idx += len / 4; - } - -- if (destroyed) { -- /* IB contains a destroy msg, free the handle */ -+ if (allocated && !created) { -+ DRM_ERROR("New session without create command!\n"); -+ r = -ENOENT; -+ } -+ -+out: -+ if ((!r && destroyed) || (r && allocated)) { -+ /* -+ * IB contains a destroy msg or we have allocated an -+ * handle and got an error, anyway free the handle -+ */ - for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) - atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0); - } - -- return 0; -+ return r; - } - - /** -diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h -index 3cf1e2921545..9ef2064b1c9c 100644 ---- a/drivers/gpu/drm/radeon/rv770d.h -+++ b/drivers/gpu/drm/radeon/rv770d.h -@@ -989,6 +989,9 @@ - ((n) & 0x3FFF) << 16) - - /* UVD */ -+#define UVD_SEMA_ADDR_LOW 0xef00 -+#define UVD_SEMA_ADDR_HIGH 0xef04 -+#define UVD_SEMA_CMD 0xef08 - #define UVD_GPCOM_VCPU_CMD 0xef0c - #define UVD_GPCOM_VCPU_DATA0 0xef10 - #define UVD_GPCOM_VCPU_DATA1 0xef14 -diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c -index e72b3cb59358..c6b1cbca47fc 100644 ---- a/drivers/gpu/drm/radeon/uvd_v1_0.c -+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c -@@ -466,18 +466,8 @@ bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev, - struct radeon_semaphore *semaphore, - bool emit_wait) - { -- uint64_t addr = semaphore->gpu_addr; -- -- radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0)); -- radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF); -- -- radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0)); -- radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF); -- -- radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0)); -- radeon_ring_write(ring, emit_wait ? 1 : 0); -- -- return true; -+ /* disable semaphores for UVD V1 hardware */ -+ return false; - } - - /** -diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c -index 89193519f8a1..7ed778cec7c6 100644 ---- a/drivers/gpu/drm/radeon/uvd_v2_2.c -+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c -@@ -60,6 +60,35 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev, - } - - /** -+ * uvd_v2_2_semaphore_emit - emit semaphore command -+ * -+ * @rdev: radeon_device pointer -+ * @ring: radeon_ring pointer -+ * @semaphore: semaphore to emit commands for -+ * @emit_wait: true if we should emit a wait command -+ * -+ * Emit a semaphore command (either wait or signal) to the UVD ring. -+ */ -+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev, -+ struct radeon_ring *ring, -+ struct radeon_semaphore *semaphore, -+ bool emit_wait) -+{ -+ uint64_t addr = semaphore->gpu_addr; -+ -+ radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0)); -+ radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF); -+ -+ radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0)); -+ radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF); -+ -+ radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0)); -+ radeon_ring_write(ring, emit_wait ? 1 : 0); -+ -+ return true; -+} -+ -+/** - * uvd_v2_2_resume - memory controller programming - * - * @rdev: radeon_device pointer -diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c -index d570030d899c..06441a43c3aa 100644 ---- a/drivers/infiniband/core/cma.c -+++ b/drivers/infiniband/core/cma.c -@@ -859,19 +859,27 @@ static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id - memcpy(&ib->sib_addr, &path->dgid, 16); - } - -+static __be16 ss_get_port(const struct sockaddr_storage *ss) -+{ -+ if (ss->ss_family == AF_INET) -+ return ((struct sockaddr_in *)ss)->sin_port; -+ else if (ss->ss_family == AF_INET6) -+ return ((struct sockaddr_in6 *)ss)->sin6_port; -+ BUG(); -+} -+ - static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, - struct cma_hdr *hdr) - { -- struct sockaddr_in *listen4, *ip4; -+ struct sockaddr_in *ip4; - -- listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr; - ip4 = (struct sockaddr_in *) &id->route.addr.src_addr; -- ip4->sin_family = listen4->sin_family; -+ ip4->sin_family = AF_INET; - ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr; -- ip4->sin_port = listen4->sin_port; -+ ip4->sin_port = ss_get_port(&listen_id->route.addr.src_addr); - - ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr; -- ip4->sin_family = listen4->sin_family; -+ ip4->sin_family = AF_INET; - ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr; - ip4->sin_port = hdr->port; - } -@@ -879,16 +887,15 @@ static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_i - static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, - struct cma_hdr *hdr) - { -- struct sockaddr_in6 *listen6, *ip6; -+ struct sockaddr_in6 *ip6; - -- listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr; - ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr; -- ip6->sin6_family = listen6->sin6_family; -+ ip6->sin6_family = AF_INET6; - ip6->sin6_addr = hdr->dst_addr.ip6; -- ip6->sin6_port = listen6->sin6_port; -+ ip6->sin6_port = ss_get_port(&listen_id->route.addr.src_addr); - - ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr; -- ip6->sin6_family = listen6->sin6_family; -+ ip6->sin6_family = AF_INET6; - ip6->sin6_addr = hdr->src_addr.ip6; - ip6->sin6_port = hdr->port; - } -diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c -index 414739295d04..713a96237a80 100644 ---- a/drivers/md/dm-crypt.c -+++ b/drivers/md/dm-crypt.c -@@ -925,10 +925,11 @@ static int crypt_convert(struct crypt_config *cc, - - switch (r) { - /* async */ -- case -EINPROGRESS: - case -EBUSY: - wait_for_completion(&ctx->restart); - reinit_completion(&ctx->restart); -+ /* fall through*/ -+ case -EINPROGRESS: - ctx->req = NULL; - ctx->cc_sector++; - continue; -@@ -1345,8 +1346,10 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, - struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); - struct crypt_config *cc = io->cc; - -- if (error == -EINPROGRESS) -+ if (error == -EINPROGRESS) { -+ complete(&ctx->restart); - return; -+ } - - if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post) - error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq); -@@ -1357,15 +1360,12 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, - crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio); - - if (!atomic_dec_and_test(&ctx->cc_pending)) -- goto done; -+ return; - - if (bio_data_dir(io->base_bio) == READ) - kcryptd_crypt_read_done(io); - else - kcryptd_crypt_write_io_submit(io, 1); --done: -- if (!completion_done(&ctx->restart)) -- complete(&ctx->restart); - } - - static void kcryptd_crypt(struct work_struct *work) -diff --git a/drivers/md/md.c b/drivers/md/md.c -index e6178787ce3d..e47d1dd046da 100644 ---- a/drivers/md/md.c -+++ b/drivers/md/md.c -@@ -4754,12 +4754,12 @@ static void md_free(struct kobject *ko) - if (mddev->sysfs_state) - sysfs_put(mddev->sysfs_state); - -+ if (mddev->queue) -+ blk_cleanup_queue(mddev->queue); - if (mddev->gendisk) { - del_gendisk(mddev->gendisk); - put_disk(mddev->gendisk); - } -- if (mddev->queue) -- blk_cleanup_queue(mddev->queue); - - kfree(mddev); - } -diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c -index dd5b1415f974..f902eb4ee569 100644 ---- a/drivers/media/platform/marvell-ccic/mcam-core.c -+++ b/drivers/media/platform/marvell-ccic/mcam-core.c -@@ -116,8 +116,8 @@ static struct mcam_format_struct { - .planar = false, - }, - { -- .desc = "UYVY 4:2:2", -- .pixelformat = V4L2_PIX_FMT_UYVY, -+ .desc = "YVYU 4:2:2", -+ .pixelformat = V4L2_PIX_FMT_YVYU, - .mbus_code = MEDIA_BUS_FMT_YUYV8_2X8, - .bpp = 2, - .planar = false, -@@ -748,7 +748,7 @@ static void mcam_ctlr_image(struct mcam_camera *cam) - - switch (fmt->pixelformat) { - case V4L2_PIX_FMT_YUYV: -- case V4L2_PIX_FMT_UYVY: -+ case V4L2_PIX_FMT_YVYU: - widthy = fmt->width * 2; - widthuv = 0; - break; -@@ -784,15 +784,15 @@ static void mcam_ctlr_image(struct mcam_camera *cam) - case V4L2_PIX_FMT_YUV420: - case V4L2_PIX_FMT_YVU420: - mcam_reg_write_mask(cam, REG_CTRL0, -- C0_DF_YUV | C0_YUV_420PL | C0_YUVE_YVYU, C0_DF_MASK); -+ C0_DF_YUV | C0_YUV_420PL | C0_YUVE_VYUY, C0_DF_MASK); - break; - case V4L2_PIX_FMT_YUYV: - mcam_reg_write_mask(cam, REG_CTRL0, -- C0_DF_YUV | C0_YUV_PACKED | C0_YUVE_UYVY, C0_DF_MASK); -+ C0_DF_YUV | C0_YUV_PACKED | C0_YUVE_NOSWAP, C0_DF_MASK); - break; -- case V4L2_PIX_FMT_UYVY: -+ case V4L2_PIX_FMT_YVYU: - mcam_reg_write_mask(cam, REG_CTRL0, -- C0_DF_YUV | C0_YUV_PACKED | C0_YUVE_YUYV, C0_DF_MASK); -+ C0_DF_YUV | C0_YUV_PACKED | C0_YUVE_SWAP24, C0_DF_MASK); - break; - case V4L2_PIX_FMT_JPEG: - mcam_reg_write_mask(cam, REG_CTRL0, -diff --git a/drivers/media/platform/marvell-ccic/mcam-core.h b/drivers/media/platform/marvell-ccic/mcam-core.h -index aa0c6eac254a..7ffdf4dbaf8c 100644 ---- a/drivers/media/platform/marvell-ccic/mcam-core.h -+++ b/drivers/media/platform/marvell-ccic/mcam-core.h -@@ -330,10 +330,10 @@ int mccic_resume(struct mcam_camera *cam); - #define C0_YUVE_YVYU 0x00010000 /* Y1CrY0Cb */ - #define C0_YUVE_VYUY 0x00020000 /* CrY1CbY0 */ - #define C0_YUVE_UYVY 0x00030000 /* CbY1CrY0 */ --#define C0_YUVE_XYUV 0x00000000 /* 420: .YUV */ --#define C0_YUVE_XYVU 0x00010000 /* 420: .YVU */ --#define C0_YUVE_XUVY 0x00020000 /* 420: .UVY */ --#define C0_YUVE_XVUY 0x00030000 /* 420: .VUY */ -+#define C0_YUVE_NOSWAP 0x00000000 /* no bytes swapping */ -+#define C0_YUVE_SWAP13 0x00010000 /* swap byte 1 and 3 */ -+#define C0_YUVE_SWAP24 0x00020000 /* swap byte 2 and 4 */ -+#define C0_YUVE_SWAP1324 0x00030000 /* swap bytes 1&3 and 2&4 */ - /* Bayer bits 18,19 if needed */ - #define C0_EOF_VSYNC 0x00400000 /* Generate EOF by VSYNC */ - #define C0_VEDGE_CTRL 0x00800000 /* Detect falling edge of VSYNC */ -diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c -index c69afb5e264e..ed2e71a74a58 100644 ---- a/drivers/mmc/card/block.c -+++ b/drivers/mmc/card/block.c -@@ -1029,6 +1029,18 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type) - md->reset_done &= ~type; - } - -+int mmc_access_rpmb(struct mmc_queue *mq) -+{ -+ struct mmc_blk_data *md = mq->data; -+ /* -+ * If this is a RPMB partition access, return ture -+ */ -+ if (md && md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) -+ return true; -+ -+ return false; -+} -+ - static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) - { - struct mmc_blk_data *md = mq->data; -diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c -index 236d194c2883..8efa3684aef8 100644 ---- a/drivers/mmc/card/queue.c -+++ b/drivers/mmc/card/queue.c -@@ -38,7 +38,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) - return BLKPREP_KILL; - } - -- if (mq && mmc_card_removed(mq->card)) -+ if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq))) - return BLKPREP_KILL; - - req->cmd_flags |= REQ_DONTPREP; -diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h -index 5752d50049a3..99e6521e6169 100644 ---- a/drivers/mmc/card/queue.h -+++ b/drivers/mmc/card/queue.h -@@ -73,4 +73,6 @@ extern void mmc_queue_bounce_post(struct mmc_queue_req *); - extern int mmc_packed_init(struct mmc_queue *, struct mmc_card *); - extern void mmc_packed_clean(struct mmc_queue *); - -+extern int mmc_access_rpmb(struct mmc_queue *); -+ - #endif -diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c -index 23f10f72e5f3..57a8d00672d3 100644 ---- a/drivers/mmc/core/core.c -+++ b/drivers/mmc/core/core.c -@@ -2648,6 +2648,7 @@ int mmc_pm_notify(struct notifier_block *notify_block, - switch (mode) { - case PM_HIBERNATION_PREPARE: - case PM_SUSPEND_PREPARE: -+ case PM_RESTORE_PREPARE: - spin_lock_irqsave(&host->lock, flags); - host->rescan_disable = 1; - spin_unlock_irqrestore(&host->lock, flags); -diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c -index 7d9d6a321521..5165ae75d540 100644 ---- a/drivers/mmc/host/sh_mmcif.c -+++ b/drivers/mmc/host/sh_mmcif.c -@@ -1402,7 +1402,7 @@ static int sh_mmcif_probe(struct platform_device *pdev) - host = mmc_priv(mmc); - host->mmc = mmc; - host->addr = reg; -- host->timeout = msecs_to_jiffies(1000); -+ host->timeout = msecs_to_jiffies(10000); - host->ccs_enable = !pd || !pd->ccs_unsupported; - host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present; - -diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c -index 89dca77ca038..18ee2089df4a 100644 ---- a/drivers/pinctrl/core.c -+++ b/drivers/pinctrl/core.c -@@ -1110,7 +1110,7 @@ void devm_pinctrl_put(struct pinctrl *p) - EXPORT_SYMBOL_GPL(devm_pinctrl_put); - - int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, -- bool dup, bool locked) -+ bool dup) - { - int i, ret; - struct pinctrl_maps *maps_node; -@@ -1178,11 +1178,9 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, - maps_node->maps = maps; - } - -- if (!locked) -- mutex_lock(&pinctrl_maps_mutex); -+ mutex_lock(&pinctrl_maps_mutex); - list_add_tail(&maps_node->node, &pinctrl_maps); -- if (!locked) -- mutex_unlock(&pinctrl_maps_mutex); -+ mutex_unlock(&pinctrl_maps_mutex); - - return 0; - } -@@ -1197,7 +1195,7 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, - int pinctrl_register_mappings(struct pinctrl_map const *maps, - unsigned num_maps) - { -- return pinctrl_register_map(maps, num_maps, true, false); -+ return pinctrl_register_map(maps, num_maps, true); - } - - void pinctrl_unregister_map(struct pinctrl_map const *map) -diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h -index 75476b3d87da..b24ea846c867 100644 ---- a/drivers/pinctrl/core.h -+++ b/drivers/pinctrl/core.h -@@ -183,7 +183,7 @@ static inline struct pin_desc *pin_desc_get(struct pinctrl_dev *pctldev, - } - - int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, -- bool dup, bool locked); -+ bool dup); - void pinctrl_unregister_map(struct pinctrl_map const *map); - - extern int pinctrl_force_sleep(struct pinctrl_dev *pctldev); -diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c -index eda13de2e7c0..0bbf7d71b281 100644 ---- a/drivers/pinctrl/devicetree.c -+++ b/drivers/pinctrl/devicetree.c -@@ -92,7 +92,7 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, - dt_map->num_maps = num_maps; - list_add_tail(&dt_map->node, &p->dt_maps); - -- return pinctrl_register_map(map, num_maps, false, true); -+ return pinctrl_register_map(map, num_maps, false); - } - - struct pinctrl_dev *of_pinctrl_get(struct device_node *np) -diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c -index 43e04af39e09..cb70ced7e0db 100644 ---- a/drivers/rtc/rtc-armada38x.c -+++ b/drivers/rtc/rtc-armada38x.c -@@ -40,6 +40,13 @@ struct armada38x_rtc { - void __iomem *regs; - void __iomem *regs_soc; - spinlock_t lock; -+ /* -+ * While setting the time, the RTC TIME register should not be -+ * accessed. Setting the RTC time involves sleeping during -+ * 100ms, so a mutex instead of a spinlock is used to protect -+ * it -+ */ -+ struct mutex mutex_time; - int irq; - }; - -@@ -59,8 +66,7 @@ static int armada38x_rtc_read_time(struct device *dev, struct rtc_time *tm) - struct armada38x_rtc *rtc = dev_get_drvdata(dev); - unsigned long time, time_check, flags; - -- spin_lock_irqsave(&rtc->lock, flags); -- -+ mutex_lock(&rtc->mutex_time); - time = readl(rtc->regs + RTC_TIME); - /* - * WA for failing time set attempts. As stated in HW ERRATA if -@@ -71,7 +77,7 @@ static int armada38x_rtc_read_time(struct device *dev, struct rtc_time *tm) - if ((time_check - time) > 1) - time_check = readl(rtc->regs + RTC_TIME); - -- spin_unlock_irqrestore(&rtc->lock, flags); -+ mutex_unlock(&rtc->mutex_time); - - rtc_time_to_tm(time_check, tm); - -@@ -94,19 +100,12 @@ static int armada38x_rtc_set_time(struct device *dev, struct rtc_time *tm) - * then wait for 100ms before writing to the time register to be - * sure that the data will be taken into account. - */ -- spin_lock_irqsave(&rtc->lock, flags); -- -+ mutex_lock(&rtc->mutex_time); - rtc_delayed_write(0, rtc, RTC_STATUS); -- -- spin_unlock_irqrestore(&rtc->lock, flags); -- - msleep(100); -- -- spin_lock_irqsave(&rtc->lock, flags); -- - rtc_delayed_write(time, rtc, RTC_TIME); -+ mutex_unlock(&rtc->mutex_time); - -- spin_unlock_irqrestore(&rtc->lock, flags); - out: - return ret; - } -@@ -230,6 +229,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev) - return -ENOMEM; - - spin_lock_init(&rtc->lock); -+ mutex_init(&rtc->mutex_time); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rtc"); - rtc->regs = devm_ioremap_resource(&pdev->dev, res); -diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c -index f1e57425e39f..5bab1c684bb1 100644 ---- a/drivers/tty/hvc/hvc_xen.c -+++ b/drivers/tty/hvc/hvc_xen.c -@@ -299,11 +299,27 @@ static int xen_initial_domain_console_init(void) - return 0; - } - -+static void xen_console_update_evtchn(struct xencons_info *info) -+{ -+ if (xen_hvm_domain()) { -+ uint64_t v; -+ int err; -+ -+ err = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v); -+ if (!err && v) -+ info->evtchn = v; -+ } else -+ info->evtchn = xen_start_info->console.domU.evtchn; -+} -+ - void xen_console_resume(void) - { - struct xencons_info *info = vtermno_to_xencons(HVC_COOKIE); -- if (info != NULL && info->irq) -+ if (info != NULL && info->irq) { -+ if (!xen_initial_domain()) -+ xen_console_update_evtchn(info); - rebind_evtchn_irq(info->evtchn, info->irq); -+ } - } - - static void xencons_disconnect_backend(struct xencons_info *info) -diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c -index 4cde85501444..837d1778970b 100644 ---- a/drivers/vfio/vfio.c -+++ b/drivers/vfio/vfio.c -@@ -711,6 +711,8 @@ void *vfio_del_group_dev(struct device *dev) - void *device_data = device->device_data; - struct vfio_unbound_dev *unbound; - unsigned int i = 0; -+ long ret; -+ bool interrupted = false; - - /* - * The group exists so long as we have a device reference. Get -@@ -756,9 +758,22 @@ void *vfio_del_group_dev(struct device *dev) - - vfio_device_put(device); - -- } while (wait_event_interruptible_timeout(vfio.release_q, -- !vfio_dev_present(group, dev), -- HZ * 10) <= 0); -+ if (interrupted) { -+ ret = wait_event_timeout(vfio.release_q, -+ !vfio_dev_present(group, dev), HZ * 10); -+ } else { -+ ret = wait_event_interruptible_timeout(vfio.release_q, -+ !vfio_dev_present(group, dev), HZ * 10); -+ if (ret == -ERESTARTSYS) { -+ interrupted = true; -+ dev_warn(dev, -+ "Device is currently in use, task" -+ " \"%s\" (%d) " -+ "blocked until device is released", -+ current->comm, task_pid_nr(current)); -+ } -+ } -+ } while (ret <= 0); - - vfio_group_put(group); - -diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c -index 5db43fc100a4..7dd46312c180 100644 ---- a/drivers/xen/events/events_2l.c -+++ b/drivers/xen/events/events_2l.c -@@ -345,6 +345,15 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) - return IRQ_HANDLED; - } - -+static void evtchn_2l_resume(void) -+{ -+ int i; -+ -+ for_each_online_cpu(i) -+ memset(per_cpu(cpu_evtchn_mask, i), 0, sizeof(xen_ulong_t) * -+ EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD); -+} -+ - static const struct evtchn_ops evtchn_ops_2l = { - .max_channels = evtchn_2l_max_channels, - .nr_channels = evtchn_2l_max_channels, -@@ -356,6 +365,7 @@ static const struct evtchn_ops evtchn_ops_2l = { - .mask = evtchn_2l_mask, - .unmask = evtchn_2l_unmask, - .handle_events = evtchn_2l_handle_events, -+ .resume = evtchn_2l_resume, - }; - - void __init xen_evtchn_2l_init(void) -diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c -index 70fba973a107..2b8553bd8715 100644 ---- a/drivers/xen/events/events_base.c -+++ b/drivers/xen/events/events_base.c -@@ -529,8 +529,8 @@ static unsigned int __startup_pirq(unsigned int irq) - if (rc) - goto err; - -- bind_evtchn_to_cpu(evtchn, 0); - info->evtchn = evtchn; -+ bind_evtchn_to_cpu(evtchn, 0); - - rc = xen_evtchn_port_setup(info); - if (rc) -@@ -1279,8 +1279,9 @@ void rebind_evtchn_irq(int evtchn, int irq) - - mutex_unlock(&irq_mapping_update_lock); - -- /* new event channels are always bound to cpu 0 */ -- irq_set_affinity(irq, cpumask_of(0)); -+ bind_evtchn_to_cpu(evtchn, info->cpu); -+ /* This will be deferred until interrupt is processed */ -+ irq_set_affinity(irq, cpumask_of(info->cpu)); - - /* Unmask the event channel. */ - enable_irq(irq); -diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c -index 75fe3d466515..9c234209d8b5 100644 ---- a/drivers/xen/xen-pciback/conf_space.c -+++ b/drivers/xen/xen-pciback/conf_space.c -@@ -16,8 +16,8 @@ - #include "conf_space.h" - #include "conf_space_quirks.h" - --bool permissive; --module_param(permissive, bool, 0644); -+bool xen_pcibk_permissive; -+module_param_named(permissive, xen_pcibk_permissive, bool, 0644); - - /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word, - * xen_pcibk_write_config_word, and xen_pcibk_write_config_byte are created. */ -@@ -262,7 +262,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) - * This means that some fields may still be read-only because - * they have entries in the config_field list that intercept - * the write and do nothing. */ -- if (dev_data->permissive || permissive) { -+ if (dev_data->permissive || xen_pcibk_permissive) { - switch (size) { - case 1: - err = pci_write_config_byte(dev, offset, -diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h -index 2e1d73d1d5d0..62461a8ba1d6 100644 ---- a/drivers/xen/xen-pciback/conf_space.h -+++ b/drivers/xen/xen-pciback/conf_space.h -@@ -64,7 +64,7 @@ struct config_field_entry { - void *data; - }; - --extern bool permissive; -+extern bool xen_pcibk_permissive; - - #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) - -diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c -index 2d7369391472..f8baf463dd35 100644 ---- a/drivers/xen/xen-pciback/conf_space_header.c -+++ b/drivers/xen/xen-pciback/conf_space_header.c -@@ -105,7 +105,7 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) - - cmd->val = value; - -- if (!permissive && (!dev_data || !dev_data->permissive)) -+ if (!xen_pcibk_permissive && (!dev_data || !dev_data->permissive)) - return 0; - - /* Only allow the guest to control certain bits. */ -diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c -index 564b31584860..5390a674b5e3 100644 ---- a/drivers/xen/xenbus/xenbus_probe.c -+++ b/drivers/xen/xenbus/xenbus_probe.c -@@ -57,6 +57,7 @@ - #include - #include - #include -+#include - #include - - #include -@@ -735,6 +736,30 @@ static int __init xenstored_local_init(void) - return err; - } - -+static int xenbus_resume_cb(struct notifier_block *nb, -+ unsigned long action, void *data) -+{ -+ int err = 0; -+ -+ if (xen_hvm_domain()) { -+ uint64_t v; -+ -+ err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); -+ if (!err && v) -+ xen_store_evtchn = v; -+ else -+ pr_warn("Cannot update xenstore event channel: %d\n", -+ err); -+ } else -+ xen_store_evtchn = xen_start_info->store_evtchn; -+ -+ return err; -+} -+ -+static struct notifier_block xenbus_resume_nb = { -+ .notifier_call = xenbus_resume_cb, -+}; -+ - static int __init xenbus_init(void) - { - int err = 0; -@@ -793,6 +818,10 @@ static int __init xenbus_init(void) - goto out_error; - } - -+ if ((xen_store_domain_type != XS_LOCAL) && -+ (xen_store_domain_type != XS_UNKNOWN)) -+ xen_resume_notifier_register(&xenbus_resume_nb); -+ - #ifdef CONFIG_XEN_COMPAT_XENFS - /* - * Create xenfs mountpoint in /proc for compatibility with -diff --git a/fs/coredump.c b/fs/coredump.c -index f319926ddf8c..bbbe139ab280 100644 ---- a/fs/coredump.c -+++ b/fs/coredump.c -@@ -657,7 +657,7 @@ void do_coredump(const siginfo_t *siginfo) - */ - if (!uid_eq(inode->i_uid, current_fsuid())) - goto close_fail; -- if (!cprm.file->f_op->write) -+ if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) - goto close_fail; - if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) - goto close_fail; -diff --git a/fs/namei.c b/fs/namei.c -index caa38a24e1f7..50a8583e8156 100644 ---- a/fs/namei.c -+++ b/fs/namei.c -@@ -3228,7 +3228,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, - - if (unlikely(file->f_flags & __O_TMPFILE)) { - error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened); -- goto out; -+ goto out2; - } - - error = path_init(dfd, pathname->name, flags, nd); -@@ -3258,6 +3258,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, - } - out: - path_cleanup(nd); -+out2: - if (!(opened & FILE_OPENED)) { - BUG_ON(!error); - put_filp(file); -diff --git a/fs/namespace.c b/fs/namespace.c -index 4622ee32a5e2..38ed1e1bed41 100644 ---- a/fs/namespace.c -+++ b/fs/namespace.c -@@ -3178,6 +3178,12 @@ bool fs_fully_visible(struct file_system_type *type) - if (mnt->mnt.mnt_sb->s_type != type) - continue; - -+ /* This mount is not fully visible if it's root directory -+ * is not the root directory of the filesystem. -+ */ -+ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) -+ continue; -+ - /* This mount is not fully visible if there are any child mounts - * that cover anything except for empty directories. - */ -diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c -index ecdbae19a766..090d8ce25bd1 100644 ---- a/fs/nilfs2/btree.c -+++ b/fs/nilfs2/btree.c -@@ -388,7 +388,7 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, - nchildren = nilfs_btree_node_get_nchildren(node); - - if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || -- level > NILFS_BTREE_LEVEL_MAX || -+ level >= NILFS_BTREE_LEVEL_MAX || - nchildren < 0 || - nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { - pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n", -diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c -index a6944b25fd5b..fdf4b41d0609 100644 ---- a/fs/ocfs2/dlm/dlmmaster.c -+++ b/fs/ocfs2/dlm/dlmmaster.c -@@ -757,6 +757,19 @@ lookup: - if (tmpres) { - spin_unlock(&dlm->spinlock); - spin_lock(&tmpres->spinlock); -+ -+ /* -+ * Right after dlm spinlock was released, dlm_thread could have -+ * purged the lockres. Check if lockres got unhashed. If so -+ * start over. -+ */ -+ if (hlist_unhashed(&tmpres->hash_node)) { -+ spin_unlock(&tmpres->spinlock); -+ dlm_lockres_put(tmpres); -+ tmpres = NULL; -+ goto lookup; -+ } -+ - /* Wait on the thread that is mastering the resource */ - if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { - __dlm_wait_on_lockres(tmpres); -diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h -index d56f5d722138..65aa4fa0ae4e 100644 ---- a/include/acpi/acpixf.h -+++ b/include/acpi/acpixf.h -@@ -431,13 +431,13 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init acpi_load_tables(void)) - ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init acpi_reallocate_root_table(void)) - - ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init -- acpi_find_root_pointer(acpi_size * rsdp_address)) -- -+ acpi_find_root_pointer(acpi_physical_address * -+ rsdp_address)) - ACPI_EXTERNAL_RETURN_STATUS(acpi_status -- acpi_get_table_header(acpi_string signature, -- u32 instance, -- struct acpi_table_header -- *out_table_header)) -+ acpi_get_table_header(acpi_string signature, -+ u32 instance, -+ struct acpi_table_header -+ *out_table_header)) - ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_get_table(acpi_string signature, u32 instance, - struct acpi_table_header -diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h -index ff3fea3194c6..9abb763e4b86 100644 ---- a/include/linux/nilfs2_fs.h -+++ b/include/linux/nilfs2_fs.h -@@ -460,7 +460,7 @@ struct nilfs_btree_node { - /* level */ - #define NILFS_BTREE_LEVEL_DATA 0 - #define NILFS_BTREE_LEVEL_NODE_MIN (NILFS_BTREE_LEVEL_DATA + 1) --#define NILFS_BTREE_LEVEL_MAX 14 -+#define NILFS_BTREE_LEVEL_MAX 14 /* Max level (exclusive) */ - - /** - * struct nilfs_palloc_group_desc - block group descriptor -diff --git a/mm/memory-failure.c b/mm/memory-failure.c -index d487f8dc6d39..72a5224c8084 100644 ---- a/mm/memory-failure.c -+++ b/mm/memory-failure.c -@@ -1141,10 +1141,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) - * The check (unnecessarily) ignores LRU pages being isolated and - * walked by the page reclaim code, however that's not a big loss. - */ -- if (!PageHuge(p) && !PageTransTail(p)) { -- if (!PageLRU(p)) -- shake_page(p, 0); -- if (!PageLRU(p)) { -+ if (!PageHuge(p)) { -+ if (!PageLRU(hpage)) -+ shake_page(hpage, 0); -+ if (!PageLRU(hpage)) { - /* - * shake_page could have turned it free. - */ -@@ -1721,12 +1721,12 @@ int soft_offline_page(struct page *page, int flags) - } else if (ret == 0) { /* for free pages */ - if (PageHuge(page)) { - set_page_hwpoison_huge_page(hpage); -- dequeue_hwpoisoned_huge_page(hpage); -- atomic_long_add(1 << compound_order(hpage), -+ if (!dequeue_hwpoisoned_huge_page(hpage)) -+ atomic_long_add(1 << compound_order(hpage), - &num_poisoned_pages); - } else { -- SetPageHWPoison(page); -- atomic_long_inc(&num_poisoned_pages); -+ if (!TestSetPageHWPoison(page)) -+ atomic_long_inc(&num_poisoned_pages); - } - } - unset_migratetype_isolate(page, MIGRATE_MOVABLE); -diff --git a/mm/page-writeback.c b/mm/page-writeback.c -index 644bcb665773..ad05f2f7bb65 100644 ---- a/mm/page-writeback.c -+++ b/mm/page-writeback.c -@@ -580,7 +580,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, - long x; - - x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, -- limit - setpoint + 1); -+ (limit - setpoint) | 1); - pos_ratio = x; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; -@@ -807,7 +807,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, - * scale global setpoint to bdi's: - * bdi_setpoint = setpoint * bdi_thresh / thresh - */ -- x = div_u64((u64)bdi_thresh << 16, thresh + 1); -+ x = div_u64((u64)bdi_thresh << 16, thresh | 1); - bdi_setpoint = setpoint * (u64)x >> 16; - /* - * Use span=(8*write_bw) in single bdi case as indicated by -@@ -822,7 +822,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, - - if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), -- x_intercept - bdi_setpoint + 1); -+ (x_intercept - bdi_setpoint) | 1); - } else - pos_ratio /= 4; - -diff --git a/sound/oss/sequencer.c b/sound/oss/sequencer.c -index c0eea1dfe90f..f19da4b47c1d 100644 ---- a/sound/oss/sequencer.c -+++ b/sound/oss/sequencer.c -@@ -681,13 +681,8 @@ static int seq_timing_event(unsigned char *event_rec) - break; - - case TMR_ECHO: -- if (seq_mode == SEQ_2) -- seq_copy_to_input(event_rec, 8); -- else -- { -- parm = (parm << 8 | SEQ_ECHO); -- seq_copy_to_input((unsigned char *) &parm, 4); -- } -+ parm = (parm << 8 | SEQ_ECHO); -+ seq_copy_to_input((unsigned char *) &parm, 4); - break; - - default:; -@@ -1324,7 +1319,6 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a - int mode = translate_mode(file); - struct synth_info inf; - struct seq_event_rec event_rec; -- unsigned long flags; - int __user *p = arg; - - orig_dev = dev = dev >> 4; -@@ -1479,9 +1473,7 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a - case SNDCTL_SEQ_OUTOFBAND: - if (copy_from_user(&event_rec, arg, sizeof(event_rec))) - return -EFAULT; -- spin_lock_irqsave(&lock,flags); - play_event(event_rec.arr); -- spin_unlock_irqrestore(&lock,flags); - return 0; - - case SNDCTL_MIDI_INFO: diff --git a/1004_linux-4.0.5.patch b/1004_linux-4.0.5.patch deleted file mode 100644 index 84509c00..00000000 --- a/1004_linux-4.0.5.patch +++ /dev/null @@ -1,4937 +0,0 @@ -diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401 -index 8eb88e974055..711f75e189eb 100644 ---- a/Documentation/hwmon/tmp401 -+++ b/Documentation/hwmon/tmp401 -@@ -20,7 +20,7 @@ Supported chips: - Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html - * Texas Instruments TMP435 - Prefix: 'tmp435' -- Addresses scanned: I2C 0x37, 0x48 - 0x4f -+ Addresses scanned: I2C 0x48 - 0x4f - Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html - - Authors: -diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt -index 1e52d67d0abf..dbe6623fed1c 100644 ---- a/Documentation/serial/tty.txt -+++ b/Documentation/serial/tty.txt -@@ -198,6 +198,9 @@ TTY_IO_ERROR If set, causes all subsequent userspace read/write - - TTY_OTHER_CLOSED Device is a pty and the other side has closed. - -+TTY_OTHER_DONE Device is a pty and the other side has closed and -+ all pending input processing has been completed. -+ - TTY_NO_WRITE_SPLIT Prevent driver from splitting up writes into - smaller chunks. - -diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt -index 53838d9c6295..c59bd9bc41ef 100644 ---- a/Documentation/virtual/kvm/mmu.txt -+++ b/Documentation/virtual/kvm/mmu.txt -@@ -169,6 +169,10 @@ Shadow pages contain the following information: - Contains the value of cr4.smep && !cr0.wp for which the page is valid - (pages for which this is true are different from other pages; see the - treatment of cr0.wp=0 below). -+ role.smap_andnot_wp: -+ Contains the value of cr4.smap && !cr0.wp for which the page is valid -+ (pages for which this is true are different from other pages; see the -+ treatment of cr0.wp=0 below). - gfn: - Either the guest page table containing the translations shadowed by this - page, or the base page frame for linear translations. See role.direct. -@@ -344,10 +348,16 @@ on fault type: - - (user write faults generate a #PF) - --In the first case there is an additional complication if CR4.SMEP is --enabled: since we've turned the page into a kernel page, the kernel may now --execute it. We handle this by also setting spte.nx. If we get a user --fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back. -+In the first case there are two additional complications: -+- if CR4.SMEP is enabled: since we've turned the page into a kernel page, -+ the kernel may now execute it. We handle this by also setting spte.nx. -+ If we get a user fetch or read fault, we'll change spte.u=1 and -+ spte.nx=gpte.nx back. -+- if CR4.SMAP is disabled: since the page has been changed to a kernel -+ page, it can not be reused when CR4.SMAP is enabled. We set -+ CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, -+ here we do not care the case that CR4.SMAP is enabled since KVM will -+ directly inject #PF to guest due to failed permission check. - - To prevent an spte that was converted into a kernel page with cr0.wp=0 - from being written by the kernel after cr0.wp has changed to 1, we make -diff --git a/Makefile b/Makefile -index 3d16bcc87585..1880cf77059b 100644 ---- a/Makefile -+++ b/Makefile -@@ -1,6 +1,6 @@ - VERSION = 4 - PATCHLEVEL = 0 --SUBLEVEL = 4 -+SUBLEVEL = 5 - EXTRAVERSION = - NAME = Hurr durr I'ma sheep - -diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h -index 067551b6920a..9917a45fc430 100644 ---- a/arch/arc/include/asm/atomic.h -+++ b/arch/arc/include/asm/atomic.h -@@ -99,7 +99,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ - atomic_ops_unlock(flags); \ - } - --#define ATOMIC_OP_RETURN(op, c_op) \ -+#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ - static inline int atomic_##op##_return(int i, atomic_t *v) \ - { \ - unsigned long flags; \ -diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile -index a1c776b8dcec..992ea0b063d5 100644 ---- a/arch/arm/boot/dts/Makefile -+++ b/arch/arm/boot/dts/Makefile -@@ -215,7 +215,7 @@ dtb-$(CONFIG_SOC_IMX25) += \ - imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \ - imx25-karo-tx25.dtb \ - imx25-pdk.dtb --dtb-$(CONFIG_SOC_IMX31) += \ -+dtb-$(CONFIG_SOC_IMX27) += \ - imx27-apf27.dtb \ - imx27-apf27dev.dtb \ - imx27-eukrea-mbimxsd27-baseboard.dtb \ -diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts -index 173ffa479ad3..792394dd0f2a 100644 ---- a/arch/arm/boot/dts/exynos4412-trats2.dts -+++ b/arch/arm/boot/dts/exynos4412-trats2.dts -@@ -736,7 +736,7 @@ - - display-timings { - timing-0 { -- clock-frequency = <0>; -+ clock-frequency = <57153600>; - hactive = <720>; - vactive = <1280>; - hfront-porch = <5>; -diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi -index 4b063b68db44..9ce1d2128749 100644 ---- a/arch/arm/boot/dts/imx27.dtsi -+++ b/arch/arm/boot/dts/imx27.dtsi -@@ -531,7 +531,7 @@ - - fec: ethernet@1002b000 { - compatible = "fsl,imx27-fec"; -- reg = <0x1002b000 0x4000>; -+ reg = <0x1002b000 0x1000>; - interrupts = <50>; - clocks = <&clks IMX27_CLK_FEC_IPG_GATE>, - <&clks IMX27_CLK_FEC_AHB_GATE>; -diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S -index f8ccc21fa032..4e7f40c577e6 100644 ---- a/arch/arm/kernel/entry-common.S -+++ b/arch/arm/kernel/entry-common.S -@@ -33,7 +33,9 @@ ret_fast_syscall: - UNWIND(.fnstart ) - UNWIND(.cantunwind ) - disable_irq @ disable interrupts -- ldr r1, [tsk, #TI_FLAGS] -+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing -+ tst r1, #_TIF_SYSCALL_WORK -+ bne __sys_trace_return - tst r1, #_TIF_WORK_MASK - bne fast_work_pending - asm_trace_hardirqs_on -diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c -index 37266a826437..1f02bcb350e5 100644 ---- a/arch/arm/mach-exynos/pm_domains.c -+++ b/arch/arm/mach-exynos/pm_domains.c -@@ -169,7 +169,7 @@ no_clk: - args.np = np; - args.args_count = 0; - child_domain = of_genpd_get_from_provider(&args); -- if (!child_domain) -+ if (IS_ERR(child_domain)) - continue; - - if (of_parse_phandle_with_args(np, "power-domains", -@@ -177,7 +177,7 @@ no_clk: - continue; - - parent_domain = of_genpd_get_from_provider(&args); -- if (!parent_domain) -+ if (IS_ERR(parent_domain)) - continue; - - if (pm_genpd_add_subdomain(parent_domain, child_domain)) -diff --git a/arch/arm/mach-exynos/sleep.S b/arch/arm/mach-exynos/sleep.S -index 31d25834b9c4..cf950790fbdc 100644 ---- a/arch/arm/mach-exynos/sleep.S -+++ b/arch/arm/mach-exynos/sleep.S -@@ -23,14 +23,7 @@ - #define CPU_MASK 0xff0ffff0 - #define CPU_CORTEX_A9 0x410fc090 - -- /* -- * The following code is located into the .data section. This is to -- * allow l2x0_regs_phys to be accessed with a relative load while we -- * can't rely on any MMU translation. We could have put l2x0_regs_phys -- * in the .text section as well, but some setups might insist on it to -- * be truly read-only. (Reference from: arch/arm/kernel/sleep.S) -- */ -- .data -+ .text - .align - - /* -@@ -69,10 +62,12 @@ ENTRY(exynos_cpu_resume_ns) - cmp r0, r1 - bne skip_cp15 - -- adr r0, cp15_save_power -+ adr r0, _cp15_save_power - ldr r1, [r0] -- adr r0, cp15_save_diag -+ ldr r1, [r0, r1] -+ adr r0, _cp15_save_diag - ldr r2, [r0] -+ ldr r2, [r0, r2] - mov r0, #SMC_CMD_C15RESUME - dsb - smc #0 -@@ -118,14 +113,20 @@ skip_l2x0: - skip_cp15: - b cpu_resume - ENDPROC(exynos_cpu_resume_ns) -+ -+ .align -+_cp15_save_power: -+ .long cp15_save_power - . -+_cp15_save_diag: -+ .long cp15_save_diag - . -+#ifdef CONFIG_CACHE_L2X0 -+1: .long l2x0_saved_regs - . -+#endif /* CONFIG_CACHE_L2X0 */ -+ -+ .data - .globl cp15_save_diag - cp15_save_diag: - .long 0 @ cp15 diagnostic - .globl cp15_save_power - cp15_save_power: - .long 0 @ cp15 power control -- --#ifdef CONFIG_CACHE_L2X0 -- .align --1: .long l2x0_saved_regs - . --#endif /* CONFIG_CACHE_L2X0 */ -diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c -index 4e6ef896c619..7186382672b5 100644 ---- a/arch/arm/mm/mmu.c -+++ b/arch/arm/mm/mmu.c -@@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void) - } - - /* -- * Find the first non-section-aligned page, and point -+ * Find the first non-pmd-aligned page, and point - * memblock_limit at it. This relies on rounding the -- * limit down to be section-aligned, which happens at -- * the end of this function. -+ * limit down to be pmd-aligned, which happens at the -+ * end of this function. - * - * With this algorithm, the start or end of almost any -- * bank can be non-section-aligned. The only exception -- * is that the start of the bank 0 must be section- -+ * bank can be non-pmd-aligned. The only exception is -+ * that the start of the bank 0 must be section- - * aligned, since otherwise memory would need to be - * allocated when mapping the start of bank 0, which - * occurs before any free memory is mapped. - */ - if (!memblock_limit) { -- if (!IS_ALIGNED(block_start, SECTION_SIZE)) -+ if (!IS_ALIGNED(block_start, PMD_SIZE)) - memblock_limit = block_start; -- else if (!IS_ALIGNED(block_end, SECTION_SIZE)) -+ else if (!IS_ALIGNED(block_end, PMD_SIZE)) - memblock_limit = arm_lowmem_limit; - } - -@@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void) - high_memory = __va(arm_lowmem_limit - 1) + 1; - - /* -- * Round the memblock limit down to a section size. This -+ * Round the memblock limit down to a pmd size. This - * helps to ensure that we will allocate memory from the -- * last full section, which should be mapped. -+ * last full pmd, which should be mapped. - */ - if (memblock_limit) -- memblock_limit = round_down(memblock_limit, SECTION_SIZE); -+ memblock_limit = round_down(memblock_limit, PMD_SIZE); - if (!memblock_limit) - memblock_limit = arm_lowmem_limit; - -diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c -index edba042b2325..dc6a4842683a 100644 ---- a/arch/arm64/net/bpf_jit_comp.c -+++ b/arch/arm64/net/bpf_jit_comp.c -@@ -487,7 +487,7 @@ emit_cond_jmp: - return -EINVAL; - } - -- imm64 = (u64)insn1.imm << 32 | imm; -+ imm64 = (u64)insn1.imm << 32 | (u32)imm; - emit_a64_mov_i64(dst, imm64, ctx); - - return 1; -diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c -index d2c09f6475c5..f20cedcb50f1 100644 ---- a/arch/mips/kernel/elf.c -+++ b/arch/mips/kernel/elf.c -@@ -76,14 +76,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, - - /* Lets see if this is an O32 ELF */ - if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) { -- /* FR = 1 for N32 */ -- if (ehdr32->e_flags & EF_MIPS_ABI2) -- state->overall_fp_mode = FP_FR1; -- else -- /* Set a good default FPU mode for O32 */ -- state->overall_fp_mode = cpu_has_mips_r6 ? -- FP_FRE : FP_FR0; -- - if (ehdr32->e_flags & EF_MIPS_FP64) { - /* - * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it -@@ -104,9 +96,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, - (char *)&abiflags, - sizeof(abiflags)); - } else { -- /* FR=1 is really the only option for 64-bit */ -- state->overall_fp_mode = FP_FR1; -- - if (phdr64->p_type != PT_MIPS_ABIFLAGS) - return 0; - if (phdr64->p_filesz < sizeof(abiflags)) -@@ -147,6 +136,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, - struct elf32_hdr *ehdr = _ehdr; - struct mode_req prog_req, interp_req; - int fp_abi, interp_fp_abi, abi0, abi1, max_abi; -+ bool is_mips64; - - if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) - return 0; -@@ -162,10 +152,22 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, - abi0 = abi1 = fp_abi; - } - -- /* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */ -- max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) && -- (!(ehdr->e_flags & EF_MIPS_ABI2))) ? -- MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT; -+ is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) || -+ (ehdr->e_flags & EF_MIPS_ABI2); -+ -+ if (is_mips64) { -+ /* MIPS64 code always uses FR=1, thus the default is easy */ -+ state->overall_fp_mode = FP_FR1; -+ -+ /* Disallow access to the various FPXX & FP64 ABIs */ -+ max_abi = MIPS_ABI_FP_SOFT; -+ } else { -+ /* Default to a mode capable of running code expecting FR=0 */ -+ state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0; -+ -+ /* Allow all ABIs we know about */ -+ max_abi = MIPS_ABI_FP_64A; -+ } - - if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) || - (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN)) -diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h -index 3391d061eccc..78c9fd32c554 100644 ---- a/arch/parisc/include/asm/elf.h -+++ b/arch/parisc/include/asm/elf.h -@@ -348,6 +348,10 @@ struct pt_regs; /* forward declaration... */ - - #define ELF_HWCAP 0 - -+#define STACK_RND_MASK (is_32bit_task() ? \ -+ 0x7ff >> (PAGE_SHIFT - 12) : \ -+ 0x3ffff >> (PAGE_SHIFT - 12)) -+ - struct mm_struct; - extern unsigned long arch_randomize_brk(struct mm_struct *); - #define arch_randomize_brk arch_randomize_brk -diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c -index e1ffea2f9a0b..5aba01ac457f 100644 ---- a/arch/parisc/kernel/sys_parisc.c -+++ b/arch/parisc/kernel/sys_parisc.c -@@ -77,6 +77,9 @@ static unsigned long mmap_upper_limit(void) - if (stack_base > STACK_SIZE_MAX) - stack_base = STACK_SIZE_MAX; - -+ /* Add space for stack randomization. */ -+ stack_base += (STACK_RND_MASK << PAGE_SHIFT); -+ - return PAGE_ALIGN(STACK_TOP - stack_base); - } - -diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c -index 15c99b649b04..b2eb4686bd8f 100644 ---- a/arch/powerpc/kernel/mce.c -+++ b/arch/powerpc/kernel/mce.c -@@ -73,7 +73,7 @@ void save_mce_event(struct pt_regs *regs, long handled, - uint64_t nip, uint64_t addr) - { - uint64_t srr1; -- int index = __this_cpu_inc_return(mce_nest_count); -+ int index = __this_cpu_inc_return(mce_nest_count) - 1; - struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]); - - /* -@@ -184,7 +184,7 @@ void machine_check_queue_event(void) - if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) - return; - -- index = __this_cpu_inc_return(mce_queue_count); -+ index = __this_cpu_inc_return(mce_queue_count) - 1; - /* If queue is full, just return for now. */ - if (index >= MAX_MC_EVT) { - __this_cpu_dec(mce_queue_count); -diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S -index f096e72262f4..1db685104ffc 100644 ---- a/arch/powerpc/kernel/vmlinux.lds.S -+++ b/arch/powerpc/kernel/vmlinux.lds.S -@@ -213,6 +213,7 @@ SECTIONS - *(.opd) - } - -+ . = ALIGN(256); - .got : AT(ADDR(.got) - LOAD_OFFSET) { - __toc_start = .; - #ifndef CONFIG_RELOCATABLE -diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c -index 7940dc90e80b..b258110da952 100644 ---- a/arch/s390/crypto/ghash_s390.c -+++ b/arch/s390/crypto/ghash_s390.c -@@ -16,11 +16,12 @@ - #define GHASH_DIGEST_SIZE 16 - - struct ghash_ctx { -- u8 icv[16]; -- u8 key[16]; -+ u8 key[GHASH_BLOCK_SIZE]; - }; - - struct ghash_desc_ctx { -+ u8 icv[GHASH_BLOCK_SIZE]; -+ u8 key[GHASH_BLOCK_SIZE]; - u8 buffer[GHASH_BLOCK_SIZE]; - u32 bytes; - }; -@@ -28,8 +29,10 @@ struct ghash_desc_ctx { - static int ghash_init(struct shash_desc *desc) - { - struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); -+ struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); - - memset(dctx, 0, sizeof(*dctx)); -+ memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE); - - return 0; - } -@@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm, - } - - memcpy(ctx->key, key, GHASH_BLOCK_SIZE); -- memset(ctx->icv, 0, GHASH_BLOCK_SIZE); - - return 0; - } -@@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc, - const u8 *src, unsigned int srclen) - { - struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); -- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); - unsigned int n; - u8 *buf = dctx->buffer; - int ret; -@@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc, - src += n; - - if (!dctx->bytes) { -- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, -+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, - GHASH_BLOCK_SIZE); - if (ret != GHASH_BLOCK_SIZE) - return -EIO; -@@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc, - - n = srclen & ~(GHASH_BLOCK_SIZE - 1); - if (n) { -- ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n); -+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n); - if (ret != n) - return -EIO; - src += n; -@@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc, - return 0; - } - --static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) -+static int ghash_flush(struct ghash_desc_ctx *dctx) - { - u8 *buf = dctx->buffer; - int ret; -@@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) - - memset(pos, 0, dctx->bytes); - -- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE); -+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE); - if (ret != GHASH_BLOCK_SIZE) - return -EIO; -+ -+ dctx->bytes = 0; - } - -- dctx->bytes = 0; - return 0; - } - - static int ghash_final(struct shash_desc *desc, u8 *dst) - { - struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); -- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); - int ret; - -- ret = ghash_flush(ctx, dctx); -+ ret = ghash_flush(dctx); - if (!ret) -- memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE); -+ memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE); - return ret; - } - -diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h -index e08ec38f8c6e..e10112da008d 100644 ---- a/arch/s390/include/asm/pgtable.h -+++ b/arch/s390/include/asm/pgtable.h -@@ -600,7 +600,7 @@ static inline int pmd_large(pmd_t pmd) - return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; - } - --static inline int pmd_pfn(pmd_t pmd) -+static inline unsigned long pmd_pfn(pmd_t pmd) - { - unsigned long origin_mask; - -diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h -index a236e39cc385..1c0fb570b5c2 100644 ---- a/arch/x86/include/asm/kvm_host.h -+++ b/arch/x86/include/asm/kvm_host.h -@@ -212,6 +212,7 @@ union kvm_mmu_page_role { - unsigned nxe:1; - unsigned cr0_wp:1; - unsigned smep_andnot_wp:1; -+ unsigned smap_andnot_wp:1; - }; - }; - -@@ -404,6 +405,7 @@ struct kvm_vcpu_arch { - struct kvm_mmu_memory_cache mmu_page_header_cache; - - struct fpu guest_fpu; -+ bool eager_fpu; - u64 xcr0; - u64 guest_supported_xcr0; - u32 guest_xstate_size; -@@ -735,6 +737,7 @@ struct kvm_x86_ops { - void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); - unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); - void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); -+ void (*fpu_activate)(struct kvm_vcpu *vcpu); - void (*fpu_deactivate)(struct kvm_vcpu *vcpu); - - void (*tlb_flush)(struct kvm_vcpu *vcpu); -diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c -index 3c036cb4a370..11dd8f23fcea 100644 ---- a/arch/x86/kernel/cpu/mcheck/mce.c -+++ b/arch/x86/kernel/cpu/mcheck/mce.c -@@ -705,6 +705,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, - struct pt_regs *regs) - { - int i, ret = 0; -+ char *tmp; - - for (i = 0; i < mca_cfg.banks; i++) { - m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); -@@ -713,9 +714,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); - } -- if (mce_severity(m, mca_cfg.tolerant, msg, true) >= -- MCE_PANIC_SEVERITY) -+ -+ if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { -+ *msg = tmp; - ret = 1; -+ } - } - return ret; - } -diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c -index c4bb8b8e5017..76d8cbe5a10f 100644 ---- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c -+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c -@@ -680,6 +680,7 @@ static int __init rapl_pmu_init(void) - break; - case 60: /* Haswell */ - case 69: /* Haswell-Celeron */ -+ case 61: /* Broadwell */ - rapl_cntr_mask = RAPL_IDX_HSW; - rapl_pmu_events_group.attrs = rapl_events_hsw_attr; - break; -diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c -index d5651fce0b71..f341d56b7883 100644 ---- a/arch/x86/kernel/i387.c -+++ b/arch/x86/kernel/i387.c -@@ -169,6 +169,21 @@ static void init_thread_xstate(void) - xstate_size = sizeof(struct i387_fxsave_struct); - else - xstate_size = sizeof(struct i387_fsave_struct); -+ -+ /* -+ * Quirk: we don't yet handle the XSAVES* instructions -+ * correctly, as we don't correctly convert between -+ * standard and compacted format when interfacing -+ * with user-space - so disable it for now. -+ * -+ * The difference is small: with recent CPUs the -+ * compacted format is only marginally smaller than -+ * the standard FPU state format. -+ * -+ * ( This is easy to backport while we are fixing -+ * XSAVES* support. ) -+ */ -+ setup_clear_cpu_cap(X86_FEATURE_XSAVES); - } - - /* -diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c -index 8a80737ee6e6..307f9ec28e08 100644 ---- a/arch/x86/kvm/cpuid.c -+++ b/arch/x86/kvm/cpuid.c -@@ -16,6 +16,8 @@ - #include - #include - #include -+#include /* For use_eager_fpu. Ugh! */ -+#include /* For use_eager_fpu. Ugh! */ - #include - #include - #include "cpuid.h" -@@ -95,6 +97,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) - if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) - best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - -+ vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu); -+ - /* - * The existing code assumes virtual address is 48-bit in the canonical - * address checks; exit if it is ever changed. -diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h -index 4452eedfaedd..9bec2b8cdced 100644 ---- a/arch/x86/kvm/cpuid.h -+++ b/arch/x86/kvm/cpuid.h -@@ -111,4 +111,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) - best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_RTM)); - } -+ -+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) -+{ -+ struct kvm_cpuid_entry2 *best; -+ -+ best = kvm_find_cpuid_entry(vcpu, 7, 0); -+ return best && (best->ebx & bit(X86_FEATURE_MPX)); -+} - #endif -diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c -index cee759299a35..88ee9282a57e 100644 ---- a/arch/x86/kvm/mmu.c -+++ b/arch/x86/kvm/mmu.c -@@ -3736,8 +3736,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - } - } - --void update_permission_bitmask(struct kvm_vcpu *vcpu, -- struct kvm_mmu *mmu, bool ept) -+static void update_permission_bitmask(struct kvm_vcpu *vcpu, -+ struct kvm_mmu *mmu, bool ept) - { - unsigned bit, byte, pfec; - u8 map; -@@ -3918,6 +3918,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) - void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) - { - bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); -+ bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); - struct kvm_mmu *context = &vcpu->arch.mmu; - - MMU_WARN_ON(VALID_PAGE(context->root_hpa)); -@@ -3936,6 +3937,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) - context->base_role.cr0_wp = is_write_protection(vcpu); - context->base_role.smep_andnot_wp - = smep && !is_write_protection(vcpu); -+ context->base_role.smap_andnot_wp -+ = smap && !is_write_protection(vcpu); - } - EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); - -@@ -4207,12 +4210,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) - { - gfn_t gfn = gpa >> PAGE_SHIFT; -- union kvm_mmu_page_role mask = { .word = 0 }; - struct kvm_mmu_page *sp; - LIST_HEAD(invalid_list); - u64 entry, gentry, *spte; - int npte; - bool remote_flush, local_flush, zap_page; -+ union kvm_mmu_page_role mask = (union kvm_mmu_page_role) { -+ .cr0_wp = 1, -+ .cr4_pae = 1, -+ .nxe = 1, -+ .smep_andnot_wp = 1, -+ .smap_andnot_wp = 1, -+ }; - - /* - * If we don't have indirect shadow pages, it means no page is -@@ -4238,7 +4247,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - ++vcpu->kvm->stat.mmu_pte_write; - kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - -- mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { - if (detect_write_misaligned(sp, gpa, bytes) || - detect_write_flooding(sp)) { -diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h -index c7d65637c851..0ada65ecddcf 100644 ---- a/arch/x86/kvm/mmu.h -+++ b/arch/x86/kvm/mmu.h -@@ -71,8 +71,6 @@ enum { - int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); - void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); - void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); --void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, -- bool ept); - - static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) - { -@@ -166,6 +164,8 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - int index = (pfec >> 1) + - (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); - -+ WARN_ON(pfec & PFERR_RSVD_MASK); -+ - return (mmu->permissions[index] >> pte_access) & 1; - } - -diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h -index fd49c867b25a..6e6d115fe9b5 100644 ---- a/arch/x86/kvm/paging_tmpl.h -+++ b/arch/x86/kvm/paging_tmpl.h -@@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, - mmu_is_nested(vcpu)); - if (likely(r != RET_MMIO_PF_INVALID)) - return r; -+ -+ /* -+ * page fault with PFEC.RSVD = 1 is caused by shadow -+ * page fault, should not be used to walk guest page -+ * table. -+ */ -+ error_code &= ~PFERR_RSVD_MASK; - }; - - r = mmu_topup_memory_caches(vcpu); -diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c -index cc618c882f90..a4e62fcfabcb 100644 ---- a/arch/x86/kvm/svm.c -+++ b/arch/x86/kvm/svm.c -@@ -4374,6 +4374,7 @@ static struct kvm_x86_ops svm_x86_ops = { - .cache_reg = svm_cache_reg, - .get_rflags = svm_get_rflags, - .set_rflags = svm_set_rflags, -+ .fpu_activate = svm_fpu_activate, - .fpu_deactivate = svm_fpu_deactivate, - - .tlb_flush = svm_flush_tlb, -diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c -index a60bd3aa0965..5318d64674b0 100644 ---- a/arch/x86/kvm/vmx.c -+++ b/arch/x86/kvm/vmx.c -@@ -10179,6 +10179,7 @@ static struct kvm_x86_ops vmx_x86_ops = { - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, -+ .fpu_activate = vmx_fpu_activate, - .fpu_deactivate = vmx_fpu_deactivate, - - .tlb_flush = vmx_flush_tlb, -diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c -index e222ba5d2beb..8838057da9c3 100644 ---- a/arch/x86/kvm/x86.c -+++ b/arch/x86/kvm/x86.c -@@ -702,8 +702,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); - int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) - { - unsigned long old_cr4 = kvm_read_cr4(vcpu); -- unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | -- X86_CR4_PAE | X86_CR4_SMEP; -+ unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | -+ X86_CR4_SMEP | X86_CR4_SMAP; -+ - if (cr4 & CR4_RESERVED_BITS) - return 1; - -@@ -744,9 +745,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) - (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) - kvm_mmu_reset_context(vcpu); - -- if ((cr4 ^ old_cr4) & X86_CR4_SMAP) -- update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false); -- - if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) - kvm_update_cpuid(vcpu); - -@@ -6141,6 +6139,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) - return; - - page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); -+ if (is_error_page(page)) -+ return; - kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); - - /* -@@ -6996,7 +6996,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) - fpu_save_init(&vcpu->arch.guest_fpu); - __kernel_fpu_end(); - ++vcpu->stat.fpu_reload; -- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); -+ if (!vcpu->arch.eager_fpu) -+ kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); -+ - trace_kvm_fpu(0); - } - -@@ -7012,11 +7014,21 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) - struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) - { -+ struct kvm_vcpu *vcpu; -+ - if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) - printk_once(KERN_WARNING - "kvm: SMP vm created on host with unstable TSC; " - "guest TSC will not be reliable\n"); -- return kvm_x86_ops->vcpu_create(kvm, id); -+ -+ vcpu = kvm_x86_ops->vcpu_create(kvm, id); -+ -+ /* -+ * Activate fpu unconditionally in case the guest needs eager FPU. It will be -+ * deactivated soon if it doesn't. -+ */ -+ kvm_x86_ops->fpu_activate(vcpu); -+ return vcpu; - } - - int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c -index f9eeae871593..5aa1f6e281d2 100644 ---- a/drivers/acpi/osl.c -+++ b/drivers/acpi/osl.c -@@ -182,7 +182,7 @@ static void __init acpi_request_region (struct acpi_generic_address *gas, - request_mem_region(addr, length, desc); - } - --static int __init acpi_reserve_resources(void) -+static void __init acpi_reserve_resources(void) - { - acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length, - "ACPI PM1a_EVT_BLK"); -@@ -211,10 +211,7 @@ static int __init acpi_reserve_resources(void) - if (!(acpi_gbl_FADT.gpe1_block_length & 0x1)) - acpi_request_region(&acpi_gbl_FADT.xgpe1_block, - acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK"); -- -- return 0; - } --device_initcall(acpi_reserve_resources); - - void acpi_os_printf(const char *fmt, ...) - { -@@ -1845,6 +1842,7 @@ acpi_status __init acpi_os_initialize(void) - - acpi_status __init acpi_os_initialize1(void) - { -+ acpi_reserve_resources(); - kacpid_wq = alloc_workqueue("kacpid", 0, 1); - kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1); - kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0); -diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c -index 33bb06e006c9..adce56fa9cef 100644 ---- a/drivers/ata/ahci.c -+++ b/drivers/ata/ahci.c -@@ -66,6 +66,7 @@ enum board_ids { - board_ahci_yes_fbs, - - /* board IDs for specific chipsets in alphabetical order */ -+ board_ahci_avn, - board_ahci_mcp65, - board_ahci_mcp77, - board_ahci_mcp89, -@@ -84,6 +85,8 @@ enum board_ids { - static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); - static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, - unsigned long deadline); -+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, -+ unsigned long deadline); - static void ahci_mcp89_apple_enable(struct pci_dev *pdev); - static bool is_mcp89_apple(struct pci_dev *pdev); - static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class, -@@ -107,6 +110,11 @@ static struct ata_port_operations ahci_p5wdh_ops = { - .hardreset = ahci_p5wdh_hardreset, - }; - -+static struct ata_port_operations ahci_avn_ops = { -+ .inherits = &ahci_ops, -+ .hardreset = ahci_avn_hardreset, -+}; -+ - static const struct ata_port_info ahci_port_info[] = { - /* by features */ - [board_ahci] = { -@@ -151,6 +159,12 @@ static const struct ata_port_info ahci_port_info[] = { - .port_ops = &ahci_ops, - }, - /* by chipsets */ -+ [board_ahci_avn] = { -+ .flags = AHCI_FLAG_COMMON, -+ .pio_mask = ATA_PIO4, -+ .udma_mask = ATA_UDMA6, -+ .port_ops = &ahci_avn_ops, -+ }, - [board_ahci_mcp65] = { - AHCI_HFLAGS (AHCI_HFLAG_NO_FPDMA_AA | AHCI_HFLAG_NO_PMP | - AHCI_HFLAG_YES_NCQ), -@@ -290,14 +304,14 @@ static const struct pci_device_id ahci_pci_tbl[] = { - { PCI_VDEVICE(INTEL, 0x1f27), board_ahci }, /* Avoton RAID */ - { PCI_VDEVICE(INTEL, 0x1f2e), board_ahci }, /* Avoton RAID */ - { PCI_VDEVICE(INTEL, 0x1f2f), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f32), board_ahci }, /* Avoton AHCI */ -- { PCI_VDEVICE(INTEL, 0x1f33), board_ahci }, /* Avoton AHCI */ -- { PCI_VDEVICE(INTEL, 0x1f34), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f35), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f36), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f37), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci }, /* Avoton RAID */ -- { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f32), board_ahci_avn }, /* Avoton AHCI */ -+ { PCI_VDEVICE(INTEL, 0x1f33), board_ahci_avn }, /* Avoton AHCI */ -+ { PCI_VDEVICE(INTEL, 0x1f34), board_ahci_avn }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f35), board_ahci_avn }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f36), board_ahci_avn }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */ -+ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */ - { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */ - { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */ - { PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */ -@@ -670,6 +684,79 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class, - return rc; - } - -+/* -+ * ahci_avn_hardreset - attempt more aggressive recovery of Avoton ports. -+ * -+ * It has been observed with some SSDs that the timing of events in the -+ * link synchronization phase can leave the port in a state that can not -+ * be recovered by a SATA-hard-reset alone. The failing signature is -+ * SStatus.DET stuck at 1 ("Device presence detected but Phy -+ * communication not established"). It was found that unloading and -+ * reloading the driver when this problem occurs allows the drive -+ * connection to be recovered (DET advanced to 0x3). The critical -+ * component of reloading the driver is that the port state machines are -+ * reset by bouncing "port enable" in the AHCI PCS configuration -+ * register. So, reproduce that effect by bouncing a port whenever we -+ * see DET==1 after a reset. -+ */ -+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, -+ unsigned long deadline) -+{ -+ const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context); -+ struct ata_port *ap = link->ap; -+ struct ahci_port_priv *pp = ap->private_data; -+ struct ahci_host_priv *hpriv = ap->host->private_data; -+ u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG; -+ unsigned long tmo = deadline - jiffies; -+ struct ata_taskfile tf; -+ bool online; -+ int rc, i; -+ -+ DPRINTK("ENTER\n"); -+ -+ ahci_stop_engine(ap); -+ -+ for (i = 0; i < 2; i++) { -+ u16 val; -+ u32 sstatus; -+ int port = ap->port_no; -+ struct ata_host *host = ap->host; -+ struct pci_dev *pdev = to_pci_dev(host->dev); -+ -+ /* clear D2H reception area to properly wait for D2H FIS */ -+ ata_tf_init(link->device, &tf); -+ tf.command = ATA_BUSY; -+ ata_tf_to_fis(&tf, 0, 0, d2h_fis); -+ -+ rc = sata_link_hardreset(link, timing, deadline, &online, -+ ahci_check_ready); -+ -+ if (sata_scr_read(link, SCR_STATUS, &sstatus) != 0 || -+ (sstatus & 0xf) != 1) -+ break; -+ -+ ata_link_printk(link, KERN_INFO, "avn bounce port%d\n", -+ port); -+ -+ pci_read_config_word(pdev, 0x92, &val); -+ val &= ~(1 << port); -+ pci_write_config_word(pdev, 0x92, val); -+ ata_msleep(ap, 1000); -+ val |= 1 << port; -+ pci_write_config_word(pdev, 0x92, val); -+ deadline += tmo; -+ } -+ -+ hpriv->start_engine(ap); -+ -+ if (online) -+ *class = ahci_dev_classify(ap); -+ -+ DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class); -+ return rc; -+} -+ -+ - #ifdef CONFIG_PM - static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg) - { -diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c -index 61a9c07e0dff..287c4ba0219f 100644 ---- a/drivers/ata/libahci.c -+++ b/drivers/ata/libahci.c -@@ -1707,8 +1707,7 @@ static void ahci_handle_port_interrupt(struct ata_port *ap, - if (unlikely(resetting)) - status &= ~PORT_IRQ_BAD_PMP; - -- /* if LPM is enabled, PHYRDY doesn't mean anything */ -- if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) { -+ if (sata_lpm_ignore_phy_events(&ap->link)) { - status &= ~PORT_IRQ_PHYRDY; - ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG); - } -diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c -index 23dac3babfe3..87b4b7f9fdc6 100644 ---- a/drivers/ata/libata-core.c -+++ b/drivers/ata/libata-core.c -@@ -4214,7 +4214,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { - ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, -- { "Samsung SSD 850 PRO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | -+ { "Samsung SSD 8*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, - - /* -@@ -6728,6 +6728,38 @@ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val, - return tmp; - } - -+/** -+ * sata_lpm_ignore_phy_events - test if PHY event should be ignored -+ * @link: Link receiving the event -+ * -+ * Test whether the received PHY event has to be ignored or not. -+ * -+ * LOCKING: -+ * None: -+ * -+ * RETURNS: -+ * True if the event has to be ignored. -+ */ -+bool sata_lpm_ignore_phy_events(struct ata_link *link) -+{ -+ unsigned long lpm_timeout = link->last_lpm_change + -+ msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY); -+ -+ /* if LPM is enabled, PHYRDY doesn't mean anything */ -+ if (link->lpm_policy > ATA_LPM_MAX_POWER) -+ return true; -+ -+ /* ignore the first PHY event after the LPM policy changed -+ * as it is might be spurious -+ */ -+ if ((link->flags & ATA_LFLAG_CHANGED) && -+ time_before(jiffies, lpm_timeout)) -+ return true; -+ -+ return false; -+} -+EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events); -+ - /* - * Dummy port_ops - */ -diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c -index d2029a462e2c..89c3d83e1ca7 100644 ---- a/drivers/ata/libata-eh.c -+++ b/drivers/ata/libata-eh.c -@@ -3489,6 +3489,9 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, - } - } - -+ link->last_lpm_change = jiffies; -+ link->flags |= ATA_LFLAG_CHANGED; -+ - return 0; - - fail: -diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c -index 237f23f68bfc..1daa0ea2f1ac 100644 ---- a/drivers/clk/clk.c -+++ b/drivers/clk/clk.c -@@ -1443,8 +1443,10 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *clk, - */ - if (clk->prepare_count) { - clk_core_prepare(parent); -+ flags = clk_enable_lock(); - clk_core_enable(parent); - clk_core_enable(clk); -+ clk_enable_unlock(flags); - } - - /* update the clk tree topology */ -@@ -1459,13 +1461,17 @@ static void __clk_set_parent_after(struct clk_core *core, - struct clk_core *parent, - struct clk_core *old_parent) - { -+ unsigned long flags; -+ - /* - * Finish the migration of prepare state and undo the changes done - * for preventing a race with clk_enable(). - */ - if (core->prepare_count) { -+ flags = clk_enable_lock(); - clk_core_disable(core); - clk_core_disable(old_parent); -+ clk_enable_unlock(flags); - clk_core_unprepare(old_parent); - } - } -@@ -1489,8 +1495,10 @@ static int __clk_set_parent(struct clk_core *clk, struct clk_core *parent, - clk_enable_unlock(flags); - - if (clk->prepare_count) { -+ flags = clk_enable_lock(); - clk_core_disable(clk); - clk_core_disable(parent); -+ clk_enable_unlock(flags); - clk_core_unprepare(parent); - } - return ret; -diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c -index 07d666cc6a29..bea4a173eef5 100644 ---- a/drivers/clk/samsung/clk-exynos5420.c -+++ b/drivers/clk/samsung/clk-exynos5420.c -@@ -271,6 +271,7 @@ static const struct samsung_clk_reg_dump exynos5420_set_clksrc[] = { - { .offset = SRC_MASK_PERIC0, .value = 0x11111110, }, - { .offset = SRC_MASK_PERIC1, .value = 0x11111100, }, - { .offset = SRC_MASK_ISP, .value = 0x11111000, }, -+ { .offset = GATE_BUS_TOP, .value = 0xffffffff, }, - { .offset = GATE_BUS_DISP1, .value = 0xffffffff, }, - { .offset = GATE_IP_PERIC, .value = 0xffffffff, }, - }; -diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c -index 2eebd28b4c40..ccc20188f00c 100644 ---- a/drivers/firmware/dmi_scan.c -+++ b/drivers/firmware/dmi_scan.c -@@ -499,18 +499,19 @@ static int __init dmi_present(const u8 *buf) - buf += 16; - - if (memcmp(buf, "_DMI_", 5) == 0 && dmi_checksum(buf, 15)) { -+ if (smbios_ver) -+ dmi_ver = smbios_ver; -+ else -+ dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F); - dmi_num = get_unaligned_le16(buf + 12); - dmi_len = get_unaligned_le16(buf + 6); - dmi_base = get_unaligned_le32(buf + 8); - - if (dmi_walk_early(dmi_decode) == 0) { - if (smbios_ver) { -- dmi_ver = smbios_ver; - pr_info("SMBIOS %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); - } else { -- dmi_ver = (buf[14] & 0xF0) << 4 | -- (buf[14] & 0x0F); - pr_info("Legacy DMI %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); - } -diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c -index 443518f63f15..a6b0def4bd7b 100644 ---- a/drivers/gpio/gpio-kempld.c -+++ b/drivers/gpio/gpio-kempld.c -@@ -117,7 +117,7 @@ static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset) - = container_of(chip, struct kempld_gpio_data, chip); - struct kempld_device_data *pld = gpio->pld; - -- return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); -+ return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset); - } - - static int kempld_gpio_pincount(struct kempld_device_data *pld) -diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c -index 498399323a8c..406624a0b201 100644 ---- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c -+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c -@@ -729,7 +729,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, - kfd2kgd->get_max_engine_clock_in_mhz( - dev->gpu->kgd)); - sysfs_show_64bit_prop(buffer, "local_mem_size", -- kfd2kgd->get_vmem_size(dev->gpu->kgd)); -+ (unsigned long long int) 0); - - sysfs_show_32bit_prop(buffer, "fw_version", - kfd2kgd->get_fw_version( -diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c -index 5ba5792bfdba..98b125763ecd 100644 ---- a/drivers/gpu/drm/drm_plane_helper.c -+++ b/drivers/gpu/drm/drm_plane_helper.c -@@ -476,6 +476,9 @@ int drm_plane_helper_commit(struct drm_plane *plane, - if (!crtc[i]) - continue; - -+ if (crtc[i]->cursor == plane) -+ continue; -+ - /* There's no other way to figure out whether the crtc is running. */ - ret = drm_crtc_vblank_get(crtc[i]); - if (ret == 0) { -diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c -index 1afc0b419da2..965a45619f6b 100644 ---- a/drivers/gpu/drm/radeon/atombios_crtc.c -+++ b/drivers/gpu/drm/radeon/atombios_crtc.c -@@ -1789,7 +1789,9 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc) - if ((crtc->mode.clock == test_crtc->mode.clock) && - (adjusted_clock == test_adjusted_clock) && - (radeon_crtc->ss_enabled == test_radeon_crtc->ss_enabled) && -- (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)) -+ (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) && -+ (drm_detect_monitor_audio(radeon_connector_edid(test_radeon_crtc->connector)) == -+ drm_detect_monitor_audio(radeon_connector_edid(radeon_crtc->connector)))) - return test_radeon_crtc->pll_id; - } - } -diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c -index 8d74de82456e..8b2c4c890507 100644 ---- a/drivers/gpu/drm/radeon/atombios_dp.c -+++ b/drivers/gpu/drm/radeon/atombios_dp.c -@@ -412,19 +412,21 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector) - { - struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv; - u8 msg[DP_DPCD_SIZE]; -- int ret; -+ int ret, i; - -- ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg, -- DP_DPCD_SIZE); -- if (ret > 0) { -- memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE); -+ for (i = 0; i < 7; i++) { -+ ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg, -+ DP_DPCD_SIZE); -+ if (ret == DP_DPCD_SIZE) { -+ memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE); - -- DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd), -- dig_connector->dpcd); -+ DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd), -+ dig_connector->dpcd); - -- radeon_dp_probe_oui(radeon_connector); -+ radeon_dp_probe_oui(radeon_connector); - -- return true; -+ return true; -+ } - } - dig_connector->dpcd[0] = 0; - return false; -diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c -index 3e670d344a20..19aafb71fd8e 100644 ---- a/drivers/gpu/drm/radeon/cik.c -+++ b/drivers/gpu/drm/radeon/cik.c -@@ -5804,7 +5804,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev) - /* restore context1-15 */ - /* set vm size, must be a multiple of 4 */ - WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); -- WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); -+ WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1); - for (i = 1; i < 16; i++) { - if (i < 8) - WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), -diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c -index 0926739c9fa7..9953356fe263 100644 ---- a/drivers/gpu/drm/radeon/evergreen_hdmi.c -+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c -@@ -400,7 +400,7 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) - if (enable) { - struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - -- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { -+ if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) { - WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, - HDMI_AVI_INFO_SEND | /* enable AVI info frames */ - HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */ -@@ -438,7 +438,8 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable) - if (!dig || !dig->afmt) - return; - -- if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) { -+ if (enable && connector && -+ drm_detect_monitor_audio(radeon_connector_edid(connector))) { - struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector; -diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c -index dab00812abaa..02d585455f49 100644 ---- a/drivers/gpu/drm/radeon/ni.c -+++ b/drivers/gpu/drm/radeon/ni.c -@@ -1272,7 +1272,8 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev) - */ - for (i = 1; i < 8; i++) { - WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0); -- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn); -+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), -+ rdev->vm_manager.max_pfn - 1); - WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), - rdev->vm_manager.saved_table_addr[i]); - } -diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c -index b7c6bb69f3c7..88c04bc0a7f6 100644 ---- a/drivers/gpu/drm/radeon/radeon_audio.c -+++ b/drivers/gpu/drm/radeon/radeon_audio.c -@@ -460,9 +460,6 @@ void radeon_audio_detect(struct drm_connector *connector, - if (!connector || !connector->encoder) - return; - -- if (!radeon_encoder_is_digital(connector->encoder)) -- return; -- - rdev = connector->encoder->dev->dev_private; - - if (!radeon_audio_chipset_supported(rdev)) -@@ -471,26 +468,26 @@ void radeon_audio_detect(struct drm_connector *connector, - radeon_encoder = to_radeon_encoder(connector->encoder); - dig = radeon_encoder->enc_priv; - -- if (!dig->afmt) -- return; -- - if (status == connector_status_connected) { -- struct radeon_connector *radeon_connector = to_radeon_connector(connector); -+ struct radeon_connector *radeon_connector; -+ int sink_type; -+ -+ if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) { -+ radeon_encoder->audio = NULL; -+ return; -+ } -+ -+ radeon_connector = to_radeon_connector(connector); -+ sink_type = radeon_dp_getsinktype(radeon_connector); - - if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort && -- radeon_dp_getsinktype(radeon_connector) == -- CONNECTOR_OBJECT_ID_DISPLAYPORT) -+ sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) - radeon_encoder->audio = rdev->audio.dp_funcs; - else - radeon_encoder->audio = rdev->audio.hdmi_funcs; - - dig->afmt->pin = radeon_audio_get_pin(connector->encoder); -- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { -- radeon_audio_enable(rdev, dig->afmt->pin, 0xf); -- } else { -- radeon_audio_enable(rdev, dig->afmt->pin, 0); -- dig->afmt->pin = NULL; -- } -+ radeon_audio_enable(rdev, dig->afmt->pin, 0xf); - } else { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; -diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c -index 27973e3faf0e..27def67cb6be 100644 ---- a/drivers/gpu/drm/radeon/radeon_connectors.c -+++ b/drivers/gpu/drm/radeon/radeon_connectors.c -@@ -1333,10 +1333,8 @@ out: - /* updated in get modes as well since we need to know if it's analog or digital */ - radeon_connector_update_scratch_regs(connector, ret); - -- if (radeon_audio != 0) { -- radeon_connector_get_edid(connector); -+ if (radeon_audio != 0) - radeon_audio_detect(connector, ret); -- } - - exit: - pm_runtime_mark_last_busy(connector->dev->dev); -@@ -1661,10 +1659,8 @@ radeon_dp_detect(struct drm_connector *connector, bool force) - - radeon_connector_update_scratch_regs(connector, ret); - -- if (radeon_audio != 0) { -- radeon_connector_get_edid(connector); -+ if (radeon_audio != 0) - radeon_audio_detect(connector, ret); -- } - - out: - pm_runtime_mark_last_busy(connector->dev->dev); -diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c -index a7fb2735d4a9..f433491fab6f 100644 ---- a/drivers/gpu/drm/radeon/si.c -+++ b/drivers/gpu/drm/radeon/si.c -@@ -4288,7 +4288,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev) - /* empty context1-15 */ - /* set vm size, must be a multiple of 4 */ - WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); -- WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); -+ WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1); - /* Assign the pt base to something valid for now; the pts used for - * the VMs are determined by the application and setup and assigned - * on the fly in the vm part of radeon_gart.c -diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c -index e77658cd037c..2caf5b2f3446 100644 ---- a/drivers/hid/hid-logitech-hidpp.c -+++ b/drivers/hid/hid-logitech-hidpp.c -@@ -39,7 +39,6 @@ MODULE_AUTHOR("Nestor Lopez Casado "); - /* bits 1..20 are reserved for classes */ - #define HIDPP_QUIRK_DELAYED_INIT BIT(21) - #define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS BIT(22) --#define HIDPP_QUIRK_MULTI_INPUT BIT(23) - - /* - * There are two hidpp protocols in use, the first version hidpp10 is known -@@ -701,12 +700,6 @@ static int wtp_input_mapping(struct hid_device *hdev, struct hid_input *hi, - struct hid_field *field, struct hid_usage *usage, - unsigned long **bit, int *max) - { -- struct hidpp_device *hidpp = hid_get_drvdata(hdev); -- -- if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) && -- (field->application == HID_GD_KEYBOARD)) -- return 0; -- - return -1; - } - -@@ -715,10 +708,6 @@ static void wtp_populate_input(struct hidpp_device *hidpp, - { - struct wtp_data *wd = hidpp->private_data; - -- if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) && origin_is_hid_core) -- /* this is the generic hid-input call */ -- return; -- - __set_bit(EV_ABS, input_dev->evbit); - __set_bit(EV_KEY, input_dev->evbit); - __clear_bit(EV_REL, input_dev->evbit); -@@ -1234,10 +1223,6 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) - if (hidpp->quirks & HIDPP_QUIRK_DELAYED_INIT) - connect_mask &= ~HID_CONNECT_HIDINPUT; - -- /* Re-enable hidinput for multi-input devices */ -- if (hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) -- connect_mask |= HID_CONNECT_HIDINPUT; -- - ret = hid_hw_start(hdev, connect_mask); - if (ret) { - hid_err(hdev, "%s:hid_hw_start returned error\n", __func__); -@@ -1285,11 +1270,6 @@ static const struct hid_device_id hidpp_devices[] = { - HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, - USB_DEVICE_ID_LOGITECH_T651), - .driver_data = HIDPP_QUIRK_CLASS_WTP }, -- { /* Keyboard TK820 */ -- HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, -- USB_VENDOR_ID_LOGITECH, 0x4102), -- .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_MULTI_INPUT | -- HIDPP_QUIRK_CLASS_WTP }, - - { HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, HID_ANY_ID)}, -diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c -index f3830db02d46..37f01702d081 100644 ---- a/drivers/hwmon/nct6683.c -+++ b/drivers/hwmon/nct6683.c -@@ -439,6 +439,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg, - (*t)->dev_attr.attr.name, tg->base + i); - if ((*t)->s2) { - a2 = &su->u.a2; -+ sysfs_attr_init(&a2->dev_attr.attr); - a2->dev_attr.attr.name = su->name; - a2->nr = (*t)->u.s.nr + i; - a2->index = (*t)->u.s.index; -@@ -449,6 +450,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg, - *attrs = &a2->dev_attr.attr; - } else { - a = &su->u.a1; -+ sysfs_attr_init(&a->dev_attr.attr); - a->dev_attr.attr.name = su->name; - a->index = (*t)->u.index + i; - a->dev_attr.attr.mode = -diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c -index 1be41177b620..0773930c110e 100644 ---- a/drivers/hwmon/nct6775.c -+++ b/drivers/hwmon/nct6775.c -@@ -994,6 +994,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, - (*t)->dev_attr.attr.name, tg->base + i); - if ((*t)->s2) { - a2 = &su->u.a2; -+ sysfs_attr_init(&a2->dev_attr.attr); - a2->dev_attr.attr.name = su->name; - a2->nr = (*t)->u.s.nr + i; - a2->index = (*t)->u.s.index; -@@ -1004,6 +1005,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg, - *attrs = &a2->dev_attr.attr; - } else { - a = &su->u.a1; -+ sysfs_attr_init(&a->dev_attr.attr); - a->dev_attr.attr.name = su->name; - a->index = (*t)->u.index + i; - a->dev_attr.attr.mode = -diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c -index 112e4d45e4a0..68800115876b 100644 ---- a/drivers/hwmon/ntc_thermistor.c -+++ b/drivers/hwmon/ntc_thermistor.c -@@ -239,8 +239,10 @@ static struct ntc_thermistor_platform_data * - ntc_thermistor_parse_dt(struct platform_device *pdev) - { - struct iio_channel *chan; -+ enum iio_chan_type type; - struct device_node *np = pdev->dev.of_node; - struct ntc_thermistor_platform_data *pdata; -+ int ret; - - if (!np) - return NULL; -@@ -253,6 +255,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev) - if (IS_ERR(chan)) - return ERR_CAST(chan); - -+ ret = iio_get_channel_type(chan, &type); -+ if (ret < 0) -+ return ERR_PTR(ret); -+ -+ if (type != IIO_VOLTAGE) -+ return ERR_PTR(-EINVAL); -+ - if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv)) - return ERR_PTR(-ENODEV); - if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm)) -diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c -index 99664ebc738d..ccf4cffe0ee1 100644 ---- a/drivers/hwmon/tmp401.c -+++ b/drivers/hwmon/tmp401.c -@@ -44,7 +44,7 @@ - #include - - /* Addresses to scan */ --static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d, -+static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d, - 0x4e, 0x4f, I2C_CLIENT_END }; - - enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 }; -diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c -index 53f32629283a..6805db0e4f07 100644 ---- a/drivers/iio/accel/st_accel_core.c -+++ b/drivers/iio/accel/st_accel_core.c -@@ -465,6 +465,7 @@ int st_accel_common_probe(struct iio_dev *indio_dev) - - indio_dev->modes = INDIO_DIRECT_MODE; - indio_dev->info = &accel_info; -+ mutex_init(&adata->tb.buf_lock); - - st_sensors_power_enable(indio_dev); - -diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c -index 08bcfb061ca5..56008a86b78f 100644 ---- a/drivers/iio/adc/axp288_adc.c -+++ b/drivers/iio/adc/axp288_adc.c -@@ -53,39 +53,42 @@ static const struct iio_chan_spec const axp288_adc_channels[] = { - .channel = 0, - .address = AXP288_TS_ADC_H, - .datasheet_name = "TS_PIN", -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, { - .indexed = 1, - .type = IIO_TEMP, - .channel = 1, - .address = AXP288_PMIC_ADC_H, - .datasheet_name = "PMIC_TEMP", -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, { - .indexed = 1, - .type = IIO_TEMP, - .channel = 2, - .address = AXP288_GP_ADC_H, - .datasheet_name = "GPADC", -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, { - .indexed = 1, - .type = IIO_CURRENT, - .channel = 3, - .address = AXP20X_BATT_CHRG_I_H, - .datasheet_name = "BATT_CHG_I", -- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, { - .indexed = 1, - .type = IIO_CURRENT, - .channel = 4, - .address = AXP20X_BATT_DISCHRG_I_H, - .datasheet_name = "BATT_DISCHRG_I", -- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, { - .indexed = 1, - .type = IIO_VOLTAGE, - .channel = 5, - .address = AXP20X_BATT_V_H, - .datasheet_name = "BATT_V", -- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), -+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - }, - }; - -@@ -151,9 +154,6 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, - chan->address)) - dev_err(&indio_dev->dev, "TS pin restore\n"); - break; -- case IIO_CHAN_INFO_PROCESSED: -- ret = axp288_adc_read_channel(val, chan->address, info->regmap); -- break; - default: - ret = -EINVAL; - } -diff --git a/drivers/iio/adc/cc10001_adc.c b/drivers/iio/adc/cc10001_adc.c -index 51e2a83c9404..115f6e99a7fa 100644 ---- a/drivers/iio/adc/cc10001_adc.c -+++ b/drivers/iio/adc/cc10001_adc.c -@@ -35,8 +35,9 @@ - #define CC10001_ADC_EOC_SET BIT(0) - - #define CC10001_ADC_CHSEL_SAMPLED 0x0c --#define CC10001_ADC_POWER_UP 0x10 --#define CC10001_ADC_POWER_UP_SET BIT(0) -+#define CC10001_ADC_POWER_DOWN 0x10 -+#define CC10001_ADC_POWER_DOWN_SET BIT(0) -+ - #define CC10001_ADC_DEBUG 0x14 - #define CC10001_ADC_DATA_COUNT 0x20 - -@@ -62,7 +63,6 @@ struct cc10001_adc_device { - u16 *buf; - - struct mutex lock; -- unsigned long channel_map; - unsigned int start_delay_ns; - unsigned int eoc_delay_ns; - }; -@@ -79,6 +79,18 @@ static inline u32 cc10001_adc_read_reg(struct cc10001_adc_device *adc_dev, - return readl(adc_dev->reg_base + reg); - } - -+static void cc10001_adc_power_up(struct cc10001_adc_device *adc_dev) -+{ -+ cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN, 0); -+ ndelay(adc_dev->start_delay_ns); -+} -+ -+static void cc10001_adc_power_down(struct cc10001_adc_device *adc_dev) -+{ -+ cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN, -+ CC10001_ADC_POWER_DOWN_SET); -+} -+ - static void cc10001_adc_start(struct cc10001_adc_device *adc_dev, - unsigned int channel) - { -@@ -88,6 +100,7 @@ static void cc10001_adc_start(struct cc10001_adc_device *adc_dev, - val = (channel & CC10001_ADC_CH_MASK) | CC10001_ADC_MODE_SINGLE_CONV; - cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val); - -+ udelay(1); - val = cc10001_adc_read_reg(adc_dev, CC10001_ADC_CONFIG); - val = val | CC10001_ADC_START_CONV; - cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val); -@@ -129,6 +142,7 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p) - struct iio_dev *indio_dev; - unsigned int delay_ns; - unsigned int channel; -+ unsigned int scan_idx; - bool sample_invalid; - u16 *data; - int i; -@@ -139,20 +153,17 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p) - - mutex_lock(&adc_dev->lock); - -- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, -- CC10001_ADC_POWER_UP_SET); -- -- /* Wait for 8 (6+2) clock cycles before activating START */ -- ndelay(adc_dev->start_delay_ns); -+ cc10001_adc_power_up(adc_dev); - - /* Calculate delay step for eoc and sampled data */ - delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT; - - i = 0; - sample_invalid = false; -- for_each_set_bit(channel, indio_dev->active_scan_mask, -+ for_each_set_bit(scan_idx, indio_dev->active_scan_mask, - indio_dev->masklength) { - -+ channel = indio_dev->channels[scan_idx].channel; - cc10001_adc_start(adc_dev, channel); - - data[i] = cc10001_adc_poll_done(indio_dev, channel, delay_ns); -@@ -166,7 +177,7 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p) - } - - done: -- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0); -+ cc10001_adc_power_down(adc_dev); - - mutex_unlock(&adc_dev->lock); - -@@ -185,11 +196,7 @@ static u16 cc10001_adc_read_raw_voltage(struct iio_dev *indio_dev, - unsigned int delay_ns; - u16 val; - -- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, -- CC10001_ADC_POWER_UP_SET); -- -- /* Wait for 8 (6+2) clock cycles before activating START */ -- ndelay(adc_dev->start_delay_ns); -+ cc10001_adc_power_up(adc_dev); - - /* Calculate delay step for eoc and sampled data */ - delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT; -@@ -198,7 +205,7 @@ static u16 cc10001_adc_read_raw_voltage(struct iio_dev *indio_dev, - - val = cc10001_adc_poll_done(indio_dev, chan->channel, delay_ns); - -- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0); -+ cc10001_adc_power_down(adc_dev); - - return val; - } -@@ -224,7 +231,7 @@ static int cc10001_adc_read_raw(struct iio_dev *indio_dev, - - case IIO_CHAN_INFO_SCALE: - ret = regulator_get_voltage(adc_dev->reg); -- if (ret) -+ if (ret < 0) - return ret; - - *val = ret / 1000; -@@ -255,22 +262,22 @@ static const struct iio_info cc10001_adc_info = { - .update_scan_mode = &cc10001_update_scan_mode, - }; - --static int cc10001_adc_channel_init(struct iio_dev *indio_dev) -+static int cc10001_adc_channel_init(struct iio_dev *indio_dev, -+ unsigned long channel_map) - { -- struct cc10001_adc_device *adc_dev = iio_priv(indio_dev); - struct iio_chan_spec *chan_array, *timestamp; - unsigned int bit, idx = 0; - -- indio_dev->num_channels = bitmap_weight(&adc_dev->channel_map, -- CC10001_ADC_NUM_CHANNELS); -+ indio_dev->num_channels = bitmap_weight(&channel_map, -+ CC10001_ADC_NUM_CHANNELS) + 1; - -- chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels + 1, -+ chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels, - sizeof(struct iio_chan_spec), - GFP_KERNEL); - if (!chan_array) - return -ENOMEM; - -- for_each_set_bit(bit, &adc_dev->channel_map, CC10001_ADC_NUM_CHANNELS) { -+ for_each_set_bit(bit, &channel_map, CC10001_ADC_NUM_CHANNELS) { - struct iio_chan_spec *chan = &chan_array[idx]; - - chan->type = IIO_VOLTAGE; -@@ -305,6 +312,7 @@ static int cc10001_adc_probe(struct platform_device *pdev) - unsigned long adc_clk_rate; - struct resource *res; - struct iio_dev *indio_dev; -+ unsigned long channel_map; - int ret; - - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc_dev)); -@@ -313,9 +321,9 @@ static int cc10001_adc_probe(struct platform_device *pdev) - - adc_dev = iio_priv(indio_dev); - -- adc_dev->channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0); -+ channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0); - if (!of_property_read_u32(node, "adc-reserved-channels", &ret)) -- adc_dev->channel_map &= ~ret; -+ channel_map &= ~ret; - - adc_dev->reg = devm_regulator_get(&pdev->dev, "vref"); - if (IS_ERR(adc_dev->reg)) -@@ -361,7 +369,7 @@ static int cc10001_adc_probe(struct platform_device *pdev) - adc_dev->start_delay_ns = adc_dev->eoc_delay_ns * CC10001_WAIT_CYCLES; - - /* Setup the ADC channels available on the device */ -- ret = cc10001_adc_channel_init(indio_dev); -+ ret = cc10001_adc_channel_init(indio_dev, channel_map); - if (ret < 0) - goto err_disable_clk; - -diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c -index 3211729bcb0b..0c4618b4d515 100644 ---- a/drivers/iio/adc/qcom-spmi-vadc.c -+++ b/drivers/iio/adc/qcom-spmi-vadc.c -@@ -18,6 +18,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -471,11 +472,11 @@ static s32 vadc_calibrate(struct vadc_priv *vadc, - const struct vadc_channel_prop *prop, u16 adc_code) - { - const struct vadc_prescale_ratio *prescale; -- s32 voltage; -+ s64 voltage; - - voltage = adc_code - vadc->graph[prop->calibration].gnd; - voltage *= vadc->graph[prop->calibration].dx; -- voltage = voltage / vadc->graph[prop->calibration].dy; -+ voltage = div64_s64(voltage, vadc->graph[prop->calibration].dy); - - if (prop->calibration == VADC_CALIB_ABSOLUTE) - voltage += vadc->graph[prop->calibration].dx; -@@ -487,7 +488,7 @@ static s32 vadc_calibrate(struct vadc_priv *vadc, - - voltage = voltage * prescale->den; - -- return voltage / prescale->num; -+ return div64_s64(voltage, prescale->num); - } - - static int vadc_decimation_from_dt(u32 value) -diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c -index a221f7329b79..ce93bd8e3f68 100644 ---- a/drivers/iio/adc/xilinx-xadc-core.c -+++ b/drivers/iio/adc/xilinx-xadc-core.c -@@ -856,6 +856,7 @@ static int xadc_read_raw(struct iio_dev *indio_dev, - switch (chan->address) { - case XADC_REG_VCCINT: - case XADC_REG_VCCAUX: -+ case XADC_REG_VREFP: - case XADC_REG_VCCBRAM: - case XADC_REG_VCCPINT: - case XADC_REG_VCCPAUX: -@@ -996,7 +997,7 @@ static const struct iio_event_spec xadc_voltage_events[] = { - .num_event_specs = (_alarm) ? ARRAY_SIZE(xadc_voltage_events) : 0, \ - .scan_index = (_scan_index), \ - .scan_type = { \ -- .sign = 'u', \ -+ .sign = ((_addr) == XADC_REG_VREFN) ? 's' : 'u', \ - .realbits = 12, \ - .storagebits = 16, \ - .shift = 4, \ -@@ -1008,7 +1009,7 @@ static const struct iio_event_spec xadc_voltage_events[] = { - static const struct iio_chan_spec xadc_channels[] = { - XADC_CHAN_TEMP(0, 8, XADC_REG_TEMP), - XADC_CHAN_VOLTAGE(0, 9, XADC_REG_VCCINT, "vccint", true), -- XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCINT, "vccaux", true), -+ XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCAUX, "vccaux", true), - XADC_CHAN_VOLTAGE(2, 14, XADC_REG_VCCBRAM, "vccbram", true), - XADC_CHAN_VOLTAGE(3, 5, XADC_REG_VCCPINT, "vccpint", true), - XADC_CHAN_VOLTAGE(4, 6, XADC_REG_VCCPAUX, "vccpaux", true), -diff --git a/drivers/iio/adc/xilinx-xadc.h b/drivers/iio/adc/xilinx-xadc.h -index c7487e8d7f80..54adc5087210 100644 ---- a/drivers/iio/adc/xilinx-xadc.h -+++ b/drivers/iio/adc/xilinx-xadc.h -@@ -145,9 +145,9 @@ static inline int xadc_write_adc_reg(struct xadc *xadc, unsigned int reg, - #define XADC_REG_MAX_VCCPINT 0x28 - #define XADC_REG_MAX_VCCPAUX 0x29 - #define XADC_REG_MAX_VCCO_DDR 0x2a --#define XADC_REG_MIN_VCCPINT 0x2b --#define XADC_REG_MIN_VCCPAUX 0x2c --#define XADC_REG_MIN_VCCO_DDR 0x2d -+#define XADC_REG_MIN_VCCPINT 0x2c -+#define XADC_REG_MIN_VCCPAUX 0x2d -+#define XADC_REG_MIN_VCCO_DDR 0x2e - - #define XADC_REG_CONF0 0x40 - #define XADC_REG_CONF1 0x41 -diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c -index edd13d2b4121..8dd0477e201c 100644 ---- a/drivers/iio/common/st_sensors/st_sensors_core.c -+++ b/drivers/iio/common/st_sensors/st_sensors_core.c -@@ -304,8 +304,6 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, - struct st_sensors_platform_data *of_pdata; - int err = 0; - -- mutex_init(&sdata->tb.buf_lock); -- - /* If OF/DT pdata exists, it will take precedence of anything else */ - of_pdata = st_sensors_of_probe(indio_dev->dev.parent, pdata); - if (of_pdata) -diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c -index f07a2336f7dc..566f7d2df031 100644 ---- a/drivers/iio/gyro/st_gyro_core.c -+++ b/drivers/iio/gyro/st_gyro_core.c -@@ -317,6 +317,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) - - indio_dev->modes = INDIO_DIRECT_MODE; - indio_dev->info = &gyro_info; -+ mutex_init(&gdata->tb.buf_lock); - - st_sensors_power_enable(indio_dev); - -diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c -index 3ecf79ed08ac..88f21bbe947c 100644 ---- a/drivers/iio/light/hid-sensor-prox.c -+++ b/drivers/iio/light/hid-sensor-prox.c -@@ -43,8 +43,6 @@ struct prox_state { - static const struct iio_chan_spec prox_channels[] = { - { - .type = IIO_PROXIMITY, -- .modified = 1, -- .channel2 = IIO_NO_MOD, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | - BIT(IIO_CHAN_INFO_SCALE) | -diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c -index 8ade473f99fe..2e56f812a644 100644 ---- a/drivers/iio/magnetometer/st_magn_core.c -+++ b/drivers/iio/magnetometer/st_magn_core.c -@@ -369,6 +369,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev) - - indio_dev->modes = INDIO_DIRECT_MODE; - indio_dev->info = &magn_info; -+ mutex_init(&mdata->tb.buf_lock); - - st_sensors_power_enable(indio_dev); - -diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c -index 1af314926ebd..476a7d03d2ce 100644 ---- a/drivers/iio/pressure/hid-sensor-press.c -+++ b/drivers/iio/pressure/hid-sensor-press.c -@@ -47,8 +47,6 @@ struct press_state { - static const struct iio_chan_spec press_channels[] = { - { - .type = IIO_PRESSURE, -- .modified = 1, -- .channel2 = IIO_NO_MOD, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) | - BIT(IIO_CHAN_INFO_SCALE) | -diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c -index 97baf40d424b..e881fa6291e9 100644 ---- a/drivers/iio/pressure/st_pressure_core.c -+++ b/drivers/iio/pressure/st_pressure_core.c -@@ -417,6 +417,7 @@ int st_press_common_probe(struct iio_dev *indio_dev) - - indio_dev->modes = INDIO_DIRECT_MODE; - indio_dev->info = &press_info; -+ mutex_init(&press_data->tb.buf_lock); - - st_sensors_power_enable(indio_dev); - -diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c -index b85ddbc979e0..e5558b2660f2 100644 ---- a/drivers/infiniband/core/iwpm_msg.c -+++ b/drivers/infiniband/core/iwpm_msg.c -@@ -33,7 +33,7 @@ - - #include "iwpm_util.h" - --static const char iwpm_ulib_name[] = "iWarpPortMapperUser"; -+static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser"; - static int iwpm_ulib_version = 3; - static int iwpm_user_pid = IWPM_PID_UNDEFINED; - static atomic_t echo_nlmsg_seq; -diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c -index 991dc6b20a58..79363b687195 100644 ---- a/drivers/input/mouse/elantech.c -+++ b/drivers/input/mouse/elantech.c -@@ -315,7 +315,7 @@ static void elantech_report_semi_mt_data(struct input_dev *dev, - unsigned int x2, unsigned int y2) - { - elantech_set_slot(dev, 0, num_fingers != 0, x1, y1); -- elantech_set_slot(dev, 1, num_fingers == 2, x2, y2); -+ elantech_set_slot(dev, 1, num_fingers >= 2, x2, y2); - } - - /* -diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c -index 6d5a5c44453b..173e70dbf61b 100644 ---- a/drivers/iommu/amd_iommu_v2.c -+++ b/drivers/iommu/amd_iommu_v2.c -@@ -266,6 +266,7 @@ static void put_pasid_state(struct pasid_state *pasid_state) - - static void put_pasid_state_wait(struct pasid_state *pasid_state) - { -+ atomic_dec(&pasid_state->count); - wait_event(pasid_state->wq, !atomic_read(&pasid_state->count)); - free_pasid_state(pasid_state); - } -diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c -index a3adde6519f0..bd6252b01510 100644 ---- a/drivers/iommu/arm-smmu.c -+++ b/drivers/iommu/arm-smmu.c -@@ -224,14 +224,7 @@ - #define RESUME_TERMINATE (1 << 0) - - #define TTBCR2_SEP_SHIFT 15 --#define TTBCR2_SEP_MASK 0x7 -- --#define TTBCR2_ADDR_32 0 --#define TTBCR2_ADDR_36 1 --#define TTBCR2_ADDR_40 2 --#define TTBCR2_ADDR_42 3 --#define TTBCR2_ADDR_44 4 --#define TTBCR2_ADDR_48 5 -+#define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT) - - #define TTBRn_HI_ASID_SHIFT 16 - -@@ -783,26 +776,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, - writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR); - if (smmu->version > ARM_SMMU_V1) { - reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32; -- switch (smmu->va_size) { -- case 32: -- reg |= (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT); -- break; -- case 36: -- reg |= (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT); -- break; -- case 40: -- reg |= (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT); -- break; -- case 42: -- reg |= (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT); -- break; -- case 44: -- reg |= (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT); -- break; -- case 48: -- reg |= (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT); -- break; -- } -+ reg |= TTBCR2_SEP_UPSTREAM; - writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2); - } - } else { -diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c -index 7dc93aa004c8..312ffd3d0017 100644 ---- a/drivers/lguest/core.c -+++ b/drivers/lguest/core.c -@@ -173,7 +173,7 @@ static void unmap_switcher(void) - bool lguest_address_ok(const struct lguest *lg, - unsigned long addr, unsigned long len) - { -- return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr); -+ return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr); - } - - /* -diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c -index 6554d9148927..757f1ba34c4d 100644 ---- a/drivers/md/dm-table.c -+++ b/drivers/md/dm-table.c -@@ -823,6 +823,12 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args) - } - EXPORT_SYMBOL(dm_consume_args); - -+static bool __table_type_request_based(unsigned table_type) -+{ -+ return (table_type == DM_TYPE_REQUEST_BASED || -+ table_type == DM_TYPE_MQ_REQUEST_BASED); -+} -+ - static int dm_table_set_type(struct dm_table *t) - { - unsigned i; -@@ -855,8 +861,7 @@ static int dm_table_set_type(struct dm_table *t) - * Determine the type from the live device. - * Default to bio-based if device is new. - */ -- if (live_md_type == DM_TYPE_REQUEST_BASED || -- live_md_type == DM_TYPE_MQ_REQUEST_BASED) -+ if (__table_type_request_based(live_md_type)) - request_based = 1; - else - bio_based = 1; -@@ -906,7 +911,7 @@ static int dm_table_set_type(struct dm_table *t) - } - t->type = DM_TYPE_MQ_REQUEST_BASED; - -- } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) { -+ } else if (list_empty(devices) && __table_type_request_based(live_md_type)) { - /* inherit live MD type */ - t->type = live_md_type; - -@@ -928,10 +933,7 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t) - - bool dm_table_request_based(struct dm_table *t) - { -- unsigned table_type = dm_table_get_type(t); -- -- return (table_type == DM_TYPE_REQUEST_BASED || -- table_type == DM_TYPE_MQ_REQUEST_BASED); -+ return __table_type_request_based(dm_table_get_type(t)); - } - - bool dm_table_mq_request_based(struct dm_table *t) -diff --git a/drivers/md/dm.c b/drivers/md/dm.c -index 8001fe9e3434..9b4e30a82e4a 100644 ---- a/drivers/md/dm.c -+++ b/drivers/md/dm.c -@@ -1642,8 +1642,7 @@ static int dm_merge_bvec(struct request_queue *q, - struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table_fast(md); - struct dm_target *ti; -- sector_t max_sectors; -- int max_size = 0; -+ sector_t max_sectors, max_size = 0; - - if (unlikely(!map)) - goto out; -@@ -1658,8 +1657,16 @@ static int dm_merge_bvec(struct request_queue *q, - max_sectors = min(max_io_len(bvm->bi_sector, ti), - (sector_t) queue_max_sectors(q)); - max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; -- if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */ -- max_size = 0; -+ -+ /* -+ * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t -+ * to the targets' merge function since it holds sectors not bytes). -+ * Just doing this as an interim fix for stable@ because the more -+ * comprehensive cleanup of switching to sector_t will impact every -+ * DM target that implements a ->merge hook. -+ */ -+ if (max_size > INT_MAX) -+ max_size = INT_MAX; - - /* - * merge_bvec_fn() returns number of bytes -@@ -1667,7 +1674,7 @@ static int dm_merge_bvec(struct request_queue *q, - * max is precomputed maximal io size - */ - if (max_size && ti->type->merge) -- max_size = ti->type->merge(ti, bvm, biovec, max_size); -+ max_size = ti->type->merge(ti, bvm, biovec, (int) max_size); - /* - * If the target doesn't support merge method and some of the devices - * provided their merge_bvec method (we know this by looking for the -diff --git a/drivers/md/md.c b/drivers/md/md.c -index e47d1dd046da..907534b7f40d 100644 ---- a/drivers/md/md.c -+++ b/drivers/md/md.c -@@ -4138,12 +4138,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) - if (!mddev->pers || !mddev->pers->sync_request) - return -EINVAL; - -- if (cmd_match(page, "frozen")) -- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); -- else -- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - - if (cmd_match(page, "idle") || cmd_match(page, "frozen")) { -+ if (cmd_match(page, "frozen")) -+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); -+ else -+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - flush_workqueue(md_misc_wq); - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); -@@ -4156,16 +4156,17 @@ action_store(struct mddev *mddev, const char *page, size_t len) - test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) - return -EBUSY; - else if (cmd_match(page, "resync")) -- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); -+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else if (cmd_match(page, "recover")) { -+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); -- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - } else if (cmd_match(page, "reshape")) { - int err; - if (mddev->pers->start_reshape == NULL) - return -EINVAL; - err = mddev_lock(mddev); - if (!err) { -+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - err = mddev->pers->start_reshape(mddev); - mddev_unlock(mddev); - } -@@ -4177,6 +4178,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) - set_bit(MD_RECOVERY_CHECK, &mddev->recovery); - else if (!cmd_match(page, "repair")) - return -EINVAL; -+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); - set_bit(MD_RECOVERY_SYNC, &mddev->recovery); - } -diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c -index 3b5d7f704aa3..903391ce9353 100644 ---- a/drivers/md/raid0.c -+++ b/drivers/md/raid0.c -@@ -517,6 +517,9 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) - ? (sector & (chunk_sects-1)) - : sector_div(sector, chunk_sects)); - -+ /* Restore due to sector_div */ -+ sector = bio->bi_iter.bi_sector; -+ - if (sectors < bio_sectors(bio)) { - split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set); - bio_chain(split, bio); -@@ -524,7 +527,6 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) - split = bio; - } - -- sector = bio->bi_iter.bi_sector; - zone = find_zone(mddev->private, §or); - tmp_dev = map_sector(mddev, zone, sector, §or); - split->bi_bdev = tmp_dev->bdev; -diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c -index cd2f96b2c572..007ab861eca0 100644 ---- a/drivers/md/raid5.c -+++ b/drivers/md/raid5.c -@@ -1933,7 +1933,8 @@ static int resize_stripes(struct r5conf *conf, int newsize) - - conf->slab_cache = sc; - conf->active_name = 1-conf->active_name; -- conf->pool_size = newsize; -+ if (!err) -+ conf->pool_size = newsize; - return err; - } - -diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c -index ae498b53ee40..46e3840c7a37 100644 ---- a/drivers/mfd/da9052-core.c -+++ b/drivers/mfd/da9052-core.c -@@ -433,6 +433,10 @@ EXPORT_SYMBOL_GPL(da9052_adc_read_temp); - static const struct mfd_cell da9052_subdev_info[] = { - { - .name = "da9052-regulator", -+ .id = 0, -+ }, -+ { -+ .name = "da9052-regulator", - .id = 1, - }, - { -@@ -484,10 +488,6 @@ static const struct mfd_cell da9052_subdev_info[] = { - .id = 13, - }, - { -- .name = "da9052-regulator", -- .id = 14, -- }, -- { - .name = "da9052-onkey", - }, - { -diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c -index 03d7c7521d97..9a39e0b7e583 100644 ---- a/drivers/mmc/host/atmel-mci.c -+++ b/drivers/mmc/host/atmel-mci.c -@@ -1304,7 +1304,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) - - if (ios->clock) { - unsigned int clock_min = ~0U; -- u32 clkdiv; -+ int clkdiv; - - spin_lock_bh(&host->lock); - if (!host->mode_reg) { -@@ -1328,7 +1328,12 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) - /* Calculate clock divider */ - if (host->caps.has_odd_clk_div) { - clkdiv = DIV_ROUND_UP(host->bus_hz, clock_min) - 2; -- if (clkdiv > 511) { -+ if (clkdiv < 0) { -+ dev_warn(&mmc->class_dev, -+ "clock %u too fast; using %lu\n", -+ clock_min, host->bus_hz / 2); -+ clkdiv = 0; -+ } else if (clkdiv > 511) { - dev_warn(&mmc->class_dev, - "clock %u too slow; using %lu\n", - clock_min, host->bus_hz / (511 + 2)); -diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c -index db2c05b6fe7f..c9eb78f10a0d 100644 ---- a/drivers/mtd/ubi/block.c -+++ b/drivers/mtd/ubi/block.c -@@ -310,6 +310,8 @@ static void ubiblock_do_work(struct work_struct *work) - blk_rq_map_sg(req->q, req, pdu->usgl.sg); - - ret = ubiblock_read(pdu); -+ rq_flush_dcache_pages(req); -+ - blk_mq_end_request(req, ret); - } - -diff --git a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c -index 6262612dec45..7a3231d8b933 100644 ---- a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c -+++ b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c -@@ -512,11 +512,9 @@ static int brcmf_msgbuf_query_dcmd(struct brcmf_pub *drvr, int ifidx, - msgbuf->rx_pktids, - msgbuf->ioctl_resp_pktid); - if (msgbuf->ioctl_resp_ret_len != 0) { -- if (!skb) { -- brcmf_err("Invalid packet id idx recv'd %d\n", -- msgbuf->ioctl_resp_pktid); -+ if (!skb) - return -EBADF; -- } -+ - memcpy(buf, skb->data, (len < msgbuf->ioctl_resp_ret_len) ? - len : msgbuf->ioctl_resp_ret_len); - } -@@ -875,10 +873,8 @@ brcmf_msgbuf_process_txstatus(struct brcmf_msgbuf *msgbuf, void *buf) - flowid -= BRCMF_NROF_H2D_COMMON_MSGRINGS; - skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev, - msgbuf->tx_pktids, idx); -- if (!skb) { -- brcmf_err("Invalid packet id idx recv'd %d\n", idx); -+ if (!skb) - return; -- } - - set_bit(flowid, msgbuf->txstatus_done_map); - commonring = msgbuf->flowrings[flowid]; -@@ -1157,6 +1153,8 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf) - - skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev, - msgbuf->rx_pktids, idx); -+ if (!skb) -+ return; - - if (data_offset) - skb_pull(skb, data_offset); -diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c -index 14e8fd661889..fd5a0bb1493f 100644 ---- a/drivers/net/wireless/iwlwifi/mvm/d3.c -+++ b/drivers/net/wireless/iwlwifi/mvm/d3.c -@@ -1742,8 +1742,10 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, - int i, j, n_matches, ret; - - fw_status = iwl_mvm_get_wakeup_status(mvm, vif); -- if (!IS_ERR_OR_NULL(fw_status)) -+ if (!IS_ERR_OR_NULL(fw_status)) { - reasons = le32_to_cpu(fw_status->wakeup_reasons); -+ kfree(fw_status); -+ } - - if (reasons & IWL_WOWLAN_WAKEUP_BY_RFKILL_DEASSERTED) - wakeup.rfkill_release = true; -@@ -1860,15 +1862,15 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) - /* get the BSS vif pointer again */ - vif = iwl_mvm_get_bss_vif(mvm); - if (IS_ERR_OR_NULL(vif)) -- goto out_unlock; -+ goto err; - - ret = iwl_trans_d3_resume(mvm->trans, &d3_status, test); - if (ret) -- goto out_unlock; -+ goto err; - - if (d3_status != IWL_D3_STATUS_ALIVE) { - IWL_INFO(mvm, "Device was reset during suspend\n"); -- goto out_unlock; -+ goto err; - } - - /* query SRAM first in case we want event logging */ -@@ -1886,7 +1888,8 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) - /* has unlocked the mutex, so skip that */ - goto out; - -- out_unlock: -+err: -+ iwl_mvm_free_nd(mvm); - mutex_unlock(&mvm->mutex); - - out: -diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c -index 69935aa5a1b3..cb72edb3d16a 100644 ---- a/drivers/net/wireless/iwlwifi/pcie/trans.c -+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c -@@ -5,8 +5,8 @@ - * - * GPL LICENSE SUMMARY - * -- * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved. -- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH -+ * Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved. -+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as -@@ -31,8 +31,8 @@ - * - * BSD LICENSE - * -- * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. -- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH -+ * Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved. -+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without -@@ -104,7 +104,7 @@ static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans) - static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans) - { - struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); -- struct page *page; -+ struct page *page = NULL; - dma_addr_t phys; - u32 size; - u8 power; -@@ -131,6 +131,7 @@ static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans) - DMA_FROM_DEVICE); - if (dma_mapping_error(trans->dev, phys)) { - __free_pages(page, order); -+ page = NULL; - continue; - } - IWL_INFO(trans, -diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c -index 8444313eabe2..8694dddcce9a 100644 ---- a/drivers/net/wireless/rt2x00/rt2800usb.c -+++ b/drivers/net/wireless/rt2x00/rt2800usb.c -@@ -1040,6 +1040,7 @@ static struct usb_device_id rt2800usb_device_table[] = { - { USB_DEVICE(0x07d1, 0x3c17) }, - { USB_DEVICE(0x2001, 0x3317) }, - { USB_DEVICE(0x2001, 0x3c1b) }, -+ { USB_DEVICE(0x2001, 0x3c25) }, - /* Draytek */ - { USB_DEVICE(0x07fa, 0x7712) }, - /* DVICO */ -diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c -index 46ee956d0235..27cd6cabf6c5 100644 ---- a/drivers/net/wireless/rtlwifi/usb.c -+++ b/drivers/net/wireless/rtlwifi/usb.c -@@ -126,7 +126,7 @@ static int _usbctrl_vendorreq_sync_read(struct usb_device *udev, u8 request, - - do { - status = usb_control_msg(udev, pipe, request, reqtype, value, -- index, pdata, len, 0); /*max. timeout*/ -+ index, pdata, len, 1000); - if (status < 0) { - /* firmware download is checksumed, don't retry */ - if ((value >= FW_8192C_START_ADDRESS && -diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c -index 13584e24736a..4d7d60e593b8 100644 ---- a/drivers/power/reset/at91-reset.c -+++ b/drivers/power/reset/at91-reset.c -@@ -212,9 +212,9 @@ static int at91_reset_platform_probe(struct platform_device *pdev) - res = platform_get_resource(pdev, IORESOURCE_MEM, idx + 1 ); - at91_ramc_base[idx] = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); -- if (IS_ERR(at91_ramc_base[idx])) { -+ if (!at91_ramc_base[idx]) { - dev_err(&pdev->dev, "Could not map ram controller address\n"); -- return PTR_ERR(at91_ramc_base[idx]); -+ return -ENOMEM; - } - } - -diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c -index 476171a768d6..8a029f9bc18c 100644 ---- a/drivers/pwm/pwm-img.c -+++ b/drivers/pwm/pwm-img.c -@@ -16,6 +16,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -38,7 +39,22 @@ - #define PERIP_PWM_PDM_CONTROL_CH_MASK 0x1 - #define PERIP_PWM_PDM_CONTROL_CH_SHIFT(ch) ((ch) * 4) - --#define MAX_TMBASE_STEPS 65536 -+/* -+ * PWM period is specified with a timebase register, -+ * in number of step periods. The PWM duty cycle is also -+ * specified in step periods, in the [0, $timebase] range. -+ * In other words, the timebase imposes the duty cycle -+ * resolution. Therefore, let's constraint the timebase to -+ * a minimum value to allow a sane range of duty cycle values. -+ * Imposing a minimum timebase, will impose a maximum PWM frequency. -+ * -+ * The value chosen is completely arbitrary. -+ */ -+#define MIN_TMBASE_STEPS 16 -+ -+struct img_pwm_soc_data { -+ u32 max_timebase; -+}; - - struct img_pwm_chip { - struct device *dev; -@@ -47,6 +63,9 @@ struct img_pwm_chip { - struct clk *sys_clk; - void __iomem *base; - struct regmap *periph_regs; -+ int max_period_ns; -+ int min_period_ns; -+ const struct img_pwm_soc_data *data; - }; - - static inline struct img_pwm_chip *to_img_pwm_chip(struct pwm_chip *chip) -@@ -72,24 +91,31 @@ static int img_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, - u32 val, div, duty, timebase; - unsigned long mul, output_clk_hz, input_clk_hz; - struct img_pwm_chip *pwm_chip = to_img_pwm_chip(chip); -+ unsigned int max_timebase = pwm_chip->data->max_timebase; -+ -+ if (period_ns < pwm_chip->min_period_ns || -+ period_ns > pwm_chip->max_period_ns) { -+ dev_err(chip->dev, "configured period not in range\n"); -+ return -ERANGE; -+ } - - input_clk_hz = clk_get_rate(pwm_chip->pwm_clk); - output_clk_hz = DIV_ROUND_UP(NSEC_PER_SEC, period_ns); - - mul = DIV_ROUND_UP(input_clk_hz, output_clk_hz); -- if (mul <= MAX_TMBASE_STEPS) { -+ if (mul <= max_timebase) { - div = PWM_CTRL_CFG_NO_SUB_DIV; - timebase = DIV_ROUND_UP(mul, 1); -- } else if (mul <= MAX_TMBASE_STEPS * 8) { -+ } else if (mul <= max_timebase * 8) { - div = PWM_CTRL_CFG_SUB_DIV0; - timebase = DIV_ROUND_UP(mul, 8); -- } else if (mul <= MAX_TMBASE_STEPS * 64) { -+ } else if (mul <= max_timebase * 64) { - div = PWM_CTRL_CFG_SUB_DIV1; - timebase = DIV_ROUND_UP(mul, 64); -- } else if (mul <= MAX_TMBASE_STEPS * 512) { -+ } else if (mul <= max_timebase * 512) { - div = PWM_CTRL_CFG_SUB_DIV0_DIV1; - timebase = DIV_ROUND_UP(mul, 512); -- } else if (mul > MAX_TMBASE_STEPS * 512) { -+ } else if (mul > max_timebase * 512) { - dev_err(chip->dev, - "failed to configure timebase steps/divider value\n"); - return -EINVAL; -@@ -143,11 +169,27 @@ static const struct pwm_ops img_pwm_ops = { - .owner = THIS_MODULE, - }; - -+static const struct img_pwm_soc_data pistachio_pwm = { -+ .max_timebase = 255, -+}; -+ -+static const struct of_device_id img_pwm_of_match[] = { -+ { -+ .compatible = "img,pistachio-pwm", -+ .data = &pistachio_pwm, -+ }, -+ { } -+}; -+MODULE_DEVICE_TABLE(of, img_pwm_of_match); -+ - static int img_pwm_probe(struct platform_device *pdev) - { - int ret; -+ u64 val; -+ unsigned long clk_rate; - struct resource *res; - struct img_pwm_chip *pwm; -+ const struct of_device_id *of_dev_id; - - pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL); - if (!pwm) -@@ -160,6 +202,11 @@ static int img_pwm_probe(struct platform_device *pdev) - if (IS_ERR(pwm->base)) - return PTR_ERR(pwm->base); - -+ of_dev_id = of_match_device(img_pwm_of_match, &pdev->dev); -+ if (!of_dev_id) -+ return -ENODEV; -+ pwm->data = of_dev_id->data; -+ - pwm->periph_regs = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "img,cr-periph"); - if (IS_ERR(pwm->periph_regs)) -@@ -189,6 +236,17 @@ static int img_pwm_probe(struct platform_device *pdev) - goto disable_sysclk; - } - -+ clk_rate = clk_get_rate(pwm->pwm_clk); -+ -+ /* The maximum input clock divider is 512 */ -+ val = (u64)NSEC_PER_SEC * 512 * pwm->data->max_timebase; -+ do_div(val, clk_rate); -+ pwm->max_period_ns = val; -+ -+ val = (u64)NSEC_PER_SEC * MIN_TMBASE_STEPS; -+ do_div(val, clk_rate); -+ pwm->min_period_ns = val; -+ - pwm->chip.dev = &pdev->dev; - pwm->chip.ops = &img_pwm_ops; - pwm->chip.base = -1; -@@ -228,12 +286,6 @@ static int img_pwm_remove(struct platform_device *pdev) - return pwmchip_remove(&pwm_chip->chip); - } - --static const struct of_device_id img_pwm_of_match[] = { -- { .compatible = "img,pistachio-pwm", }, -- { } --}; --MODULE_DEVICE_TABLE(of, img_pwm_of_match); -- - static struct platform_driver img_pwm_driver = { - .driver = { - .name = "img-pwm", -diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c -index 8a4df7a1f2ee..e628d4c2f2ae 100644 ---- a/drivers/regulator/da9052-regulator.c -+++ b/drivers/regulator/da9052-regulator.c -@@ -394,6 +394,7 @@ static inline struct da9052_regulator_info *find_regulator_info(u8 chip_id, - - static int da9052_regulator_probe(struct platform_device *pdev) - { -+ const struct mfd_cell *cell = mfd_get_cell(pdev); - struct regulator_config config = { }; - struct da9052_regulator *regulator; - struct da9052 *da9052; -@@ -409,7 +410,7 @@ static int da9052_regulator_probe(struct platform_device *pdev) - regulator->da9052 = da9052; - - regulator->info = find_regulator_info(regulator->da9052->chip_id, -- pdev->id); -+ cell->id); - if (regulator->info == NULL) { - dev_err(&pdev->dev, "invalid regulator ID specified\n"); - return -EINVAL; -@@ -419,7 +420,7 @@ static int da9052_regulator_probe(struct platform_device *pdev) - config.driver_data = regulator; - config.regmap = da9052->regmap; - if (pdata && pdata->regulators) { -- config.init_data = pdata->regulators[pdev->id]; -+ config.init_data = pdata->regulators[cell->id]; - } else { - #ifdef CONFIG_OF - struct device_node *nproot = da9052->dev->of_node; -diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c -index 3290a3ed5b31..a661d339adf7 100644 ---- a/drivers/scsi/sd.c -+++ b/drivers/scsi/sd.c -@@ -1624,6 +1624,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) - { - u64 start_lba = blk_rq_pos(scmd->request); - u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512); -+ u64 factor = scmd->device->sector_size / 512; - u64 bad_lba; - int info_valid; - /* -@@ -1645,16 +1646,9 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) - if (scsi_bufflen(scmd) <= scmd->device->sector_size) - return 0; - -- if (scmd->device->sector_size < 512) { -- /* only legitimate sector_size here is 256 */ -- start_lba <<= 1; -- end_lba <<= 1; -- } else { -- /* be careful ... don't want any overflows */ -- unsigned int factor = scmd->device->sector_size / 512; -- do_div(start_lba, factor); -- do_div(end_lba, factor); -- } -+ /* be careful ... don't want any overflows */ -+ do_div(start_lba, factor); -+ do_div(end_lba, factor); - - /* The bad lba was reported incorrectly, we have no idea where - * the error is. -@@ -2212,8 +2206,7 @@ got_data: - if (sector_size != 512 && - sector_size != 1024 && - sector_size != 2048 && -- sector_size != 4096 && -- sector_size != 256) { -+ sector_size != 4096) { - sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n", - sector_size); - /* -@@ -2268,8 +2261,6 @@ got_data: - sdkp->capacity <<= 2; - else if (sector_size == 1024) - sdkp->capacity <<= 1; -- else if (sector_size == 256) -- sdkp->capacity >>= 1; - - blk_queue_physical_block_size(sdp->request_queue, - sdkp->physical_block_size); -diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c -index bf8c5c1e254e..75efaaeb0eca 100644 ---- a/drivers/scsi/storvsc_drv.c -+++ b/drivers/scsi/storvsc_drv.c -@@ -1565,8 +1565,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) - break; - default: - vm_srb->data_in = UNKNOWN_TYPE; -- vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN | -- SRB_FLAGS_DATA_OUT); -+ vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER; - break; - } - -diff --git a/drivers/staging/gdm724x/gdm_mux.c b/drivers/staging/gdm724x/gdm_mux.c -index d1ab996b3305..a21a51efaad0 100644 ---- a/drivers/staging/gdm724x/gdm_mux.c -+++ b/drivers/staging/gdm724x/gdm_mux.c -@@ -158,7 +158,7 @@ static int up_to_host(struct mux_rx *r) - unsigned int start_flag; - unsigned int payload_size; - unsigned short packet_type; -- int dummy_cnt; -+ int total_len; - u32 packet_size_sum = r->offset; - int index; - int ret = TO_HOST_INVALID_PACKET; -@@ -176,10 +176,10 @@ static int up_to_host(struct mux_rx *r) - break; - } - -- dummy_cnt = ALIGN(MUX_HEADER_SIZE + payload_size, 4); -+ total_len = ALIGN(MUX_HEADER_SIZE + payload_size, 4); - - if (len - packet_size_sum < -- MUX_HEADER_SIZE + payload_size + dummy_cnt) { -+ total_len) { - pr_err("invalid payload : %d %d %04x\n", - payload_size, len, packet_type); - break; -@@ -202,7 +202,7 @@ static int up_to_host(struct mux_rx *r) - break; - } - -- packet_size_sum += MUX_HEADER_SIZE + payload_size + dummy_cnt; -+ packet_size_sum += total_len; - if (len - packet_size_sum <= MUX_HEADER_SIZE + 2) { - ret = r->callback(NULL, - 0, -@@ -361,7 +361,6 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, - struct mux_pkt_header *mux_header; - struct mux_tx *t = NULL; - static u32 seq_num = 1; -- int dummy_cnt; - int total_len; - int ret; - unsigned long flags; -@@ -374,9 +373,7 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, - - spin_lock_irqsave(&mux_dev->write_lock, flags); - -- dummy_cnt = ALIGN(MUX_HEADER_SIZE + len, 4); -- -- total_len = len + MUX_HEADER_SIZE + dummy_cnt; -+ total_len = ALIGN(MUX_HEADER_SIZE + len, 4); - - t = alloc_mux_tx(total_len); - if (!t) { -@@ -392,7 +389,8 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index, - mux_header->packet_type = __cpu_to_le16(packet_type[tty_index]); - - memcpy(t->buf+MUX_HEADER_SIZE, data, len); -- memset(t->buf+MUX_HEADER_SIZE+len, 0, dummy_cnt); -+ memset(t->buf+MUX_HEADER_SIZE+len, 0, total_len - MUX_HEADER_SIZE - -+ len); - - t->len = total_len; - t->callback = cb; -diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c -index 03b2a90b9ac0..992236f605d8 100644 ---- a/drivers/staging/vt6655/device_main.c -+++ b/drivers/staging/vt6655/device_main.c -@@ -911,7 +911,11 @@ static int vnt_int_report_rate(struct vnt_private *priv, - - if (!(tsr1 & TSR1_TERR)) { - info->status.rates[0].idx = idx; -- info->flags |= IEEE80211_TX_STAT_ACK; -+ -+ if (info->flags & IEEE80211_TX_CTL_NO_ACK) -+ info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED; -+ else -+ info->flags |= IEEE80211_TX_STAT_ACK; - } - - return 0; -@@ -936,9 +940,6 @@ static int device_tx_srv(struct vnt_private *pDevice, unsigned int uIdx) - //Only the status of first TD in the chain is correct - if (pTD->m_td1TD1.byTCR & TCR_STP) { - if ((pTD->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB) != 0) { -- -- vnt_int_report_rate(pDevice, pTD->pTDInfo, byTsr0, byTsr1); -- - if (!(byTsr1 & TSR1_TERR)) { - if (byTsr0 != 0) { - pr_debug(" Tx[%d] OK but has error. tsr1[%02X] tsr0[%02X]\n", -@@ -957,6 +958,9 @@ static int device_tx_srv(struct vnt_private *pDevice, unsigned int uIdx) - (int)uIdx, byTsr1, byTsr0); - } - } -+ -+ vnt_int_report_rate(pDevice, pTD->pTDInfo, byTsr0, byTsr1); -+ - device_free_tx_buf(pDevice, pTD); - pDevice->iTDUsed[uIdx]--; - } -@@ -988,10 +992,8 @@ static void device_free_tx_buf(struct vnt_private *pDevice, PSTxDesc pDesc) - PCI_DMA_TODEVICE); - } - -- if (pTDInfo->byFlags & TD_FLAGS_NETIF_SKB) -+ if (skb) - ieee80211_tx_status_irqsafe(pDevice->hw, skb); -- else -- dev_kfree_skb_irq(skb); - - pTDInfo->skb_dma = 0; - pTDInfo->skb = NULL; -@@ -1201,14 +1203,6 @@ static int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) - if (dma_idx == TYPE_AC0DMA) - head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB; - -- priv->iTDUsed[dma_idx]++; -- -- /* Take ownership */ -- wmb(); -- head_td->m_td0TD0.f1Owner = OWNED_BY_NIC; -- -- /* get Next */ -- wmb(); - priv->apCurrTD[dma_idx] = head_td->next; - - spin_unlock_irqrestore(&priv->lock, flags); -@@ -1229,11 +1223,18 @@ static int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) - - head_td->buff_addr = cpu_to_le32(head_td->pTDInfo->skb_dma); - -+ /* Poll Transmit the adapter */ -+ wmb(); -+ head_td->m_td0TD0.f1Owner = OWNED_BY_NIC; -+ wmb(); /* second memory barrier */ -+ - if (head_td->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB) - MACvTransmitAC0(priv->PortOffset); - else - MACvTransmit0(priv->PortOffset); - -+ priv->iTDUsed[dma_idx]++; -+ - spin_unlock_irqrestore(&priv->lock, flags); - - return 0; -@@ -1413,9 +1414,16 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw, - - priv->current_aid = conf->aid; - -- if (changed & BSS_CHANGED_BSSID) -+ if (changed & BSS_CHANGED_BSSID) { -+ unsigned long flags; -+ -+ spin_lock_irqsave(&priv->lock, flags); -+ - MACvWriteBSSIDAddress(priv->PortOffset, (u8 *)conf->bssid); - -+ spin_unlock_irqrestore(&priv->lock, flags); -+ } -+ - if (changed & BSS_CHANGED_BASIC_RATES) { - priv->basic_rates = conf->basic_rates; - -diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c -index 33baf26de4b5..ee9ce165dcde 100644 ---- a/drivers/staging/vt6656/rxtx.c -+++ b/drivers/staging/vt6656/rxtx.c -@@ -805,10 +805,18 @@ int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) - vnt_schedule_command(priv, WLAN_CMD_SETPOWER); - } - -- if (current_rate > RATE_11M) -- pkt_type = priv->packet_type; -- else -+ if (current_rate > RATE_11M) { -+ if (info->band == IEEE80211_BAND_5GHZ) { -+ pkt_type = PK_TYPE_11A; -+ } else { -+ if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT) -+ pkt_type = PK_TYPE_11GB; -+ else -+ pkt_type = PK_TYPE_11GA; -+ } -+ } else { - pkt_type = PK_TYPE_11B; -+ } - - spin_lock_irqsave(&priv->lock, flags); - -diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c -index f6c954c4635f..4073869d2090 100644 ---- a/drivers/target/target_core_pscsi.c -+++ b/drivers/target/target_core_pscsi.c -@@ -521,6 +521,7 @@ static int pscsi_configure_device(struct se_device *dev) - " pdv_host_id: %d\n", pdv->pdv_host_id); - return -EINVAL; - } -+ pdv->pdv_lld_host = sh; - } - } else { - if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) { -@@ -603,6 +604,8 @@ static void pscsi_free_device(struct se_device *dev) - if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) && - (phv->phv_lld_host != NULL)) - scsi_host_put(phv->phv_lld_host); -+ else if (pdv->pdv_lld_host) -+ scsi_host_put(pdv->pdv_lld_host); - - if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM)) - scsi_device_put(sd); -diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h -index 1bd757dff8ee..820d3052b775 100644 ---- a/drivers/target/target_core_pscsi.h -+++ b/drivers/target/target_core_pscsi.h -@@ -45,6 +45,7 @@ struct pscsi_dev_virt { - int pdv_lun_id; - struct block_device *pdv_bd; - struct scsi_device *pdv_sd; -+ struct Scsi_Host *pdv_lld_host; - } ____cacheline_aligned; - - typedef enum phv_modes { -diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c -index c2556cf5186b..01255fd65135 100644 ---- a/drivers/thermal/armada_thermal.c -+++ b/drivers/thermal/armada_thermal.c -@@ -224,9 +224,9 @@ static const struct armada_thermal_data armada380_data = { - .is_valid_shift = 10, - .temp_shift = 0, - .temp_mask = 0x3ff, -- .coef_b = 1169498786UL, -- .coef_m = 2000000UL, -- .coef_div = 4289, -+ .coef_b = 2931108200UL, -+ .coef_m = 5000000UL, -+ .coef_div = 10502, - .inverted = true, - }; - -diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c -index 5bab1c684bb1..7a3d146a5f0e 100644 ---- a/drivers/tty/hvc/hvc_xen.c -+++ b/drivers/tty/hvc/hvc_xen.c -@@ -289,7 +289,7 @@ static int xen_initial_domain_console_init(void) - return -ENOMEM; - } - -- info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0); -+ info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); - info->vtermno = HVC_COOKIE; - - spin_lock(&xencons_lock); -diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c -index c4343764cc5b..bce16e405d59 100644 ---- a/drivers/tty/n_gsm.c -+++ b/drivers/tty/n_gsm.c -@@ -3170,7 +3170,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state) - return gsmtty_modem_update(dlci, encode); - } - --static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty) -+static void gsmtty_cleanup(struct tty_struct *tty) - { - struct gsm_dlci *dlci = tty->driver_data; - struct gsm_mux *gsm = dlci->gsm; -@@ -3178,7 +3178,6 @@ static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty) - dlci_put(dlci); - dlci_put(gsm->dlci[0]); - mux_put(gsm); -- driver->ttys[tty->index] = NULL; - } - - /* Virtual ttys for the demux */ -@@ -3199,7 +3198,7 @@ static const struct tty_operations gsmtty_ops = { - .tiocmget = gsmtty_tiocmget, - .tiocmset = gsmtty_tiocmset, - .break_ctl = gsmtty_break_ctl, -- .remove = gsmtty_remove, -+ .cleanup = gsmtty_cleanup, - }; - - -diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c -index 644ddb841d9f..bbc4ce66c2c1 100644 ---- a/drivers/tty/n_hdlc.c -+++ b/drivers/tty/n_hdlc.c -@@ -600,7 +600,7 @@ static ssize_t n_hdlc_tty_read(struct tty_struct *tty, struct file *file, - add_wait_queue(&tty->read_wait, &wait); - - for (;;) { -- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) { -+ if (test_bit(TTY_OTHER_DONE, &tty->flags)) { - ret = -EIO; - break; - } -@@ -828,7 +828,7 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, - /* set bits for operations that won't block */ - if (n_hdlc->rx_buf_list.head) - mask |= POLLIN | POLLRDNORM; /* readable */ -- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) -+ if (test_bit(TTY_OTHER_DONE, &tty->flags)) - mask |= POLLHUP; - if (tty_hung_up_p(filp)) - mask |= POLLHUP; -diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c -index cf6e0f2e1331..cc57a3a6b02b 100644 ---- a/drivers/tty/n_tty.c -+++ b/drivers/tty/n_tty.c -@@ -1949,6 +1949,18 @@ static inline int input_available_p(struct tty_struct *tty, int poll) - return ldata->commit_head - ldata->read_tail >= amt; - } - -+static inline int check_other_done(struct tty_struct *tty) -+{ -+ int done = test_bit(TTY_OTHER_DONE, &tty->flags); -+ if (done) { -+ /* paired with cmpxchg() in check_other_closed(); ensures -+ * read buffer head index is not stale -+ */ -+ smp_mb__after_atomic(); -+ } -+ return done; -+} -+ - /** - * copy_from_read_buf - copy read data directly - * @tty: terminal device -@@ -2167,7 +2179,7 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, - struct n_tty_data *ldata = tty->disc_data; - unsigned char __user *b = buf; - DEFINE_WAIT_FUNC(wait, woken_wake_function); -- int c; -+ int c, done; - int minimum, time; - ssize_t retval = 0; - long timeout; -@@ -2235,8 +2247,10 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, - ((minimum - (b - buf)) >= 1)) - ldata->minimum_to_wake = (minimum - (b - buf)); - -+ done = check_other_done(tty); -+ - if (!input_available_p(tty, 0)) { -- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) { -+ if (done) { - retval = -EIO; - break; - } -@@ -2443,12 +2457,12 @@ static unsigned int n_tty_poll(struct tty_struct *tty, struct file *file, - - poll_wait(file, &tty->read_wait, wait); - poll_wait(file, &tty->write_wait, wait); -+ if (check_other_done(tty)) -+ mask |= POLLHUP; - if (input_available_p(tty, 1)) - mask |= POLLIN | POLLRDNORM; - if (tty->packet && tty->link->ctrl_status) - mask |= POLLPRI | POLLIN | POLLRDNORM; -- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) -- mask |= POLLHUP; - if (tty_hung_up_p(file)) - mask |= POLLHUP; - if (!(mask & (POLLHUP | POLLIN | POLLRDNORM))) { -diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c -index e72ee629cead..4d5e8409769c 100644 ---- a/drivers/tty/pty.c -+++ b/drivers/tty/pty.c -@@ -53,9 +53,8 @@ static void pty_close(struct tty_struct *tty, struct file *filp) - /* Review - krefs on tty_link ?? */ - if (!tty->link) - return; -- tty_flush_to_ldisc(tty->link); - set_bit(TTY_OTHER_CLOSED, &tty->link->flags); -- wake_up_interruptible(&tty->link->read_wait); -+ tty_flip_buffer_push(tty->link->port); - wake_up_interruptible(&tty->link->write_wait); - if (tty->driver->subtype == PTY_TYPE_MASTER) { - set_bit(TTY_OTHER_CLOSED, &tty->flags); -@@ -243,7 +242,9 @@ static int pty_open(struct tty_struct *tty, struct file *filp) - goto out; - - clear_bit(TTY_IO_ERROR, &tty->flags); -+ /* TTY_OTHER_CLOSED must be cleared before TTY_OTHER_DONE */ - clear_bit(TTY_OTHER_CLOSED, &tty->link->flags); -+ clear_bit(TTY_OTHER_DONE, &tty->link->flags); - set_bit(TTY_THROTTLED, &tty->flags); - return 0; - -diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c -index 75661641f5fe..2f78b77f0f81 100644 ---- a/drivers/tty/tty_buffer.c -+++ b/drivers/tty/tty_buffer.c -@@ -37,6 +37,28 @@ - - #define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) - -+/* -+ * If all tty flip buffers have been processed by flush_to_ldisc() or -+ * dropped by tty_buffer_flush(), check if the linked pty has been closed. -+ * If so, wake the reader/poll to process -+ */ -+static inline void check_other_closed(struct tty_struct *tty) -+{ -+ unsigned long flags, old; -+ -+ /* transition from TTY_OTHER_CLOSED => TTY_OTHER_DONE must be atomic */ -+ for (flags = ACCESS_ONCE(tty->flags); -+ test_bit(TTY_OTHER_CLOSED, &flags); -+ ) { -+ old = flags; -+ __set_bit(TTY_OTHER_DONE, &flags); -+ flags = cmpxchg(&tty->flags, old, flags); -+ if (old == flags) { -+ wake_up_interruptible(&tty->read_wait); -+ break; -+ } -+ } -+} - - /** - * tty_buffer_lock_exclusive - gain exclusive access to buffer -@@ -229,6 +251,8 @@ void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld) - if (ld && ld->ops->flush_buffer) - ld->ops->flush_buffer(tty); - -+ check_other_closed(tty); -+ - atomic_dec(&buf->priority); - mutex_unlock(&buf->lock); - } -@@ -471,8 +495,10 @@ static void flush_to_ldisc(struct work_struct *work) - smp_rmb(); - count = head->commit - head->read; - if (!count) { -- if (next == NULL) -+ if (next == NULL) { -+ check_other_closed(tty); - break; -+ } - buf->head = next; - tty_buffer_free(port, head); - continue; -@@ -489,19 +515,6 @@ static void flush_to_ldisc(struct work_struct *work) - } - - /** -- * tty_flush_to_ldisc -- * @tty: tty to push -- * -- * Push the terminal flip buffers to the line discipline. -- * -- * Must not be called from IRQ context. -- */ --void tty_flush_to_ldisc(struct tty_struct *tty) --{ -- flush_work(&tty->port->buf.work); --} -- --/** - * tty_flip_buffer_push - terminal - * @port: tty port to push - * -diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c -index c42765b3a060..0495c94a23d7 100644 ---- a/drivers/usb/gadget/configfs.c -+++ b/drivers/usb/gadget/configfs.c -@@ -1295,6 +1295,7 @@ static void purge_configs_funcs(struct gadget_info *gi) - } - } - c->next_interface_id = 0; -+ memset(c->interface, 0, sizeof(c->interface)); - c->superspeed = 0; - c->highspeed = 0; - c->fullspeed = 0; -diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c -index eeedde8c435a..6994c99e58a6 100644 ---- a/drivers/usb/host/xhci-ring.c -+++ b/drivers/usb/host/xhci-ring.c -@@ -2026,8 +2026,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, - break; - case COMP_DEV_ERR: - case COMP_STALL: -+ frame->status = -EPROTO; -+ skip_td = true; -+ break; - case COMP_TX_ERR: - frame->status = -EPROTO; -+ if (event_trb != td->last_trb) -+ return 0; - skip_td = true; - break; - case COMP_STOP: -@@ -2640,7 +2645,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) - xhci_halt(xhci); - hw_died: - spin_unlock(&xhci->lock); -- return -ESHUTDOWN; -+ return IRQ_HANDLED; - } - - /* -diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h -index 8e421b89632d..ea75e8ccd3c1 100644 ---- a/drivers/usb/host/xhci.h -+++ b/drivers/usb/host/xhci.h -@@ -1267,7 +1267,7 @@ union xhci_trb { - * since the command ring is 64-byte aligned. - * It must also be greater than 16. - */ --#define TRBS_PER_SEGMENT 64 -+#define TRBS_PER_SEGMENT 256 - /* Allow two commands + a link TRB, along with any reserved command TRBs */ - #define MAX_RSVD_CMD_TRBS (TRBS_PER_SEGMENT - 3) - #define TRB_SEGMENT_SIZE (TRBS_PER_SEGMENT*16) -diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c -index 84ce2d74894c..9031750e7404 100644 ---- a/drivers/usb/serial/cp210x.c -+++ b/drivers/usb/serial/cp210x.c -@@ -127,6 +127,7 @@ static const struct usb_device_id id_table[] = { - { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */ - { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */ - { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ -+ { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ - { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ - { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ - { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ -diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c -index 829604d11f3f..f5257af33ecf 100644 ---- a/drivers/usb/serial/pl2303.c -+++ b/drivers/usb/serial/pl2303.c -@@ -61,7 +61,6 @@ static const struct usb_device_id id_table[] = { - { USB_DEVICE(DCU10_VENDOR_ID, DCU10_PRODUCT_ID) }, - { USB_DEVICE(SITECOM_VENDOR_ID, SITECOM_PRODUCT_ID) }, - { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_ID) }, -- { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_ID) }, - { USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_SX1), - .driver_info = PL2303_QUIRK_UART_STATE_IDX0 }, - { USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_X65), -diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h -index 71fd9da1d6e7..e3b7af8adfb7 100644 ---- a/drivers/usb/serial/pl2303.h -+++ b/drivers/usb/serial/pl2303.h -@@ -62,10 +62,6 @@ - #define ALCATEL_VENDOR_ID 0x11f7 - #define ALCATEL_PRODUCT_ID 0x02df - --/* Samsung I330 phone cradle */ --#define SAMSUNG_VENDOR_ID 0x04e8 --#define SAMSUNG_PRODUCT_ID 0x8001 -- - #define SIEMENS_VENDOR_ID 0x11f5 - #define SIEMENS_PRODUCT_ID_SX1 0x0001 - #define SIEMENS_PRODUCT_ID_X65 0x0003 -diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c -index bf2bd40e5f2a..60afb39eb73c 100644 ---- a/drivers/usb/serial/visor.c -+++ b/drivers/usb/serial/visor.c -@@ -95,7 +95,7 @@ static const struct usb_device_id id_table[] = { - .driver_info = (kernel_ulong_t)&palm_os_4_probe }, - { USB_DEVICE(ACER_VENDOR_ID, ACER_S10_ID), - .driver_info = (kernel_ulong_t)&palm_os_4_probe }, -- { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID), -+ { USB_DEVICE_INTERFACE_CLASS(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID, 0xff), - .driver_info = (kernel_ulong_t)&palm_os_4_probe }, - { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SPH_I500_ID), - .driver_info = (kernel_ulong_t)&palm_os_4_probe }, -diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h -index d684b4b8108f..caf188800c67 100644 ---- a/drivers/usb/storage/unusual_devs.h -+++ b/drivers/usb/storage/unusual_devs.h -@@ -766,6 +766,13 @@ UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000, - USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_GO_SLOW ), - -+/* Reported by Christian Schaller */ -+UNUSUAL_DEV( 0x059f, 0x0651, 0x0000, 0x0000, -+ "LaCie", -+ "External HDD", -+ USB_SC_DEVICE, USB_PR_DEVICE, NULL, -+ US_FL_NO_WP_DETECT ), -+ - /* Submitted by Joel Bourquard - * Some versions of this device need the SubClass and Protocol overrides - * while others don't. -diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c -index 2b8553bd8715..38387950490e 100644 ---- a/drivers/xen/events/events_base.c -+++ b/drivers/xen/events/events_base.c -@@ -957,7 +957,7 @@ unsigned xen_evtchn_nr_channels(void) - } - EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels); - --int bind_virq_to_irq(unsigned int virq, unsigned int cpu) -+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu) - { - struct evtchn_bind_virq bind_virq; - int evtchn, irq, ret; -@@ -971,8 +971,12 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu) - if (irq < 0) - goto out; - -- irq_set_chip_and_handler_name(irq, &xen_percpu_chip, -- handle_percpu_irq, "virq"); -+ if (percpu) -+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip, -+ handle_percpu_irq, "virq"); -+ else -+ irq_set_chip_and_handler_name(irq, &xen_dynamic_chip, -+ handle_edge_irq, "virq"); - - bind_virq.virq = virq; - bind_virq.vcpu = cpu; -@@ -1062,7 +1066,7 @@ int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, - { - int irq, retval; - -- irq = bind_virq_to_irq(virq, cpu); -+ irq = bind_virq_to_irq(virq, cpu, irqflags & IRQF_PERCPU); - if (irq < 0) - return irq; - retval = request_irq(irq, handler, irqflags, devname, dev_id); -diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c -index d925f55e4857..8081aba116a7 100644 ---- a/fs/binfmt_elf.c -+++ b/fs/binfmt_elf.c -@@ -928,7 +928,7 @@ static int load_elf_binary(struct linux_binprm *bprm) - total_size = total_mapping_size(elf_phdata, - loc->elf_ex.e_phnum); - if (!total_size) { -- error = -EINVAL; -+ retval = -EINVAL; - goto out_free_dentry; - } - } -diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c -index 0a795c969c78..8b33da6ec3dd 100644 ---- a/fs/btrfs/extent-tree.c -+++ b/fs/btrfs/extent-tree.c -@@ -8548,7 +8548,9 @@ int btrfs_set_block_group_ro(struct btrfs_root *root, - out: - if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) { - alloc_flags = update_block_group_flags(root, cache->flags); -+ lock_chunks(root->fs_info->chunk_root); - check_system_chunk(trans, root, alloc_flags); -+ unlock_chunks(root->fs_info->chunk_root); - } - - btrfs_end_transaction(trans, root); -diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c -index 8222f6f74147..44a7e0398d97 100644 ---- a/fs/btrfs/volumes.c -+++ b/fs/btrfs/volumes.c -@@ -4626,6 +4626,7 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, - { - u64 chunk_offset; - -+ ASSERT(mutex_is_locked(&extent_root->fs_info->chunk_mutex)); - chunk_offset = find_next_chunk(extent_root->fs_info); - return __btrfs_alloc_chunk(trans, extent_root, chunk_offset, type); - } -diff --git a/fs/dcache.c b/fs/dcache.c -index c71e3732e53b..922f23ef6041 100644 ---- a/fs/dcache.c -+++ b/fs/dcache.c -@@ -1205,13 +1205,13 @@ ascend: - /* might go back up the wrong parent if we have had a rename. */ - if (need_seqretry(&rename_lock, seq)) - goto rename_retry; -- next = child->d_child.next; -- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { -+ /* go into the first sibling still alive */ -+ do { -+ next = child->d_child.next; - if (next == &this_parent->d_subdirs) - goto ascend; - child = list_entry(next, struct dentry, d_child); -- next = next->next; -- } -+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); - rcu_read_unlock(); - goto resume; - } -diff --git a/fs/exec.c b/fs/exec.c -index 00400cf522dc..120244523647 100644 ---- a/fs/exec.c -+++ b/fs/exec.c -@@ -659,6 +659,9 @@ int setup_arg_pages(struct linux_binprm *bprm, - if (stack_base > STACK_SIZE_MAX) - stack_base = STACK_SIZE_MAX; - -+ /* Add space for stack randomization. */ -+ stack_base += (STACK_RND_MASK << PAGE_SHIFT); -+ - /* Make sure we didn't let the argument array grow too large. */ - if (vma->vm_end - vma->vm_start > stack_base) - return -ENOMEM; -diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c -index 3445035c7e01..d41843181818 100644 ---- a/fs/ext4/ext4_jbd2.c -+++ b/fs/ext4/ext4_jbd2.c -@@ -87,6 +87,12 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) - ext4_put_nojournal(handle); - return 0; - } -+ -+ if (!handle->h_transaction) { -+ err = jbd2_journal_stop(handle); -+ return handle->h_err ? handle->h_err : err; -+ } -+ - sb = handle->h_transaction->t_journal->j_private; - err = handle->h_err; - rc = jbd2_journal_stop(handle); -diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c -index 16f6365f65e7..ea4ee1732143 100644 ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -377,7 +377,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) - ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); - ext4_lblk_t last = lblock + len - 1; - -- if (lblock > last) -+ if (len == 0 || lblock > last) - return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); - } -diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c -index 852cc521f327..1f252b4e0f51 100644 ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4233,7 +4233,7 @@ static void ext4_update_other_inodes_time(struct super_block *sb, - int inode_size = EXT4_INODE_SIZE(sb); - - oi.orig_ino = orig_ino; -- ino = orig_ino & ~(inodes_per_block - 1); -+ ino = (orig_ino & ~(inodes_per_block - 1)) + 1; - for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { - if (ino == orig_ino) - continue; -diff --git a/fs/fhandle.c b/fs/fhandle.c -index 999ff5c3cab0..d59712dfa3e7 100644 ---- a/fs/fhandle.c -+++ b/fs/fhandle.c -@@ -195,8 +195,9 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, - goto out_err; - } - /* copy the full handle */ -- if (copy_from_user(handle, ufh, -- sizeof(struct file_handle) + -+ *handle = f_handle; -+ if (copy_from_user(&handle->f_handle, -+ &ufh->f_handle, - f_handle.handle_bytes)) { - retval = -EFAULT; - goto out_handle; -diff --git a/fs/fs_pin.c b/fs/fs_pin.c -index b06c98796afb..611b5408f6ec 100644 ---- a/fs/fs_pin.c -+++ b/fs/fs_pin.c -@@ -9,8 +9,8 @@ static DEFINE_SPINLOCK(pin_lock); - void pin_remove(struct fs_pin *pin) - { - spin_lock(&pin_lock); -- hlist_del(&pin->m_list); -- hlist_del(&pin->s_list); -+ hlist_del_init(&pin->m_list); -+ hlist_del_init(&pin->s_list); - spin_unlock(&pin_lock); - spin_lock_irq(&pin->wait.lock); - pin->done = 1; -diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c -index b5128c6e63ad..a9079d035ae5 100644 ---- a/fs/jbd2/recovery.c -+++ b/fs/jbd2/recovery.c -@@ -842,15 +842,23 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, - { - jbd2_journal_revoke_header_t *header; - int offset, max; -+ int csum_size = 0; -+ __u32 rcount; - int record_len = 4; - - header = (jbd2_journal_revoke_header_t *) bh->b_data; - offset = sizeof(jbd2_journal_revoke_header_t); -- max = be32_to_cpu(header->r_count); -+ rcount = be32_to_cpu(header->r_count); - - if (!jbd2_revoke_block_csum_verify(journal, header)) - return -EINVAL; - -+ if (jbd2_journal_has_csum_v2or3(journal)) -+ csum_size = sizeof(struct jbd2_journal_revoke_tail); -+ if (rcount > journal->j_blocksize - csum_size) -+ return -EINVAL; -+ max = rcount; -+ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - record_len = 8; - -diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c -index c6cbaef2bda1..14214da80eb8 100644 ---- a/fs/jbd2/revoke.c -+++ b/fs/jbd2/revoke.c -@@ -577,7 +577,7 @@ static void write_one_revoke_record(journal_t *journal, - { - int csum_size = 0; - struct buffer_head *descriptor; -- int offset; -+ int sz, offset; - journal_header_t *header; - - /* If we are already aborting, this all becomes a noop. We -@@ -594,9 +594,14 @@ static void write_one_revoke_record(journal_t *journal, - if (jbd2_journal_has_csum_v2or3(journal)) - csum_size = sizeof(struct jbd2_journal_revoke_tail); - -+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) -+ sz = 8; -+ else -+ sz = 4; -+ - /* Make sure we have a descriptor with space left for the record */ - if (descriptor) { -- if (offset >= journal->j_blocksize - csum_size) { -+ if (offset + sz > journal->j_blocksize - csum_size) { - flush_descriptor(journal, descriptor, offset, write_op); - descriptor = NULL; - } -@@ -619,16 +624,13 @@ static void write_one_revoke_record(journal_t *journal, - *descriptorp = descriptor; - } - -- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) { -+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - * ((__be64 *)(&descriptor->b_data[offset])) = - cpu_to_be64(record->blocknr); -- offset += 8; -- -- } else { -+ else - * ((__be32 *)(&descriptor->b_data[offset])) = - cpu_to_be32(record->blocknr); -- offset += 4; -- } -+ offset += sz; - - *offsetp = offset; - } -diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c -index 5f09370c90a8..ff2f2e6ad311 100644 ---- a/fs/jbd2/transaction.c -+++ b/fs/jbd2/transaction.c -@@ -551,7 +551,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) - int result; - int wanted; - -- WARN_ON(!transaction); - if (is_handle_aborted(handle)) - return -EROFS; - journal = transaction->t_journal; -@@ -627,7 +626,6 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) - tid_t tid; - int need_to_start, ret; - -- WARN_ON(!transaction); - /* If we've had an abort of any type, don't even think about - * actually doing the restart! */ - if (is_handle_aborted(handle)) -@@ -785,7 +783,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, - int need_copy = 0; - unsigned long start_lock, time_lock; - -- WARN_ON(!transaction); - if (is_handle_aborted(handle)) - return -EROFS; - journal = transaction->t_journal; -@@ -1051,7 +1048,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) - int err; - - jbd_debug(5, "journal_head %p\n", jh); -- WARN_ON(!transaction); - err = -EROFS; - if (is_handle_aborted(handle)) - goto out; -@@ -1266,7 +1262,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) - struct journal_head *jh; - int ret = 0; - -- WARN_ON(!transaction); - if (is_handle_aborted(handle)) - return -EROFS; - journal = transaction->t_journal; -@@ -1397,7 +1392,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) - int err = 0; - int was_modified = 0; - -- WARN_ON(!transaction); - if (is_handle_aborted(handle)) - return -EROFS; - journal = transaction->t_journal; -@@ -1530,8 +1524,22 @@ int jbd2_journal_stop(handle_t *handle) - tid_t tid; - pid_t pid; - -- if (!transaction) -- goto free_and_exit; -+ if (!transaction) { -+ /* -+ * Handle is already detached from the transaction so -+ * there is nothing to do other than decrease a refcount, -+ * or free the handle if refcount drops to zero -+ */ -+ if (--handle->h_ref > 0) { -+ jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, -+ handle->h_ref); -+ return err; -+ } else { -+ if (handle->h_rsv_handle) -+ jbd2_free_handle(handle->h_rsv_handle); -+ goto free_and_exit; -+ } -+ } - journal = transaction->t_journal; - - J_ASSERT(journal_current_handle() == handle); -@@ -2373,7 +2381,6 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode) - transaction_t *transaction = handle->h_transaction; - journal_t *journal; - -- WARN_ON(!transaction); - if (is_handle_aborted(handle)) - return -EROFS; - journal = transaction->t_journal; -diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c -index 6acc9648f986..345b35fd329d 100644 ---- a/fs/kernfs/dir.c -+++ b/fs/kernfs/dir.c -@@ -518,7 +518,14 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, - if (!kn) - goto err_out1; - -- ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL); -+ /* -+ * If the ino of the sysfs entry created for a kmem cache gets -+ * allocated from an ida layer, which is accounted to the memcg that -+ * owns the cache, the memcg will get pinned forever. So do not account -+ * ino ida allocations. -+ */ -+ ret = ida_simple_get(&root->ino_ida, 1, 0, -+ GFP_KERNEL | __GFP_NOACCOUNT); - if (ret < 0) - goto err_out2; - kn->ino = ret; -diff --git a/fs/namespace.c b/fs/namespace.c -index 38ed1e1bed41..13b0f7bfc096 100644 ---- a/fs/namespace.c -+++ b/fs/namespace.c -@@ -1709,8 +1709,11 @@ struct vfsmount *collect_mounts(struct path *path) - { - struct mount *tree; - namespace_lock(); -- tree = copy_tree(real_mount(path->mnt), path->dentry, -- CL_COPY_ALL | CL_PRIVATE); -+ if (!check_mnt(real_mount(path->mnt))) -+ tree = ERR_PTR(-EINVAL); -+ else -+ tree = copy_tree(real_mount(path->mnt), path->dentry, -+ CL_COPY_ALL | CL_PRIVATE); - namespace_unlock(); - if (IS_ERR(tree)) - return ERR_CAST(tree); -diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c -index 03d647bf195d..cdefaa331a07 100644 ---- a/fs/nfsd/blocklayout.c -+++ b/fs/nfsd/blocklayout.c -@@ -181,6 +181,17 @@ nfsd4_block_proc_layoutcommit(struct inode *inode, - } - - const struct nfsd4_layout_ops bl_layout_ops = { -+ /* -+ * Pretend that we send notification to the client. This is a blatant -+ * lie to force recent Linux clients to cache our device IDs. -+ * We rarely ever change the device ID, so the harm of leaking deviceids -+ * for a while isn't too bad. Unfortunately RFC5661 is a complete mess -+ * in this regard, but I filed errata 4119 for this a while ago, and -+ * hopefully the Linux client will eventually start caching deviceids -+ * without this again. -+ */ -+ .notify_types = -+ NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, - .proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo, - .encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo, - .proc_layoutget = nfsd4_block_proc_layoutget, -diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c -index ee1cccdb083a..b4541ede7cb8 100644 ---- a/fs/nfsd/nfs4state.c -+++ b/fs/nfsd/nfs4state.c -@@ -4386,10 +4386,17 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s - return nfserr_old_stateid; - } - -+static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols) -+{ -+ if (ols->st_stateowner->so_is_open_owner && -+ !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED)) -+ return nfserr_bad_stateid; -+ return nfs_ok; -+} -+ - static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) - { - struct nfs4_stid *s; -- struct nfs4_ol_stateid *ols; - __be32 status = nfserr_bad_stateid; - - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) -@@ -4419,13 +4426,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) - break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: -- ols = openlockstateid(s); -- if (ols->st_stateowner->so_is_open_owner -- && !(openowner(ols->st_stateowner)->oo_flags -- & NFS4_OO_CONFIRMED)) -- status = nfserr_bad_stateid; -- else -- status = nfs_ok; -+ status = nfsd4_check_openowner_confirmed(openlockstateid(s)); - break; - default: - printk("unknown stateid type %x\n", s->sc_type); -@@ -4517,8 +4518,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, - status = nfs4_check_fh(current_fh, stp); - if (status) - goto out; -- if (stp->st_stateowner->so_is_open_owner -- && !(openowner(stp->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED)) -+ status = nfsd4_check_openowner_confirmed(stp); -+ if (status) - goto out; - status = nfs4_check_openmode(stp, flags); - if (status) -diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c -index 138321b0c6c2..454111a3308e 100644 ---- a/fs/omfs/inode.c -+++ b/fs/omfs/inode.c -@@ -306,7 +306,8 @@ static const struct super_operations omfs_sops = { - */ - static int omfs_get_imap(struct super_block *sb) - { -- unsigned int bitmap_size, count, array_size; -+ unsigned int bitmap_size, array_size; -+ int count; - struct omfs_sb_info *sbi = OMFS_SB(sb); - struct buffer_head *bh; - unsigned long **ptr; -@@ -359,7 +360,7 @@ nomem: - } - - enum { -- Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask -+ Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err - }; - - static const match_table_t tokens = { -@@ -368,6 +369,7 @@ static const match_table_t tokens = { - {Opt_umask, "umask=%o"}, - {Opt_dmask, "dmask=%o"}, - {Opt_fmask, "fmask=%o"}, -+ {Opt_err, NULL}, - }; - - static int parse_options(char *options, struct omfs_sb_info *sbi) -diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c -index 24f640441bd9..84d693d37428 100644 ---- a/fs/overlayfs/copy_up.c -+++ b/fs/overlayfs/copy_up.c -@@ -299,6 +299,9 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct cred *override_cred; - char *link = NULL; - -+ if (WARN_ON(!workdir)) -+ return -EROFS; -+ - ovl_path_upper(parent, &parentpath); - upperdir = parentpath.dentry; - -diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c -index d139405d2bfa..692ceda3bc21 100644 ---- a/fs/overlayfs/dir.c -+++ b/fs/overlayfs/dir.c -@@ -222,6 +222,9 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, - struct kstat stat; - int err; - -+ if (WARN_ON(!workdir)) -+ return ERR_PTR(-EROFS); -+ - err = ovl_lock_rename_workdir(workdir, upperdir); - if (err) - goto out; -@@ -322,6 +325,9 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, - struct dentry *newdentry; - int err; - -+ if (WARN_ON(!workdir)) -+ return -EROFS; -+ - err = ovl_lock_rename_workdir(workdir, upperdir); - if (err) - goto out; -@@ -506,11 +512,28 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) - struct dentry *opaquedir = NULL; - int err; - -- if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { -- opaquedir = ovl_check_empty_and_clear(dentry); -- err = PTR_ERR(opaquedir); -- if (IS_ERR(opaquedir)) -- goto out; -+ if (WARN_ON(!workdir)) -+ return -EROFS; -+ -+ if (is_dir) { -+ if (OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { -+ opaquedir = ovl_check_empty_and_clear(dentry); -+ err = PTR_ERR(opaquedir); -+ if (IS_ERR(opaquedir)) -+ goto out; -+ } else { -+ LIST_HEAD(list); -+ -+ /* -+ * When removing an empty opaque directory, then it -+ * makes no sense to replace it with an exact replica of -+ * itself. But emptiness still needs to be checked. -+ */ -+ err = ovl_check_empty_dir(dentry, &list); -+ ovl_cache_free(&list); -+ if (err) -+ goto out; -+ } - } - - err = ovl_lock_rename_workdir(workdir, upperdir); -diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c -index 5f0d1993e6e3..bf8537c7f455 100644 ---- a/fs/overlayfs/super.c -+++ b/fs/overlayfs/super.c -@@ -529,7 +529,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) - { - struct ovl_fs *ufs = sb->s_fs_info; - -- if (!(*flags & MS_RDONLY) && !ufs->upper_mnt) -+ if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir)) - return -EROFS; - - return 0; -@@ -925,9 +925,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) - ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); - err = PTR_ERR(ufs->workdir); - if (IS_ERR(ufs->workdir)) { -- pr_err("overlayfs: failed to create directory %s/%s\n", -- ufs->config.workdir, OVL_WORKDIR_NAME); -- goto out_put_upper_mnt; -+ pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n", -+ ufs->config.workdir, OVL_WORKDIR_NAME, -err); -+ sb->s_flags |= MS_RDONLY; -+ ufs->workdir = NULL; - } - } - -@@ -997,7 +998,6 @@ out_put_lower_mnt: - kfree(ufs->lower_mnt); - out_put_workdir: - dput(ufs->workdir); --out_put_upper_mnt: - mntput(ufs->upper_mnt); - out_put_lowerpath: - for (i = 0; i < numlower; i++) -diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c -index 15105dbc9e28..0166e7e829a7 100644 ---- a/fs/xfs/libxfs/xfs_attr_leaf.c -+++ b/fs/xfs/libxfs/xfs_attr_leaf.c -@@ -498,8 +498,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff) - * After the last attribute is removed revert to original inode format, - * making all literal area available to the data fork once more. - */ --STATIC void --xfs_attr_fork_reset( -+void -+xfs_attr_fork_remove( - struct xfs_inode *ip, - struct xfs_trans *tp) - { -@@ -565,7 +565,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) - (mp->m_flags & XFS_MOUNT_ATTR2) && - (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) && - !(args->op_flags & XFS_DA_OP_ADDNAME)) { -- xfs_attr_fork_reset(dp, args->trans); -+ xfs_attr_fork_remove(dp, args->trans); - } else { - xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); - dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); -@@ -828,7 +828,7 @@ xfs_attr3_leaf_to_shortform( - if (forkoff == -1) { - ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2); - ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE); -- xfs_attr_fork_reset(dp, args->trans); -+ xfs_attr_fork_remove(dp, args->trans); - goto out; - } - -diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h -index e2929da7c3ba..4f3a60aa93d4 100644 ---- a/fs/xfs/libxfs/xfs_attr_leaf.h -+++ b/fs/xfs/libxfs/xfs_attr_leaf.h -@@ -53,7 +53,7 @@ int xfs_attr_shortform_remove(struct xfs_da_args *args); - int xfs_attr_shortform_list(struct xfs_attr_list_context *context); - int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); - int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes); -- -+void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp); - - /* - * Internal routines when attribute fork size == XFS_LBSIZE(mp). -diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c -index 83af4c149635..487c8374a1e0 100644 ---- a/fs/xfs/xfs_attr_inactive.c -+++ b/fs/xfs/xfs_attr_inactive.c -@@ -379,23 +379,31 @@ xfs_attr3_root_inactive( - return error; - } - -+/* -+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It -+ * removes both the on-disk and in-memory inode fork. Note that this also has to -+ * handle the condition of inodes without attributes but with an attribute fork -+ * configured, so we can't use xfs_inode_hasattr() here. -+ * -+ * The in-memory attribute fork is removed even on error. -+ */ - int --xfs_attr_inactive(xfs_inode_t *dp) -+xfs_attr_inactive( -+ struct xfs_inode *dp) - { -- xfs_trans_t *trans; -- xfs_mount_t *mp; -- int error; -+ struct xfs_trans *trans; -+ struct xfs_mount *mp; -+ int cancel_flags = 0; -+ int lock_mode = XFS_ILOCK_SHARED; -+ int error = 0; - - mp = dp->i_mount; - ASSERT(! XFS_NOT_DQATTACHED(mp, dp)); - -- xfs_ilock(dp, XFS_ILOCK_SHARED); -- if (!xfs_inode_hasattr(dp) || -- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { -- xfs_iunlock(dp, XFS_ILOCK_SHARED); -- return 0; -- } -- xfs_iunlock(dp, XFS_ILOCK_SHARED); -+ xfs_ilock(dp, lock_mode); -+ if (!XFS_IFORK_Q(dp)) -+ goto out_destroy_fork; -+ xfs_iunlock(dp, lock_mode); - - /* - * Start our first transaction of the day. -@@ -407,13 +415,18 @@ xfs_attr_inactive(xfs_inode_t *dp) - * the inode in every transaction to let it float upward through - * the log. - */ -+ lock_mode = 0; - trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL); - error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0); -- if (error) { -- xfs_trans_cancel(trans, 0); -- return error; -- } -- xfs_ilock(dp, XFS_ILOCK_EXCL); -+ if (error) -+ goto out_cancel; -+ -+ lock_mode = XFS_ILOCK_EXCL; -+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT; -+ xfs_ilock(dp, lock_mode); -+ -+ if (!XFS_IFORK_Q(dp)) -+ goto out_cancel; - - /* - * No need to make quota reservations here. We expect to release some -@@ -421,29 +434,31 @@ xfs_attr_inactive(xfs_inode_t *dp) - */ - xfs_trans_ijoin(trans, dp, 0); - -- /* -- * Decide on what work routines to call based on the inode size. -- */ -- if (!xfs_inode_hasattr(dp) || -- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { -- error = 0; -- goto out; -+ /* invalidate and truncate the attribute fork extents */ -+ if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) { -+ error = xfs_attr3_root_inactive(&trans, dp); -+ if (error) -+ goto out_cancel; -+ -+ error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); -+ if (error) -+ goto out_cancel; - } -- error = xfs_attr3_root_inactive(&trans, dp); -- if (error) -- goto out; - -- error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); -- if (error) -- goto out; -+ /* Reset the attribute fork - this also destroys the in-core fork */ -+ xfs_attr_fork_remove(dp, trans); - - error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES); -- xfs_iunlock(dp, XFS_ILOCK_EXCL); -- -+ xfs_iunlock(dp, lock_mode); - return error; - --out: -- xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT); -- xfs_iunlock(dp, XFS_ILOCK_EXCL); -+out_cancel: -+ xfs_trans_cancel(trans, cancel_flags); -+out_destroy_fork: -+ /* kill the in-core attr fork before we drop the inode lock */ -+ if (dp->i_afp) -+ xfs_idestroy_fork(dp, XFS_ATTR_FORK); -+ if (lock_mode) -+ xfs_iunlock(dp, lock_mode); - return error; - } -diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c -index a2e1cb8a568b..f3ba637a8ece 100644 ---- a/fs/xfs/xfs_file.c -+++ b/fs/xfs/xfs_file.c -@@ -125,7 +125,7 @@ xfs_iozero( - status = 0; - } while (count); - -- return (-status); -+ return status; - } - - int -diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c -index 6163767aa856..b1edda7890f4 100644 ---- a/fs/xfs/xfs_inode.c -+++ b/fs/xfs/xfs_inode.c -@@ -1889,21 +1889,17 @@ xfs_inactive( - /* - * If there are attributes associated with the file then blow them away - * now. The code calls a routine that recursively deconstructs the -- * attribute fork. We need to just commit the current transaction -- * because we can't use it for xfs_attr_inactive(). -+ * attribute fork. If also blows away the in-core attribute fork. - */ -- if (ip->i_d.di_anextents > 0) { -- ASSERT(ip->i_d.di_forkoff != 0); -- -+ if (XFS_IFORK_Q(ip)) { - error = xfs_attr_inactive(ip); - if (error) - return; - } - -- if (ip->i_afp) -- xfs_idestroy_fork(ip, XFS_ATTR_FORK); -- -+ ASSERT(!ip->i_afp); - ASSERT(ip->i_d.di_anextents == 0); -+ ASSERT(ip->i_d.di_forkoff == 0); - - /* - * Free the inode. -diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h -index 2dd405c9be78..45c39a37f924 100644 ---- a/include/drm/drm_pciids.h -+++ b/include/drm/drm_pciids.h -@@ -186,6 +186,7 @@ - {0x1002, 0x6658, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ - {0x1002, 0x665c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ - {0x1002, 0x665d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ -+ {0x1002, 0x665f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \ - {0x1002, 0x6660, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ - {0x1002, 0x6663, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ - {0x1002, 0x6664, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ -diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h -index 9dc4e0384bfb..3886b3bffd7f 100644 ---- a/include/linux/fs_pin.h -+++ b/include/linux/fs_pin.h -@@ -13,6 +13,8 @@ struct vfsmount; - static inline void init_fs_pin(struct fs_pin *p, void (*kill)(struct fs_pin *)) - { - init_waitqueue_head(&p->wait); -+ INIT_HLIST_NODE(&p->s_list); -+ INIT_HLIST_NODE(&p->m_list); - p->kill = kill; - } - -diff --git a/include/linux/gfp.h b/include/linux/gfp.h -index 51bd1e72a917..eb6fafe66bec 100644 ---- a/include/linux/gfp.h -+++ b/include/linux/gfp.h -@@ -30,6 +30,7 @@ struct vm_area_struct; - #define ___GFP_HARDWALL 0x20000u - #define ___GFP_THISNODE 0x40000u - #define ___GFP_RECLAIMABLE 0x80000u -+#define ___GFP_NOACCOUNT 0x100000u - #define ___GFP_NOTRACK 0x200000u - #define ___GFP_NO_KSWAPD 0x400000u - #define ___GFP_OTHER_NODE 0x800000u -@@ -85,6 +86,7 @@ struct vm_area_struct; - #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ - #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ - #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ -+#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ - #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ - - #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) -diff --git a/include/linux/ktime.h b/include/linux/ktime.h -index 5fc3d1083071..2b6a204bd8d4 100644 ---- a/include/linux/ktime.h -+++ b/include/linux/ktime.h -@@ -166,19 +166,34 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) - } - - #if BITS_PER_LONG < 64 --extern u64 __ktime_divns(const ktime_t kt, s64 div); --static inline u64 ktime_divns(const ktime_t kt, s64 div) -+extern s64 __ktime_divns(const ktime_t kt, s64 div); -+static inline s64 ktime_divns(const ktime_t kt, s64 div) - { -+ /* -+ * Negative divisors could cause an inf loop, -+ * so bug out here. -+ */ -+ BUG_ON(div < 0); - if (__builtin_constant_p(div) && !(div >> 32)) { -- u64 ns = kt.tv64; -- do_div(ns, div); -- return ns; -+ s64 ns = kt.tv64; -+ u64 tmp = ns < 0 ? -ns : ns; -+ -+ do_div(tmp, div); -+ return ns < 0 ? -tmp : tmp; - } else { - return __ktime_divns(kt, div); - } - } - #else /* BITS_PER_LONG < 64 */ --# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) -+static inline s64 ktime_divns(const ktime_t kt, s64 div) -+{ -+ /* -+ * 32-bit implementation cannot handle negative divisors, -+ * so catch them on 64bit as well. -+ */ -+ WARN_ON(div < 0); -+ return kt.tv64 / div; -+} - #endif - - static inline s64 ktime_to_us(const ktime_t kt) -diff --git a/include/linux/libata.h b/include/linux/libata.h -index 6b08cc106c21..f8994b4b122c 100644 ---- a/include/linux/libata.h -+++ b/include/linux/libata.h -@@ -205,6 +205,7 @@ enum { - ATA_LFLAG_SW_ACTIVITY = (1 << 7), /* keep activity stats */ - ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ - ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ -+ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ - - /* struct ata_port flags */ - ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ -@@ -310,6 +311,12 @@ enum { - */ - ATA_TMOUT_PMP_SRST_WAIT = 5000, - -+ /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might -+ * be a spurious PHY event, so ignore the first PHY event that -+ * occurs within 10s after the policy change. -+ */ -+ ATA_TMOUT_SPURIOUS_PHY = 10000, -+ - /* ATA bus states */ - BUS_UNKNOWN = 0, - BUS_DMA = 1, -@@ -789,6 +796,8 @@ struct ata_link { - struct ata_eh_context eh_context; - - struct ata_device device[ATA_MAX_DEVICES]; -+ -+ unsigned long last_lpm_change; /* when last LPM change happened */ - }; - #define ATA_LINK_CLEAR_BEGIN offsetof(struct ata_link, active_tag) - #define ATA_LINK_CLEAR_END offsetof(struct ata_link, device[0]) -@@ -1202,6 +1211,7 @@ extern struct ata_device *ata_dev_pair(struct ata_device *adev); - extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); - extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); - extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q); -+extern bool sata_lpm_ignore_phy_events(struct ata_link *link); - - extern int ata_cable_40wire(struct ata_port *ap); - extern int ata_cable_80wire(struct ata_port *ap); -diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h -index 72dff5fb0d0c..6c8918114804 100644 ---- a/include/linux/memcontrol.h -+++ b/include/linux/memcontrol.h -@@ -463,6 +463,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) - if (!memcg_kmem_enabled()) - return true; - -+ if (gfp & __GFP_NOACCOUNT) -+ return true; - /* - * __GFP_NOFAIL allocations will move on even if charging is not - * possible. Therefore we don't even try, and have this allocation -@@ -522,6 +524,8 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) - { - if (!memcg_kmem_enabled()) - return cachep; -+ if (gfp & __GFP_NOACCOUNT) -+ return cachep; - if (gfp & __GFP_NOFAIL) - return cachep; - if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) -diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h -index 6341f5be6e24..a30b172df6e1 100644 ---- a/include/linux/sched/rt.h -+++ b/include/linux/sched/rt.h -@@ -18,7 +18,7 @@ static inline int rt_task(struct task_struct *p) - #ifdef CONFIG_RT_MUTEXES - extern int rt_mutex_getprio(struct task_struct *p); - extern void rt_mutex_setprio(struct task_struct *p, int prio); --extern int rt_mutex_check_prio(struct task_struct *task, int newprio); -+extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio); - extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); - extern void rt_mutex_adjust_pi(struct task_struct *p); - static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -@@ -31,9 +31,10 @@ static inline int rt_mutex_getprio(struct task_struct *p) - return p->normal_prio; - } - --static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) -+static inline int rt_mutex_get_effective_prio(struct task_struct *task, -+ int newprio) - { -- return 0; -+ return newprio; - } - - static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) -diff --git a/include/linux/tty.h b/include/linux/tty.h -index 358a337af598..790752ac074a 100644 ---- a/include/linux/tty.h -+++ b/include/linux/tty.h -@@ -339,6 +339,7 @@ struct tty_file_private { - #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ - #define TTY_DEBUG 4 /* Debugging */ - #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -+#define TTY_OTHER_DONE 6 /* Closed pty has completed input processing */ - #define TTY_LDISC_OPEN 11 /* Line discipline is open */ - #define TTY_PTY_LOCK 16 /* pty private */ - #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ -@@ -462,7 +463,6 @@ extern int tty_hung_up_p(struct file *filp); - extern void do_SAK(struct tty_struct *tty); - extern void __do_SAK(struct tty_struct *tty); - extern void no_tty(void); --extern void tty_flush_to_ldisc(struct tty_struct *tty); - extern void tty_buffer_free_all(struct tty_port *port); - extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); - extern void tty_buffer_init(struct tty_port *port); -diff --git a/include/xen/events.h b/include/xen/events.h -index 5321cd9636e6..7d95fdf9cf3e 100644 ---- a/include/xen/events.h -+++ b/include/xen/events.h -@@ -17,7 +17,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, - irq_handler_t handler, - unsigned long irqflags, const char *devname, - void *dev_id); --int bind_virq_to_irq(unsigned int virq, unsigned int cpu); -+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu); - int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, - irq_handler_t handler, - unsigned long irqflags, const char *devname, -diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c -index 6357265a31ad..ce9108c059fb 100644 ---- a/kernel/locking/rtmutex.c -+++ b/kernel/locking/rtmutex.c -@@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task) - } - - /* -- * Called by sched_setscheduler() to check whether the priority change -- * is overruled by a possible priority boosting. -+ * Called by sched_setscheduler() to get the priority which will be -+ * effective after the change. - */ --int rt_mutex_check_prio(struct task_struct *task, int newprio) -+int rt_mutex_get_effective_prio(struct task_struct *task, int newprio) - { - if (!task_has_pi_waiters(task)) -- return 0; -+ return newprio; - -- return task_top_pi_waiter(task)->task->prio <= newprio; -+ if (task_top_pi_waiter(task)->task->prio <= newprio) -+ return task_top_pi_waiter(task)->task->prio; -+ return newprio; - } - - /* -diff --git a/kernel/module.c b/kernel/module.c -index ec53f594e9c9..538794ce3cc7 100644 ---- a/kernel/module.c -+++ b/kernel/module.c -@@ -3366,6 +3366,9 @@ static int load_module(struct load_info *info, const char __user *uargs, - module_bug_cleanup(mod); - mutex_unlock(&module_mutex); - -+ blocking_notifier_call_chain(&module_notify_list, -+ MODULE_STATE_GOING, mod); -+ - /* we can't deallocate the module until we clear memory protection */ - unset_module_init_ro_nx(mod); - unset_module_core_ro_nx(mod); -diff --git a/kernel/sched/core.c b/kernel/sched/core.c -index 3d5f6f6d14c2..f4da2cbbfd7f 100644 ---- a/kernel/sched/core.c -+++ b/kernel/sched/core.c -@@ -3295,15 +3295,18 @@ static void __setscheduler_params(struct task_struct *p, - - /* Actually do priority change: must hold pi & rq lock. */ - static void __setscheduler(struct rq *rq, struct task_struct *p, -- const struct sched_attr *attr) -+ const struct sched_attr *attr, bool keep_boost) - { - __setscheduler_params(p, attr); - - /* -- * If we get here, there was no pi waiters boosting the -- * task. It is safe to use the normal prio. -+ * Keep a potential priority boosting if called from -+ * sched_setscheduler(). - */ -- p->prio = normal_prio(p); -+ if (keep_boost) -+ p->prio = rt_mutex_get_effective_prio(p, normal_prio(p)); -+ else -+ p->prio = normal_prio(p); - - if (dl_prio(p->prio)) - p->sched_class = &dl_sched_class; -@@ -3403,7 +3406,7 @@ static int __sched_setscheduler(struct task_struct *p, - int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : - MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, queued, running; -- int policy = attr->sched_policy; -+ int new_effective_prio, policy = attr->sched_policy; - unsigned long flags; - const struct sched_class *prev_class; - struct rq *rq; -@@ -3585,15 +3588,14 @@ change: - oldprio = p->prio; - - /* -- * Special case for priority boosted tasks. -- * -- * If the new priority is lower or equal (user space view) -- * than the current (boosted) priority, we just store the new -+ * Take priority boosted tasks into account. If the new -+ * effective priority is unchanged, we just store the new - * normal parameters and do not touch the scheduler class and - * the runqueue. This will be done when the task deboost - * itself. - */ -- if (rt_mutex_check_prio(p, newprio)) { -+ new_effective_prio = rt_mutex_get_effective_prio(p, newprio); -+ if (new_effective_prio == oldprio) { - __setscheduler_params(p, attr); - task_rq_unlock(rq, p, &flags); - return 0; -@@ -3607,7 +3609,7 @@ change: - put_prev_task(rq, p); - - prev_class = p->sched_class; -- __setscheduler(rq, p, attr); -+ __setscheduler(rq, p, attr, true); - - if (running) - p->sched_class->set_curr_task(rq); -@@ -4382,10 +4384,7 @@ long __sched io_schedule_timeout(long timeout) - long ret; - - current->in_iowait = 1; -- if (old_iowait) -- blk_schedule_flush_plug(current); -- else -- blk_flush_plug(current); -+ blk_schedule_flush_plug(current); - - delayacct_blkio_start(); - rq = raw_rq(); -@@ -7357,7 +7356,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) - queued = task_on_rq_queued(p); - if (queued) - dequeue_task(rq, p, 0); -- __setscheduler(rq, p, &attr); -+ __setscheduler(rq, p, &attr, false); - if (queued) { - enqueue_task(rq, p, 0); - resched_curr(rq); -diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c -index bee0c1f78091..38f586c076fe 100644 ---- a/kernel/time/hrtimer.c -+++ b/kernel/time/hrtimer.c -@@ -266,21 +266,23 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) - /* - * Divide a ktime value by a nanosecond value - */ --u64 __ktime_divns(const ktime_t kt, s64 div) -+s64 __ktime_divns(const ktime_t kt, s64 div) - { -- u64 dclc; - int sft = 0; -+ s64 dclc; -+ u64 tmp; - - dclc = ktime_to_ns(kt); -+ tmp = dclc < 0 ? -dclc : dclc; -+ - /* Make sure the divisor is less than 2^32: */ - while (div >> 32) { - sft++; - div >>= 1; - } -- dclc >>= sft; -- do_div(dclc, (unsigned long) div); -- -- return dclc; -+ tmp >>= sft; -+ do_div(tmp, (unsigned long) div); -+ return dclc < 0 ? -tmp : tmp; - } - EXPORT_SYMBOL_GPL(__ktime_divns); - #endif /* BITS_PER_LONG >= 64 */ -diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c -index a28df5206d95..11649615c505 100644 ---- a/lib/strnlen_user.c -+++ b/lib/strnlen_user.c -@@ -57,7 +57,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, - return res + find_zero(data) + 1 - align; - } - res += sizeof(unsigned long); -- if (unlikely(max < sizeof(unsigned long))) -+ /* We already handled 'unsigned long' bytes. Did we do it all ? */ -+ if (unlikely(max <= sizeof(unsigned long))) - break; - max -= sizeof(unsigned long); - if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) -diff --git a/mm/kmemleak.c b/mm/kmemleak.c -index 5405aff5a590..f0fe4f2c1fa7 100644 ---- a/mm/kmemleak.c -+++ b/mm/kmemleak.c -@@ -115,7 +115,8 @@ - #define BYTES_PER_POINTER sizeof(void *) - - /* GFP bitmask for kmemleak internal allocations */ --#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ -+#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \ -+ __GFP_NOACCOUNT)) | \ - __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN) - -diff --git a/mm/mempolicy.c b/mm/mempolicy.c -index de5dc5e12691..0f7d73b3e4b1 100644 ---- a/mm/mempolicy.c -+++ b/mm/mempolicy.c -@@ -2517,7 +2517,7 @@ static void __init check_numabalancing_enable(void) - if (numabalancing_override) - set_numabalancing_state(numabalancing_override == 1); - -- if (nr_node_ids > 1 && !numabalancing_override) { -+ if (num_online_nodes() > 1 && !numabalancing_override) { - pr_info("%s automatic NUMA balancing. " - "Configure with numa_balancing= or the " - "kernel.numa_balancing sysctl", -diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c -index 41a4abc7e98e..c4ec9239249a 100644 ---- a/net/ceph/osd_client.c -+++ b/net/ceph/osd_client.c -@@ -1306,8 +1306,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, - if (list_empty(&req->r_osd_item)) - req->r_osd = NULL; - } -- -- list_del_init(&req->r_req_lru_item); /* can be on notarget */ - ceph_osdc_put_request(req); - } - -@@ -2017,20 +2015,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, - err = __map_request(osdc, req, - force_resend || force_resend_writes); - dout("__map_request returned %d\n", err); -- if (err == 0) -- continue; /* no change and no osd was specified */ - if (err < 0) - continue; /* hrm! */ -- if (req->r_osd == NULL) { -- dout("tid %llu maps to no valid osd\n", req->r_tid); -- needmap++; /* request a newer map */ -- continue; -- } -+ if (req->r_osd == NULL || err > 0) { -+ if (req->r_osd == NULL) { -+ dout("lingering %p tid %llu maps to no osd\n", -+ req, req->r_tid); -+ /* -+ * A homeless lingering request makes -+ * no sense, as it's job is to keep -+ * a particular OSD connection open. -+ * Request a newer map and kick the -+ * request, knowing that it won't be -+ * resent until we actually get a map -+ * that can tell us where to send it. -+ */ -+ needmap++; -+ } - -- dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, -- req->r_osd ? req->r_osd->o_osd : -1); -- __register_request(osdc, req); -- __unregister_linger_request(osdc, req); -+ dout("kicking lingering %p tid %llu osd%d\n", req, -+ req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); -+ __register_request(osdc, req); -+ __unregister_linger_request(osdc, req); -+ } - } - reset_changed_osds(osdc); - mutex_unlock(&osdc->request_mutex); -diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h -index 8d53d65bd2ab..81e8dc5cb7f9 100644 ---- a/net/mac80211/ieee80211_i.h -+++ b/net/mac80211/ieee80211_i.h -@@ -204,6 +204,8 @@ enum ieee80211_packet_rx_flags { - * @IEEE80211_RX_CMNTR: received on cooked monitor already - * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported - * to cfg80211_report_obss_beacon(). -+ * @IEEE80211_RX_REORDER_TIMER: this frame is released by the -+ * reorder buffer timeout timer, not the normal RX path - * - * These flags are used across handling multiple interfaces - * for a single frame. -@@ -211,6 +213,7 @@ enum ieee80211_packet_rx_flags { - enum ieee80211_rx_flags { - IEEE80211_RX_CMNTR = BIT(0), - IEEE80211_RX_BEACON_REPORTED = BIT(1), -+ IEEE80211_RX_REORDER_TIMER = BIT(2), - }; - - struct ieee80211_rx_data { -diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c -index 1eb730bf8752..4c887d053333 100644 ---- a/net/mac80211/rx.c -+++ b/net/mac80211/rx.c -@@ -2106,7 +2106,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) - /* deliver to local stack */ - skb->protocol = eth_type_trans(skb, dev); - memset(skb->cb, 0, sizeof(skb->cb)); -- if (rx->local->napi) -+ if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) && -+ rx->local->napi) - napi_gro_receive(rx->local->napi, skb); - else - netif_receive_skb(skb); -@@ -3215,7 +3216,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) - /* This is OK -- must be QoS data frame */ - .security_idx = tid, - .seqno_idx = tid, -- .flags = 0, -+ .flags = IEEE80211_RX_REORDER_TIMER, - }; - struct tid_ampdu_rx *tid_agg_rx; - -diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c -index a4220e92f0cc..efa3f48f1ec5 100644 ---- a/net/mac80211/wep.c -+++ b/net/mac80211/wep.c -@@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, - - hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); - -- if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN || -- skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) -+ if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) - return NULL; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); -@@ -167,6 +166,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, - size_t len; - u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; - -+ if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) -+ return -1; -+ - iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); - if (!iv) - return -1; -diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c -index 1ec19f6f0c2b..eeeba5adee6d 100644 ---- a/net/sunrpc/auth_gss/gss_rpc_xdr.c -+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c -@@ -793,20 +793,26 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, - { - u32 value_follows; - int err; -+ struct page *scratch; -+ -+ scratch = alloc_page(GFP_KERNEL); -+ if (!scratch) -+ return -ENOMEM; -+ xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE); - - /* res->status */ - err = gssx_dec_status(xdr, &res->status); - if (err) -- return err; -+ goto out_free; - - /* res->context_handle */ - err = gssx_dec_bool(xdr, &value_follows); - if (err) -- return err; -+ goto out_free; - if (value_follows) { - err = gssx_dec_ctx(xdr, res->context_handle); - if (err) -- return err; -+ goto out_free; - } else { - res->context_handle = NULL; - } -@@ -814,11 +820,11 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, - /* res->output_token */ - err = gssx_dec_bool(xdr, &value_follows); - if (err) -- return err; -+ goto out_free; - if (value_follows) { - err = gssx_dec_buffer(xdr, res->output_token); - if (err) -- return err; -+ goto out_free; - } else { - res->output_token = NULL; - } -@@ -826,14 +832,17 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, - /* res->delegated_cred_handle */ - err = gssx_dec_bool(xdr, &value_follows); - if (err) -- return err; -+ goto out_free; - if (value_follows) { - /* we do not support upcall servers sending this data. */ -- return -EINVAL; -+ err = -EINVAL; -+ goto out_free; - } - - /* res->options */ - err = gssx_dec_option_array(xdr, &res->options); - -+out_free: -+ __free_page(scratch); - return err; - } -diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c -index a8a1e14272a1..a002a6d1e6da 100644 ---- a/sound/pci/hda/hda_intel.c -+++ b/sound/pci/hda/hda_intel.c -@@ -2108,6 +2108,8 @@ static const struct pci_device_id azx_ids[] = { - .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, - { PCI_DEVICE(0x1002, 0xaab0), - .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, -+ { PCI_DEVICE(0x1002, 0xaac8), -+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, - /* VIA VT8251/VT8237A */ - { PCI_DEVICE(0x1106, 0x3288), - .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA }, -diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c -index da67ea8645a6..e27298bdcd6d 100644 ---- a/sound/pci/hda/patch_conexant.c -+++ b/sound/pci/hda/patch_conexant.c -@@ -973,6 +973,14 @@ static const struct hda_codec_preset snd_hda_preset_conexant[] = { - .patch = patch_conexant_auto }, - { .id = 0x14f150b9, .name = "CX20665", - .patch = patch_conexant_auto }, -+ { .id = 0x14f150f1, .name = "CX20721", -+ .patch = patch_conexant_auto }, -+ { .id = 0x14f150f2, .name = "CX20722", -+ .patch = patch_conexant_auto }, -+ { .id = 0x14f150f3, .name = "CX20723", -+ .patch = patch_conexant_auto }, -+ { .id = 0x14f150f4, .name = "CX20724", -+ .patch = patch_conexant_auto }, - { .id = 0x14f1510f, .name = "CX20751/2", - .patch = patch_conexant_auto }, - { .id = 0x14f15110, .name = "CX20751/2", -@@ -1007,6 +1015,10 @@ MODULE_ALIAS("snd-hda-codec-id:14f150ab"); - MODULE_ALIAS("snd-hda-codec-id:14f150ac"); - MODULE_ALIAS("snd-hda-codec-id:14f150b8"); - MODULE_ALIAS("snd-hda-codec-id:14f150b9"); -+MODULE_ALIAS("snd-hda-codec-id:14f150f1"); -+MODULE_ALIAS("snd-hda-codec-id:14f150f2"); -+MODULE_ALIAS("snd-hda-codec-id:14f150f3"); -+MODULE_ALIAS("snd-hda-codec-id:14f150f4"); - MODULE_ALIAS("snd-hda-codec-id:14f1510f"); - MODULE_ALIAS("snd-hda-codec-id:14f15110"); - MODULE_ALIAS("snd-hda-codec-id:14f15111"); -diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c -index 2fd490b1764b..93c78c3c4b95 100644 ---- a/sound/pci/hda/patch_realtek.c -+++ b/sound/pci/hda/patch_realtek.c -@@ -5027,6 +5027,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { - SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX), - SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), - SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), -+ SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), - SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), - SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), - SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), -@@ -5056,6 +5057,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { - SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), -+ SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK), - SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), - SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), -@@ -5246,6 +5248,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { - {0x17, 0x40000000}, - {0x1d, 0x40700001}, - {0x21, 0x02211050}), -+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5548", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, -+ ALC255_STANDARD_PINS, -+ {0x12, 0x90a60180}, -+ {0x14, 0x90170130}, -+ {0x17, 0x40000000}, -+ {0x1d, 0x40700001}, -+ {0x21, 0x02211040}), - SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC256_STANDARD_PINS, - {0x13, 0x40000000}), -diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c -index 2341fc334163..6ba0b5517c40 100644 ---- a/sound/pci/hda/thinkpad_helper.c -+++ b/sound/pci/hda/thinkpad_helper.c -@@ -72,7 +72,6 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, - if (led_set_func(TPACPI_LED_MUTE, false) >= 0) { - old_vmaster_hook = spec->vmaster_mute.hook; - spec->vmaster_mute.hook = update_tpacpi_mute_led; -- spec->vmaster_mute_enum = 1; - removefunc = false; - } - if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) { -diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c -index 2ffb9a0570dc..3d44fc50e4d0 100644 ---- a/sound/soc/codecs/mc13783.c -+++ b/sound/soc/codecs/mc13783.c -@@ -623,14 +623,14 @@ static int mc13783_probe(struct snd_soc_codec *codec) - AUDIO_SSI_SEL, 0); - else - mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_CODEC, -- 0, AUDIO_SSI_SEL); -+ AUDIO_SSI_SEL, AUDIO_SSI_SEL); - - if (priv->dac_ssi_port == MC13783_SSI1_PORT) - mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC, - AUDIO_SSI_SEL, 0); - else - mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC, -- 0, AUDIO_SSI_SEL); -+ AUDIO_SSI_SEL, AUDIO_SSI_SEL); - - return 0; - } -diff --git a/sound/soc/codecs/uda1380.c b/sound/soc/codecs/uda1380.c -index dc7778b6dd7f..c3c33bd0df1c 100644 ---- a/sound/soc/codecs/uda1380.c -+++ b/sound/soc/codecs/uda1380.c -@@ -437,7 +437,7 @@ static int uda1380_set_dai_fmt_both(struct snd_soc_dai *codec_dai, - if ((fmt & SND_SOC_DAIFMT_MASTER_MASK) != SND_SOC_DAIFMT_CBS_CFS) - return -EINVAL; - -- uda1380_write(codec, UDA1380_IFACE, iface); -+ uda1380_write_reg_cache(codec, UDA1380_IFACE, iface); - - return 0; - } -diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c -index 3035d9856415..e97a7615df85 100644 ---- a/sound/soc/codecs/wm8960.c -+++ b/sound/soc/codecs/wm8960.c -@@ -395,7 +395,7 @@ static const struct snd_soc_dapm_route audio_paths[] = { - { "Right Input Mixer", "Boost Switch", "Right Boost Mixer", }, - { "Right Input Mixer", NULL, "RINPUT1", }, /* Really Boost Switch */ - { "Right Input Mixer", NULL, "RINPUT2" }, -- { "Right Input Mixer", NULL, "LINPUT3" }, -+ { "Right Input Mixer", NULL, "RINPUT3" }, - - { "Left ADC", NULL, "Left Input Mixer" }, - { "Right ADC", NULL, "Right Input Mixer" }, -diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c -index 4fbc7689339a..a1c04dab6684 100644 ---- a/sound/soc/codecs/wm8994.c -+++ b/sound/soc/codecs/wm8994.c -@@ -2754,7 +2754,7 @@ static struct { - }; - - static int fs_ratios[] = { -- 64, 128, 192, 256, 348, 512, 768, 1024, 1408, 1536 -+ 64, 128, 192, 256, 384, 512, 768, 1024, 1408, 1536 - }; - - static int bclk_divs[] = { -diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c -index b6f88202b8c9..e19a6765bd8a 100644 ---- a/sound/soc/soc-dapm.c -+++ b/sound/soc/soc-dapm.c -@@ -3074,11 +3074,16 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm, - } - - prefix = soc_dapm_prefix(dapm); -- if (prefix) -+ if (prefix) { - w->name = kasprintf(GFP_KERNEL, "%s %s", prefix, widget->name); -- else -+ if (widget->sname) -+ w->sname = kasprintf(GFP_KERNEL, "%s %s", prefix, -+ widget->sname); -+ } else { - w->name = kasprintf(GFP_KERNEL, "%s", widget->name); -- -+ if (widget->sname) -+ w->sname = kasprintf(GFP_KERNEL, "%s", widget->sname); -+ } - if (w->name == NULL) { - kfree(w); - return NULL; -diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c -index 32631a86078b..e21ec5abcc3a 100644 ---- a/sound/usb/quirks.c -+++ b/sound/usb/quirks.c -@@ -1117,6 +1117,8 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) - switch (chip->usb_id) { - case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ - case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ -+ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ -+ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ - case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ - return true; - } -diff --git a/tools/vm/Makefile b/tools/vm/Makefile -index ac884b65a072..93aadaf7ff63 100644 ---- a/tools/vm/Makefile -+++ b/tools/vm/Makefile -@@ -3,7 +3,7 @@ - TARGETS=page-types slabinfo page_owner_sort - - LIB_DIR = ../lib/api --LIBS = $(LIB_DIR)/libapikfs.a -+LIBS = $(LIB_DIR)/libapi.a - - CC = $(CROSS_COMPILE)gcc - CFLAGS = -Wall -Wextra -I../lib/ diff --git a/1500_XATTR_USER_PREFIX.patch b/1500_XATTR_USER_PREFIX.patch deleted file mode 100644 index cc15cd51..00000000 --- a/1500_XATTR_USER_PREFIX.patch +++ /dev/null @@ -1,54 +0,0 @@ -From: Anthony G. Basile - -This patch adds support for a restricted user-controlled namespace on -tmpfs filesystem used to house PaX flags. The namespace must be of the -form user.pax.* and its value cannot exceed a size of 8 bytes. - -This is needed even on all Gentoo systems so that XATTR_PAX flags -are preserved for users who might build packages using portage on -a tmpfs system with a non-hardened kernel and then switch to a -hardened kernel with XATTR_PAX enabled. - -The namespace is added to any user with Extended Attribute support -enabled for tmpfs. Users who do not enable xattrs will not have -the XATTR_PAX flags preserved. - -diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h -index e4629b9..6958086 100644 ---- a/include/uapi/linux/xattr.h -+++ b/include/uapi/linux/xattr.h -@@ -63,5 +63,9 @@ - #define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" - #define XATTR_NAME_POSIX_ACL_DEFAULT XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_DEFAULT - -+/* User namespace */ -+#define XATTR_PAX_PREFIX XATTR_USER_PREFIX "pax." -+#define XATTR_PAX_FLAGS_SUFFIX "flags" -+#define XATTR_NAME_PAX_FLAGS XATTR_PAX_PREFIX XATTR_PAX_FLAGS_SUFFIX - - #endif /* _UAPI_LINUX_XATTR_H */ -diff --git a/mm/shmem.c b/mm/shmem.c -index 1c44af7..f23bb1b 100644 ---- a/mm/shmem.c -+++ b/mm/shmem.c -@@ -2201,6 +2201,7 @@ static const struct xattr_handler *shmem_xattr_handlers[] = { - static int shmem_xattr_validate(const char *name) - { - struct { const char *prefix; size_t len; } arr[] = { -+ { XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN}, - { XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN }, - { XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN } - }; -@@ -2256,6 +2257,12 @@ static int shmem_setxattr(struct dentry *dentry, const char *name, - if (err) - return err; - -+ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { -+ if (strcmp(name, XATTR_NAME_PAX_FLAGS)) -+ return -EOPNOTSUPP; -+ if (size > 8) -+ return -EINVAL; -+ } - return simple_xattr_set(&info->xattrs, name, value, size, flags); - } - diff --git a/1510_fs-enable-link-security-restrictions-by-default.patch b/1510_fs-enable-link-security-restrictions-by-default.patch deleted file mode 100644 index 639fb3c3..00000000 --- a/1510_fs-enable-link-security-restrictions-by-default.patch +++ /dev/null @@ -1,22 +0,0 @@ -From: Ben Hutchings -Subject: fs: Enable link security restrictions by default -Date: Fri, 02 Nov 2012 05:32:06 +0000 -Bug-Debian: https://bugs.debian.org/609455 -Forwarded: not-needed - -This reverts commit 561ec64ae67ef25cac8d72bb9c4bfc955edfd415 -('VFS: don't do protected {sym,hard}links by default'). - ---- a/fs/namei.c -+++ b/fs/namei.c -@@ -651,8 +651,8 @@ static inline void put_link(struct namei - path_put(link); - } - --int sysctl_protected_symlinks __read_mostly = 0; --int sysctl_protected_hardlinks __read_mostly = 0; -+int sysctl_protected_symlinks __read_mostly = 1; -+int sysctl_protected_hardlinks __read_mostly = 1; - - /** - * may_follow_link - Check symlink following for unsafe situations diff --git a/2600_select-REGMAP_IRQ-for-rt5033.patch b/2600_select-REGMAP_IRQ-for-rt5033.patch deleted file mode 100644 index 92fb2e0b..00000000 --- a/2600_select-REGMAP_IRQ-for-rt5033.patch +++ /dev/null @@ -1,30 +0,0 @@ -From 23a2a22a3f3f17de094f386a893f7047c10e44a0 Mon Sep 17 00:00:00 2001 -From: Artem Savkov -Date: Thu, 5 Mar 2015 12:42:27 +0100 -Subject: mfd: rt5033: MFD_RT5033 needs to select REGMAP_IRQ - -Since commit 0b2712585(linux-next.git) this driver uses regmap_irq and so needs -to select REGMAP_IRQ. - -This fixes the following compilation errors: -ERROR: "regmap_irq_get_domain" [drivers/mfd/rt5033.ko] undefined! -ERROR: "regmap_add_irq_chip" [drivers/mfd/rt5033.ko] undefined! - -Signed-off-by: Artem Savkov -Signed-off-by: Lee Jones - -diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig -index f8ef77d9a..f49f404 100644 ---- a/drivers/mfd/Kconfig -+++ b/drivers/mfd/Kconfig -@@ -680,6 +680,7 @@ config MFD_RT5033 - depends on I2C=y - select MFD_CORE - select REGMAP_I2C -+ select REGMAP_IRQ - help - This driver provides for the Richtek RT5033 Power Management IC, - which includes the I2C driver and the Core APIs. This driver provides --- -cgit v0.10.2 - diff --git a/2700_ThinkPad-30-brightness-control-fix.patch b/2700_ThinkPad-30-brightness-control-fix.patch deleted file mode 100644 index b548c6dc..00000000 --- a/2700_ThinkPad-30-brightness-control-fix.patch +++ /dev/null @@ -1,67 +0,0 @@ -diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c -index cb96296..6c242ed 100644 ---- a/drivers/acpi/blacklist.c -+++ b/drivers/acpi/blacklist.c -@@ -269,6 +276,61 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { - }, - - /* -+ * The following Lenovo models have a broken workaround in the -+ * acpi_video backlight implementation to meet the Windows 8 -+ * requirement of 101 backlight levels. Reverting to pre-Win8 -+ * behavior fixes the problem. -+ */ -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad L430", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L430"), -+ }, -+ }, -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad T430s", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"), -+ }, -+ }, -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad T530", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T530"), -+ }, -+ }, -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad W530", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"), -+ }, -+ }, -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad X1 Carbon", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"), -+ }, -+ }, -+ { -+ .callback = dmi_disable_osi_win8, -+ .ident = "Lenovo ThinkPad X230", -+ .matches = { -+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), -+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"), -+ }, -+ }, -+ -+ /* - * BIOS invocation of _OSI(Linux) is almost always a BIOS bug. - * Linux ignores it, except for the machines enumerated below. - */ - diff --git a/2900_dev-root-proc-mount-fix.patch b/2900_dev-root-proc-mount-fix.patch deleted file mode 100644 index 4cd558e7..00000000 --- a/2900_dev-root-proc-mount-fix.patch +++ /dev/null @@ -1,30 +0,0 @@ ---- a/init/do_mounts.c 2014-08-26 08:03:30.000013100 -0400 -+++ b/init/do_mounts.c 2014-08-26 08:11:19.720014712 -0400 -@@ -484,7 +484,10 @@ void __init change_floppy(char *fmt, ... - va_start(args, fmt); - vsprintf(buf, fmt, args); - va_end(args); -- fd = sys_open("/dev/root", O_RDWR | O_NDELAY, 0); -+ if (saved_root_name[0]) -+ fd = sys_open(saved_root_name, O_RDWR | O_NDELAY, 0); -+ else -+ fd = sys_open("/dev/root", O_RDWR | O_NDELAY, 0); - if (fd >= 0) { - sys_ioctl(fd, FDEJECT, 0); - sys_close(fd); -@@ -527,8 +530,13 @@ void __init mount_root(void) - } - #endif - #ifdef CONFIG_BLOCK -- create_dev("/dev/root", ROOT_DEV); -- mount_block_root("/dev/root", root_mountflags); -+ if (saved_root_name[0] == '/') { -+ create_dev(saved_root_name, ROOT_DEV); -+ mount_block_root(saved_root_name, root_mountflags); -+ } else { -+ create_dev("/dev/root", ROOT_DEV); -+ mount_block_root("/dev/root", root_mountflags); -+ } - #endif - } - diff --git a/2905_2disk-resume-image-fix.patch b/2905_2disk-resume-image-fix.patch deleted file mode 100644 index 7e95d298..00000000 --- a/2905_2disk-resume-image-fix.patch +++ /dev/null @@ -1,24 +0,0 @@ -diff --git a/kernel/kmod.c b/kernel/kmod.c -index fb32636..d968882 100644 ---- a/kernel/kmod.c -+++ b/kernel/kmod.c -@@ -575,7 +575,8 @@ - call_usermodehelper_freeinfo(sub_info); - return -EINVAL; - } -- helper_lock(); -+ if (!(current->flags & PF_FREEZER_SKIP)) -+ helper_lock(); - if (!khelper_wq || usermodehelper_disabled) { - retval = -EBUSY; - goto out; -@@ -611,7 +612,8 @@ wait_done: - out: - call_usermodehelper_freeinfo(sub_info); - unlock: -- helper_unlock(); -+ if (!(current->flags & PF_FREEZER_SKIP)) -+ helper_unlock(); - return retval; - } - EXPORT_SYMBOL(call_usermodehelper_exec); diff --git a/2910_lz4-compression-fix.patch b/2910_lz4-compression-fix.patch deleted file mode 100644 index 1c55f322..00000000 --- a/2910_lz4-compression-fix.patch +++ /dev/null @@ -1,30 +0,0 @@ ---- a/lib/lz4/lz4_decompress.c 2015-04-13 16:20:04.896315560 +0800 -+++ b/lib/lz4/lz4_decompress.c 2015-04-13 16:27:08.929317053 +0800 -@@ -139,8 +139,12 @@ - /* Error: request to write beyond destination buffer */ - if (cpy > oend) - goto _output_error; -+#if LZ4_ARCH64 -+ if ((ref + COPYLENGTH) > oend) -+#else - if ((ref + COPYLENGTH) > oend || - (op + COPYLENGTH) > oend) -+#endif - goto _output_error; - LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); - while (op < cpy) -@@ -270,7 +274,13 @@ - if (cpy > oend - COPYLENGTH) { - if (cpy > oend) - goto _output_error; /* write outside of buf */ -- -+#if LZ4_ARCH64 -+ if ((ref + COPYLENGTH) > oend) -+#else -+ if ((ref + COPYLENGTH) > oend || -+ (op + COPYLENGTH) > oend) -+#endif -+ goto _output_error; - LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); - while (op < cpy) - *op++ = *ref++; diff --git a/4200_fbcondecor-3.19.patch b/4200_fbcondecor-3.19.patch deleted file mode 100644 index 29c379fe..00000000 --- a/4200_fbcondecor-3.19.patch +++ /dev/null @@ -1,2119 +0,0 @@ -diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX -index fe85e7c..2230930 100644 ---- a/Documentation/fb/00-INDEX -+++ b/Documentation/fb/00-INDEX -@@ -23,6 +23,8 @@ ep93xx-fb.txt - - info on the driver for EP93xx LCD controller. - fbcon.txt - - intro to and usage guide for the framebuffer console (fbcon). -+fbcondecor.txt -+ - info on the Framebuffer Console Decoration - framebuffer.txt - - introduction to frame buffer devices. - gxfb.txt -diff --git a/Documentation/fb/fbcondecor.txt b/Documentation/fb/fbcondecor.txt -new file mode 100644 -index 0000000..3388c61 ---- /dev/null -+++ b/Documentation/fb/fbcondecor.txt -@@ -0,0 +1,207 @@ -+What is it? -+----------- -+ -+The framebuffer decorations are a kernel feature which allows displaying a -+background picture on selected consoles. -+ -+What do I need to get it to work? -+--------------------------------- -+ -+To get fbcondecor up-and-running you will have to: -+ 1) get a copy of splashutils [1] or a similar program -+ 2) get some fbcondecor themes -+ 3) build the kernel helper program -+ 4) build your kernel with the FB_CON_DECOR option enabled. -+ -+To get fbcondecor operational right after fbcon initialization is finished, you -+will have to include a theme and the kernel helper into your initramfs image. -+Please refer to splashutils documentation for instructions on how to do that. -+ -+[1] The splashutils package can be downloaded from: -+ http://github.com/alanhaggai/fbsplash -+ -+The userspace helper -+-------------------- -+ -+The userspace fbcondecor helper (by default: /sbin/fbcondecor_helper) is called by the -+kernel whenever an important event occurs and the kernel needs some kind of -+job to be carried out. Important events include console switches and video -+mode switches (the kernel requests background images and configuration -+parameters for the current console). The fbcondecor helper must be accessible at -+all times. If it's not, fbcondecor will be switched off automatically. -+ -+It's possible to set path to the fbcondecor helper by writing it to -+/proc/sys/kernel/fbcondecor. -+ -+***************************************************************************** -+ -+The information below is mostly technical stuff. There's probably no need to -+read it unless you plan to develop a userspace helper. -+ -+The fbcondecor protocol -+----------------------- -+ -+The fbcondecor protocol defines a communication interface between the kernel and -+the userspace fbcondecor helper. -+ -+The kernel side is responsible for: -+ -+ * rendering console text, using an image as a background (instead of a -+ standard solid color fbcon uses), -+ * accepting commands from the user via ioctls on the fbcondecor device, -+ * calling the userspace helper to set things up as soon as the fb subsystem -+ is initialized. -+ -+The userspace helper is responsible for everything else, including parsing -+configuration files, decompressing the image files whenever the kernel needs -+it, and communicating with the kernel if necessary. -+ -+The fbcondecor protocol specifies how communication is done in both ways: -+kernel->userspace and userspace->helper. -+ -+Kernel -> Userspace -+------------------- -+ -+The kernel communicates with the userspace helper by calling it and specifying -+the task to be done in a series of arguments. -+ -+The arguments follow the pattern: -+ -+ -+All commands defined in fbcondecor protocol v2 have the following parameters: -+ virtual console -+ framebuffer number -+ theme -+ -+Fbcondecor protocol v1 specified an additional 'fbcondecor mode' after the -+framebuffer number. Fbcondecor protocol v1 is deprecated and should not be used. -+ -+Fbcondecor protocol v2 specifies the following commands: -+ -+getpic -+------ -+ The kernel issues this command to request image data. It's up to the -+ userspace helper to find a background image appropriate for the specified -+ theme and the current resolution. The userspace helper should respond by -+ issuing the FBIOCONDECOR_SETPIC ioctl. -+ -+init -+---- -+ The kernel issues this command after the fbcondecor device is created and -+ the fbcondecor interface is initialized. Upon receiving 'init', the userspace -+ helper should parse the kernel command line (/proc/cmdline) or otherwise -+ decide whether fbcondecor is to be activated. -+ -+ To activate fbcondecor on the first console the helper should issue the -+ FBIOCONDECOR_SETCFG, FBIOCONDECOR_SETPIC and FBIOCONDECOR_SETSTATE commands, -+ in the above-mentioned order. -+ -+ When the userspace helper is called in an early phase of the boot process -+ (right after the initialization of fbcon), no filesystems will be mounted. -+ The helper program should mount sysfs and then create the appropriate -+ framebuffer, fbcondecor and tty0 devices (if they don't already exist) to get -+ current display settings and to be able to communicate with the kernel side. -+ It should probably also mount the procfs to be able to parse the kernel -+ command line parameters. -+ -+ Note that the console sem is not held when the kernel calls fbcondecor_helper -+ with the 'init' command. The fbcondecor helper should perform all ioctls with -+ origin set to FBCON_DECOR_IO_ORIG_USER. -+ -+modechange -+---------- -+ The kernel issues this command on a mode change. The helper's response should -+ be similar to the response to the 'init' command. Note that this time the -+ console sem is held and all ioctls must be performed with origin set to -+ FBCON_DECOR_IO_ORIG_KERNEL. -+ -+ -+Userspace -> Kernel -+------------------- -+ -+Userspace programs can communicate with fbcondecor via ioctls on the -+fbcondecor device. These ioctls are to be used by both the userspace helper -+(called only by the kernel) and userspace configuration tools (run by the users). -+ -+The fbcondecor helper should set the origin field to FBCON_DECOR_IO_ORIG_KERNEL -+when doing the appropriate ioctls. All userspace configuration tools should -+use FBCON_DECOR_IO_ORIG_USER. Failure to set the appropriate value in the origin -+field when performing ioctls from the kernel helper will most likely result -+in a console deadlock. -+ -+FBCON_DECOR_IO_ORIG_KERNEL instructs fbcondecor not to try to acquire the console -+semaphore. Not surprisingly, FBCON_DECOR_IO_ORIG_USER instructs it to acquire -+the console sem. -+ -+The framebuffer console decoration provides the following ioctls (all defined in -+linux/fb.h): -+ -+FBIOCONDECOR_SETPIC -+description: loads a background picture for a virtual console -+argument: struct fbcon_decor_iowrapper*; data: struct fb_image* -+notes: -+If called for consoles other than the current foreground one, the picture data -+will be ignored. -+ -+If the current virtual console is running in a 8-bpp mode, the cmap substruct -+of fb_image has to be filled appropriately: start should be set to 16 (first -+16 colors are reserved for fbcon), len to a value <= 240 and red, green and -+blue should point to valid cmap data. The transp field is ingored. The fields -+dx, dy, bg_color, fg_color in fb_image are ignored as well. -+ -+FBIOCONDECOR_SETCFG -+description: sets the fbcondecor config for a virtual console -+argument: struct fbcon_decor_iowrapper*; data: struct vc_decor* -+notes: The structure has to be filled with valid data. -+ -+FBIOCONDECOR_GETCFG -+description: gets the fbcondecor config for a virtual console -+argument: struct fbcon_decor_iowrapper*; data: struct vc_decor* -+ -+FBIOCONDECOR_SETSTATE -+description: sets the fbcondecor state for a virtual console -+argument: struct fbcon_decor_iowrapper*; data: unsigned int* -+ values: 0 = disabled, 1 = enabled. -+ -+FBIOCONDECOR_GETSTATE -+description: gets the fbcondecor state for a virtual console -+argument: struct fbcon_decor_iowrapper*; data: unsigned int* -+ values: as in FBIOCONDECOR_SETSTATE -+ -+Info on used structures: -+ -+Definition of struct vc_decor can be found in linux/console_decor.h. It's -+heavily commented. Note that the 'theme' field should point to a string -+no longer than FBCON_DECOR_THEME_LEN. When FBIOCONDECOR_GETCFG call is -+performed, the theme field should point to a char buffer of length -+FBCON_DECOR_THEME_LEN. -+ -+Definition of struct fbcon_decor_iowrapper can be found in linux/fb.h. -+The fields in this struct have the following meaning: -+ -+vc: -+Virtual console number. -+ -+origin: -+Specifies if the ioctl is performed as a response to a kernel request. The -+fbcondecor helper should set this field to FBCON_DECOR_IO_ORIG_KERNEL, userspace -+programs should set it to FBCON_DECOR_IO_ORIG_USER. This field is necessary to -+avoid console semaphore deadlocks. -+ -+data: -+Pointer to a data structure appropriate for the performed ioctl. Type of -+the data struct is specified in the ioctls description. -+ -+***************************************************************************** -+ -+Credit -+------ -+ -+Original 'bootsplash' project & implementation by: -+ Volker Poplawski , Stefan Reinauer , -+ Steffen Winterfeldt , Michael Schroeder , -+ Ken Wimer . -+ -+Fbcondecor, fbcondecor protocol design, current implementation & docs by: -+ Michal Januszewski -+ -diff --git a/drivers/Makefile b/drivers/Makefile -index 7183b6a..d576148 100644 ---- a/drivers/Makefile -+++ b/drivers/Makefile -@@ -17,6 +17,10 @@ obj-y += pwm/ - obj-$(CONFIG_PCI) += pci/ - obj-$(CONFIG_PARISC) += parisc/ - obj-$(CONFIG_RAPIDIO) += rapidio/ -+# tty/ comes before char/ so that the VT console is the boot-time -+# default. -+obj-y += tty/ -+obj-y += char/ - obj-y += video/ - obj-y += idle/ - -@@ -42,11 +46,6 @@ obj-$(CONFIG_REGULATOR) += regulator/ - # reset controllers early, since gpu drivers might rely on them to initialize - obj-$(CONFIG_RESET_CONTROLLER) += reset/ - --# tty/ comes before char/ so that the VT console is the boot-time --# default. --obj-y += tty/ --obj-y += char/ -- - # iommu/ comes before gpu as gpu are using iommu controllers - obj-$(CONFIG_IOMMU_SUPPORT) += iommu/ - -diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig -index fe1cd01..6d2e87a 100644 ---- a/drivers/video/console/Kconfig -+++ b/drivers/video/console/Kconfig -@@ -126,6 +126,19 @@ config FRAMEBUFFER_CONSOLE_ROTATION - such that other users of the framebuffer will remain normally - oriented. - -+config FB_CON_DECOR -+ bool "Support for the Framebuffer Console Decorations" -+ depends on FRAMEBUFFER_CONSOLE=y && !FB_TILEBLITTING -+ default n -+ ---help--- -+ This option enables support for framebuffer console decorations which -+ makes it possible to display images in the background of the system -+ consoles. Note that userspace utilities are necessary in order to take -+ advantage of these features. Refer to Documentation/fb/fbcondecor.txt -+ for more information. -+ -+ If unsure, say N. -+ - config STI_CONSOLE - bool "STI text console" - depends on PARISC -diff --git a/drivers/video/console/Makefile b/drivers/video/console/Makefile -index 43bfa48..cc104b6f 100644 ---- a/drivers/video/console/Makefile -+++ b/drivers/video/console/Makefile -@@ -16,4 +16,5 @@ obj-$(CONFIG_FRAMEBUFFER_CONSOLE) += fbcon_rotate.o fbcon_cw.o fbcon_ud.o \ - fbcon_ccw.o - endif - -+obj-$(CONFIG_FB_CON_DECOR) += fbcondecor.o cfbcondecor.o - obj-$(CONFIG_FB_STI) += sticore.o -diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c -index 61b182b..984384b 100644 ---- a/drivers/video/console/bitblit.c -+++ b/drivers/video/console/bitblit.c -@@ -18,6 +18,7 @@ - #include - #include - #include "fbcon.h" -+#include "fbcondecor.h" - - /* - * Accelerated handlers. -@@ -55,6 +56,13 @@ static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, - area.height = height * vc->vc_font.height; - area.width = width * vc->vc_font.width; - -+ if (fbcon_decor_active(info, vc)) { -+ area.sx += vc->vc_decor.tx; -+ area.sy += vc->vc_decor.ty; -+ area.dx += vc->vc_decor.tx; -+ area.dy += vc->vc_decor.ty; -+ } -+ - info->fbops->fb_copyarea(info, &area); - } - -@@ -380,11 +388,15 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode, - cursor.image.depth = 1; - cursor.rop = ROP_XOR; - -- if (info->fbops->fb_cursor) -- err = info->fbops->fb_cursor(info, &cursor); -+ if (fbcon_decor_active(info, vc)) { -+ fbcon_decor_cursor(info, &cursor); -+ } else { -+ if (info->fbops->fb_cursor) -+ err = info->fbops->fb_cursor(info, &cursor); - -- if (err) -- soft_cursor(info, &cursor); -+ if (err) -+ soft_cursor(info, &cursor); -+ } - - ops->cursor_reset = 0; - } -diff --git a/drivers/video/console/cfbcondecor.c b/drivers/video/console/cfbcondecor.c -new file mode 100644 -index 0000000..a2b4497 ---- /dev/null -+++ b/drivers/video/console/cfbcondecor.c -@@ -0,0 +1,471 @@ -+/* -+ * linux/drivers/video/cfbcon_decor.c -- Framebuffer decor render functions -+ * -+ * Copyright (C) 2004 Michal Januszewski -+ * -+ * Code based upon "Bootdecor" (C) 2001-2003 -+ * Volker Poplawski , -+ * Stefan Reinauer , -+ * Steffen Winterfeldt , -+ * Michael Schroeder , -+ * Ken Wimer . -+ * -+ * This file is subject to the terms and conditions of the GNU General Public -+ * License. See the file COPYING in the main directory of this archive for -+ * more details. -+ */ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#include "fbcon.h" -+#include "fbcondecor.h" -+ -+#define parse_pixel(shift,bpp,type) \ -+ do { \ -+ if (d & (0x80 >> (shift))) \ -+ dd2[(shift)] = fgx; \ -+ else \ -+ dd2[(shift)] = transparent ? *(type *)decor_src : bgx; \ -+ decor_src += (bpp); \ -+ } while (0) \ -+ -+extern int get_color(struct vc_data *vc, struct fb_info *info, -+ u16 c, int is_fg); -+ -+void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc) -+{ -+ int i, j, k; -+ int minlen = min(min(info->var.red.length, info->var.green.length), -+ info->var.blue.length); -+ u32 col; -+ -+ for (j = i = 0; i < 16; i++) { -+ k = color_table[i]; -+ -+ col = ((vc->vc_palette[j++] >> (8-minlen)) -+ << info->var.red.offset); -+ col |= ((vc->vc_palette[j++] >> (8-minlen)) -+ << info->var.green.offset); -+ col |= ((vc->vc_palette[j++] >> (8-minlen)) -+ << info->var.blue.offset); -+ ((u32 *)info->pseudo_palette)[k] = col; -+ } -+} -+ -+void fbcon_decor_renderc(struct fb_info *info, int ypos, int xpos, int height, -+ int width, u8* src, u32 fgx, u32 bgx, u8 transparent) -+{ -+ unsigned int x, y; -+ u32 dd; -+ int bytespp = ((info->var.bits_per_pixel + 7) >> 3); -+ unsigned int d = ypos * info->fix.line_length + xpos * bytespp; -+ unsigned int ds = (ypos * info->var.xres + xpos) * bytespp; -+ u16 dd2[4]; -+ -+ u8* decor_src = (u8 *)(info->bgdecor.data + ds); -+ u8* dst = (u8 *)(info->screen_base + d); -+ -+ if ((ypos + height) > info->var.yres || (xpos + width) > info->var.xres) -+ return; -+ -+ for (y = 0; y < height; y++) { -+ switch (info->var.bits_per_pixel) { -+ -+ case 32: -+ for (x = 0; x < width; x++) { -+ -+ if ((x & 7) == 0) -+ d = *src++; -+ if (d & 0x80) -+ dd = fgx; -+ else -+ dd = transparent ? -+ *(u32 *)decor_src : bgx; -+ -+ d <<= 1; -+ decor_src += 4; -+ fb_writel(dd, dst); -+ dst += 4; -+ } -+ break; -+ case 24: -+ for (x = 0; x < width; x++) { -+ -+ if ((x & 7) == 0) -+ d = *src++; -+ if (d & 0x80) -+ dd = fgx; -+ else -+ dd = transparent ? -+ (*(u32 *)decor_src & 0xffffff) : bgx; -+ -+ d <<= 1; -+ decor_src += 3; -+#ifdef __LITTLE_ENDIAN -+ fb_writew(dd & 0xffff, dst); -+ dst += 2; -+ fb_writeb((dd >> 16), dst); -+#else -+ fb_writew(dd >> 8, dst); -+ dst += 2; -+ fb_writeb(dd & 0xff, dst); -+#endif -+ dst++; -+ } -+ break; -+ case 16: -+ for (x = 0; x < width; x += 2) { -+ if ((x & 7) == 0) -+ d = *src++; -+ -+ parse_pixel(0, 2, u16); -+ parse_pixel(1, 2, u16); -+#ifdef __LITTLE_ENDIAN -+ dd = dd2[0] | (dd2[1] << 16); -+#else -+ dd = dd2[1] | (dd2[0] << 16); -+#endif -+ d <<= 2; -+ fb_writel(dd, dst); -+ dst += 4; -+ } -+ break; -+ -+ case 8: -+ for (x = 0; x < width; x += 4) { -+ if ((x & 7) == 0) -+ d = *src++; -+ -+ parse_pixel(0, 1, u8); -+ parse_pixel(1, 1, u8); -+ parse_pixel(2, 1, u8); -+ parse_pixel(3, 1, u8); -+ -+#ifdef __LITTLE_ENDIAN -+ dd = dd2[0] | (dd2[1] << 8) | (dd2[2] << 16) | (dd2[3] << 24); -+#else -+ dd = dd2[3] | (dd2[2] << 8) | (dd2[1] << 16) | (dd2[0] << 24); -+#endif -+ d <<= 4; -+ fb_writel(dd, dst); -+ dst += 4; -+ } -+ } -+ -+ dst += info->fix.line_length - width * bytespp; -+ decor_src += (info->var.xres - width) * bytespp; -+ } -+} -+ -+#define cc2cx(a) \ -+ ((info->fix.visual == FB_VISUAL_TRUECOLOR || \ -+ info->fix.visual == FB_VISUAL_DIRECTCOLOR) ? \ -+ ((u32*)info->pseudo_palette)[a] : a) -+ -+void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info, -+ const unsigned short *s, int count, int yy, int xx) -+{ -+ unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; -+ struct fbcon_ops *ops = info->fbcon_par; -+ int fg_color, bg_color, transparent; -+ u8 *src; -+ u32 bgx, fgx; -+ u16 c = scr_readw(s); -+ -+ fg_color = get_color(vc, info, c, 1); -+ bg_color = get_color(vc, info, c, 0); -+ -+ /* Don't paint the background image if console is blanked */ -+ transparent = ops->blank_state ? 0 : -+ (vc->vc_decor.bg_color == bg_color); -+ -+ xx = xx * vc->vc_font.width + vc->vc_decor.tx; -+ yy = yy * vc->vc_font.height + vc->vc_decor.ty; -+ -+ fgx = cc2cx(fg_color); -+ bgx = cc2cx(bg_color); -+ -+ while (count--) { -+ c = scr_readw(s++); -+ src = vc->vc_font.data + (c & charmask) * vc->vc_font.height * -+ ((vc->vc_font.width + 7) >> 3); -+ -+ fbcon_decor_renderc(info, yy, xx, vc->vc_font.height, -+ vc->vc_font.width, src, fgx, bgx, transparent); -+ xx += vc->vc_font.width; -+ } -+} -+ -+void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor) -+{ -+ int i; -+ unsigned int dsize, s_pitch; -+ struct fbcon_ops *ops = info->fbcon_par; -+ struct vc_data* vc; -+ u8 *src; -+ -+ /* we really don't need any cursors while the console is blanked */ -+ if (info->state != FBINFO_STATE_RUNNING || ops->blank_state) -+ return; -+ -+ vc = vc_cons[ops->currcon].d; -+ -+ src = kmalloc(64 + sizeof(struct fb_image), GFP_ATOMIC); -+ if (!src) -+ return; -+ -+ s_pitch = (cursor->image.width + 7) >> 3; -+ dsize = s_pitch * cursor->image.height; -+ if (cursor->enable) { -+ switch (cursor->rop) { -+ case ROP_XOR: -+ for (i = 0; i < dsize; i++) -+ src[i] = cursor->image.data[i] ^ cursor->mask[i]; -+ break; -+ case ROP_COPY: -+ default: -+ for (i = 0; i < dsize; i++) -+ src[i] = cursor->image.data[i] & cursor->mask[i]; -+ break; -+ } -+ } else -+ memcpy(src, cursor->image.data, dsize); -+ -+ fbcon_decor_renderc(info, -+ cursor->image.dy + vc->vc_decor.ty, -+ cursor->image.dx + vc->vc_decor.tx, -+ cursor->image.height, -+ cursor->image.width, -+ (u8*)src, -+ cc2cx(cursor->image.fg_color), -+ cc2cx(cursor->image.bg_color), -+ cursor->image.bg_color == vc->vc_decor.bg_color); -+ -+ kfree(src); -+} -+ -+static void decorset(u8 *dst, int height, int width, int dstbytes, -+ u32 bgx, int bpp) -+{ -+ int i; -+ -+ if (bpp == 8) -+ bgx |= bgx << 8; -+ if (bpp == 16 || bpp == 8) -+ bgx |= bgx << 16; -+ -+ while (height-- > 0) { -+ u8 *p = dst; -+ -+ switch (bpp) { -+ -+ case 32: -+ for (i=0; i < width; i++) { -+ fb_writel(bgx, p); p += 4; -+ } -+ break; -+ case 24: -+ for (i=0; i < width; i++) { -+#ifdef __LITTLE_ENDIAN -+ fb_writew((bgx & 0xffff),(u16*)p); p += 2; -+ fb_writeb((bgx >> 16),p++); -+#else -+ fb_writew((bgx >> 8),(u16*)p); p += 2; -+ fb_writeb((bgx & 0xff),p++); -+#endif -+ } -+ case 16: -+ for (i=0; i < width/4; i++) { -+ fb_writel(bgx,p); p += 4; -+ fb_writel(bgx,p); p += 4; -+ } -+ if (width & 2) { -+ fb_writel(bgx,p); p += 4; -+ } -+ if (width & 1) -+ fb_writew(bgx,(u16*)p); -+ break; -+ case 8: -+ for (i=0; i < width/4; i++) { -+ fb_writel(bgx,p); p += 4; -+ } -+ -+ if (width & 2) { -+ fb_writew(bgx,p); p += 2; -+ } -+ if (width & 1) -+ fb_writeb(bgx,(u8*)p); -+ break; -+ -+ } -+ dst += dstbytes; -+ } -+} -+ -+void fbcon_decor_copy(u8 *dst, u8 *src, int height, int width, int linebytes, -+ int srclinebytes, int bpp) -+{ -+ int i; -+ -+ while (height-- > 0) { -+ u32 *p = (u32 *)dst; -+ u32 *q = (u32 *)src; -+ -+ switch (bpp) { -+ -+ case 32: -+ for (i=0; i < width; i++) -+ fb_writel(*q++, p++); -+ break; -+ case 24: -+ for (i=0; i < (width*3/4); i++) -+ fb_writel(*q++, p++); -+ if ((width*3) % 4) { -+ if (width & 2) { -+ fb_writeb(*(u8*)q, (u8*)p); -+ } else if (width & 1) { -+ fb_writew(*(u16*)q, (u16*)p); -+ fb_writeb(*(u8*)((u16*)q+1),(u8*)((u16*)p+2)); -+ } -+ } -+ break; -+ case 16: -+ for (i=0; i < width/4; i++) { -+ fb_writel(*q++, p++); -+ fb_writel(*q++, p++); -+ } -+ if (width & 2) -+ fb_writel(*q++, p++); -+ if (width & 1) -+ fb_writew(*(u16*)q, (u16*)p); -+ break; -+ case 8: -+ for (i=0; i < width/4; i++) -+ fb_writel(*q++, p++); -+ -+ if (width & 2) { -+ fb_writew(*(u16*)q, (u16*)p); -+ q = (u32*) ((u16*)q + 1); -+ p = (u32*) ((u16*)p + 1); -+ } -+ if (width & 1) -+ fb_writeb(*(u8*)q, (u8*)p); -+ break; -+ } -+ -+ dst += linebytes; -+ src += srclinebytes; -+ } -+} -+ -+static void decorfill(struct fb_info *info, int sy, int sx, int height, -+ int width) -+{ -+ int bytespp = ((info->var.bits_per_pixel + 7) >> 3); -+ int d = sy * info->fix.line_length + sx * bytespp; -+ int ds = (sy * info->var.xres + sx) * bytespp; -+ -+ fbcon_decor_copy((u8 *)(info->screen_base + d), (u8 *)(info->bgdecor.data + ds), -+ height, width, info->fix.line_length, info->var.xres * bytespp, -+ info->var.bits_per_pixel); -+} -+ -+void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, -+ int height, int width) -+{ -+ int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; -+ struct fbcon_ops *ops = info->fbcon_par; -+ u8 *dst; -+ int transparent, bg_color = attr_bgcol_ec(bgshift, vc, info); -+ -+ transparent = (vc->vc_decor.bg_color == bg_color); -+ sy = sy * vc->vc_font.height + vc->vc_decor.ty; -+ sx = sx * vc->vc_font.width + vc->vc_decor.tx; -+ height *= vc->vc_font.height; -+ width *= vc->vc_font.width; -+ -+ /* Don't paint the background image if console is blanked */ -+ if (transparent && !ops->blank_state) { -+ decorfill(info, sy, sx, height, width); -+ } else { -+ dst = (u8 *)(info->screen_base + sy * info->fix.line_length + -+ sx * ((info->var.bits_per_pixel + 7) >> 3)); -+ decorset(dst, height, width, info->fix.line_length, cc2cx(bg_color), -+ info->var.bits_per_pixel); -+ } -+} -+ -+void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info, -+ int bottom_only) -+{ -+ unsigned int tw = vc->vc_cols*vc->vc_font.width; -+ unsigned int th = vc->vc_rows*vc->vc_font.height; -+ -+ if (!bottom_only) { -+ /* top margin */ -+ decorfill(info, 0, 0, vc->vc_decor.ty, info->var.xres); -+ /* left margin */ -+ decorfill(info, vc->vc_decor.ty, 0, th, vc->vc_decor.tx); -+ /* right margin */ -+ decorfill(info, vc->vc_decor.ty, vc->vc_decor.tx + tw, th, -+ info->var.xres - vc->vc_decor.tx - tw); -+ } -+ decorfill(info, vc->vc_decor.ty + th, 0, -+ info->var.yres - vc->vc_decor.ty - th, info->var.xres); -+} -+ -+void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, -+ int sx, int dx, int width) -+{ -+ u16 *d = (u16 *) (vc->vc_origin + vc->vc_size_row * y + dx * 2); -+ u16 *s = d + (dx - sx); -+ u16 *start = d; -+ u16 *ls = d; -+ u16 *le = d + width; -+ u16 c; -+ int x = dx; -+ u16 attr = 1; -+ -+ do { -+ c = scr_readw(d); -+ if (attr != (c & 0xff00)) { -+ attr = c & 0xff00; -+ if (d > start) { -+ fbcon_decor_putcs(vc, info, start, d - start, y, x); -+ x += d - start; -+ start = d; -+ } -+ } -+ if (s >= ls && s < le && c == scr_readw(s)) { -+ if (d > start) { -+ fbcon_decor_putcs(vc, info, start, d - start, y, x); -+ x += d - start + 1; -+ start = d + 1; -+ } else { -+ x++; -+ start++; -+ } -+ } -+ s++; -+ d++; -+ } while (d < le); -+ if (d > start) -+ fbcon_decor_putcs(vc, info, start, d - start, y, x); -+} -+ -+void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank) -+{ -+ if (blank) { -+ decorset((u8 *)info->screen_base, info->var.yres, info->var.xres, -+ info->fix.line_length, 0, info->var.bits_per_pixel); -+ } else { -+ update_screen(vc); -+ fbcon_decor_clear_margins(vc, info, 0); -+ } -+} -+ -diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c -index f447734..da50d61 100644 ---- a/drivers/video/console/fbcon.c -+++ b/drivers/video/console/fbcon.c -@@ -79,6 +79,7 @@ - #include - - #include "fbcon.h" -+#include "../console/fbcondecor.h" - - #ifdef FBCONDEBUG - # define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __func__ , ## args) -@@ -94,7 +95,7 @@ enum { - - static struct display fb_display[MAX_NR_CONSOLES]; - --static signed char con2fb_map[MAX_NR_CONSOLES]; -+signed char con2fb_map[MAX_NR_CONSOLES]; - static signed char con2fb_map_boot[MAX_NR_CONSOLES]; - - static int logo_lines; -@@ -286,7 +287,7 @@ static inline int fbcon_is_inactive(struct vc_data *vc, struct fb_info *info) - !vt_force_oops_output(vc); - } - --static int get_color(struct vc_data *vc, struct fb_info *info, -+int get_color(struct vc_data *vc, struct fb_info *info, - u16 c, int is_fg) - { - int depth = fb_get_color_depth(&info->var, &info->fix); -@@ -551,6 +552,9 @@ static int do_fbcon_takeover(int show_logo) - info_idx = -1; - } else { - fbcon_has_console_bind = 1; -+#ifdef CONFIG_FB_CON_DECOR -+ fbcon_decor_init(); -+#endif - } - - return err; -@@ -1007,6 +1011,12 @@ static const char *fbcon_startup(void) - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); - cols /= vc->vc_font.width; - rows /= vc->vc_font.height; -+ -+ if (fbcon_decor_active(info, vc)) { -+ cols = vc->vc_decor.twidth / vc->vc_font.width; -+ rows = vc->vc_decor.theight / vc->vc_font.height; -+ } -+ - vc_resize(vc, cols, rows); - - DPRINTK("mode: %s\n", info->fix.id); -@@ -1036,7 +1046,7 @@ static void fbcon_init(struct vc_data *vc, int init) - cap = info->flags; - - if (vc != svc || logo_shown == FBCON_LOGO_DONTSHOW || -- (info->fix.type == FB_TYPE_TEXT)) -+ (info->fix.type == FB_TYPE_TEXT) || fbcon_decor_active(info, vc)) - logo = 0; - - if (var_to_display(p, &info->var, info)) -@@ -1260,6 +1270,11 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, - fbcon_clear_margins(vc, 0); - } - -+ if (fbcon_decor_active(info, vc)) { -+ fbcon_decor_clear(vc, info, sy, sx, height, width); -+ return; -+ } -+ - /* Split blits that cross physical y_wrap boundary */ - - y_break = p->vrows - p->yscroll; -@@ -1279,10 +1294,15 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, - struct display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; - -- if (!fbcon_is_inactive(vc, info)) -- ops->putcs(vc, info, s, count, real_y(p, ypos), xpos, -- get_color(vc, info, scr_readw(s), 1), -- get_color(vc, info, scr_readw(s), 0)); -+ if (!fbcon_is_inactive(vc, info)) { -+ -+ if (fbcon_decor_active(info, vc)) -+ fbcon_decor_putcs(vc, info, s, count, ypos, xpos); -+ else -+ ops->putcs(vc, info, s, count, real_y(p, ypos), xpos, -+ get_color(vc, info, scr_readw(s), 1), -+ get_color(vc, info, scr_readw(s), 0)); -+ } - } - - static void fbcon_putc(struct vc_data *vc, int c, int ypos, int xpos) -@@ -1298,8 +1318,13 @@ static void fbcon_clear_margins(struct vc_data *vc, int bottom_only) - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - -- if (!fbcon_is_inactive(vc, info)) -- ops->clear_margins(vc, info, bottom_only); -+ if (!fbcon_is_inactive(vc, info)) { -+ if (fbcon_decor_active(info, vc)) { -+ fbcon_decor_clear_margins(vc, info, bottom_only); -+ } else { -+ ops->clear_margins(vc, info, bottom_only); -+ } -+ } - } - - static void fbcon_cursor(struct vc_data *vc, int mode) -@@ -1819,7 +1844,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir, - count = vc->vc_rows; - if (softback_top) - fbcon_softback_note(vc, t, count); -- if (logo_shown >= 0) -+ if (logo_shown >= 0 || fbcon_decor_active(info, vc)) - goto redraw_up; - switch (p->scrollmode) { - case SCROLL_MOVE: -@@ -1912,6 +1937,8 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir, - count = vc->vc_rows; - if (logo_shown >= 0) - goto redraw_down; -+ if (fbcon_decor_active(info, vc)) -+ goto redraw_down; - switch (p->scrollmode) { - case SCROLL_MOVE: - fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, -@@ -2060,6 +2087,13 @@ static void fbcon_bmove_rec(struct vc_data *vc, struct display *p, int sy, int s - } - return; - } -+ -+ if (fbcon_decor_active(info, vc) && sy == dy && height == 1) { -+ /* must use slower redraw bmove to keep background pic intact */ -+ fbcon_decor_bmove_redraw(vc, info, sy, sx, dx, width); -+ return; -+ } -+ - ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, - height, width); - } -@@ -2130,8 +2164,8 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, - var.yres = virt_h * virt_fh; - x_diff = info->var.xres - var.xres; - y_diff = info->var.yres - var.yres; -- if (x_diff < 0 || x_diff > virt_fw || -- y_diff < 0 || y_diff > virt_fh) { -+ if ((x_diff < 0 || x_diff > virt_fw || -+ y_diff < 0 || y_diff > virt_fh) && !vc->vc_decor.state) { - const struct fb_videomode *mode; - - DPRINTK("attempting resize %ix%i\n", var.xres, var.yres); -@@ -2167,6 +2201,21 @@ static int fbcon_switch(struct vc_data *vc) - - info = registered_fb[con2fb_map[vc->vc_num]]; - ops = info->fbcon_par; -+ prev_console = ops->currcon; -+ if (prev_console != -1) -+ old_info = registered_fb[con2fb_map[prev_console]]; -+ -+#ifdef CONFIG_FB_CON_DECOR -+ if (!fbcon_decor_active_vc(vc) && info->fix.visual == FB_VISUAL_DIRECTCOLOR) { -+ struct vc_data *vc_curr = vc_cons[prev_console].d; -+ if (vc_curr && fbcon_decor_active_vc(vc_curr)) { -+ /* Clear the screen to avoid displaying funky colors during -+ * palette updates. */ -+ memset((u8*)info->screen_base + info->fix.line_length * info->var.yoffset, -+ 0, info->var.yres * info->fix.line_length); -+ } -+ } -+#endif - - if (softback_top) { - if (softback_lines) -@@ -2185,9 +2234,6 @@ static int fbcon_switch(struct vc_data *vc) - logo_shown = FBCON_LOGO_CANSHOW; - } - -- prev_console = ops->currcon; -- if (prev_console != -1) -- old_info = registered_fb[con2fb_map[prev_console]]; - /* - * FIXME: If we have multiple fbdev's loaded, we need to - * update all info->currcon. Perhaps, we can place this -@@ -2231,6 +2277,18 @@ static int fbcon_switch(struct vc_data *vc) - fbcon_del_cursor_timer(old_info); - } - -+ if (fbcon_decor_active_vc(vc)) { -+ struct vc_data *vc_curr = vc_cons[prev_console].d; -+ -+ if (!vc_curr->vc_decor.theme || -+ strcmp(vc->vc_decor.theme, vc_curr->vc_decor.theme) || -+ (fbcon_decor_active_nores(info, vc_curr) && -+ !fbcon_decor_active(info, vc_curr))) { -+ fbcon_decor_disable(vc, 0); -+ fbcon_decor_call_helper("modechange", vc->vc_num); -+ } -+ } -+ - if (fbcon_is_inactive(vc, info) || - ops->blank_state != FB_BLANK_UNBLANK) - fbcon_del_cursor_timer(info); -@@ -2339,15 +2397,20 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) - } - } - -- if (!fbcon_is_inactive(vc, info)) { -+ if (!fbcon_is_inactive(vc, info)) { - if (ops->blank_state != blank) { - ops->blank_state = blank; - fbcon_cursor(vc, blank ? CM_ERASE : CM_DRAW); - ops->cursor_flash = (!blank); - -- if (!(info->flags & FBINFO_MISC_USEREVENT)) -- if (fb_blank(info, blank)) -- fbcon_generic_blank(vc, info, blank); -+ if (!(info->flags & FBINFO_MISC_USEREVENT)) { -+ if (fb_blank(info, blank)) { -+ if (fbcon_decor_active(info, vc)) -+ fbcon_decor_blank(vc, info, blank); -+ else -+ fbcon_generic_blank(vc, info, blank); -+ } -+ } - } - - if (!blank) -@@ -2522,13 +2585,22 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, - } - - if (resize) { -+ /* reset wrap/pan */ - int cols, rows; - - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); -+ -+ if (fbcon_decor_active(info, vc)) { -+ info->var.xoffset = info->var.yoffset = p->yscroll = 0; -+ cols = vc->vc_decor.twidth; -+ rows = vc->vc_decor.theight; -+ } - cols /= w; - rows /= h; -+ - vc_resize(vc, cols, rows); -+ - if (CON_IS_VISIBLE(vc) && softback_buf) - fbcon_update_softback(vc); - } else if (CON_IS_VISIBLE(vc) -@@ -2657,7 +2729,11 @@ static int fbcon_set_palette(struct vc_data *vc, unsigned char *table) - int i, j, k, depth; - u8 val; - -- if (fbcon_is_inactive(vc, info)) -+ if (fbcon_is_inactive(vc, info) -+#ifdef CONFIG_FB_CON_DECOR -+ || vc->vc_num != fg_console -+#endif -+ ) - return -EINVAL; - - if (!CON_IS_VISIBLE(vc)) -@@ -2683,14 +2759,56 @@ static int fbcon_set_palette(struct vc_data *vc, unsigned char *table) - } else - fb_copy_cmap(fb_default_cmap(1 << depth), &palette_cmap); - -- return fb_set_cmap(&palette_cmap, info); -+ if (fbcon_decor_active(info, vc_cons[fg_console].d) && -+ info->fix.visual == FB_VISUAL_DIRECTCOLOR) { -+ -+ u16 *red, *green, *blue; -+ int minlen = min(min(info->var.red.length, info->var.green.length), -+ info->var.blue.length); -+ int h; -+ -+ struct fb_cmap cmap = { -+ .start = 0, -+ .len = (1 << minlen), -+ .red = NULL, -+ .green = NULL, -+ .blue = NULL, -+ .transp = NULL -+ }; -+ -+ red = kmalloc(256 * sizeof(u16) * 3, GFP_KERNEL); -+ -+ if (!red) -+ goto out; -+ -+ green = red + 256; -+ blue = green + 256; -+ cmap.red = red; -+ cmap.green = green; -+ cmap.blue = blue; -+ -+ for (i = 0; i < cmap.len; i++) { -+ red[i] = green[i] = blue[i] = (0xffff * i)/(cmap.len-1); -+ } -+ -+ h = fb_set_cmap(&cmap, info); -+ fbcon_decor_fix_pseudo_pal(info, vc_cons[fg_console].d); -+ kfree(red); -+ -+ return h; -+ -+ } else if (fbcon_decor_active(info, vc_cons[fg_console].d) && -+ info->var.bits_per_pixel == 8 && info->bgdecor.cmap.red != NULL) -+ fb_set_cmap(&info->bgdecor.cmap, info); -+ -+out: return fb_set_cmap(&palette_cmap, info); - } - - static u16 *fbcon_screen_pos(struct vc_data *vc, int offset) - { - unsigned long p; - int line; -- -+ - if (vc->vc_num != fg_console || !softback_lines) - return (u16 *) (vc->vc_origin + offset); - line = offset / vc->vc_size_row; -@@ -2909,7 +3027,14 @@ static void fbcon_modechanged(struct fb_info *info) - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); - cols /= vc->vc_font.width; - rows /= vc->vc_font.height; -- vc_resize(vc, cols, rows); -+ -+ if (!fbcon_decor_active_nores(info, vc)) { -+ vc_resize(vc, cols, rows); -+ } else { -+ fbcon_decor_disable(vc, 0); -+ fbcon_decor_call_helper("modechange", vc->vc_num); -+ } -+ - updatescrollmode(p, info, vc); - scrollback_max = 0; - scrollback_current = 0; -@@ -2954,7 +3079,9 @@ static void fbcon_set_all_vcs(struct fb_info *info) - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); - cols /= vc->vc_font.width; - rows /= vc->vc_font.height; -- vc_resize(vc, cols, rows); -+ if (!fbcon_decor_active_nores(info, vc)) { -+ vc_resize(vc, cols, rows); -+ } - } - - if (fg != -1) -@@ -3596,6 +3723,7 @@ static void fbcon_exit(void) - } - } - -+ fbcon_decor_exit(); - fbcon_has_exited = 1; - } - -diff --git a/drivers/video/console/fbcondecor.c b/drivers/video/console/fbcondecor.c -new file mode 100644 -index 0000000..babc8c5 ---- /dev/null -+++ b/drivers/video/console/fbcondecor.c -@@ -0,0 +1,555 @@ -+/* -+ * linux/drivers/video/console/fbcondecor.c -- Framebuffer console decorations -+ * -+ * Copyright (C) 2004-2009 Michal Januszewski -+ * -+ * Code based upon "Bootsplash" (C) 2001-2003 -+ * Volker Poplawski , -+ * Stefan Reinauer , -+ * Steffen Winterfeldt , -+ * Michael Schroeder , -+ * Ken Wimer . -+ * -+ * Compat ioctl support by Thorsten Klein . -+ * -+ * This file is subject to the terms and conditions of the GNU General Public -+ * License. See the file COPYING in the main directory of this archive for -+ * more details. -+ * -+ */ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#include -+#include -+ -+#include "fbcon.h" -+#include "fbcondecor.h" -+ -+extern signed char con2fb_map[]; -+static int fbcon_decor_enable(struct vc_data *vc); -+char fbcon_decor_path[KMOD_PATH_LEN] = "/sbin/fbcondecor_helper"; -+static int initialized = 0; -+ -+int fbcon_decor_call_helper(char* cmd, unsigned short vc) -+{ -+ char *envp[] = { -+ "HOME=/", -+ "PATH=/sbin:/bin", -+ NULL -+ }; -+ -+ char tfb[5]; -+ char tcons[5]; -+ unsigned char fb = (int) con2fb_map[vc]; -+ -+ char *argv[] = { -+ fbcon_decor_path, -+ "2", -+ cmd, -+ tcons, -+ tfb, -+ vc_cons[vc].d->vc_decor.theme, -+ NULL -+ }; -+ -+ snprintf(tfb,5,"%d",fb); -+ snprintf(tcons,5,"%d",vc); -+ -+ return call_usermodehelper(fbcon_decor_path, argv, envp, UMH_WAIT_EXEC); -+} -+ -+/* Disables fbcondecor on a virtual console; called with console sem held. */ -+int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw) -+{ -+ struct fb_info* info; -+ -+ if (!vc->vc_decor.state) -+ return -EINVAL; -+ -+ info = registered_fb[(int) con2fb_map[vc->vc_num]]; -+ -+ if (info == NULL) -+ return -EINVAL; -+ -+ vc->vc_decor.state = 0; -+ vc_resize(vc, info->var.xres / vc->vc_font.width, -+ info->var.yres / vc->vc_font.height); -+ -+ if (fg_console == vc->vc_num && redraw) { -+ redraw_screen(vc, 0); -+ update_region(vc, vc->vc_origin + -+ vc->vc_size_row * vc->vc_top, -+ vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2); -+ } -+ -+ printk(KERN_INFO "fbcondecor: switched decor state to 'off' on console %d\n", -+ vc->vc_num); -+ -+ return 0; -+} -+ -+/* Enables fbcondecor on a virtual console; called with console sem held. */ -+static int fbcon_decor_enable(struct vc_data *vc) -+{ -+ struct fb_info* info; -+ -+ info = registered_fb[(int) con2fb_map[vc->vc_num]]; -+ -+ if (vc->vc_decor.twidth == 0 || vc->vc_decor.theight == 0 || -+ info == NULL || vc->vc_decor.state || (!info->bgdecor.data && -+ vc->vc_num == fg_console)) -+ return -EINVAL; -+ -+ vc->vc_decor.state = 1; -+ vc_resize(vc, vc->vc_decor.twidth / vc->vc_font.width, -+ vc->vc_decor.theight / vc->vc_font.height); -+ -+ if (fg_console == vc->vc_num) { -+ redraw_screen(vc, 0); -+ update_region(vc, vc->vc_origin + -+ vc->vc_size_row * vc->vc_top, -+ vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2); -+ fbcon_decor_clear_margins(vc, info, 0); -+ } -+ -+ printk(KERN_INFO "fbcondecor: switched decor state to 'on' on console %d\n", -+ vc->vc_num); -+ -+ return 0; -+} -+ -+static inline int fbcon_decor_ioctl_dosetstate(struct vc_data *vc, unsigned int state, unsigned char origin) -+{ -+ int ret; -+ -+// if (origin == FBCON_DECOR_IO_ORIG_USER) -+ console_lock(); -+ if (!state) -+ ret = fbcon_decor_disable(vc, 1); -+ else -+ ret = fbcon_decor_enable(vc); -+// if (origin == FBCON_DECOR_IO_ORIG_USER) -+ console_unlock(); -+ -+ return ret; -+} -+ -+static inline void fbcon_decor_ioctl_dogetstate(struct vc_data *vc, unsigned int *state) -+{ -+ *state = vc->vc_decor.state; -+} -+ -+static int fbcon_decor_ioctl_dosetcfg(struct vc_data *vc, struct vc_decor *cfg, unsigned char origin) -+{ -+ struct fb_info *info; -+ int len; -+ char *tmp; -+ -+ info = registered_fb[(int) con2fb_map[vc->vc_num]]; -+ -+ if (info == NULL || !cfg->twidth || !cfg->theight || -+ cfg->tx + cfg->twidth > info->var.xres || -+ cfg->ty + cfg->theight > info->var.yres) -+ return -EINVAL; -+ -+ len = strlen_user(cfg->theme); -+ if (!len || len > FBCON_DECOR_THEME_LEN) -+ return -EINVAL; -+ tmp = kmalloc(len, GFP_KERNEL); -+ if (!tmp) -+ return -ENOMEM; -+ if (copy_from_user(tmp, (void __user *)cfg->theme, len)) -+ return -EFAULT; -+ cfg->theme = tmp; -+ cfg->state = 0; -+ -+ /* If this ioctl is a response to a request from kernel, the console sem -+ * is already held; we also don't need to disable decor because either the -+ * new config and background picture will be successfully loaded, and the -+ * decor will stay on, or in case of a failure it'll be turned off in fbcon. */ -+// if (origin == FBCON_DECOR_IO_ORIG_USER) { -+ console_lock(); -+ if (vc->vc_decor.state) -+ fbcon_decor_disable(vc, 1); -+// } -+ -+ if (vc->vc_decor.theme) -+ kfree(vc->vc_decor.theme); -+ -+ vc->vc_decor = *cfg; -+ -+// if (origin == FBCON_DECOR_IO_ORIG_USER) -+ console_unlock(); -+ -+ printk(KERN_INFO "fbcondecor: console %d using theme '%s'\n", -+ vc->vc_num, vc->vc_decor.theme); -+ return 0; -+} -+ -+static int fbcon_decor_ioctl_dogetcfg(struct vc_data *vc, struct vc_decor *decor) -+{ -+ char __user *tmp; -+ -+ tmp = decor->theme; -+ *decor = vc->vc_decor; -+ decor->theme = tmp; -+ -+ if (vc->vc_decor.theme) { -+ if (copy_to_user(tmp, vc->vc_decor.theme, strlen(vc->vc_decor.theme) + 1)) -+ return -EFAULT; -+ } else -+ if (put_user(0, tmp)) -+ return -EFAULT; -+ -+ return 0; -+} -+ -+static int fbcon_decor_ioctl_dosetpic(struct vc_data *vc, struct fb_image *img, unsigned char origin) -+{ -+ struct fb_info *info; -+ int len; -+ u8 *tmp; -+ -+ if (vc->vc_num != fg_console) -+ return -EINVAL; -+ -+ info = registered_fb[(int) con2fb_map[vc->vc_num]]; -+ -+ if (info == NULL) -+ return -EINVAL; -+ -+ if (img->width != info->var.xres || img->height != info->var.yres) { -+ printk(KERN_ERR "fbcondecor: picture dimensions mismatch\n"); -+ printk(KERN_ERR "%dx%d vs %dx%d\n", img->width, img->height, info->var.xres, info->var.yres); -+ return -EINVAL; -+ } -+ -+ if (img->depth != info->var.bits_per_pixel) { -+ printk(KERN_ERR "fbcondecor: picture depth mismatch\n"); -+ return -EINVAL; -+ } -+ -+ if (img->depth == 8) { -+ if (!img->cmap.len || !img->cmap.red || !img->cmap.green || -+ !img->cmap.blue) -+ return -EINVAL; -+ -+ tmp = vmalloc(img->cmap.len * 3 * 2); -+ if (!tmp) -+ return -ENOMEM; -+ -+ if (copy_from_user(tmp, -+ (void __user*)img->cmap.red, (img->cmap.len << 1)) || -+ copy_from_user(tmp + (img->cmap.len << 1), -+ (void __user*)img->cmap.green, (img->cmap.len << 1)) || -+ copy_from_user(tmp + (img->cmap.len << 2), -+ (void __user*)img->cmap.blue, (img->cmap.len << 1))) { -+ vfree(tmp); -+ return -EFAULT; -+ } -+ -+ img->cmap.transp = NULL; -+ img->cmap.red = (u16*)tmp; -+ img->cmap.green = img->cmap.red + img->cmap.len; -+ img->cmap.blue = img->cmap.green + img->cmap.len; -+ } else { -+ img->cmap.red = NULL; -+ } -+ -+ len = ((img->depth + 7) >> 3) * img->width * img->height; -+ -+ /* -+ * Allocate an additional byte so that we never go outside of the -+ * buffer boundaries in the rendering functions in a 24 bpp mode. -+ */ -+ tmp = vmalloc(len + 1); -+ -+ if (!tmp) -+ goto out; -+ -+ if (copy_from_user(tmp, (void __user*)img->data, len)) -+ goto out; -+ -+ img->data = tmp; -+ -+ /* If this ioctl is a response to a request from kernel, the console sem -+ * is already held. */ -+// if (origin == FBCON_DECOR_IO_ORIG_USER) -+ console_lock(); -+ -+ if (info->bgdecor.data) -+ vfree((u8*)info->bgdecor.data); -+ if (info->bgdecor.cmap.red) -+ vfree(info->bgdecor.cmap.red); -+ -+ info->bgdecor = *img; -+ -+ if (fbcon_decor_active_vc(vc) && fg_console == vc->vc_num) { -+ redraw_screen(vc, 0); -+ update_region(vc, vc->vc_origin + -+ vc->vc_size_row * vc->vc_top, -+ vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2); -+ fbcon_decor_clear_margins(vc, info, 0); -+ } -+ -+// if (origin == FBCON_DECOR_IO_ORIG_USER) -+ console_unlock(); -+ -+ return 0; -+ -+out: if (img->cmap.red) -+ vfree(img->cmap.red); -+ -+ if (tmp) -+ vfree(tmp); -+ return -ENOMEM; -+} -+ -+static long fbcon_decor_ioctl(struct file *filp, u_int cmd, u_long arg) -+{ -+ struct fbcon_decor_iowrapper __user *wrapper = (void __user*) arg; -+ struct vc_data *vc = NULL; -+ unsigned short vc_num = 0; -+ unsigned char origin = 0; -+ void __user *data = NULL; -+ -+ if (!access_ok(VERIFY_READ, wrapper, -+ sizeof(struct fbcon_decor_iowrapper))) -+ return -EFAULT; -+ -+ __get_user(vc_num, &wrapper->vc); -+ __get_user(origin, &wrapper->origin); -+ __get_user(data, &wrapper->data); -+ -+ if (!vc_cons_allocated(vc_num)) -+ return -EINVAL; -+ -+ vc = vc_cons[vc_num].d; -+ -+ switch (cmd) { -+ case FBIOCONDECOR_SETPIC: -+ { -+ struct fb_image img; -+ if (copy_from_user(&img, (struct fb_image __user *)data, sizeof(struct fb_image))) -+ return -EFAULT; -+ -+ return fbcon_decor_ioctl_dosetpic(vc, &img, origin); -+ } -+ case FBIOCONDECOR_SETCFG: -+ { -+ struct vc_decor cfg; -+ if (copy_from_user(&cfg, (struct vc_decor __user *)data, sizeof(struct vc_decor))) -+ return -EFAULT; -+ -+ return fbcon_decor_ioctl_dosetcfg(vc, &cfg, origin); -+ } -+ case FBIOCONDECOR_GETCFG: -+ { -+ int rval; -+ struct vc_decor cfg; -+ -+ if (copy_from_user(&cfg, (struct vc_decor __user *)data, sizeof(struct vc_decor))) -+ return -EFAULT; -+ -+ rval = fbcon_decor_ioctl_dogetcfg(vc, &cfg); -+ -+ if (copy_to_user(data, &cfg, sizeof(struct vc_decor))) -+ return -EFAULT; -+ return rval; -+ } -+ case FBIOCONDECOR_SETSTATE: -+ { -+ unsigned int state = 0; -+ if (get_user(state, (unsigned int __user *)data)) -+ return -EFAULT; -+ return fbcon_decor_ioctl_dosetstate(vc, state, origin); -+ } -+ case FBIOCONDECOR_GETSTATE: -+ { -+ unsigned int state = 0; -+ fbcon_decor_ioctl_dogetstate(vc, &state); -+ return put_user(state, (unsigned int __user *)data); -+ } -+ -+ default: -+ return -ENOIOCTLCMD; -+ } -+} -+ -+#ifdef CONFIG_COMPAT -+ -+static long fbcon_decor_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { -+ -+ struct fbcon_decor_iowrapper32 __user *wrapper = (void __user *)arg; -+ struct vc_data *vc = NULL; -+ unsigned short vc_num = 0; -+ unsigned char origin = 0; -+ compat_uptr_t data_compat = 0; -+ void __user *data = NULL; -+ -+ if (!access_ok(VERIFY_READ, wrapper, -+ sizeof(struct fbcon_decor_iowrapper32))) -+ return -EFAULT; -+ -+ __get_user(vc_num, &wrapper->vc); -+ __get_user(origin, &wrapper->origin); -+ __get_user(data_compat, &wrapper->data); -+ data = compat_ptr(data_compat); -+ -+ if (!vc_cons_allocated(vc_num)) -+ return -EINVAL; -+ -+ vc = vc_cons[vc_num].d; -+ -+ switch (cmd) { -+ case FBIOCONDECOR_SETPIC32: -+ { -+ struct fb_image32 img_compat; -+ struct fb_image img; -+ -+ if (copy_from_user(&img_compat, (struct fb_image32 __user *)data, sizeof(struct fb_image32))) -+ return -EFAULT; -+ -+ fb_image_from_compat(img, img_compat); -+ -+ return fbcon_decor_ioctl_dosetpic(vc, &img, origin); -+ } -+ -+ case FBIOCONDECOR_SETCFG32: -+ { -+ struct vc_decor32 cfg_compat; -+ struct vc_decor cfg; -+ -+ if (copy_from_user(&cfg_compat, (struct vc_decor32 __user *)data, sizeof(struct vc_decor32))) -+ return -EFAULT; -+ -+ vc_decor_from_compat(cfg, cfg_compat); -+ -+ return fbcon_decor_ioctl_dosetcfg(vc, &cfg, origin); -+ } -+ -+ case FBIOCONDECOR_GETCFG32: -+ { -+ int rval; -+ struct vc_decor32 cfg_compat; -+ struct vc_decor cfg; -+ -+ if (copy_from_user(&cfg_compat, (struct vc_decor32 __user *)data, sizeof(struct vc_decor32))) -+ return -EFAULT; -+ cfg.theme = compat_ptr(cfg_compat.theme); -+ -+ rval = fbcon_decor_ioctl_dogetcfg(vc, &cfg); -+ -+ vc_decor_to_compat(cfg_compat, cfg); -+ -+ if (copy_to_user((struct vc_decor32 __user *)data, &cfg_compat, sizeof(struct vc_decor32))) -+ return -EFAULT; -+ return rval; -+ } -+ -+ case FBIOCONDECOR_SETSTATE32: -+ { -+ compat_uint_t state_compat = 0; -+ unsigned int state = 0; -+ -+ if (get_user(state_compat, (compat_uint_t __user *)data)) -+ return -EFAULT; -+ -+ state = (unsigned int)state_compat; -+ -+ return fbcon_decor_ioctl_dosetstate(vc, state, origin); -+ } -+ -+ case FBIOCONDECOR_GETSTATE32: -+ { -+ compat_uint_t state_compat = 0; -+ unsigned int state = 0; -+ -+ fbcon_decor_ioctl_dogetstate(vc, &state); -+ state_compat = (compat_uint_t)state; -+ -+ return put_user(state_compat, (compat_uint_t __user *)data); -+ } -+ -+ default: -+ return -ENOIOCTLCMD; -+ } -+} -+#else -+ #define fbcon_decor_compat_ioctl NULL -+#endif -+ -+static struct file_operations fbcon_decor_ops = { -+ .owner = THIS_MODULE, -+ .unlocked_ioctl = fbcon_decor_ioctl, -+ .compat_ioctl = fbcon_decor_compat_ioctl -+}; -+ -+static struct miscdevice fbcon_decor_dev = { -+ .minor = MISC_DYNAMIC_MINOR, -+ .name = "fbcondecor", -+ .fops = &fbcon_decor_ops -+}; -+ -+void fbcon_decor_reset(void) -+{ -+ int i; -+ -+ for (i = 0; i < num_registered_fb; i++) { -+ registered_fb[i]->bgdecor.data = NULL; -+ registered_fb[i]->bgdecor.cmap.red = NULL; -+ } -+ -+ for (i = 0; i < MAX_NR_CONSOLES && vc_cons[i].d; i++) { -+ vc_cons[i].d->vc_decor.state = vc_cons[i].d->vc_decor.twidth = -+ vc_cons[i].d->vc_decor.theight = 0; -+ vc_cons[i].d->vc_decor.theme = NULL; -+ } -+ -+ return; -+} -+ -+int fbcon_decor_init(void) -+{ -+ int i; -+ -+ fbcon_decor_reset(); -+ -+ if (initialized) -+ return 0; -+ -+ i = misc_register(&fbcon_decor_dev); -+ if (i) { -+ printk(KERN_ERR "fbcondecor: failed to register device\n"); -+ return i; -+ } -+ -+ fbcon_decor_call_helper("init", 0); -+ initialized = 1; -+ return 0; -+} -+ -+int fbcon_decor_exit(void) -+{ -+ fbcon_decor_reset(); -+ return 0; -+} -+ -+EXPORT_SYMBOL(fbcon_decor_path); -diff --git a/drivers/video/console/fbcondecor.h b/drivers/video/console/fbcondecor.h -new file mode 100644 -index 0000000..3b3724b ---- /dev/null -+++ b/drivers/video/console/fbcondecor.h -@@ -0,0 +1,78 @@ -+/* -+ * linux/drivers/video/console/fbcondecor.h -- Framebuffer Console Decoration headers -+ * -+ * Copyright (C) 2004 Michal Januszewski -+ * -+ */ -+ -+#ifndef __FBCON_DECOR_H -+#define __FBCON_DECOR_H -+ -+#ifndef _LINUX_FB_H -+#include -+#endif -+ -+/* This is needed for vc_cons in fbcmap.c */ -+#include -+ -+struct fb_cursor; -+struct fb_info; -+struct vc_data; -+ -+#ifdef CONFIG_FB_CON_DECOR -+/* fbcondecor.c */ -+int fbcon_decor_init(void); -+int fbcon_decor_exit(void); -+int fbcon_decor_call_helper(char* cmd, unsigned short cons); -+int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw); -+ -+/* cfbcondecor.c */ -+void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx); -+void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor); -+void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width); -+void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only); -+void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank); -+void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, int sx, int dx, int width); -+void fbcon_decor_copy(u8 *dst, u8 *src, int height, int width, int linebytes, int srclinesbytes, int bpp); -+void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc); -+ -+/* vt.c */ -+void acquire_console_sem(void); -+void release_console_sem(void); -+void do_unblank_screen(int entering_gfx); -+ -+/* struct vc_data *y */ -+#define fbcon_decor_active_vc(y) (y->vc_decor.state && y->vc_decor.theme) -+ -+/* struct fb_info *x, struct vc_data *y */ -+#define fbcon_decor_active_nores(x,y) (x->bgdecor.data && fbcon_decor_active_vc(y)) -+ -+/* struct fb_info *x, struct vc_data *y */ -+#define fbcon_decor_active(x,y) (fbcon_decor_active_nores(x,y) && \ -+ x->bgdecor.width == x->var.xres && \ -+ x->bgdecor.height == x->var.yres && \ -+ x->bgdecor.depth == x->var.bits_per_pixel) -+ -+ -+#else /* CONFIG_FB_CON_DECOR */ -+ -+static inline void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx) {} -+static inline void fbcon_decor_putc(struct vc_data *vc, struct fb_info *info, int c, int ypos, int xpos) {} -+static inline void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor) {} -+static inline void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) {} -+static inline void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only) {} -+static inline void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank) {} -+static inline void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, int sx, int dx, int width) {} -+static inline void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc) {} -+static inline int fbcon_decor_call_helper(char* cmd, unsigned short cons) { return 0; } -+static inline int fbcon_decor_init(void) { return 0; } -+static inline int fbcon_decor_exit(void) { return 0; } -+static inline int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw) { return 0; } -+ -+#define fbcon_decor_active_vc(y) (0) -+#define fbcon_decor_active_nores(x,y) (0) -+#define fbcon_decor_active(x,y) (0) -+ -+#endif /* CONFIG_FB_CON_DECOR */ -+ -+#endif /* __FBCON_DECOR_H */ -diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig -index e1f4727..2952e33 100644 ---- a/drivers/video/fbdev/Kconfig -+++ b/drivers/video/fbdev/Kconfig -@@ -1204,7 +1204,6 @@ config FB_MATROX - select FB_CFB_FILLRECT - select FB_CFB_COPYAREA - select FB_CFB_IMAGEBLIT -- select FB_TILEBLITTING - select FB_MACMODES if PPC_PMAC - ---help--- - Say Y here if you have a Matrox Millennium, Matrox Millennium II, -diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c -index f89245b..05e036c 100644 ---- a/drivers/video/fbdev/core/fbcmap.c -+++ b/drivers/video/fbdev/core/fbcmap.c -@@ -17,6 +17,8 @@ - #include - #include - -+#include "../../console/fbcondecor.h" -+ - static u16 red2[] __read_mostly = { - 0x0000, 0xaaaa - }; -@@ -249,14 +251,17 @@ int fb_set_cmap(struct fb_cmap *cmap, struct fb_info *info) - if (transp) - htransp = *transp++; - if (info->fbops->fb_setcolreg(start++, -- hred, hgreen, hblue, -+ hred, hgreen, hblue, - htransp, info)) - break; - } - } -- if (rc == 0) -+ if (rc == 0) { - fb_copy_cmap(cmap, &info->cmap); -- -+ if (fbcon_decor_active(info, vc_cons[fg_console].d) && -+ info->fix.visual == FB_VISUAL_DIRECTCOLOR) -+ fbcon_decor_fix_pseudo_pal(info, vc_cons[fg_console].d); -+ } - return rc; - } - -diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c -index b6d5008..d6703f2 100644 ---- a/drivers/video/fbdev/core/fbmem.c -+++ b/drivers/video/fbdev/core/fbmem.c -@@ -1250,15 +1250,6 @@ struct fb_fix_screeninfo32 { - u16 reserved[3]; - }; - --struct fb_cmap32 { -- u32 start; -- u32 len; -- compat_caddr_t red; -- compat_caddr_t green; -- compat_caddr_t blue; -- compat_caddr_t transp; --}; -- - static int fb_getput_cmap(struct fb_info *info, unsigned int cmd, - unsigned long arg) - { -diff --git a/include/linux/console_decor.h b/include/linux/console_decor.h -new file mode 100644 -index 0000000..04b8d80 ---- /dev/null -+++ b/include/linux/console_decor.h -@@ -0,0 +1,46 @@ -+#ifndef _LINUX_CONSOLE_DECOR_H_ -+#define _LINUX_CONSOLE_DECOR_H_ 1 -+ -+/* A structure used by the framebuffer console decorations (drivers/video/console/fbcondecor.c) */ -+struct vc_decor { -+ __u8 bg_color; /* The color that is to be treated as transparent */ -+ __u8 state; /* Current decor state: 0 = off, 1 = on */ -+ __u16 tx, ty; /* Top left corner coordinates of the text field */ -+ __u16 twidth, theight; /* Width and height of the text field */ -+ char* theme; -+}; -+ -+#ifdef __KERNEL__ -+#ifdef CONFIG_COMPAT -+#include -+ -+struct vc_decor32 { -+ __u8 bg_color; /* The color that is to be treated as transparent */ -+ __u8 state; /* Current decor state: 0 = off, 1 = on */ -+ __u16 tx, ty; /* Top left corner coordinates of the text field */ -+ __u16 twidth, theight; /* Width and height of the text field */ -+ compat_uptr_t theme; -+}; -+ -+#define vc_decor_from_compat(to, from) \ -+ (to).bg_color = (from).bg_color; \ -+ (to).state = (from).state; \ -+ (to).tx = (from).tx; \ -+ (to).ty = (from).ty; \ -+ (to).twidth = (from).twidth; \ -+ (to).theight = (from).theight; \ -+ (to).theme = compat_ptr((from).theme) -+ -+#define vc_decor_to_compat(to, from) \ -+ (to).bg_color = (from).bg_color; \ -+ (to).state = (from).state; \ -+ (to).tx = (from).tx; \ -+ (to).ty = (from).ty; \ -+ (to).twidth = (from).twidth; \ -+ (to).theight = (from).theight; \ -+ (to).theme = ptr_to_compat((from).theme) -+ -+#endif /* CONFIG_COMPAT */ -+#endif /* __KERNEL__ */ -+ -+#endif -diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h -index 7f0c329..98f5d60 100644 ---- a/include/linux/console_struct.h -+++ b/include/linux/console_struct.h -@@ -19,6 +19,7 @@ - struct vt_struct; - - #define NPAR 16 -+#include - - struct vc_data { - struct tty_port port; /* Upper level data */ -@@ -107,6 +108,8 @@ struct vc_data { - unsigned long vc_uni_pagedir; - unsigned long *vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ - bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ -+ -+ struct vc_decor vc_decor; - /* additional information is in vt_kern.h */ - }; - -diff --git a/include/linux/fb.h b/include/linux/fb.h -index fe6ac95..1e36b03 100644 ---- a/include/linux/fb.h -+++ b/include/linux/fb.h -@@ -219,6 +219,34 @@ struct fb_deferred_io { - }; - #endif - -+#ifdef __KERNEL__ -+#ifdef CONFIG_COMPAT -+struct fb_image32 { -+ __u32 dx; /* Where to place image */ -+ __u32 dy; -+ __u32 width; /* Size of image */ -+ __u32 height; -+ __u32 fg_color; /* Only used when a mono bitmap */ -+ __u32 bg_color; -+ __u8 depth; /* Depth of the image */ -+ const compat_uptr_t data; /* Pointer to image data */ -+ struct fb_cmap32 cmap; /* color map info */ -+}; -+ -+#define fb_image_from_compat(to, from) \ -+ (to).dx = (from).dx; \ -+ (to).dy = (from).dy; \ -+ (to).width = (from).width; \ -+ (to).height = (from).height; \ -+ (to).fg_color = (from).fg_color; \ -+ (to).bg_color = (from).bg_color; \ -+ (to).depth = (from).depth; \ -+ (to).data = compat_ptr((from).data); \ -+ fb_cmap_from_compat((to).cmap, (from).cmap) -+ -+#endif /* CONFIG_COMPAT */ -+#endif /* __KERNEL__ */ -+ - /* - * Frame buffer operations - * -@@ -489,6 +517,9 @@ struct fb_info { - #define FBINFO_STATE_SUSPENDED 1 - u32 state; /* Hardware state i.e suspend */ - void *fbcon_par; /* fbcon use-only private area */ -+ -+ struct fb_image bgdecor; -+ - /* From here on everything is device dependent */ - void *par; - /* we need the PCI or similar aperture base/size not -diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h -index fb795c3..dc77a03 100644 ---- a/include/uapi/linux/fb.h -+++ b/include/uapi/linux/fb.h -@@ -8,6 +8,25 @@ - - #define FB_MAX 32 /* sufficient for now */ - -+struct fbcon_decor_iowrapper -+{ -+ unsigned short vc; /* Virtual console */ -+ unsigned char origin; /* Point of origin of the request */ -+ void *data; -+}; -+ -+#ifdef __KERNEL__ -+#ifdef CONFIG_COMPAT -+#include -+struct fbcon_decor_iowrapper32 -+{ -+ unsigned short vc; /* Virtual console */ -+ unsigned char origin; /* Point of origin of the request */ -+ compat_uptr_t data; -+}; -+#endif /* CONFIG_COMPAT */ -+#endif /* __KERNEL__ */ -+ - /* ioctls - 0x46 is 'F' */ - #define FBIOGET_VSCREENINFO 0x4600 -@@ -35,6 +54,25 @@ - #define FBIOGET_DISPINFO 0x4618 - #define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) - -+#define FBIOCONDECOR_SETCFG _IOWR('F', 0x19, struct fbcon_decor_iowrapper) -+#define FBIOCONDECOR_GETCFG _IOR('F', 0x1A, struct fbcon_decor_iowrapper) -+#define FBIOCONDECOR_SETSTATE _IOWR('F', 0x1B, struct fbcon_decor_iowrapper) -+#define FBIOCONDECOR_GETSTATE _IOR('F', 0x1C, struct fbcon_decor_iowrapper) -+#define FBIOCONDECOR_SETPIC _IOWR('F', 0x1D, struct fbcon_decor_iowrapper) -+#ifdef __KERNEL__ -+#ifdef CONFIG_COMPAT -+#define FBIOCONDECOR_SETCFG32 _IOWR('F', 0x19, struct fbcon_decor_iowrapper32) -+#define FBIOCONDECOR_GETCFG32 _IOR('F', 0x1A, struct fbcon_decor_iowrapper32) -+#define FBIOCONDECOR_SETSTATE32 _IOWR('F', 0x1B, struct fbcon_decor_iowrapper32) -+#define FBIOCONDECOR_GETSTATE32 _IOR('F', 0x1C, struct fbcon_decor_iowrapper32) -+#define FBIOCONDECOR_SETPIC32 _IOWR('F', 0x1D, struct fbcon_decor_iowrapper32) -+#endif /* CONFIG_COMPAT */ -+#endif /* __KERNEL__ */ -+ -+#define FBCON_DECOR_THEME_LEN 128 /* Maximum lenght of a theme name */ -+#define FBCON_DECOR_IO_ORIG_KERNEL 0 /* Kernel ioctl origin */ -+#define FBCON_DECOR_IO_ORIG_USER 1 /* User ioctl origin */ -+ - #define FB_TYPE_PACKED_PIXELS 0 /* Packed Pixels */ - #define FB_TYPE_PLANES 1 /* Non interleaved planes */ - #define FB_TYPE_INTERLEAVED_PLANES 2 /* Interleaved planes */ -@@ -277,6 +315,29 @@ struct fb_var_screeninfo { - __u32 reserved[4]; /* Reserved for future compatibility */ - }; - -+#ifdef __KERNEL__ -+#ifdef CONFIG_COMPAT -+struct fb_cmap32 { -+ __u32 start; -+ __u32 len; /* Number of entries */ -+ compat_uptr_t red; /* Red values */ -+ compat_uptr_t green; -+ compat_uptr_t blue; -+ compat_uptr_t transp; /* transparency, can be NULL */ -+}; -+ -+#define fb_cmap_from_compat(to, from) \ -+ (to).start = (from).start; \ -+ (to).len = (from).len; \ -+ (to).red = compat_ptr((from).red); \ -+ (to).green = compat_ptr((from).green); \ -+ (to).blue = compat_ptr((from).blue); \ -+ (to).transp = compat_ptr((from).transp) -+ -+#endif /* CONFIG_COMPAT */ -+#endif /* __KERNEL__ */ -+ -+ - struct fb_cmap { - __u32 start; /* First entry */ - __u32 len; /* Number of entries */ -diff --git a/kernel/sysctl.c b/kernel/sysctl.c -index 74f5b58..6386ab0 100644 ---- a/kernel/sysctl.c -+++ b/kernel/sysctl.c -@@ -146,6 +146,10 @@ static const int cap_last_cap = CAP_LAST_CAP; - static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); - #endif - -+#ifdef CONFIG_FB_CON_DECOR -+extern char fbcon_decor_path[]; -+#endif -+ - #ifdef CONFIG_INOTIFY_USER - #include - #endif -@@ -255,6 +259,15 @@ static struct ctl_table sysctl_base_table[] = { - .mode = 0555, - .child = dev_table, - }, -+#ifdef CONFIG_FB_CON_DECOR -+ { -+ .procname = "fbcondecor", -+ .data = &fbcon_decor_path, -+ .maxlen = KMOD_PATH_LEN, -+ .mode = 0644, -+ .proc_handler = &proc_dostring, -+ }, -+#endif - { } - }; - diff --git a/5000_enable-additional-cpu-optimizations-for-gcc.patch b/5000_enable-additional-cpu-optimizations-for-gcc.patch deleted file mode 100644 index f7ab6f0f..00000000 --- a/5000_enable-additional-cpu-optimizations-for-gcc.patch +++ /dev/null @@ -1,327 +0,0 @@ -This patch has been tested on and known to work with kernel versions from 3.2 -up to the latest git version (pulled on 12/14/2013). - -This patch will expand the number of microarchitectures to include new -processors including: AMD K10-family, AMD Family 10h (Barcelona), AMD Family -14h (Bobcat), AMD Family 15h (Bulldozer), AMD Family 15h (Piledriver), AMD -Family 16h (Jaguar), Intel 1st Gen Core i3/i5/i7 (Nehalem), Intel 2nd Gen Core -i3/i5/i7 (Sandybridge), Intel 3rd Gen Core i3/i5/i7 (Ivybridge), and Intel 4th -Gen Core i3/i5/i7 (Haswell). It also offers the compiler the 'native' flag. - -Small but real speed increases are measurable using a make endpoint comparing -a generic kernel to one built with one of the respective microarchs. - -See the following experimental evidence supporting this statement: -https://github.com/graysky2/kernel_gcc_patch - -REQUIREMENTS -linux version >=3.15 -gcc version <4.9 - ---- -diff -uprN a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h ---- a/arch/x86/include/asm/module.h 2013-11-03 18:41:51.000000000 -0500 -+++ b/arch/x86/include/asm/module.h 2013-12-15 06:21:24.351122516 -0500 -@@ -15,6 +15,16 @@ - #define MODULE_PROC_FAMILY "586MMX " - #elif defined CONFIG_MCORE2 - #define MODULE_PROC_FAMILY "CORE2 " -+#elif defined CONFIG_MNATIVE -+#define MODULE_PROC_FAMILY "NATIVE " -+#elif defined CONFIG_MCOREI7 -+#define MODULE_PROC_FAMILY "COREI7 " -+#elif defined CONFIG_MCOREI7AVX -+#define MODULE_PROC_FAMILY "COREI7AVX " -+#elif defined CONFIG_MCOREAVXI -+#define MODULE_PROC_FAMILY "COREAVXI " -+#elif defined CONFIG_MCOREAVX2 -+#define MODULE_PROC_FAMILY "COREAVX2 " - #elif defined CONFIG_MATOM - #define MODULE_PROC_FAMILY "ATOM " - #elif defined CONFIG_M686 -@@ -33,6 +43,18 @@ - #define MODULE_PROC_FAMILY "K7 " - #elif defined CONFIG_MK8 - #define MODULE_PROC_FAMILY "K8 " -+#elif defined CONFIG_MK10 -+#define MODULE_PROC_FAMILY "K10 " -+#elif defined CONFIG_MBARCELONA -+#define MODULE_PROC_FAMILY "BARCELONA " -+#elif defined CONFIG_MBOBCAT -+#define MODULE_PROC_FAMILY "BOBCAT " -+#elif defined CONFIG_MBULLDOZER -+#define MODULE_PROC_FAMILY "BULLDOZER " -+#elif defined CONFIG_MPILEDRIVER -+#define MODULE_PROC_FAMILY "PILEDRIVER " -+#elif defined CONFIG_MJAGUAR -+#define MODULE_PROC_FAMILY "JAGUAR " - #elif defined CONFIG_MELAN - #define MODULE_PROC_FAMILY "ELAN " - #elif defined CONFIG_MCRUSOE -diff -uprN a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu ---- a/arch/x86/Kconfig.cpu 2013-11-03 18:41:51.000000000 -0500 -+++ b/arch/x86/Kconfig.cpu 2013-12-15 06:21:24.351122516 -0500 -@@ -139,7 +139,7 @@ config MPENTIUM4 - - - config MK6 -- bool "K6/K6-II/K6-III" -+ bool "AMD K6/K6-II/K6-III" - depends on X86_32 - ---help--- - Select this for an AMD K6-family processor. Enables use of -@@ -147,7 +147,7 @@ config MK6 - flags to GCC. - - config MK7 -- bool "Athlon/Duron/K7" -+ bool "AMD Athlon/Duron/K7" - depends on X86_32 - ---help--- - Select this for an AMD Athlon K7-family processor. Enables use of -@@ -155,12 +155,55 @@ config MK7 - flags to GCC. - - config MK8 -- bool "Opteron/Athlon64/Hammer/K8" -+ bool "AMD Opteron/Athlon64/Hammer/K8" - ---help--- - Select this for an AMD Opteron or Athlon64 Hammer-family processor. - Enables use of some extended instructions, and passes appropriate - optimization flags to GCC. - -+config MK10 -+ bool "AMD 61xx/7x50/PhenomX3/X4/II/K10" -+ ---help--- -+ Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50, -+ Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor. -+ Enables use of some extended instructions, and passes appropriate -+ optimization flags to GCC. -+ -+config MBARCELONA -+ bool "AMD Barcelona" -+ ---help--- -+ Select this for AMD Barcelona and newer processors. -+ -+ Enables -march=barcelona -+ -+config MBOBCAT -+ bool "AMD Bobcat" -+ ---help--- -+ Select this for AMD Bobcat processors. -+ -+ Enables -march=btver1 -+ -+config MBULLDOZER -+ bool "AMD Bulldozer" -+ ---help--- -+ Select this for AMD Bulldozer processors. -+ -+ Enables -march=bdver1 -+ -+config MPILEDRIVER -+ bool "AMD Piledriver" -+ ---help--- -+ Select this for AMD Piledriver processors. -+ -+ Enables -march=bdver2 -+ -+config MJAGUAR -+ bool "AMD Jaguar" -+ ---help--- -+ Select this for AMD Jaguar processors. -+ -+ Enables -march=btver2 -+ - config MCRUSOE - bool "Crusoe" - depends on X86_32 -@@ -251,8 +294,17 @@ config MPSC - using the cpu family field - in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. - -+config MATOM -+ bool "Intel Atom" -+ ---help--- -+ -+ Select this for the Intel Atom platform. Intel Atom CPUs have an -+ in-order pipelining architecture and thus can benefit from -+ accordingly optimized code. Use a recent GCC with specific Atom -+ support in order to fully benefit from selecting this option. -+ - config MCORE2 -- bool "Core 2/newer Xeon" -+ bool "Intel Core 2" - ---help--- - - Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and -@@ -260,14 +312,40 @@ config MCORE2 - family in /proc/cpuinfo. Newer ones have 6 and older ones 15 - (not a typo) - --config MATOM -- bool "Intel Atom" -+ Enables -march=core2 -+ -+config MCOREI7 -+ bool "Intel Core i7" - ---help--- - -- Select this for the Intel Atom platform. Intel Atom CPUs have an -- in-order pipelining architecture and thus can benefit from -- accordingly optimized code. Use a recent GCC with specific Atom -- support in order to fully benefit from selecting this option. -+ Select this for the Intel Nehalem platform. Intel Nehalem proecessors -+ include Core i3, i5, i7, Xeon: 34xx, 35xx, 55xx, 56xx, 75xx processors. -+ -+ Enables -march=corei7 -+ -+config MCOREI7AVX -+ bool "Intel Core 2nd Gen AVX" -+ ---help--- -+ -+ Select this for 2nd Gen Core processors including Sandy Bridge. -+ -+ Enables -march=corei7-avx -+ -+config MCOREAVXI -+ bool "Intel Core 3rd Gen AVX" -+ ---help--- -+ -+ Select this for 3rd Gen Core processors including Ivy Bridge. -+ -+ Enables -march=core-avx-i -+ -+config MCOREAVX2 -+ bool "Intel Core AVX2" -+ ---help--- -+ -+ Select this for AVX2 enabled processors including Haswell. -+ -+ Enables -march=core-avx2 - - config GENERIC_CPU - bool "Generic-x86-64" -@@ -276,6 +354,19 @@ config GENERIC_CPU - Generic x86-64 CPU. - Run equally well on all x86-64 CPUs. - -+config MNATIVE -+ bool "Native optimizations autodetected by GCC" -+ ---help--- -+ -+ GCC 4.2 and above support -march=native, which automatically detects -+ the optimum settings to use based on your processor. -march=native -+ also detects and applies additional settings beyond -march specific -+ to your CPU, (eg. -msse4). Unless you have a specific reason not to -+ (e.g. distcc cross-compiling), you should probably be using -+ -march=native rather than anything listed below. -+ -+ Enables -march=native -+ - endchoice - - config X86_GENERIC -@@ -300,7 +391,7 @@ config X86_INTERNODE_CACHE_SHIFT - config X86_L1_CACHE_SHIFT - int - default "7" if MPENTIUM4 || MPSC -- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU -+ default "6" if MK7 || MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MPENTIUMM || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MVIAC7 || X86_GENERIC || MNATIVE || GENERIC_CPU - default "4" if MELAN || M486 || MGEODEGX1 - default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - -@@ -331,11 +422,11 @@ config X86_ALIGNMENT_16 - - config X86_INTEL_USERCOPY - def_bool y -- depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 -+ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || MNATIVE || X86_GENERIC || MK8 || MK7 || MK10 || MBARCELONA || MEFFICEON || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 - - config X86_USE_PPRO_CHECKSUM - def_bool y -- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM -+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MNATIVE - - config X86_USE_3DNOW - def_bool y -@@ -363,17 +454,17 @@ config X86_P6_NOP - - config X86_TSC - def_bool y -- depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 -+ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7-AVX || MATOM) || X86_64 || MNATIVE - - config X86_CMPXCHG64 - def_bool y -- depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM -+ depends on X86_PAE || X86_64 || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM || MNATIVE - - # this should be set for all -march=.. options where the compiler - # generates cmov. - config X86_CMOV - def_bool y -- depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) -+ depends on (MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MK7 || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX) - - config X86_MINIMUM_CPU_FAMILY - int -diff -uprN a/arch/x86/Makefile b/arch/x86/Makefile ---- a/arch/x86/Makefile 2013-11-03 18:41:51.000000000 -0500 -+++ b/arch/x86/Makefile 2013-12-15 06:21:24.354455723 -0500 -@@ -61,11 +61,26 @@ else - KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3) - - # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) -+ cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) -+ cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10) -+ cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona) -+ cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1) -+ cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1) -+ cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2) -+ cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2) - cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) - - cflags-$(CONFIG_MCORE2) += \ -- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) -+ $(call cc-option,-march=core2,$(call cc-option,-mtune=core2)) -+ cflags-$(CONFIG_MCOREI7) += \ -+ $(call cc-option,-march=corei7,$(call cc-option,-mtune=corei7)) -+ cflags-$(CONFIG_MCOREI7AVX) += \ -+ $(call cc-option,-march=corei7-avx,$(call cc-option,-mtune=corei7-avx)) -+ cflags-$(CONFIG_MCOREAVXI) += \ -+ $(call cc-option,-march=core-avx-i,$(call cc-option,-mtune=core-avx-i)) -+ cflags-$(CONFIG_MCOREAVX2) += \ -+ $(call cc-option,-march=core-avx2,$(call cc-option,-mtune=core-avx2)) - cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ - $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) - cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) -diff -uprN a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu ---- a/arch/x86/Makefile_32.cpu 2013-11-03 18:41:51.000000000 -0500 -+++ b/arch/x86/Makefile_32.cpu 2013-12-15 06:21:24.354455723 -0500 -@@ -23,7 +23,14 @@ cflags-$(CONFIG_MK6) += -march=k6 - # Please note, that patches that add -march=athlon-xp and friends are pointless. - # They make zero difference whatsosever to performance at this time. - cflags-$(CONFIG_MK7) += -march=athlon -+cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -+cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10,-march=athlon) -+cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona,-march=athlon) -+cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1,-march=athlon) -+cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1,-march=athlon) -+cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2,-march=athlon) -+cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2,-march=athlon) - cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 - cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 - cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) -@@ -32,6 +39,10 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc- - cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) - cflags-$(CONFIG_MVIAC7) += -march=i686 - cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) -+cflags-$(CONFIG_MCOREI7) += -march=i686 $(call tune,corei7) -+cflags-$(CONFIG_MCOREI7AVX) += -march=i686 $(call tune,corei7-avx) -+cflags-$(CONFIG_MCOREAVXI) += -march=i686 $(call tune,core-avx-i) -+cflags-$(CONFIG_MCOREAVX2) += -march=i686 $(call tune,core-avx2) - cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ - $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) diff --git a/5001_block-cgroups-kconfig-build-bits-for-BFQ-v7r7-4.0.patch b/5001_block-cgroups-kconfig-build-bits-for-BFQ-v7r7-4.0.patch deleted file mode 100644 index 468d1573..00000000 --- a/5001_block-cgroups-kconfig-build-bits-for-BFQ-v7r7-4.0.patch +++ /dev/null @@ -1,104 +0,0 @@ -From 63e26848e2df36a3c29d2d38ce8b008539d64a5d Mon Sep 17 00:00:00 2001 -From: Paolo Valente -Date: Tue, 7 Apr 2015 13:39:12 +0200 -Subject: [PATCH 1/3] block: cgroups, kconfig, build bits for BFQ-v7r7-4.0 - -Update Kconfig.iosched and do the related Makefile changes to include -kernel configuration options for BFQ. Also add the bfqio controller -to the cgroups subsystem. - -Signed-off-by: Paolo Valente -Signed-off-by: Arianna Avanzini ---- - block/Kconfig.iosched | 32 ++++++++++++++++++++++++++++++++ - block/Makefile | 1 + - include/linux/cgroup_subsys.h | 4 ++++ - 3 files changed, 37 insertions(+) - -diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched -index 421bef9..0ee5f0f 100644 ---- a/block/Kconfig.iosched -+++ b/block/Kconfig.iosched -@@ -39,6 +39,27 @@ config CFQ_GROUP_IOSCHED - ---help--- - Enable group IO scheduling in CFQ. - -+config IOSCHED_BFQ -+ tristate "BFQ I/O scheduler" -+ default n -+ ---help--- -+ The BFQ I/O scheduler tries to distribute bandwidth among -+ all processes according to their weights. -+ It aims at distributing the bandwidth as desired, independently of -+ the disk parameters and with any workload. It also tries to -+ guarantee low latency to interactive and soft real-time -+ applications. If compiled built-in (saying Y here), BFQ can -+ be configured to support hierarchical scheduling. -+ -+config CGROUP_BFQIO -+ bool "BFQ hierarchical scheduling support" -+ depends on CGROUPS && IOSCHED_BFQ=y -+ default n -+ ---help--- -+ Enable hierarchical scheduling in BFQ, using the cgroups -+ filesystem interface. The name of the subsystem will be -+ bfqio. -+ - choice - prompt "Default I/O scheduler" - default DEFAULT_CFQ -@@ -52,6 +73,16 @@ choice - config DEFAULT_CFQ - bool "CFQ" if IOSCHED_CFQ=y - -+ config DEFAULT_BFQ -+ bool "BFQ" if IOSCHED_BFQ=y -+ help -+ Selects BFQ as the default I/O scheduler which will be -+ used by default for all block devices. -+ The BFQ I/O scheduler aims at distributing the bandwidth -+ as desired, independently of the disk parameters and with -+ any workload. It also tries to guarantee low latency to -+ interactive and soft real-time applications. -+ - config DEFAULT_NOOP - bool "No-op" - -@@ -61,6 +92,7 @@ config DEFAULT_IOSCHED - string - default "deadline" if DEFAULT_DEADLINE - default "cfq" if DEFAULT_CFQ -+ default "bfq" if DEFAULT_BFQ - default "noop" if DEFAULT_NOOP - - endmenu -diff --git a/block/Makefile b/block/Makefile -index 00ecc97..1ed86d5 100644 ---- a/block/Makefile -+++ b/block/Makefile -@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o - obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o - obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o - obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o -+obj-$(CONFIG_IOSCHED_BFQ) += bfq-iosched.o - - obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o - obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o -diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h -index e4a96fb..267d681 100644 ---- a/include/linux/cgroup_subsys.h -+++ b/include/linux/cgroup_subsys.h -@@ -35,6 +35,10 @@ SUBSYS(freezer) - SUBSYS(net_cls) - #endif - -+#if IS_ENABLED(CONFIG_CGROUP_BFQIO) -+SUBSYS(bfqio) -+#endif -+ - #if IS_ENABLED(CONFIG_CGROUP_PERF) - SUBSYS(perf_event) - #endif --- -2.1.0 - diff --git a/5002_block-introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1 b/5002_block-introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1 deleted file mode 100644 index a6cfc585..00000000 --- a/5002_block-introduce-the-BFQ-v7r7-I-O-sched-for-4.0.patch1 +++ /dev/null @@ -1,6966 +0,0 @@ -From 8cdf2dae6ee87049c7bb086d34e2ce981b545813 Mon Sep 17 00:00:00 2001 -From: Paolo Valente -Date: Thu, 9 May 2013 19:10:02 +0200 -Subject: [PATCH 2/3] block: introduce the BFQ-v7r7 I/O sched for 4.0 - -Add the BFQ-v7r7 I/O scheduler to 4.0. -The general structure is borrowed from CFQ, as much of the code for -handling I/O contexts. Over time, several useful features have been -ported from CFQ as well (details in the changelog in README.BFQ). A -(bfq_)queue is associated to each task doing I/O on a device, and each -time a scheduling decision has to be made a queue is selected and served -until it expires. - - - Slices are given in the service domain: tasks are assigned - budgets, measured in number of sectors. Once got the disk, a task - must however consume its assigned budget within a configurable - maximum time (by default, the maximum possible value of the - budgets is automatically computed to comply with this timeout). - This allows the desired latency vs "throughput boosting" tradeoff - to be set. - - - Budgets are scheduled according to a variant of WF2Q+, implemented - using an augmented rb-tree to take eligibility into account while - preserving an O(log N) overall complexity. - - - A low-latency tunable is provided; if enabled, both interactive - and soft real-time applications are guaranteed a very low latency. - - - Latency guarantees are preserved also in the presence of NCQ. - - - Also with flash-based devices, a high throughput is achieved - while still preserving latency guarantees. - - - BFQ features Early Queue Merge (EQM), a sort of fusion of the - cooperating-queue-merging and the preemption mechanisms present - in CFQ. EQM is in fact a unified mechanism that tries to get a - sequential read pattern, and hence a high throughput, with any - set of processes performing interleaved I/O over a contiguous - sequence of sectors. - - - BFQ supports full hierarchical scheduling, exporting a cgroups - interface. Since each node has a full scheduler, each group can - be assigned its own weight. - - - If the cgroups interface is not used, only I/O priorities can be - assigned to processes, with ioprio values mapped to weights - with the relation weight = IOPRIO_BE_NR - ioprio. - - - ioprio classes are served in strict priority order, i.e., lower - priority queues are not served as long as there are higher - priority queues. Among queues in the same class the bandwidth is - distributed in proportion to the weight of each queue. A very - thin extra bandwidth is however guaranteed to the Idle class, to - prevent it from starving. - -Signed-off-by: Paolo Valente -Signed-off-by: Arianna Avanzini ---- - block/bfq-cgroup.c | 936 ++++++++++++ - block/bfq-ioc.c | 36 + - block/bfq-iosched.c | 3902 +++++++++++++++++++++++++++++++++++++++++++++++++++ - block/bfq-sched.c | 1214 ++++++++++++++++ - block/bfq.h | 775 ++++++++++ - 5 files changed, 6863 insertions(+) - create mode 100644 block/bfq-cgroup.c - create mode 100644 block/bfq-ioc.c - create mode 100644 block/bfq-iosched.c - create mode 100644 block/bfq-sched.c - create mode 100644 block/bfq.h - -diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c -new file mode 100644 -index 0000000..11e2f1d ---- /dev/null -+++ b/block/bfq-cgroup.c -@@ -0,0 +1,936 @@ -+/* -+ * BFQ: CGROUPS support. -+ * -+ * Based on ideas and code from CFQ: -+ * Copyright (C) 2003 Jens Axboe -+ * -+ * Copyright (C) 2008 Fabio Checconi -+ * Paolo Valente -+ * -+ * Copyright (C) 2010 Paolo Valente -+ * -+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ -+ * file. -+ */ -+ -+#ifdef CONFIG_CGROUP_BFQIO -+ -+static DEFINE_MUTEX(bfqio_mutex); -+ -+static bool bfqio_is_removed(struct bfqio_cgroup *bgrp) -+{ -+ return bgrp ? !bgrp->online : false; -+} -+ -+static struct bfqio_cgroup bfqio_root_cgroup = { -+ .weight = BFQ_DEFAULT_GRP_WEIGHT, -+ .ioprio = BFQ_DEFAULT_GRP_IOPRIO, -+ .ioprio_class = BFQ_DEFAULT_GRP_CLASS, -+}; -+ -+static inline void bfq_init_entity(struct bfq_entity *entity, -+ struct bfq_group *bfqg) -+{ -+ entity->weight = entity->new_weight; -+ entity->orig_weight = entity->new_weight; -+ entity->ioprio = entity->new_ioprio; -+ entity->ioprio_class = entity->new_ioprio_class; -+ entity->parent = bfqg->my_entity; -+ entity->sched_data = &bfqg->sched_data; -+} -+ -+static struct bfqio_cgroup *css_to_bfqio(struct cgroup_subsys_state *css) -+{ -+ return css ? container_of(css, struct bfqio_cgroup, css) : NULL; -+} -+ -+/* -+ * Search the bfq_group for bfqd into the hash table (by now only a list) -+ * of bgrp. Must be called under rcu_read_lock(). -+ */ -+static struct bfq_group *bfqio_lookup_group(struct bfqio_cgroup *bgrp, -+ struct bfq_data *bfqd) -+{ -+ struct bfq_group *bfqg; -+ void *key; -+ -+ hlist_for_each_entry_rcu(bfqg, &bgrp->group_data, group_node) { -+ key = rcu_dereference(bfqg->bfqd); -+ if (key == bfqd) -+ return bfqg; -+ } -+ -+ return NULL; -+} -+ -+static inline void bfq_group_init_entity(struct bfqio_cgroup *bgrp, -+ struct bfq_group *bfqg) -+{ -+ struct bfq_entity *entity = &bfqg->entity; -+ -+ /* -+ * If the weight of the entity has never been set via the sysfs -+ * interface, then bgrp->weight == 0. In this case we initialize -+ * the weight from the current ioprio value. Otherwise, the group -+ * weight, if set, has priority over the ioprio value. -+ */ -+ if (bgrp->weight == 0) { -+ entity->new_weight = bfq_ioprio_to_weight(bgrp->ioprio); -+ entity->new_ioprio = bgrp->ioprio; -+ } else { -+ if (bgrp->weight < BFQ_MIN_WEIGHT || -+ bgrp->weight > BFQ_MAX_WEIGHT) { -+ printk(KERN_CRIT "bfq_group_init_entity: " -+ "bgrp->weight %d\n", bgrp->weight); -+ BUG(); -+ } -+ entity->new_weight = bgrp->weight; -+ entity->new_ioprio = bfq_weight_to_ioprio(bgrp->weight); -+ } -+ entity->orig_weight = entity->weight = entity->new_weight; -+ entity->ioprio = entity->new_ioprio; -+ entity->ioprio_class = entity->new_ioprio_class = bgrp->ioprio_class; -+ entity->my_sched_data = &bfqg->sched_data; -+ bfqg->active_entities = 0; -+} -+ -+static inline void bfq_group_set_parent(struct bfq_group *bfqg, -+ struct bfq_group *parent) -+{ -+ struct bfq_entity *entity; -+ -+ BUG_ON(parent == NULL); -+ BUG_ON(bfqg == NULL); -+ -+ entity = &bfqg->entity; -+ entity->parent = parent->my_entity; -+ entity->sched_data = &parent->sched_data; -+} -+ -+/** -+ * bfq_group_chain_alloc - allocate a chain of groups. -+ * @bfqd: queue descriptor. -+ * @css: the leaf cgroup_subsys_state this chain starts from. -+ * -+ * Allocate a chain of groups starting from the one belonging to -+ * @cgroup up to the root cgroup. Stop if a cgroup on the chain -+ * to the root has already an allocated group on @bfqd. -+ */ -+static struct bfq_group *bfq_group_chain_alloc(struct bfq_data *bfqd, -+ struct cgroup_subsys_state *css) -+{ -+ struct bfqio_cgroup *bgrp; -+ struct bfq_group *bfqg, *prev = NULL, *leaf = NULL; -+ -+ for (; css != NULL; css = css->parent) { -+ bgrp = css_to_bfqio(css); -+ -+ bfqg = bfqio_lookup_group(bgrp, bfqd); -+ if (bfqg != NULL) { -+ /* -+ * All the cgroups in the path from there to the -+ * root must have a bfq_group for bfqd, so we don't -+ * need any more allocations. -+ */ -+ break; -+ } -+ -+ bfqg = kzalloc(sizeof(*bfqg), GFP_ATOMIC); -+ if (bfqg == NULL) -+ goto cleanup; -+ -+ bfq_group_init_entity(bgrp, bfqg); -+ bfqg->my_entity = &bfqg->entity; -+ -+ if (leaf == NULL) { -+ leaf = bfqg; -+ prev = leaf; -+ } else { -+ bfq_group_set_parent(prev, bfqg); -+ /* -+ * Build a list of allocated nodes using the bfqd -+ * filed, that is still unused and will be -+ * initialized only after the node will be -+ * connected. -+ */ -+ prev->bfqd = bfqg; -+ prev = bfqg; -+ } -+ } -+ -+ return leaf; -+ -+cleanup: -+ while (leaf != NULL) { -+ prev = leaf; -+ leaf = leaf->bfqd; -+ kfree(prev); -+ } -+ -+ return NULL; -+} -+ -+/** -+ * bfq_group_chain_link - link an allocated group chain to a cgroup -+ * hierarchy. -+ * @bfqd: the queue descriptor. -+ * @css: the leaf cgroup_subsys_state to start from. -+ * @leaf: the leaf group (to be associated to @cgroup). -+ * -+ * Try to link a chain of groups to a cgroup hierarchy, connecting the -+ * nodes bottom-up, so we can be sure that when we find a cgroup in the -+ * hierarchy that already as a group associated to @bfqd all the nodes -+ * in the path to the root cgroup have one too. -+ * -+ * On locking: the queue lock protects the hierarchy (there is a hierarchy -+ * per device) while the bfqio_cgroup lock protects the list of groups -+ * belonging to the same cgroup. -+ */ -+static void bfq_group_chain_link(struct bfq_data *bfqd, -+ struct cgroup_subsys_state *css, -+ struct bfq_group *leaf) -+{ -+ struct bfqio_cgroup *bgrp; -+ struct bfq_group *bfqg, *next, *prev = NULL; -+ unsigned long flags; -+ -+ assert_spin_locked(bfqd->queue->queue_lock); -+ -+ for (; css != NULL && leaf != NULL; css = css->parent) { -+ bgrp = css_to_bfqio(css); -+ next = leaf->bfqd; -+ -+ bfqg = bfqio_lookup_group(bgrp, bfqd); -+ BUG_ON(bfqg != NULL); -+ -+ spin_lock_irqsave(&bgrp->lock, flags); -+ -+ rcu_assign_pointer(leaf->bfqd, bfqd); -+ hlist_add_head_rcu(&leaf->group_node, &bgrp->group_data); -+ hlist_add_head(&leaf->bfqd_node, &bfqd->group_list); -+ -+ spin_unlock_irqrestore(&bgrp->lock, flags); -+ -+ prev = leaf; -+ leaf = next; -+ } -+ -+ BUG_ON(css == NULL && leaf != NULL); -+ if (css != NULL && prev != NULL) { -+ bgrp = css_to_bfqio(css); -+ bfqg = bfqio_lookup_group(bgrp, bfqd); -+ bfq_group_set_parent(prev, bfqg); -+ } -+} -+ -+/** -+ * bfq_find_alloc_group - return the group associated to @bfqd in @cgroup. -+ * @bfqd: queue descriptor. -+ * @cgroup: cgroup being searched for. -+ * -+ * Return a group associated to @bfqd in @cgroup, allocating one if -+ * necessary. When a group is returned all the cgroups in the path -+ * to the root have a group associated to @bfqd. -+ * -+ * If the allocation fails, return the root group: this breaks guarantees -+ * but is a safe fallback. If this loss becomes a problem it can be -+ * mitigated using the equivalent weight (given by the product of the -+ * weights of the groups in the path from @group to the root) in the -+ * root scheduler. -+ * -+ * We allocate all the missing nodes in the path from the leaf cgroup -+ * to the root and we connect the nodes only after all the allocations -+ * have been successful. -+ */ -+static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd, -+ struct cgroup_subsys_state *css) -+{ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); -+ struct bfq_group *bfqg; -+ -+ bfqg = bfqio_lookup_group(bgrp, bfqd); -+ if (bfqg != NULL) -+ return bfqg; -+ -+ bfqg = bfq_group_chain_alloc(bfqd, css); -+ if (bfqg != NULL) -+ bfq_group_chain_link(bfqd, css, bfqg); -+ else -+ bfqg = bfqd->root_group; -+ -+ return bfqg; -+} -+ -+/** -+ * bfq_bfqq_move - migrate @bfqq to @bfqg. -+ * @bfqd: queue descriptor. -+ * @bfqq: the queue to move. -+ * @entity: @bfqq's entity. -+ * @bfqg: the group to move to. -+ * -+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating -+ * it on the new one. Avoid putting the entity on the old group idle tree. -+ * -+ * Must be called under the queue lock; the cgroup owning @bfqg must -+ * not disappear (by now this just means that we are called under -+ * rcu_read_lock()). -+ */ -+static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ struct bfq_entity *entity, struct bfq_group *bfqg) -+{ -+ int busy, resume; -+ -+ busy = bfq_bfqq_busy(bfqq); -+ resume = !RB_EMPTY_ROOT(&bfqq->sort_list); -+ -+ BUG_ON(resume && !entity->on_st); -+ BUG_ON(busy && !resume && entity->on_st && -+ bfqq != bfqd->in_service_queue); -+ -+ if (busy) { -+ BUG_ON(atomic_read(&bfqq->ref) < 2); -+ -+ if (!resume) -+ bfq_del_bfqq_busy(bfqd, bfqq, 0); -+ else -+ bfq_deactivate_bfqq(bfqd, bfqq, 0); -+ } else if (entity->on_st) -+ bfq_put_idle_entity(bfq_entity_service_tree(entity), entity); -+ -+ /* -+ * Here we use a reference to bfqg. We don't need a refcounter -+ * as the cgroup reference will not be dropped, so that its -+ * destroy() callback will not be invoked. -+ */ -+ entity->parent = bfqg->my_entity; -+ entity->sched_data = &bfqg->sched_data; -+ -+ if (busy && resume) -+ bfq_activate_bfqq(bfqd, bfqq); -+ -+ if (bfqd->in_service_queue == NULL && !bfqd->rq_in_driver) -+ bfq_schedule_dispatch(bfqd); -+} -+ -+/** -+ * __bfq_bic_change_cgroup - move @bic to @cgroup. -+ * @bfqd: the queue descriptor. -+ * @bic: the bic to move. -+ * @cgroup: the cgroup to move to. -+ * -+ * Move bic to cgroup, assuming that bfqd->queue is locked; the caller -+ * has to make sure that the reference to cgroup is valid across the call. -+ * -+ * NOTE: an alternative approach might have been to store the current -+ * cgroup in bfqq and getting a reference to it, reducing the lookup -+ * time here, at the price of slightly more complex code. -+ */ -+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, -+ struct bfq_io_cq *bic, -+ struct cgroup_subsys_state *css) -+{ -+ struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); -+ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); -+ struct bfq_entity *entity; -+ struct bfq_group *bfqg; -+ struct bfqio_cgroup *bgrp; -+ -+ bgrp = css_to_bfqio(css); -+ -+ bfqg = bfq_find_alloc_group(bfqd, css); -+ if (async_bfqq != NULL) { -+ entity = &async_bfqq->entity; -+ -+ if (entity->sched_data != &bfqg->sched_data) { -+ bic_set_bfqq(bic, NULL, 0); -+ bfq_log_bfqq(bfqd, async_bfqq, -+ "bic_change_group: %p %d", -+ async_bfqq, atomic_read(&async_bfqq->ref)); -+ bfq_put_queue(async_bfqq); -+ } -+ } -+ -+ if (sync_bfqq != NULL) { -+ entity = &sync_bfqq->entity; -+ if (entity->sched_data != &bfqg->sched_data) -+ bfq_bfqq_move(bfqd, sync_bfqq, entity, bfqg); -+ } -+ -+ return bfqg; -+} -+ -+/** -+ * bfq_bic_change_cgroup - move @bic to @cgroup. -+ * @bic: the bic being migrated. -+ * @cgroup: the destination cgroup. -+ * -+ * When the task owning @bic is moved to @cgroup, @bic is immediately -+ * moved into its new parent group. -+ */ -+static void bfq_bic_change_cgroup(struct bfq_io_cq *bic, -+ struct cgroup_subsys_state *css) -+{ -+ struct bfq_data *bfqd; -+ unsigned long uninitialized_var(flags); -+ -+ bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data), -+ &flags); -+ if (bfqd != NULL) { -+ __bfq_bic_change_cgroup(bfqd, bic, css); -+ bfq_put_bfqd_unlock(bfqd, &flags); -+ } -+} -+ -+/** -+ * bfq_bic_update_cgroup - update the cgroup of @bic. -+ * @bic: the @bic to update. -+ * -+ * Make sure that @bic is enqueued in the cgroup of the current task. -+ * We need this in addition to moving bics during the cgroup attach -+ * phase because the task owning @bic could be at its first disk -+ * access or we may end up in the root cgroup as the result of a -+ * memory allocation failure and here we try to move to the right -+ * group. -+ * -+ * Must be called under the queue lock. It is safe to use the returned -+ * value even after the rcu_read_unlock() as the migration/destruction -+ * paths act under the queue lock too. IOW it is impossible to race with -+ * group migration/destruction and end up with an invalid group as: -+ * a) here cgroup has not yet been destroyed, nor its destroy callback -+ * has started execution, as current holds a reference to it, -+ * b) if it is destroyed after rcu_read_unlock() [after current is -+ * migrated to a different cgroup] its attach() callback will have -+ * taken care of remove all the references to the old cgroup data. -+ */ -+static struct bfq_group *bfq_bic_update_cgroup(struct bfq_io_cq *bic) -+{ -+ struct bfq_data *bfqd = bic_to_bfqd(bic); -+ struct bfq_group *bfqg; -+ struct cgroup_subsys_state *css; -+ -+ BUG_ON(bfqd == NULL); -+ -+ rcu_read_lock(); -+ css = task_css(current, bfqio_cgrp_id); -+ bfqg = __bfq_bic_change_cgroup(bfqd, bic, css); -+ rcu_read_unlock(); -+ -+ return bfqg; -+} -+ -+/** -+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st. -+ * @st: the service tree being flushed. -+ */ -+static inline void bfq_flush_idle_tree(struct bfq_service_tree *st) -+{ -+ struct bfq_entity *entity = st->first_idle; -+ -+ for (; entity != NULL; entity = st->first_idle) -+ __bfq_deactivate_entity(entity, 0); -+} -+ -+/** -+ * bfq_reparent_leaf_entity - move leaf entity to the root_group. -+ * @bfqd: the device data structure with the root group. -+ * @entity: the entity to move. -+ */ -+static inline void bfq_reparent_leaf_entity(struct bfq_data *bfqd, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ -+ BUG_ON(bfqq == NULL); -+ bfq_bfqq_move(bfqd, bfqq, entity, bfqd->root_group); -+ return; -+} -+ -+/** -+ * bfq_reparent_active_entities - move to the root group all active -+ * entities. -+ * @bfqd: the device data structure with the root group. -+ * @bfqg: the group to move from. -+ * @st: the service tree with the entities. -+ * -+ * Needs queue_lock to be taken and reference to be valid over the call. -+ */ -+static inline void bfq_reparent_active_entities(struct bfq_data *bfqd, -+ struct bfq_group *bfqg, -+ struct bfq_service_tree *st) -+{ -+ struct rb_root *active = &st->active; -+ struct bfq_entity *entity = NULL; -+ -+ if (!RB_EMPTY_ROOT(&st->active)) -+ entity = bfq_entity_of(rb_first(active)); -+ -+ for (; entity != NULL; entity = bfq_entity_of(rb_first(active))) -+ bfq_reparent_leaf_entity(bfqd, entity); -+ -+ if (bfqg->sched_data.in_service_entity != NULL) -+ bfq_reparent_leaf_entity(bfqd, -+ bfqg->sched_data.in_service_entity); -+ -+ return; -+} -+ -+/** -+ * bfq_destroy_group - destroy @bfqg. -+ * @bgrp: the bfqio_cgroup containing @bfqg. -+ * @bfqg: the group being destroyed. -+ * -+ * Destroy @bfqg, making sure that it is not referenced from its parent. -+ */ -+static void bfq_destroy_group(struct bfqio_cgroup *bgrp, struct bfq_group *bfqg) -+{ -+ struct bfq_data *bfqd; -+ struct bfq_service_tree *st; -+ struct bfq_entity *entity = bfqg->my_entity; -+ unsigned long uninitialized_var(flags); -+ int i; -+ -+ hlist_del(&bfqg->group_node); -+ -+ /* -+ * Empty all service_trees belonging to this group before -+ * deactivating the group itself. -+ */ -+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) { -+ st = bfqg->sched_data.service_tree + i; -+ -+ /* -+ * The idle tree may still contain bfq_queues belonging -+ * to exited task because they never migrated to a different -+ * cgroup from the one being destroyed now. No one else -+ * can access them so it's safe to act without any lock. -+ */ -+ bfq_flush_idle_tree(st); -+ -+ /* -+ * It may happen that some queues are still active -+ * (busy) upon group destruction (if the corresponding -+ * processes have been forced to terminate). We move -+ * all the leaf entities corresponding to these queues -+ * to the root_group. -+ * Also, it may happen that the group has an entity -+ * in service, which is disconnected from the active -+ * tree: it must be moved, too. -+ * There is no need to put the sync queues, as the -+ * scheduler has taken no reference. -+ */ -+ bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags); -+ if (bfqd != NULL) { -+ bfq_reparent_active_entities(bfqd, bfqg, st); -+ bfq_put_bfqd_unlock(bfqd, &flags); -+ } -+ BUG_ON(!RB_EMPTY_ROOT(&st->active)); -+ BUG_ON(!RB_EMPTY_ROOT(&st->idle)); -+ } -+ BUG_ON(bfqg->sched_data.next_in_service != NULL); -+ BUG_ON(bfqg->sched_data.in_service_entity != NULL); -+ -+ /* -+ * We may race with device destruction, take extra care when -+ * dereferencing bfqg->bfqd. -+ */ -+ bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags); -+ if (bfqd != NULL) { -+ hlist_del(&bfqg->bfqd_node); -+ __bfq_deactivate_entity(entity, 0); -+ bfq_put_async_queues(bfqd, bfqg); -+ bfq_put_bfqd_unlock(bfqd, &flags); -+ } -+ BUG_ON(entity->tree != NULL); -+ -+ /* -+ * No need to defer the kfree() to the end of the RCU grace -+ * period: we are called from the destroy() callback of our -+ * cgroup, so we can be sure that no one is a) still using -+ * this cgroup or b) doing lookups in it. -+ */ -+ kfree(bfqg); -+} -+ -+static void bfq_end_wr_async(struct bfq_data *bfqd) -+{ -+ struct hlist_node *tmp; -+ struct bfq_group *bfqg; -+ -+ hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node) -+ bfq_end_wr_async_queues(bfqd, bfqg); -+ bfq_end_wr_async_queues(bfqd, bfqd->root_group); -+} -+ -+/** -+ * bfq_disconnect_groups - disconnect @bfqd from all its groups. -+ * @bfqd: the device descriptor being exited. -+ * -+ * When the device exits we just make sure that no lookup can return -+ * the now unused group structures. They will be deallocated on cgroup -+ * destruction. -+ */ -+static void bfq_disconnect_groups(struct bfq_data *bfqd) -+{ -+ struct hlist_node *tmp; -+ struct bfq_group *bfqg; -+ -+ bfq_log(bfqd, "disconnect_groups beginning"); -+ hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node) { -+ hlist_del(&bfqg->bfqd_node); -+ -+ __bfq_deactivate_entity(bfqg->my_entity, 0); -+ -+ /* -+ * Don't remove from the group hash, just set an -+ * invalid key. No lookups can race with the -+ * assignment as bfqd is being destroyed; this -+ * implies also that new elements cannot be added -+ * to the list. -+ */ -+ rcu_assign_pointer(bfqg->bfqd, NULL); -+ -+ bfq_log(bfqd, "disconnect_groups: put async for group %p", -+ bfqg); -+ bfq_put_async_queues(bfqd, bfqg); -+ } -+} -+ -+static inline void bfq_free_root_group(struct bfq_data *bfqd) -+{ -+ struct bfqio_cgroup *bgrp = &bfqio_root_cgroup; -+ struct bfq_group *bfqg = bfqd->root_group; -+ -+ bfq_put_async_queues(bfqd, bfqg); -+ -+ spin_lock_irq(&bgrp->lock); -+ hlist_del_rcu(&bfqg->group_node); -+ spin_unlock_irq(&bgrp->lock); -+ -+ /* -+ * No need to synchronize_rcu() here: since the device is gone -+ * there cannot be any read-side access to its root_group. -+ */ -+ kfree(bfqg); -+} -+ -+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node) -+{ -+ struct bfq_group *bfqg; -+ struct bfqio_cgroup *bgrp; -+ int i; -+ -+ bfqg = kzalloc_node(sizeof(*bfqg), GFP_KERNEL, node); -+ if (bfqg == NULL) -+ return NULL; -+ -+ bfqg->entity.parent = NULL; -+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) -+ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; -+ -+ bgrp = &bfqio_root_cgroup; -+ spin_lock_irq(&bgrp->lock); -+ rcu_assign_pointer(bfqg->bfqd, bfqd); -+ hlist_add_head_rcu(&bfqg->group_node, &bgrp->group_data); -+ spin_unlock_irq(&bgrp->lock); -+ -+ return bfqg; -+} -+ -+#define SHOW_FUNCTION(__VAR) \ -+static u64 bfqio_cgroup_##__VAR##_read(struct cgroup_subsys_state *css, \ -+ struct cftype *cftype) \ -+{ \ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); \ -+ u64 ret = -ENODEV; \ -+ \ -+ mutex_lock(&bfqio_mutex); \ -+ if (bfqio_is_removed(bgrp)) \ -+ goto out_unlock; \ -+ \ -+ spin_lock_irq(&bgrp->lock); \ -+ ret = bgrp->__VAR; \ -+ spin_unlock_irq(&bgrp->lock); \ -+ \ -+out_unlock: \ -+ mutex_unlock(&bfqio_mutex); \ -+ return ret; \ -+} -+ -+SHOW_FUNCTION(weight); -+SHOW_FUNCTION(ioprio); -+SHOW_FUNCTION(ioprio_class); -+#undef SHOW_FUNCTION -+ -+#define STORE_FUNCTION(__VAR, __MIN, __MAX) \ -+static int bfqio_cgroup_##__VAR##_write(struct cgroup_subsys_state *css,\ -+ struct cftype *cftype, \ -+ u64 val) \ -+{ \ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); \ -+ struct bfq_group *bfqg; \ -+ int ret = -EINVAL; \ -+ \ -+ if (val < (__MIN) || val > (__MAX)) \ -+ return ret; \ -+ \ -+ ret = -ENODEV; \ -+ mutex_lock(&bfqio_mutex); \ -+ if (bfqio_is_removed(bgrp)) \ -+ goto out_unlock; \ -+ ret = 0; \ -+ \ -+ spin_lock_irq(&bgrp->lock); \ -+ bgrp->__VAR = (unsigned short)val; \ -+ hlist_for_each_entry(bfqg, &bgrp->group_data, group_node) { \ -+ /* \ -+ * Setting the ioprio_changed flag of the entity \ -+ * to 1 with new_##__VAR == ##__VAR would re-set \ -+ * the value of the weight to its ioprio mapping. \ -+ * Set the flag only if necessary. \ -+ */ \ -+ if ((unsigned short)val != bfqg->entity.new_##__VAR) { \ -+ bfqg->entity.new_##__VAR = (unsigned short)val; \ -+ /* \ -+ * Make sure that the above new value has been \ -+ * stored in bfqg->entity.new_##__VAR before \ -+ * setting the ioprio_changed flag. In fact, \ -+ * this flag may be read asynchronously (in \ -+ * critical sections protected by a different \ -+ * lock than that held here), and finding this \ -+ * flag set may cause the execution of the code \ -+ * for updating parameters whose value may \ -+ * depend also on bfqg->entity.new_##__VAR (in \ -+ * __bfq_entity_update_weight_prio). \ -+ * This barrier makes sure that the new value \ -+ * of bfqg->entity.new_##__VAR is correctly \ -+ * seen in that code. \ -+ */ \ -+ smp_wmb(); \ -+ bfqg->entity.ioprio_changed = 1; \ -+ } \ -+ } \ -+ spin_unlock_irq(&bgrp->lock); \ -+ \ -+out_unlock: \ -+ mutex_unlock(&bfqio_mutex); \ -+ return ret; \ -+} -+ -+STORE_FUNCTION(weight, BFQ_MIN_WEIGHT, BFQ_MAX_WEIGHT); -+STORE_FUNCTION(ioprio, 0, IOPRIO_BE_NR - 1); -+STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE); -+#undef STORE_FUNCTION -+ -+static struct cftype bfqio_files[] = { -+ { -+ .name = "weight", -+ .read_u64 = bfqio_cgroup_weight_read, -+ .write_u64 = bfqio_cgroup_weight_write, -+ }, -+ { -+ .name = "ioprio", -+ .read_u64 = bfqio_cgroup_ioprio_read, -+ .write_u64 = bfqio_cgroup_ioprio_write, -+ }, -+ { -+ .name = "ioprio_class", -+ .read_u64 = bfqio_cgroup_ioprio_class_read, -+ .write_u64 = bfqio_cgroup_ioprio_class_write, -+ }, -+ { }, /* terminate */ -+}; -+ -+static struct cgroup_subsys_state *bfqio_create(struct cgroup_subsys_state -+ *parent_css) -+{ -+ struct bfqio_cgroup *bgrp; -+ -+ if (parent_css != NULL) { -+ bgrp = kzalloc(sizeof(*bgrp), GFP_KERNEL); -+ if (bgrp == NULL) -+ return ERR_PTR(-ENOMEM); -+ } else -+ bgrp = &bfqio_root_cgroup; -+ -+ spin_lock_init(&bgrp->lock); -+ INIT_HLIST_HEAD(&bgrp->group_data); -+ bgrp->ioprio = BFQ_DEFAULT_GRP_IOPRIO; -+ bgrp->ioprio_class = BFQ_DEFAULT_GRP_CLASS; -+ -+ return &bgrp->css; -+} -+ -+/* -+ * We cannot support shared io contexts, as we have no means to support -+ * two tasks with the same ioc in two different groups without major rework -+ * of the main bic/bfqq data structures. By now we allow a task to change -+ * its cgroup only if it's the only owner of its ioc; the drawback of this -+ * behavior is that a group containing a task that forked using CLONE_IO -+ * will not be destroyed until the tasks sharing the ioc die. -+ */ -+static int bfqio_can_attach(struct cgroup_subsys_state *css, -+ struct cgroup_taskset *tset) -+{ -+ struct task_struct *task; -+ struct io_context *ioc; -+ int ret = 0; -+ -+ cgroup_taskset_for_each(task, tset) { -+ /* -+ * task_lock() is needed to avoid races with -+ * exit_io_context() -+ */ -+ task_lock(task); -+ ioc = task->io_context; -+ if (ioc != NULL && atomic_read(&ioc->nr_tasks) > 1) -+ /* -+ * ioc == NULL means that the task is either too -+ * young or exiting: if it has still no ioc the -+ * ioc can't be shared, if the task is exiting the -+ * attach will fail anyway, no matter what we -+ * return here. -+ */ -+ ret = -EINVAL; -+ task_unlock(task); -+ if (ret) -+ break; -+ } -+ -+ return ret; -+} -+ -+static void bfqio_attach(struct cgroup_subsys_state *css, -+ struct cgroup_taskset *tset) -+{ -+ struct task_struct *task; -+ struct io_context *ioc; -+ struct io_cq *icq; -+ -+ /* -+ * IMPORTANT NOTE: The move of more than one process at a time to a -+ * new group has not yet been tested. -+ */ -+ cgroup_taskset_for_each(task, tset) { -+ ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE); -+ if (ioc) { -+ /* -+ * Handle cgroup change here. -+ */ -+ rcu_read_lock(); -+ hlist_for_each_entry_rcu(icq, &ioc->icq_list, ioc_node) -+ if (!strncmp( -+ icq->q->elevator->type->elevator_name, -+ "bfq", ELV_NAME_MAX)) -+ bfq_bic_change_cgroup(icq_to_bic(icq), -+ css); -+ rcu_read_unlock(); -+ put_io_context(ioc); -+ } -+ } -+} -+ -+static void bfqio_destroy(struct cgroup_subsys_state *css) -+{ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); -+ struct hlist_node *tmp; -+ struct bfq_group *bfqg; -+ -+ /* -+ * Since we are destroying the cgroup, there are no more tasks -+ * referencing it, and all the RCU grace periods that may have -+ * referenced it are ended (as the destruction of the parent -+ * cgroup is RCU-safe); bgrp->group_data will not be accessed by -+ * anything else and we don't need any synchronization. -+ */ -+ hlist_for_each_entry_safe(bfqg, tmp, &bgrp->group_data, group_node) -+ bfq_destroy_group(bgrp, bfqg); -+ -+ BUG_ON(!hlist_empty(&bgrp->group_data)); -+ -+ kfree(bgrp); -+} -+ -+static int bfqio_css_online(struct cgroup_subsys_state *css) -+{ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); -+ -+ mutex_lock(&bfqio_mutex); -+ bgrp->online = true; -+ mutex_unlock(&bfqio_mutex); -+ -+ return 0; -+} -+ -+static void bfqio_css_offline(struct cgroup_subsys_state *css) -+{ -+ struct bfqio_cgroup *bgrp = css_to_bfqio(css); -+ -+ mutex_lock(&bfqio_mutex); -+ bgrp->online = false; -+ mutex_unlock(&bfqio_mutex); -+} -+ -+struct cgroup_subsys bfqio_cgrp_subsys = { -+ .css_alloc = bfqio_create, -+ .css_online = bfqio_css_online, -+ .css_offline = bfqio_css_offline, -+ .can_attach = bfqio_can_attach, -+ .attach = bfqio_attach, -+ .css_free = bfqio_destroy, -+ .legacy_cftypes = bfqio_files, -+}; -+#else -+static inline void bfq_init_entity(struct bfq_entity *entity, -+ struct bfq_group *bfqg) -+{ -+ entity->weight = entity->new_weight; -+ entity->orig_weight = entity->new_weight; -+ entity->ioprio = entity->new_ioprio; -+ entity->ioprio_class = entity->new_ioprio_class; -+ entity->sched_data = &bfqg->sched_data; -+} -+ -+static inline struct bfq_group * -+bfq_bic_update_cgroup(struct bfq_io_cq *bic) -+{ -+ struct bfq_data *bfqd = bic_to_bfqd(bic); -+ return bfqd->root_group; -+} -+ -+static inline void bfq_bfqq_move(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ struct bfq_entity *entity, -+ struct bfq_group *bfqg) -+{ -+} -+ -+static void bfq_end_wr_async(struct bfq_data *bfqd) -+{ -+ bfq_end_wr_async_queues(bfqd, bfqd->root_group); -+} -+ -+static inline void bfq_disconnect_groups(struct bfq_data *bfqd) -+{ -+ bfq_put_async_queues(bfqd, bfqd->root_group); -+} -+ -+static inline void bfq_free_root_group(struct bfq_data *bfqd) -+{ -+ kfree(bfqd->root_group); -+} -+ -+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node) -+{ -+ struct bfq_group *bfqg; -+ int i; -+ -+ bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node); -+ if (bfqg == NULL) -+ return NULL; -+ -+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) -+ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; -+ -+ return bfqg; -+} -+#endif -diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c -new file mode 100644 -index 0000000..7f6b000 ---- /dev/null -+++ b/block/bfq-ioc.c -@@ -0,0 +1,36 @@ -+/* -+ * BFQ: I/O context handling. -+ * -+ * Based on ideas and code from CFQ: -+ * Copyright (C) 2003 Jens Axboe -+ * -+ * Copyright (C) 2008 Fabio Checconi -+ * Paolo Valente -+ * -+ * Copyright (C) 2010 Paolo Valente -+ */ -+ -+/** -+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq. -+ * @icq: the iocontext queue. -+ */ -+static inline struct bfq_io_cq *icq_to_bic(struct io_cq *icq) -+{ -+ /* bic->icq is the first member, %NULL will convert to %NULL */ -+ return container_of(icq, struct bfq_io_cq, icq); -+} -+ -+/** -+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd. -+ * @bfqd: the lookup key. -+ * @ioc: the io_context of the process doing I/O. -+ * -+ * Queue lock must be held. -+ */ -+static inline struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, -+ struct io_context *ioc) -+{ -+ if (ioc) -+ return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue)); -+ return NULL; -+} -diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c -new file mode 100644 -index 0000000..97ee934 ---- /dev/null -+++ b/block/bfq-iosched.c -@@ -0,0 +1,3902 @@ -+/* -+ * Budget Fair Queueing (BFQ) disk scheduler. -+ * -+ * Based on ideas and code from CFQ: -+ * Copyright (C) 2003 Jens Axboe -+ * -+ * Copyright (C) 2008 Fabio Checconi -+ * Paolo Valente -+ * -+ * Copyright (C) 2010 Paolo Valente -+ * -+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ -+ * file. -+ * -+ * BFQ is a proportional-share storage-I/O scheduling algorithm based on -+ * the slice-by-slice service scheme of CFQ. But BFQ assigns budgets, -+ * measured in number of sectors, to processes instead of time slices. The -+ * device is not granted to the in-service process for a given time slice, -+ * but until it has exhausted its assigned budget. This change from the time -+ * to the service domain allows BFQ to distribute the device throughput -+ * among processes as desired, without any distortion due to ZBR, workload -+ * fluctuations or other factors. BFQ uses an ad hoc internal scheduler, -+ * called B-WF2Q+, to schedule processes according to their budgets. More -+ * precisely, BFQ schedules queues associated to processes. Thanks to the -+ * accurate policy of B-WF2Q+, BFQ can afford to assign high budgets to -+ * I/O-bound processes issuing sequential requests (to boost the -+ * throughput), and yet guarantee a low latency to interactive and soft -+ * real-time applications. -+ * -+ * BFQ is described in [1], where also a reference to the initial, more -+ * theoretical paper on BFQ can be found. The interested reader can find -+ * in the latter paper full details on the main algorithm, as well as -+ * formulas of the guarantees and formal proofs of all the properties. -+ * With respect to the version of BFQ presented in these papers, this -+ * implementation adds a few more heuristics, such as the one that -+ * guarantees a low latency to soft real-time applications, and a -+ * hierarchical extension based on H-WF2Q+. -+ * -+ * B-WF2Q+ is based on WF2Q+, that is described in [2], together with -+ * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N) -+ * complexity derives from the one introduced with EEVDF in [3]. -+ * -+ * [1] P. Valente and M. Andreolini, ``Improving Application Responsiveness -+ * with the BFQ Disk I/O Scheduler'', -+ * Proceedings of the 5th Annual International Systems and Storage -+ * Conference (SYSTOR '12), June 2012. -+ * -+ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf -+ * -+ * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing -+ * Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689, -+ * Oct 1997. -+ * -+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz -+ * -+ * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline -+ * First: A Flexible and Accurate Mechanism for Proportional Share -+ * Resource Allocation,'' technical report. -+ * -+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf -+ */ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include "bfq.h" -+#include "blk.h" -+ -+/* Max number of dispatches in one round of service. */ -+static const int bfq_quantum = 4; -+ -+/* Expiration time of sync (0) and async (1) requests, in jiffies. */ -+static const int bfq_fifo_expire[2] = { HZ / 4, HZ / 8 }; -+ -+/* Maximum backwards seek, in KiB. */ -+static const int bfq_back_max = 16 * 1024; -+ -+/* Penalty of a backwards seek, in number of sectors. */ -+static const int bfq_back_penalty = 2; -+ -+/* Idling period duration, in jiffies. */ -+static int bfq_slice_idle = HZ / 125; -+ -+/* Default maximum budget values, in sectors and number of requests. */ -+static const int bfq_default_max_budget = 16 * 1024; -+static const int bfq_max_budget_async_rq = 4; -+ -+/* -+ * Async to sync throughput distribution is controlled as follows: -+ * when an async request is served, the entity is charged the number -+ * of sectors of the request, multiplied by the factor below -+ */ -+static const int bfq_async_charge_factor = 10; -+ -+/* Default timeout values, in jiffies, approximating CFQ defaults. */ -+static const int bfq_timeout_sync = HZ / 8; -+static int bfq_timeout_async = HZ / 25; -+ -+struct kmem_cache *bfq_pool; -+ -+/* Below this threshold (in ms), we consider thinktime immediate. */ -+#define BFQ_MIN_TT 2 -+ -+/* hw_tag detection: parallel requests threshold and min samples needed. */ -+#define BFQ_HW_QUEUE_THRESHOLD 4 -+#define BFQ_HW_QUEUE_SAMPLES 32 -+ -+#define BFQQ_SEEK_THR (sector_t)(8 * 1024) -+#define BFQQ_SEEKY(bfqq) ((bfqq)->seek_mean > BFQQ_SEEK_THR) -+ -+/* Min samples used for peak rate estimation (for autotuning). */ -+#define BFQ_PEAK_RATE_SAMPLES 32 -+ -+/* Shift used for peak rate fixed precision calculations. */ -+#define BFQ_RATE_SHIFT 16 -+ -+/* -+ * By default, BFQ computes the duration of the weight raising for -+ * interactive applications automatically, using the following formula: -+ * duration = (R / r) * T, where r is the peak rate of the device, and -+ * R and T are two reference parameters. -+ * In particular, R is the peak rate of the reference device (see below), -+ * and T is a reference time: given the systems that are likely to be -+ * installed on the reference device according to its speed class, T is -+ * about the maximum time needed, under BFQ and while reading two files in -+ * parallel, to load typical large applications on these systems. -+ * In practice, the slower/faster the device at hand is, the more/less it -+ * takes to load applications with respect to the reference device. -+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive -+ * applications. -+ * -+ * BFQ uses four different reference pairs (R, T), depending on: -+ * . whether the device is rotational or non-rotational; -+ * . whether the device is slow, such as old or portable HDDs, as well as -+ * SD cards, or fast, such as newer HDDs and SSDs. -+ * -+ * The device's speed class is dynamically (re)detected in -+ * bfq_update_peak_rate() every time the estimated peak rate is updated. -+ * -+ * In the following definitions, R_slow[0]/R_fast[0] and T_slow[0]/T_fast[0] -+ * are the reference values for a slow/fast rotational device, whereas -+ * R_slow[1]/R_fast[1] and T_slow[1]/T_fast[1] are the reference values for -+ * a slow/fast non-rotational device. Finally, device_speed_thresh are the -+ * thresholds used to switch between speed classes. -+ * Both the reference peak rates and the thresholds are measured in -+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT. -+ */ -+static int R_slow[2] = {1536, 10752}; -+static int R_fast[2] = {17415, 34791}; -+/* -+ * To improve readability, a conversion function is used to initialize the -+ * following arrays, which entails that they can be initialized only in a -+ * function. -+ */ -+static int T_slow[2]; -+static int T_fast[2]; -+static int device_speed_thresh[2]; -+ -+#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \ -+ { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 }) -+ -+#define RQ_BIC(rq) ((struct bfq_io_cq *) (rq)->elv.priv[0]) -+#define RQ_BFQQ(rq) ((rq)->elv.priv[1]) -+ -+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd); -+ -+#include "bfq-ioc.c" -+#include "bfq-sched.c" -+#include "bfq-cgroup.c" -+ -+#define bfq_class_idle(bfqq) ((bfqq)->entity.ioprio_class ==\ -+ IOPRIO_CLASS_IDLE) -+#define bfq_class_rt(bfqq) ((bfqq)->entity.ioprio_class ==\ -+ IOPRIO_CLASS_RT) -+ -+#define bfq_sample_valid(samples) ((samples) > 80) -+ -+/* -+ * We regard a request as SYNC, if either it's a read or has the SYNC bit -+ * set (in which case it could also be a direct WRITE). -+ */ -+static inline int bfq_bio_sync(struct bio *bio) -+{ -+ if (bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC)) -+ return 1; -+ -+ return 0; -+} -+ -+/* -+ * Scheduler run of queue, if there are requests pending and no one in the -+ * driver that will restart queueing. -+ */ -+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd) -+{ -+ if (bfqd->queued != 0) { -+ bfq_log(bfqd, "schedule dispatch"); -+ kblockd_schedule_work(&bfqd->unplug_work); -+ } -+} -+ -+/* -+ * Lifted from AS - choose which of rq1 and rq2 that is best served now. -+ * We choose the request that is closesr to the head right now. Distance -+ * behind the head is penalized and only allowed to a certain extent. -+ */ -+static struct request *bfq_choose_req(struct bfq_data *bfqd, -+ struct request *rq1, -+ struct request *rq2, -+ sector_t last) -+{ -+ sector_t s1, s2, d1 = 0, d2 = 0; -+ unsigned long back_max; -+#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */ -+#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */ -+ unsigned wrap = 0; /* bit mask: requests behind the disk head? */ -+ -+ if (rq1 == NULL || rq1 == rq2) -+ return rq2; -+ if (rq2 == NULL) -+ return rq1; -+ -+ if (rq_is_sync(rq1) && !rq_is_sync(rq2)) -+ return rq1; -+ else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) -+ return rq2; -+ if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META)) -+ return rq1; -+ else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META)) -+ return rq2; -+ -+ s1 = blk_rq_pos(rq1); -+ s2 = blk_rq_pos(rq2); -+ -+ /* -+ * By definition, 1KiB is 2 sectors. -+ */ -+ back_max = bfqd->bfq_back_max * 2; -+ -+ /* -+ * Strict one way elevator _except_ in the case where we allow -+ * short backward seeks which are biased as twice the cost of a -+ * similar forward seek. -+ */ -+ if (s1 >= last) -+ d1 = s1 - last; -+ else if (s1 + back_max >= last) -+ d1 = (last - s1) * bfqd->bfq_back_penalty; -+ else -+ wrap |= BFQ_RQ1_WRAP; -+ -+ if (s2 >= last) -+ d2 = s2 - last; -+ else if (s2 + back_max >= last) -+ d2 = (last - s2) * bfqd->bfq_back_penalty; -+ else -+ wrap |= BFQ_RQ2_WRAP; -+ -+ /* Found required data */ -+ -+ /* -+ * By doing switch() on the bit mask "wrap" we avoid having to -+ * check two variables for all permutations: --> faster! -+ */ -+ switch (wrap) { -+ case 0: /* common case for CFQ: rq1 and rq2 not wrapped */ -+ if (d1 < d2) -+ return rq1; -+ else if (d2 < d1) -+ return rq2; -+ else { -+ if (s1 >= s2) -+ return rq1; -+ else -+ return rq2; -+ } -+ -+ case BFQ_RQ2_WRAP: -+ return rq1; -+ case BFQ_RQ1_WRAP: -+ return rq2; -+ case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */ -+ default: -+ /* -+ * Since both rqs are wrapped, -+ * start with the one that's further behind head -+ * (--> only *one* back seek required), -+ * since back seek takes more time than forward. -+ */ -+ if (s1 <= s2) -+ return rq1; -+ else -+ return rq2; -+ } -+} -+ -+static struct bfq_queue * -+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root, -+ sector_t sector, struct rb_node **ret_parent, -+ struct rb_node ***rb_link) -+{ -+ struct rb_node **p, *parent; -+ struct bfq_queue *bfqq = NULL; -+ -+ parent = NULL; -+ p = &root->rb_node; -+ while (*p) { -+ struct rb_node **n; -+ -+ parent = *p; -+ bfqq = rb_entry(parent, struct bfq_queue, pos_node); -+ -+ /* -+ * Sort strictly based on sector. Smallest to the left, -+ * largest to the right. -+ */ -+ if (sector > blk_rq_pos(bfqq->next_rq)) -+ n = &(*p)->rb_right; -+ else if (sector < blk_rq_pos(bfqq->next_rq)) -+ n = &(*p)->rb_left; -+ else -+ break; -+ p = n; -+ bfqq = NULL; -+ } -+ -+ *ret_parent = parent; -+ if (rb_link) -+ *rb_link = p; -+ -+ bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d", -+ (long long unsigned)sector, -+ bfqq != NULL ? bfqq->pid : 0); -+ -+ return bfqq; -+} -+ -+static void bfq_rq_pos_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ struct rb_node **p, *parent; -+ struct bfq_queue *__bfqq; -+ -+ if (bfqq->pos_root != NULL) { -+ rb_erase(&bfqq->pos_node, bfqq->pos_root); -+ bfqq->pos_root = NULL; -+ } -+ -+ if (bfq_class_idle(bfqq)) -+ return; -+ if (!bfqq->next_rq) -+ return; -+ -+ bfqq->pos_root = &bfqd->rq_pos_tree; -+ __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root, -+ blk_rq_pos(bfqq->next_rq), &parent, &p); -+ if (__bfqq == NULL) { -+ rb_link_node(&bfqq->pos_node, parent, p); -+ rb_insert_color(&bfqq->pos_node, bfqq->pos_root); -+ } else -+ bfqq->pos_root = NULL; -+} -+ -+/* -+ * Tell whether there are active queues or groups with differentiated weights. -+ */ -+static inline bool bfq_differentiated_weights(struct bfq_data *bfqd) -+{ -+ BUG_ON(!bfqd->hw_tag); -+ /* -+ * For weights to differ, at least one of the trees must contain -+ * at least two nodes. -+ */ -+ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && -+ (bfqd->queue_weights_tree.rb_node->rb_left || -+ bfqd->queue_weights_tree.rb_node->rb_right) -+#ifdef CONFIG_CGROUP_BFQIO -+ ) || -+ (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) && -+ (bfqd->group_weights_tree.rb_node->rb_left || -+ bfqd->group_weights_tree.rb_node->rb_right) -+#endif -+ ); -+} -+ -+/* -+ * If the weight-counter tree passed as input contains no counter for -+ * the weight of the input entity, then add that counter; otherwise just -+ * increment the existing counter. -+ * -+ * Note that weight-counter trees contain few nodes in mostly symmetric -+ * scenarios. For example, if all queues have the same weight, then the -+ * weight-counter tree for the queues may contain at most one node. -+ * This holds even if low_latency is on, because weight-raised queues -+ * are not inserted in the tree. -+ * In most scenarios, the rate at which nodes are created/destroyed -+ * should be low too. -+ */ -+static void bfq_weights_tree_add(struct bfq_data *bfqd, -+ struct bfq_entity *entity, -+ struct rb_root *root) -+{ -+ struct rb_node **new = &(root->rb_node), *parent = NULL; -+ -+ /* -+ * Do not insert if: -+ * - the device does not support queueing; -+ * - the entity is already associated with a counter, which happens if: -+ * 1) the entity is associated with a queue, 2) a request arrival -+ * has caused the queue to become both non-weight-raised, and hence -+ * change its weight, and backlogged; in this respect, each -+ * of the two events causes an invocation of this function, -+ * 3) this is the invocation of this function caused by the second -+ * event. This second invocation is actually useless, and we handle -+ * this fact by exiting immediately. More efficient or clearer -+ * solutions might possibly be adopted. -+ */ -+ if (!bfqd->hw_tag || entity->weight_counter) -+ return; -+ -+ while (*new) { -+ struct bfq_weight_counter *__counter = container_of(*new, -+ struct bfq_weight_counter, -+ weights_node); -+ parent = *new; -+ -+ if (entity->weight == __counter->weight) { -+ entity->weight_counter = __counter; -+ goto inc_counter; -+ } -+ if (entity->weight < __counter->weight) -+ new = &((*new)->rb_left); -+ else -+ new = &((*new)->rb_right); -+ } -+ -+ entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter), -+ GFP_ATOMIC); -+ entity->weight_counter->weight = entity->weight; -+ rb_link_node(&entity->weight_counter->weights_node, parent, new); -+ rb_insert_color(&entity->weight_counter->weights_node, root); -+ -+inc_counter: -+ entity->weight_counter->num_active++; -+} -+ -+/* -+ * Decrement the weight counter associated with the entity, and, if the -+ * counter reaches 0, remove the counter from the tree. -+ * See the comments to the function bfq_weights_tree_add() for considerations -+ * about overhead. -+ */ -+static void bfq_weights_tree_remove(struct bfq_data *bfqd, -+ struct bfq_entity *entity, -+ struct rb_root *root) -+{ -+ /* -+ * Check whether the entity is actually associated with a counter. -+ * In fact, the device may not be considered NCQ-capable for a while, -+ * which implies that no insertion in the weight trees is performed, -+ * after which the device may start to be deemed NCQ-capable, and hence -+ * this function may start to be invoked. This may cause the function -+ * to be invoked for entities that are not associated with any counter. -+ */ -+ if (!entity->weight_counter) -+ return; -+ -+ BUG_ON(RB_EMPTY_ROOT(root)); -+ BUG_ON(entity->weight_counter->weight != entity->weight); -+ -+ BUG_ON(!entity->weight_counter->num_active); -+ entity->weight_counter->num_active--; -+ if (entity->weight_counter->num_active > 0) -+ goto reset_entity_pointer; -+ -+ rb_erase(&entity->weight_counter->weights_node, root); -+ kfree(entity->weight_counter); -+ -+reset_entity_pointer: -+ entity->weight_counter = NULL; -+} -+ -+static struct request *bfq_find_next_rq(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ struct request *last) -+{ -+ struct rb_node *rbnext = rb_next(&last->rb_node); -+ struct rb_node *rbprev = rb_prev(&last->rb_node); -+ struct request *next = NULL, *prev = NULL; -+ -+ BUG_ON(RB_EMPTY_NODE(&last->rb_node)); -+ -+ if (rbprev != NULL) -+ prev = rb_entry_rq(rbprev); -+ -+ if (rbnext != NULL) -+ next = rb_entry_rq(rbnext); -+ else { -+ rbnext = rb_first(&bfqq->sort_list); -+ if (rbnext && rbnext != &last->rb_node) -+ next = rb_entry_rq(rbnext); -+ } -+ -+ return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last)); -+} -+ -+/* see the definition of bfq_async_charge_factor for details */ -+static inline unsigned long bfq_serv_to_charge(struct request *rq, -+ struct bfq_queue *bfqq) -+{ -+ return blk_rq_sectors(rq) * -+ (1 + ((!bfq_bfqq_sync(bfqq)) * (bfqq->wr_coeff == 1) * -+ bfq_async_charge_factor)); -+} -+ -+/** -+ * bfq_updated_next_req - update the queue after a new next_rq selection. -+ * @bfqd: the device data the queue belongs to. -+ * @bfqq: the queue to update. -+ * -+ * If the first request of a queue changes we make sure that the queue -+ * has enough budget to serve at least its first request (if the -+ * request has grown). We do this because if the queue has not enough -+ * budget for its first request, it has to go through two dispatch -+ * rounds to actually get it dispatched. -+ */ -+static void bfq_updated_next_req(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ struct bfq_service_tree *st = bfq_entity_service_tree(entity); -+ struct request *next_rq = bfqq->next_rq; -+ unsigned long new_budget; -+ -+ if (next_rq == NULL) -+ return; -+ -+ if (bfqq == bfqd->in_service_queue) -+ /* -+ * In order not to break guarantees, budgets cannot be -+ * changed after an entity has been selected. -+ */ -+ return; -+ -+ BUG_ON(entity->tree != &st->active); -+ BUG_ON(entity == entity->sched_data->in_service_entity); -+ -+ new_budget = max_t(unsigned long, bfqq->max_budget, -+ bfq_serv_to_charge(next_rq, bfqq)); -+ if (entity->budget != new_budget) { -+ entity->budget = new_budget; -+ bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu", -+ new_budget); -+ bfq_activate_bfqq(bfqd, bfqq); -+ } -+} -+ -+static inline unsigned int bfq_wr_duration(struct bfq_data *bfqd) -+{ -+ u64 dur; -+ -+ if (bfqd->bfq_wr_max_time > 0) -+ return bfqd->bfq_wr_max_time; -+ -+ dur = bfqd->RT_prod; -+ do_div(dur, bfqd->peak_rate); -+ -+ return dur; -+} -+ -+/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */ -+static inline void bfq_reset_burst_list(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ struct bfq_queue *item; -+ struct hlist_node *n; -+ -+ hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node) -+ hlist_del_init(&item->burst_list_node); -+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); -+ bfqd->burst_size = 1; -+} -+ -+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */ -+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ /* Increment burst size to take into account also bfqq */ -+ bfqd->burst_size++; -+ -+ if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) { -+ struct bfq_queue *pos, *bfqq_item; -+ struct hlist_node *n; -+ -+ /* -+ * Enough queues have been activated shortly after each -+ * other to consider this burst as large. -+ */ -+ bfqd->large_burst = true; -+ -+ /* -+ * We can now mark all queues in the burst list as -+ * belonging to a large burst. -+ */ -+ hlist_for_each_entry(bfqq_item, &bfqd->burst_list, -+ burst_list_node) -+ bfq_mark_bfqq_in_large_burst(bfqq_item); -+ bfq_mark_bfqq_in_large_burst(bfqq); -+ -+ /* -+ * From now on, and until the current burst finishes, any -+ * new queue being activated shortly after the last queue -+ * was inserted in the burst can be immediately marked as -+ * belonging to a large burst. So the burst list is not -+ * needed any more. Remove it. -+ */ -+ hlist_for_each_entry_safe(pos, n, &bfqd->burst_list, -+ burst_list_node) -+ hlist_del_init(&pos->burst_list_node); -+ } else /* burst not yet large: add bfqq to the burst list */ -+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); -+} -+ -+/* -+ * If many queues happen to become active shortly after each other, then, -+ * to help the processes associated to these queues get their job done as -+ * soon as possible, it is usually better to not grant either weight-raising -+ * or device idling to these queues. In this comment we describe, firstly, -+ * the reasons why this fact holds, and, secondly, the next function, which -+ * implements the main steps needed to properly mark these queues so that -+ * they can then be treated in a different way. -+ * -+ * As for the terminology, we say that a queue becomes active, i.e., -+ * switches from idle to backlogged, either when it is created (as a -+ * consequence of the arrival of an I/O request), or, if already existing, -+ * when a new request for the queue arrives while the queue is idle. -+ * Bursts of activations, i.e., activations of different queues occurring -+ * shortly after each other, are typically caused by services or applications -+ * that spawn or reactivate many parallel threads/processes. Examples are -+ * systemd during boot or git grep. -+ * -+ * These services or applications benefit mostly from a high throughput: -+ * the quicker the requests of the activated queues are cumulatively served, -+ * the sooner the target job of these queues gets completed. As a consequence, -+ * weight-raising any of these queues, which also implies idling the device -+ * for it, is almost always counterproductive: in most cases it just lowers -+ * throughput. -+ * -+ * On the other hand, a burst of activations may be also caused by the start -+ * of an application that does not consist in a lot of parallel I/O-bound -+ * threads. In fact, with a complex application, the burst may be just a -+ * consequence of the fact that several processes need to be executed to -+ * start-up the application. To start an application as quickly as possible, -+ * the best thing to do is to privilege the I/O related to the application -+ * with respect to all other I/O. Therefore, the best strategy to start as -+ * quickly as possible an application that causes a burst of activations is -+ * to weight-raise all the queues activated during the burst. This is the -+ * exact opposite of the best strategy for the other type of bursts. -+ * -+ * In the end, to take the best action for each of the two cases, the two -+ * types of bursts need to be distinguished. Fortunately, this seems -+ * relatively easy to do, by looking at the sizes of the bursts. In -+ * particular, we found a threshold such that bursts with a larger size -+ * than that threshold are apparently caused only by services or commands -+ * such as systemd or git grep. For brevity, hereafter we call just 'large' -+ * these bursts. BFQ *does not* weight-raise queues whose activations occur -+ * in a large burst. In addition, for each of these queues BFQ performs or -+ * does not perform idling depending on which choice boosts the throughput -+ * most. The exact choice depends on the device and request pattern at -+ * hand. -+ * -+ * Turning back to the next function, it implements all the steps needed -+ * to detect the occurrence of a large burst and to properly mark all the -+ * queues belonging to it (so that they can then be treated in a different -+ * way). This goal is achieved by maintaining a special "burst list" that -+ * holds, temporarily, the queues that belong to the burst in progress. The -+ * list is then used to mark these queues as belonging to a large burst if -+ * the burst does become large. The main steps are the following. -+ * -+ * . when the very first queue is activated, the queue is inserted into the -+ * list (as it could be the first queue in a possible burst) -+ * -+ * . if the current burst has not yet become large, and a queue Q that does -+ * not yet belong to the burst is activated shortly after the last time -+ * at which a new queue entered the burst list, then the function appends -+ * Q to the burst list -+ * -+ * . if, as a consequence of the previous step, the burst size reaches -+ * the large-burst threshold, then -+ * -+ * . all the queues in the burst list are marked as belonging to a -+ * large burst -+ * -+ * . the burst list is deleted; in fact, the burst list already served -+ * its purpose (keeping temporarily track of the queues in a burst, -+ * so as to be able to mark them as belonging to a large burst in the -+ * previous sub-step), and now is not needed any more -+ * -+ * . the device enters a large-burst mode -+ * -+ * . if a queue Q that does not belong to the burst is activated while -+ * the device is in large-burst mode and shortly after the last time -+ * at which a queue either entered the burst list or was marked as -+ * belonging to the current large burst, then Q is immediately marked -+ * as belonging to a large burst. -+ * -+ * . if a queue Q that does not belong to the burst is activated a while -+ * later, i.e., not shortly after, than the last time at which a queue -+ * either entered the burst list or was marked as belonging to the -+ * current large burst, then the current burst is deemed as finished and: -+ * -+ * . the large-burst mode is reset if set -+ * -+ * . the burst list is emptied -+ * -+ * . Q is inserted in the burst list, as Q may be the first queue -+ * in a possible new burst (then the burst list contains just Q -+ * after this step). -+ */ -+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ bool idle_for_long_time) -+{ -+ /* -+ * If bfqq happened to be activated in a burst, but has been idle -+ * for at least as long as an interactive queue, then we assume -+ * that, in the overall I/O initiated in the burst, the I/O -+ * associated to bfqq is finished. So bfqq does not need to be -+ * treated as a queue belonging to a burst anymore. Accordingly, -+ * we reset bfqq's in_large_burst flag if set, and remove bfqq -+ * from the burst list if it's there. We do not decrement instead -+ * burst_size, because the fact that bfqq does not need to belong -+ * to the burst list any more does not invalidate the fact that -+ * bfqq may have been activated during the current burst. -+ */ -+ if (idle_for_long_time) { -+ hlist_del_init(&bfqq->burst_list_node); -+ bfq_clear_bfqq_in_large_burst(bfqq); -+ } -+ -+ /* -+ * If bfqq is already in the burst list or is part of a large -+ * burst, then there is nothing else to do. -+ */ -+ if (!hlist_unhashed(&bfqq->burst_list_node) || -+ bfq_bfqq_in_large_burst(bfqq)) -+ return; -+ -+ /* -+ * If bfqq's activation happens late enough, then the current -+ * burst is finished, and related data structures must be reset. -+ * -+ * In this respect, consider the special case where bfqq is the very -+ * first queue being activated. In this case, last_ins_in_burst is -+ * not yet significant when we get here. But it is easy to verify -+ * that, whether or not the following condition is true, bfqq will -+ * end up being inserted into the burst list. In particular the -+ * list will happen to contain only bfqq. And this is exactly what -+ * has to happen, as bfqq may be the first queue in a possible -+ * burst. -+ */ -+ if (time_is_before_jiffies(bfqd->last_ins_in_burst + -+ bfqd->bfq_burst_interval)) { -+ bfqd->large_burst = false; -+ bfq_reset_burst_list(bfqd, bfqq); -+ return; -+ } -+ -+ /* -+ * If we get here, then bfqq is being activated shortly after the -+ * last queue. So, if the current burst is also large, we can mark -+ * bfqq as belonging to this large burst immediately. -+ */ -+ if (bfqd->large_burst) { -+ bfq_mark_bfqq_in_large_burst(bfqq); -+ return; -+ } -+ -+ /* -+ * If we get here, then a large-burst state has not yet been -+ * reached, but bfqq is being activated shortly after the last -+ * queue. Then we add bfqq to the burst. -+ */ -+ bfq_add_to_burst(bfqd, bfqq); -+} -+ -+static void bfq_add_request(struct request *rq) -+{ -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ struct bfq_entity *entity = &bfqq->entity; -+ struct bfq_data *bfqd = bfqq->bfqd; -+ struct request *next_rq, *prev; -+ unsigned long old_wr_coeff = bfqq->wr_coeff; -+ bool interactive = false; -+ -+ bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq)); -+ bfqq->queued[rq_is_sync(rq)]++; -+ bfqd->queued++; -+ -+ elv_rb_add(&bfqq->sort_list, rq); -+ -+ /* -+ * Check if this request is a better next-serve candidate. -+ */ -+ prev = bfqq->next_rq; -+ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position); -+ BUG_ON(next_rq == NULL); -+ bfqq->next_rq = next_rq; -+ -+ /* -+ * Adjust priority tree position, if next_rq changes. -+ */ -+ if (prev != bfqq->next_rq) -+ bfq_rq_pos_tree_add(bfqd, bfqq); -+ -+ if (!bfq_bfqq_busy(bfqq)) { -+ bool soft_rt, -+ idle_for_long_time = time_is_before_jiffies( -+ bfqq->budget_timeout + -+ bfqd->bfq_wr_min_idle_time); -+ -+ if (bfq_bfqq_sync(bfqq)) { -+ bool already_in_burst = -+ !hlist_unhashed(&bfqq->burst_list_node) || -+ bfq_bfqq_in_large_burst(bfqq); -+ bfq_handle_burst(bfqd, bfqq, idle_for_long_time); -+ /* -+ * If bfqq was not already in the current burst, -+ * then, at this point, bfqq either has been -+ * added to the current burst or has caused the -+ * current burst to terminate. In particular, in -+ * the second case, bfqq has become the first -+ * queue in a possible new burst. -+ * In both cases last_ins_in_burst needs to be -+ * moved forward. -+ */ -+ if (!already_in_burst) -+ bfqd->last_ins_in_burst = jiffies; -+ } -+ -+ soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && -+ !bfq_bfqq_in_large_burst(bfqq) && -+ time_is_before_jiffies(bfqq->soft_rt_next_start); -+ interactive = !bfq_bfqq_in_large_burst(bfqq) && -+ idle_for_long_time; -+ entity->budget = max_t(unsigned long, bfqq->max_budget, -+ bfq_serv_to_charge(next_rq, bfqq)); -+ -+ if (!bfq_bfqq_IO_bound(bfqq)) { -+ if (time_before(jiffies, -+ RQ_BIC(rq)->ttime.last_end_request + -+ bfqd->bfq_slice_idle)) { -+ bfqq->requests_within_timer++; -+ if (bfqq->requests_within_timer >= -+ bfqd->bfq_requests_within_timer) -+ bfq_mark_bfqq_IO_bound(bfqq); -+ } else -+ bfqq->requests_within_timer = 0; -+ } -+ -+ if (!bfqd->low_latency) -+ goto add_bfqq_busy; -+ -+ /* -+ * If the queue is not being boosted and has been idle -+ * for enough time, start a weight-raising period -+ */ -+ if (old_wr_coeff == 1 && (interactive || soft_rt)) { -+ bfqq->wr_coeff = bfqd->bfq_wr_coeff; -+ if (interactive) -+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); -+ else -+ bfqq->wr_cur_max_time = -+ bfqd->bfq_wr_rt_max_time; -+ bfq_log_bfqq(bfqd, bfqq, -+ "wrais starting at %lu, rais_max_time %u", -+ jiffies, -+ jiffies_to_msecs(bfqq->wr_cur_max_time)); -+ } else if (old_wr_coeff > 1) { -+ if (interactive) -+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); -+ else if (bfq_bfqq_in_large_burst(bfqq) || -+ (bfqq->wr_cur_max_time == -+ bfqd->bfq_wr_rt_max_time && -+ !soft_rt)) { -+ bfqq->wr_coeff = 1; -+ bfq_log_bfqq(bfqd, bfqq, -+ "wrais ending at %lu, rais_max_time %u", -+ jiffies, -+ jiffies_to_msecs(bfqq-> -+ wr_cur_max_time)); -+ } else if (time_before( -+ bfqq->last_wr_start_finish + -+ bfqq->wr_cur_max_time, -+ jiffies + -+ bfqd->bfq_wr_rt_max_time) && -+ soft_rt) { -+ /* -+ * -+ * The remaining weight-raising time is lower -+ * than bfqd->bfq_wr_rt_max_time, which -+ * means that the application is enjoying -+ * weight raising either because deemed soft- -+ * rt in the near past, or because deemed -+ * interactive a long ago. In both cases, -+ * resetting now the current remaining weight- -+ * raising time for the application to the -+ * weight-raising duration for soft rt -+ * applications would not cause any latency -+ * increase for the application (as the new -+ * duration would be higher than the remaining -+ * time). -+ * -+ * In addition, the application is now meeting -+ * the requirements for being deemed soft rt. -+ * In the end we can correctly and safely -+ * (re)charge the weight-raising duration for -+ * the application with the weight-raising -+ * duration for soft rt applications. -+ * -+ * In particular, doing this recharge now, i.e., -+ * before the weight-raising period for the -+ * application finishes, reduces the probability -+ * of the following negative scenario: -+ * 1) the weight of a soft rt application is -+ * raised at startup (as for any newly -+ * created application), -+ * 2) since the application is not interactive, -+ * at a certain time weight-raising is -+ * stopped for the application, -+ * 3) at that time the application happens to -+ * still have pending requests, and hence -+ * is destined to not have a chance to be -+ * deemed soft rt before these requests are -+ * completed (see the comments to the -+ * function bfq_bfqq_softrt_next_start() -+ * for details on soft rt detection), -+ * 4) these pending requests experience a high -+ * latency because the application is not -+ * weight-raised while they are pending. -+ */ -+ bfqq->last_wr_start_finish = jiffies; -+ bfqq->wr_cur_max_time = -+ bfqd->bfq_wr_rt_max_time; -+ } -+ } -+ if (old_wr_coeff != bfqq->wr_coeff) -+ entity->ioprio_changed = 1; -+add_bfqq_busy: -+ bfqq->last_idle_bklogged = jiffies; -+ bfqq->service_from_backlogged = 0; -+ bfq_clear_bfqq_softrt_update(bfqq); -+ bfq_add_bfqq_busy(bfqd, bfqq); -+ } else { -+ if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) && -+ time_is_before_jiffies( -+ bfqq->last_wr_start_finish + -+ bfqd->bfq_wr_min_inter_arr_async)) { -+ bfqq->wr_coeff = bfqd->bfq_wr_coeff; -+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); -+ -+ bfqd->wr_busy_queues++; -+ entity->ioprio_changed = 1; -+ bfq_log_bfqq(bfqd, bfqq, -+ "non-idle wrais starting at %lu, rais_max_time %u", -+ jiffies, -+ jiffies_to_msecs(bfqq->wr_cur_max_time)); -+ } -+ if (prev != bfqq->next_rq) -+ bfq_updated_next_req(bfqd, bfqq); -+ } -+ -+ if (bfqd->low_latency && -+ (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive)) -+ bfqq->last_wr_start_finish = jiffies; -+} -+ -+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd, -+ struct bio *bio) -+{ -+ struct task_struct *tsk = current; -+ struct bfq_io_cq *bic; -+ struct bfq_queue *bfqq; -+ -+ bic = bfq_bic_lookup(bfqd, tsk->io_context); -+ if (bic == NULL) -+ return NULL; -+ -+ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); -+ if (bfqq != NULL) -+ return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio)); -+ -+ return NULL; -+} -+ -+static void bfq_activate_request(struct request_queue *q, struct request *rq) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ -+ bfqd->rq_in_driver++; -+ bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); -+ bfq_log(bfqd, "activate_request: new bfqd->last_position %llu", -+ (long long unsigned)bfqd->last_position); -+} -+ -+static inline void bfq_deactivate_request(struct request_queue *q, -+ struct request *rq) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ -+ BUG_ON(bfqd->rq_in_driver == 0); -+ bfqd->rq_in_driver--; -+} -+ -+static void bfq_remove_request(struct request *rq) -+{ -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ struct bfq_data *bfqd = bfqq->bfqd; -+ const int sync = rq_is_sync(rq); -+ -+ if (bfqq->next_rq == rq) { -+ bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq); -+ bfq_updated_next_req(bfqd, bfqq); -+ } -+ -+ list_del_init(&rq->queuelist); -+ BUG_ON(bfqq->queued[sync] == 0); -+ bfqq->queued[sync]--; -+ bfqd->queued--; -+ elv_rb_del(&bfqq->sort_list, rq); -+ -+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) { -+ if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) -+ bfq_del_bfqq_busy(bfqd, bfqq, 1); -+ /* -+ * Remove queue from request-position tree as it is empty. -+ */ -+ if (bfqq->pos_root != NULL) { -+ rb_erase(&bfqq->pos_node, bfqq->pos_root); -+ bfqq->pos_root = NULL; -+ } -+ } -+ -+ if (rq->cmd_flags & REQ_META) { -+ BUG_ON(bfqq->meta_pending == 0); -+ bfqq->meta_pending--; -+ } -+} -+ -+static int bfq_merge(struct request_queue *q, struct request **req, -+ struct bio *bio) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct request *__rq; -+ -+ __rq = bfq_find_rq_fmerge(bfqd, bio); -+ if (__rq != NULL && elv_rq_merge_ok(__rq, bio)) { -+ *req = __rq; -+ return ELEVATOR_FRONT_MERGE; -+ } -+ -+ return ELEVATOR_NO_MERGE; -+} -+ -+static void bfq_merged_request(struct request_queue *q, struct request *req, -+ int type) -+{ -+ if (type == ELEVATOR_FRONT_MERGE && -+ rb_prev(&req->rb_node) && -+ blk_rq_pos(req) < -+ blk_rq_pos(container_of(rb_prev(&req->rb_node), -+ struct request, rb_node))) { -+ struct bfq_queue *bfqq = RQ_BFQQ(req); -+ struct bfq_data *bfqd = bfqq->bfqd; -+ struct request *prev, *next_rq; -+ -+ /* Reposition request in its sort_list */ -+ elv_rb_del(&bfqq->sort_list, req); -+ elv_rb_add(&bfqq->sort_list, req); -+ /* Choose next request to be served for bfqq */ -+ prev = bfqq->next_rq; -+ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req, -+ bfqd->last_position); -+ BUG_ON(next_rq == NULL); -+ bfqq->next_rq = next_rq; -+ /* -+ * If next_rq changes, update both the queue's budget to -+ * fit the new request and the queue's position in its -+ * rq_pos_tree. -+ */ -+ if (prev != bfqq->next_rq) { -+ bfq_updated_next_req(bfqd, bfqq); -+ bfq_rq_pos_tree_add(bfqd, bfqq); -+ } -+ } -+} -+ -+static void bfq_merged_requests(struct request_queue *q, struct request *rq, -+ struct request *next) -+{ -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ -+ /* -+ * Reposition in fifo if next is older than rq. -+ */ -+ if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && -+ time_before(next->fifo_time, rq->fifo_time)) { -+ list_move(&rq->queuelist, &next->queuelist); -+ rq->fifo_time = next->fifo_time; -+ } -+ -+ if (bfqq->next_rq == next) -+ bfqq->next_rq = rq; -+ -+ bfq_remove_request(next); -+} -+ -+/* Must be called with bfqq != NULL */ -+static inline void bfq_bfqq_end_wr(struct bfq_queue *bfqq) -+{ -+ BUG_ON(bfqq == NULL); -+ if (bfq_bfqq_busy(bfqq)) -+ bfqq->bfqd->wr_busy_queues--; -+ bfqq->wr_coeff = 1; -+ bfqq->wr_cur_max_time = 0; -+ /* Trigger a weight change on the next activation of the queue */ -+ bfqq->entity.ioprio_changed = 1; -+} -+ -+static void bfq_end_wr_async_queues(struct bfq_data *bfqd, -+ struct bfq_group *bfqg) -+{ -+ int i, j; -+ -+ for (i = 0; i < 2; i++) -+ for (j = 0; j < IOPRIO_BE_NR; j++) -+ if (bfqg->async_bfqq[i][j] != NULL) -+ bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); -+ if (bfqg->async_idle_bfqq != NULL) -+ bfq_bfqq_end_wr(bfqg->async_idle_bfqq); -+} -+ -+static void bfq_end_wr(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq; -+ -+ spin_lock_irq(bfqd->queue->queue_lock); -+ -+ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) -+ bfq_bfqq_end_wr(bfqq); -+ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) -+ bfq_bfqq_end_wr(bfqq); -+ bfq_end_wr_async(bfqd); -+ -+ spin_unlock_irq(bfqd->queue->queue_lock); -+} -+ -+static int bfq_allow_merge(struct request_queue *q, struct request *rq, -+ struct bio *bio) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_io_cq *bic; -+ struct bfq_queue *bfqq; -+ -+ /* -+ * Disallow merge of a sync bio into an async request. -+ */ -+ if (bfq_bio_sync(bio) && !rq_is_sync(rq)) -+ return 0; -+ -+ /* -+ * Lookup the bfqq that this bio will be queued with. Allow -+ * merge only if rq is queued there. -+ * Queue lock is held here. -+ */ -+ bic = bfq_bic_lookup(bfqd, current->io_context); -+ if (bic == NULL) -+ return 0; -+ -+ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); -+ return bfqq == RQ_BFQQ(rq); -+} -+ -+static void __bfq_set_in_service_queue(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ if (bfqq != NULL) { -+ bfq_mark_bfqq_must_alloc(bfqq); -+ bfq_mark_bfqq_budget_new(bfqq); -+ bfq_clear_bfqq_fifo_expire(bfqq); -+ -+ bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "set_in_service_queue, cur-budget = %lu", -+ bfqq->entity.budget); -+ } -+ -+ bfqd->in_service_queue = bfqq; -+} -+ -+/* -+ * Get and set a new queue for service. -+ */ -+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ if (!bfqq) -+ bfqq = bfq_get_next_queue(bfqd); -+ else -+ bfq_get_next_queue_forced(bfqd, bfqq); -+ -+ __bfq_set_in_service_queue(bfqd, bfqq); -+ return bfqq; -+} -+ -+static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd, -+ struct request *rq) -+{ -+ if (blk_rq_pos(rq) >= bfqd->last_position) -+ return blk_rq_pos(rq) - bfqd->last_position; -+ else -+ return bfqd->last_position - blk_rq_pos(rq); -+} -+ -+/* -+ * Return true if bfqq has no request pending and rq is close enough to -+ * bfqd->last_position, or if rq is closer to bfqd->last_position than -+ * bfqq->next_rq -+ */ -+static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq) -+{ -+ return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR; -+} -+ -+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) -+{ -+ struct rb_root *root = &bfqd->rq_pos_tree; -+ struct rb_node *parent, *node; -+ struct bfq_queue *__bfqq; -+ sector_t sector = bfqd->last_position; -+ -+ if (RB_EMPTY_ROOT(root)) -+ return NULL; -+ -+ /* -+ * First, if we find a request starting at the end of the last -+ * request, choose it. -+ */ -+ __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL); -+ if (__bfqq != NULL) -+ return __bfqq; -+ -+ /* -+ * If the exact sector wasn't found, the parent of the NULL leaf -+ * will contain the closest sector (rq_pos_tree sorted by -+ * next_request position). -+ */ -+ __bfqq = rb_entry(parent, struct bfq_queue, pos_node); -+ if (bfq_rq_close(bfqd, __bfqq->next_rq)) -+ return __bfqq; -+ -+ if (blk_rq_pos(__bfqq->next_rq) < sector) -+ node = rb_next(&__bfqq->pos_node); -+ else -+ node = rb_prev(&__bfqq->pos_node); -+ if (node == NULL) -+ return NULL; -+ -+ __bfqq = rb_entry(node, struct bfq_queue, pos_node); -+ if (bfq_rq_close(bfqd, __bfqq->next_rq)) -+ return __bfqq; -+ -+ return NULL; -+} -+ -+/* -+ * bfqd - obvious -+ * cur_bfqq - passed in so that we don't decide that the current queue -+ * is closely cooperating with itself. -+ * -+ * We are assuming that cur_bfqq has dispatched at least one request, -+ * and that bfqd->last_position reflects a position on the disk associated -+ * with the I/O issued by cur_bfqq. -+ */ -+static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, -+ struct bfq_queue *cur_bfqq) -+{ -+ struct bfq_queue *bfqq; -+ -+ if (bfq_class_idle(cur_bfqq)) -+ return NULL; -+ if (!bfq_bfqq_sync(cur_bfqq)) -+ return NULL; -+ if (BFQQ_SEEKY(cur_bfqq)) -+ return NULL; -+ -+ /* If device has only one backlogged bfq_queue, don't search. */ -+ if (bfqd->busy_queues == 1) -+ return NULL; -+ -+ /* -+ * We should notice if some of the queues are cooperating, e.g. -+ * working closely on the same area of the disk. In that case, -+ * we can group them together and don't waste time idling. -+ */ -+ bfqq = bfqq_close(bfqd); -+ if (bfqq == NULL || bfqq == cur_bfqq) -+ return NULL; -+ -+ /* -+ * Do not merge queues from different bfq_groups. -+ */ -+ if (bfqq->entity.parent != cur_bfqq->entity.parent) -+ return NULL; -+ -+ /* -+ * It only makes sense to merge sync queues. -+ */ -+ if (!bfq_bfqq_sync(bfqq)) -+ return NULL; -+ if (BFQQ_SEEKY(bfqq)) -+ return NULL; -+ -+ /* -+ * Do not merge queues of different priority classes. -+ */ -+ if (bfq_class_rt(bfqq) != bfq_class_rt(cur_bfqq)) -+ return NULL; -+ -+ return bfqq; -+} -+ -+/* -+ * If enough samples have been computed, return the current max budget -+ * stored in bfqd, which is dynamically updated according to the -+ * estimated disk peak rate; otherwise return the default max budget -+ */ -+static inline unsigned long bfq_max_budget(struct bfq_data *bfqd) -+{ -+ if (bfqd->budgets_assigned < 194) -+ return bfq_default_max_budget; -+ else -+ return bfqd->bfq_max_budget; -+} -+ -+/* -+ * Return min budget, which is a fraction of the current or default -+ * max budget (trying with 1/32) -+ */ -+static inline unsigned long bfq_min_budget(struct bfq_data *bfqd) -+{ -+ if (bfqd->budgets_assigned < 194) -+ return bfq_default_max_budget / 32; -+ else -+ return bfqd->bfq_max_budget / 32; -+} -+ -+static void bfq_arm_slice_timer(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq = bfqd->in_service_queue; -+ struct bfq_io_cq *bic; -+ unsigned long sl; -+ -+ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); -+ -+ /* Processes have exited, don't wait. */ -+ bic = bfqd->in_service_bic; -+ if (bic == NULL || atomic_read(&bic->icq.ioc->active_ref) == 0) -+ return; -+ -+ bfq_mark_bfqq_wait_request(bfqq); -+ -+ /* -+ * We don't want to idle for seeks, but we do want to allow -+ * fair distribution of slice time for a process doing back-to-back -+ * seeks. So allow a little bit of time for him to submit a new rq. -+ * -+ * To prevent processes with (partly) seeky workloads from -+ * being too ill-treated, grant them a small fraction of the -+ * assigned budget before reducing the waiting time to -+ * BFQ_MIN_TT. This happened to help reduce latency. -+ */ -+ sl = bfqd->bfq_slice_idle; -+ /* -+ * Unless the queue is being weight-raised, grant only minimum idle -+ * time if the queue either has been seeky for long enough or has -+ * already proved to be constantly seeky. -+ */ -+ if (bfq_sample_valid(bfqq->seek_samples) && -+ ((BFQQ_SEEKY(bfqq) && bfqq->entity.service > -+ bfq_max_budget(bfqq->bfqd) / 8) || -+ bfq_bfqq_constantly_seeky(bfqq)) && bfqq->wr_coeff == 1) -+ sl = min(sl, msecs_to_jiffies(BFQ_MIN_TT)); -+ else if (bfqq->wr_coeff > 1) -+ sl = sl * 3; -+ bfqd->last_idling_start = ktime_get(); -+ mod_timer(&bfqd->idle_slice_timer, jiffies + sl); -+ bfq_log(bfqd, "arm idle: %u/%u ms", -+ jiffies_to_msecs(sl), jiffies_to_msecs(bfqd->bfq_slice_idle)); -+} -+ -+/* -+ * Set the maximum time for the in-service queue to consume its -+ * budget. This prevents seeky processes from lowering the disk -+ * throughput (always guaranteed with a time slice scheme as in CFQ). -+ */ -+static void bfq_set_budget_timeout(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq = bfqd->in_service_queue; -+ unsigned int timeout_coeff; -+ if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time) -+ timeout_coeff = 1; -+ else -+ timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight; -+ -+ bfqd->last_budget_start = ktime_get(); -+ -+ bfq_clear_bfqq_budget_new(bfqq); -+ bfqq->budget_timeout = jiffies + -+ bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] * timeout_coeff; -+ -+ bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u", -+ jiffies_to_msecs(bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] * -+ timeout_coeff)); -+} -+ -+/* -+ * Move request from internal lists to the request queue dispatch list. -+ */ -+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ -+ /* -+ * For consistency, the next instruction should have been executed -+ * after removing the request from the queue and dispatching it. -+ * We execute instead this instruction before bfq_remove_request() -+ * (and hence introduce a temporary inconsistency), for efficiency. -+ * In fact, in a forced_dispatch, this prevents two counters related -+ * to bfqq->dispatched to risk to be uselessly decremented if bfqq -+ * is not in service, and then to be incremented again after -+ * incrementing bfqq->dispatched. -+ */ -+ bfqq->dispatched++; -+ bfq_remove_request(rq); -+ elv_dispatch_sort(q, rq); -+ -+ if (bfq_bfqq_sync(bfqq)) -+ bfqd->sync_flight++; -+} -+ -+/* -+ * Return expired entry, or NULL to just start from scratch in rbtree. -+ */ -+static struct request *bfq_check_fifo(struct bfq_queue *bfqq) -+{ -+ struct request *rq = NULL; -+ -+ if (bfq_bfqq_fifo_expire(bfqq)) -+ return NULL; -+ -+ bfq_mark_bfqq_fifo_expire(bfqq); -+ -+ if (list_empty(&bfqq->fifo)) -+ return NULL; -+ -+ rq = rq_entry_fifo(bfqq->fifo.next); -+ -+ if (time_before(jiffies, rq->fifo_time)) -+ return NULL; -+ -+ return rq; -+} -+ -+/* Must be called with the queue_lock held. */ -+static int bfqq_process_refs(struct bfq_queue *bfqq) -+{ -+ int process_refs, io_refs; -+ -+ io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; -+ process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st; -+ BUG_ON(process_refs < 0); -+ return process_refs; -+} -+ -+static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) -+{ -+ int process_refs, new_process_refs; -+ struct bfq_queue *__bfqq; -+ -+ /* -+ * If there are no process references on the new_bfqq, then it is -+ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain -+ * may have dropped their last reference (not just their last process -+ * reference). -+ */ -+ if (!bfqq_process_refs(new_bfqq)) -+ return; -+ -+ /* Avoid a circular list and skip interim queue merges. */ -+ while ((__bfqq = new_bfqq->new_bfqq)) { -+ if (__bfqq == bfqq) -+ return; -+ new_bfqq = __bfqq; -+ } -+ -+ process_refs = bfqq_process_refs(bfqq); -+ new_process_refs = bfqq_process_refs(new_bfqq); -+ /* -+ * If the process for the bfqq has gone away, there is no -+ * sense in merging the queues. -+ */ -+ if (process_refs == 0 || new_process_refs == 0) -+ return; -+ -+ /* -+ * Merge in the direction of the lesser amount of work. -+ */ -+ if (new_process_refs >= process_refs) { -+ bfqq->new_bfqq = new_bfqq; -+ atomic_add(process_refs, &new_bfqq->ref); -+ } else { -+ new_bfqq->new_bfqq = bfqq; -+ atomic_add(new_process_refs, &bfqq->ref); -+ } -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", -+ new_bfqq->pid); -+} -+ -+static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ return entity->budget - entity->service; -+} -+ -+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ BUG_ON(bfqq != bfqd->in_service_queue); -+ -+ __bfq_bfqd_reset_in_service(bfqd); -+ -+ /* -+ * If this bfqq is shared between multiple processes, check -+ * to make sure that those processes are still issuing I/Os -+ * within the mean seek distance. If not, it may be time to -+ * break the queues apart again. -+ */ -+ if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq)) -+ bfq_mark_bfqq_split_coop(bfqq); -+ -+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) { -+ /* -+ * Overloading budget_timeout field to store the time -+ * at which the queue remains with no backlog; used by -+ * the weight-raising mechanism. -+ */ -+ bfqq->budget_timeout = jiffies; -+ bfq_del_bfqq_busy(bfqd, bfqq, 1); -+ } else { -+ bfq_activate_bfqq(bfqd, bfqq); -+ /* -+ * Resort priority tree of potential close cooperators. -+ */ -+ bfq_rq_pos_tree_add(bfqd, bfqq); -+ } -+} -+ -+/** -+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior. -+ * @bfqd: device data. -+ * @bfqq: queue to update. -+ * @reason: reason for expiration. -+ * -+ * Handle the feedback on @bfqq budget. See the body for detailed -+ * comments. -+ */ -+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ enum bfqq_expiration reason) -+{ -+ struct request *next_rq; -+ unsigned long budget, min_budget; -+ -+ budget = bfqq->max_budget; -+ min_budget = bfq_min_budget(bfqd); -+ -+ BUG_ON(bfqq != bfqd->in_service_queue); -+ -+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %lu, budg left %lu", -+ bfqq->entity.budget, bfq_bfqq_budget_left(bfqq)); -+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %lu, min budg %lu", -+ budget, bfq_min_budget(bfqd)); -+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d", -+ bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue)); -+ -+ if (bfq_bfqq_sync(bfqq)) { -+ switch (reason) { -+ /* -+ * Caveat: in all the following cases we trade latency -+ * for throughput. -+ */ -+ case BFQ_BFQQ_TOO_IDLE: -+ /* -+ * This is the only case where we may reduce -+ * the budget: if there is no request of the -+ * process still waiting for completion, then -+ * we assume (tentatively) that the timer has -+ * expired because the batch of requests of -+ * the process could have been served with a -+ * smaller budget. Hence, betting that -+ * process will behave in the same way when it -+ * becomes backlogged again, we reduce its -+ * next budget. As long as we guess right, -+ * this budget cut reduces the latency -+ * experienced by the process. -+ * -+ * However, if there are still outstanding -+ * requests, then the process may have not yet -+ * issued its next request just because it is -+ * still waiting for the completion of some of -+ * the still outstanding ones. So in this -+ * subcase we do not reduce its budget, on the -+ * contrary we increase it to possibly boost -+ * the throughput, as discussed in the -+ * comments to the BUDGET_TIMEOUT case. -+ */ -+ if (bfqq->dispatched > 0) /* still outstanding reqs */ -+ budget = min(budget * 2, bfqd->bfq_max_budget); -+ else { -+ if (budget > 5 * min_budget) -+ budget -= 4 * min_budget; -+ else -+ budget = min_budget; -+ } -+ break; -+ case BFQ_BFQQ_BUDGET_TIMEOUT: -+ /* -+ * We double the budget here because: 1) it -+ * gives the chance to boost the throughput if -+ * this is not a seeky process (which may have -+ * bumped into this timeout because of, e.g., -+ * ZBR), 2) together with charge_full_budget -+ * it helps give seeky processes higher -+ * timestamps, and hence be served less -+ * frequently. -+ */ -+ budget = min(budget * 2, bfqd->bfq_max_budget); -+ break; -+ case BFQ_BFQQ_BUDGET_EXHAUSTED: -+ /* -+ * The process still has backlog, and did not -+ * let either the budget timeout or the disk -+ * idling timeout expire. Hence it is not -+ * seeky, has a short thinktime and may be -+ * happy with a higher budget too. So -+ * definitely increase the budget of this good -+ * candidate to boost the disk throughput. -+ */ -+ budget = min(budget * 4, bfqd->bfq_max_budget); -+ break; -+ case BFQ_BFQQ_NO_MORE_REQUESTS: -+ /* -+ * Leave the budget unchanged. -+ */ -+ default: -+ return; -+ } -+ } else /* async queue */ -+ /* async queues get always the maximum possible budget -+ * (their ability to dispatch is limited by -+ * @bfqd->bfq_max_budget_async_rq). -+ */ -+ budget = bfqd->bfq_max_budget; -+ -+ bfqq->max_budget = budget; -+ -+ if (bfqd->budgets_assigned >= 194 && bfqd->bfq_user_max_budget == 0 && -+ bfqq->max_budget > bfqd->bfq_max_budget) -+ bfqq->max_budget = bfqd->bfq_max_budget; -+ -+ /* -+ * Make sure that we have enough budget for the next request. -+ * Since the finish time of the bfqq must be kept in sync with -+ * the budget, be sure to call __bfq_bfqq_expire() after the -+ * update. -+ */ -+ next_rq = bfqq->next_rq; -+ if (next_rq != NULL) -+ bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget, -+ bfq_serv_to_charge(next_rq, bfqq)); -+ else -+ bfqq->entity.budget = bfqq->max_budget; -+ -+ bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %lu", -+ next_rq != NULL ? blk_rq_sectors(next_rq) : 0, -+ bfqq->entity.budget); -+} -+ -+static unsigned long bfq_calc_max_budget(u64 peak_rate, u64 timeout) -+{ -+ unsigned long max_budget; -+ -+ /* -+ * The max_budget calculated when autotuning is equal to the -+ * amount of sectors transfered in timeout_sync at the -+ * estimated peak rate. -+ */ -+ max_budget = (unsigned long)(peak_rate * 1000 * -+ timeout >> BFQ_RATE_SHIFT); -+ -+ return max_budget; -+} -+ -+/* -+ * In addition to updating the peak rate, checks whether the process -+ * is "slow", and returns 1 if so. This slow flag is used, in addition -+ * to the budget timeout, to reduce the amount of service provided to -+ * seeky processes, and hence reduce their chances to lower the -+ * throughput. See the code for more details. -+ */ -+static int bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ int compensate, enum bfqq_expiration reason) -+{ -+ u64 bw, usecs, expected, timeout; -+ ktime_t delta; -+ int update = 0; -+ -+ if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq)) -+ return 0; -+ -+ if (compensate) -+ delta = bfqd->last_idling_start; -+ else -+ delta = ktime_get(); -+ delta = ktime_sub(delta, bfqd->last_budget_start); -+ usecs = ktime_to_us(delta); -+ -+ /* Don't trust short/unrealistic values. */ -+ if (usecs < 100 || usecs >= LONG_MAX) -+ return 0; -+ -+ /* -+ * Calculate the bandwidth for the last slice. We use a 64 bit -+ * value to store the peak rate, in sectors per usec in fixed -+ * point math. We do so to have enough precision in the estimate -+ * and to avoid overflows. -+ */ -+ bw = (u64)bfqq->entity.service << BFQ_RATE_SHIFT; -+ do_div(bw, (unsigned long)usecs); -+ -+ timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]); -+ -+ /* -+ * Use only long (> 20ms) intervals to filter out spikes for -+ * the peak rate estimation. -+ */ -+ if (usecs > 20000) { -+ if (bw > bfqd->peak_rate || -+ (!BFQQ_SEEKY(bfqq) && -+ reason == BFQ_BFQQ_BUDGET_TIMEOUT)) { -+ bfq_log(bfqd, "measured bw =%llu", bw); -+ /* -+ * To smooth oscillations use a low-pass filter with -+ * alpha=7/8, i.e., -+ * new_rate = (7/8) * old_rate + (1/8) * bw -+ */ -+ do_div(bw, 8); -+ if (bw == 0) -+ return 0; -+ bfqd->peak_rate *= 7; -+ do_div(bfqd->peak_rate, 8); -+ bfqd->peak_rate += bw; -+ update = 1; -+ bfq_log(bfqd, "new peak_rate=%llu", bfqd->peak_rate); -+ } -+ -+ update |= bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES - 1; -+ -+ if (bfqd->peak_rate_samples < BFQ_PEAK_RATE_SAMPLES) -+ bfqd->peak_rate_samples++; -+ -+ if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES && -+ update) { -+ int dev_type = blk_queue_nonrot(bfqd->queue); -+ if (bfqd->bfq_user_max_budget == 0) { -+ bfqd->bfq_max_budget = -+ bfq_calc_max_budget(bfqd->peak_rate, -+ timeout); -+ bfq_log(bfqd, "new max_budget=%lu", -+ bfqd->bfq_max_budget); -+ } -+ if (bfqd->device_speed == BFQ_BFQD_FAST && -+ bfqd->peak_rate < device_speed_thresh[dev_type]) { -+ bfqd->device_speed = BFQ_BFQD_SLOW; -+ bfqd->RT_prod = R_slow[dev_type] * -+ T_slow[dev_type]; -+ } else if (bfqd->device_speed == BFQ_BFQD_SLOW && -+ bfqd->peak_rate > device_speed_thresh[dev_type]) { -+ bfqd->device_speed = BFQ_BFQD_FAST; -+ bfqd->RT_prod = R_fast[dev_type] * -+ T_fast[dev_type]; -+ } -+ } -+ } -+ -+ /* -+ * If the process has been served for a too short time -+ * interval to let its possible sequential accesses prevail on -+ * the initial seek time needed to move the disk head on the -+ * first sector it requested, then give the process a chance -+ * and for the moment return false. -+ */ -+ if (bfqq->entity.budget <= bfq_max_budget(bfqd) / 8) -+ return 0; -+ -+ /* -+ * A process is considered ``slow'' (i.e., seeky, so that we -+ * cannot treat it fairly in the service domain, as it would -+ * slow down too much the other processes) if, when a slice -+ * ends for whatever reason, it has received service at a -+ * rate that would not be high enough to complete the budget -+ * before the budget timeout expiration. -+ */ -+ expected = bw * 1000 * timeout >> BFQ_RATE_SHIFT; -+ -+ /* -+ * Caveat: processes doing IO in the slower disk zones will -+ * tend to be slow(er) even if not seeky. And the estimated -+ * peak rate will actually be an average over the disk -+ * surface. Hence, to not be too harsh with unlucky processes, -+ * we keep a budget/3 margin of safety before declaring a -+ * process slow. -+ */ -+ return expected > (4 * bfqq->entity.budget) / 3; -+} -+ -+/* -+ * To be deemed as soft real-time, an application must meet two -+ * requirements. First, the application must not require an average -+ * bandwidth higher than the approximate bandwidth required to playback or -+ * record a compressed high-definition video. -+ * The next function is invoked on the completion of the last request of a -+ * batch, to compute the next-start time instant, soft_rt_next_start, such -+ * that, if the next request of the application does not arrive before -+ * soft_rt_next_start, then the above requirement on the bandwidth is met. -+ * -+ * The second requirement is that the request pattern of the application is -+ * isochronous, i.e., that, after issuing a request or a batch of requests, -+ * the application stops issuing new requests until all its pending requests -+ * have been completed. After that, the application may issue a new batch, -+ * and so on. -+ * For this reason the next function is invoked to compute -+ * soft_rt_next_start only for applications that meet this requirement, -+ * whereas soft_rt_next_start is set to infinity for applications that do -+ * not. -+ * -+ * Unfortunately, even a greedy application may happen to behave in an -+ * isochronous way if the CPU load is high. In fact, the application may -+ * stop issuing requests while the CPUs are busy serving other processes, -+ * then restart, then stop again for a while, and so on. In addition, if -+ * the disk achieves a low enough throughput with the request pattern -+ * issued by the application (e.g., because the request pattern is random -+ * and/or the device is slow), then the application may meet the above -+ * bandwidth requirement too. To prevent such a greedy application to be -+ * deemed as soft real-time, a further rule is used in the computation of -+ * soft_rt_next_start: soft_rt_next_start must be higher than the current -+ * time plus the maximum time for which the arrival of a request is waited -+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle. -+ * This filters out greedy applications, as the latter issue instead their -+ * next request as soon as possible after the last one has been completed -+ * (in contrast, when a batch of requests is completed, a soft real-time -+ * application spends some time processing data). -+ * -+ * Unfortunately, the last filter may easily generate false positives if -+ * only bfqd->bfq_slice_idle is used as a reference time interval and one -+ * or both the following cases occur: -+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher -+ * than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with -+ * HZ=100. -+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing -+ * for a while, then suddenly 'jump' by several units to recover the lost -+ * increments. This seems to happen, e.g., inside virtual machines. -+ * To address this issue, we do not use as a reference time interval just -+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In -+ * particular we add the minimum number of jiffies for which the filter -+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual -+ * machines. -+ */ -+static inline unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ return max(bfqq->last_idle_bklogged + -+ HZ * bfqq->service_from_backlogged / -+ bfqd->bfq_wr_max_softrt_rate, -+ jiffies + bfqq->bfqd->bfq_slice_idle + 4); -+} -+ -+/* -+ * Return the largest-possible time instant such that, for as long as possible, -+ * the current time will be lower than this time instant according to the macro -+ * time_is_before_jiffies(). -+ */ -+static inline unsigned long bfq_infinity_from_now(unsigned long now) -+{ -+ return now + ULONG_MAX / 2; -+} -+ -+/** -+ * bfq_bfqq_expire - expire a queue. -+ * @bfqd: device owning the queue. -+ * @bfqq: the queue to expire. -+ * @compensate: if true, compensate for the time spent idling. -+ * @reason: the reason causing the expiration. -+ * -+ * -+ * If the process associated to the queue is slow (i.e., seeky), or in -+ * case of budget timeout, or, finally, if it is async, we -+ * artificially charge it an entire budget (independently of the -+ * actual service it received). As a consequence, the queue will get -+ * higher timestamps than the correct ones upon reactivation, and -+ * hence it will be rescheduled as if it had received more service -+ * than what it actually received. In the end, this class of processes -+ * will receive less service in proportion to how slowly they consume -+ * their budgets (and hence how seriously they tend to lower the -+ * throughput). -+ * -+ * In contrast, when a queue expires because it has been idling for -+ * too much or because it exhausted its budget, we do not touch the -+ * amount of service it has received. Hence when the queue will be -+ * reactivated and its timestamps updated, the latter will be in sync -+ * with the actual service received by the queue until expiration. -+ * -+ * Charging a full budget to the first type of queues and the exact -+ * service to the others has the effect of using the WF2Q+ policy to -+ * schedule the former on a timeslice basis, without violating the -+ * service domain guarantees of the latter. -+ */ -+static void bfq_bfqq_expire(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ int compensate, -+ enum bfqq_expiration reason) -+{ -+ int slow; -+ BUG_ON(bfqq != bfqd->in_service_queue); -+ -+ /* Update disk peak rate for autotuning and check whether the -+ * process is slow (see bfq_update_peak_rate). -+ */ -+ slow = bfq_update_peak_rate(bfqd, bfqq, compensate, reason); -+ -+ /* -+ * As above explained, 'punish' slow (i.e., seeky), timed-out -+ * and async queues, to favor sequential sync workloads. -+ * -+ * Processes doing I/O in the slower disk zones will tend to be -+ * slow(er) even if not seeky. Hence, since the estimated peak -+ * rate is actually an average over the disk surface, these -+ * processes may timeout just for bad luck. To avoid punishing -+ * them we do not charge a full budget to a process that -+ * succeeded in consuming at least 2/3 of its budget. -+ */ -+ if (slow || (reason == BFQ_BFQQ_BUDGET_TIMEOUT && -+ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3)) -+ bfq_bfqq_charge_full_budget(bfqq); -+ -+ bfqq->service_from_backlogged += bfqq->entity.service; -+ -+ if (BFQQ_SEEKY(bfqq) && reason == BFQ_BFQQ_BUDGET_TIMEOUT && -+ !bfq_bfqq_constantly_seeky(bfqq)) { -+ bfq_mark_bfqq_constantly_seeky(bfqq); -+ if (!blk_queue_nonrot(bfqd->queue)) -+ bfqd->const_seeky_busy_in_flight_queues++; -+ } -+ -+ if (reason == BFQ_BFQQ_TOO_IDLE && -+ bfqq->entity.service <= 2 * bfqq->entity.budget / 10 ) -+ bfq_clear_bfqq_IO_bound(bfqq); -+ -+ if (bfqd->low_latency && bfqq->wr_coeff == 1) -+ bfqq->last_wr_start_finish = jiffies; -+ -+ if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 && -+ RB_EMPTY_ROOT(&bfqq->sort_list)) { -+ /* -+ * If we get here, and there are no outstanding requests, -+ * then the request pattern is isochronous (see the comments -+ * to the function bfq_bfqq_softrt_next_start()). Hence we -+ * can compute soft_rt_next_start. If, instead, the queue -+ * still has outstanding requests, then we have to wait -+ * for the completion of all the outstanding requests to -+ * discover whether the request pattern is actually -+ * isochronous. -+ */ -+ if (bfqq->dispatched == 0) -+ bfqq->soft_rt_next_start = -+ bfq_bfqq_softrt_next_start(bfqd, bfqq); -+ else { -+ /* -+ * The application is still waiting for the -+ * completion of one or more requests: -+ * prevent it from possibly being incorrectly -+ * deemed as soft real-time by setting its -+ * soft_rt_next_start to infinity. In fact, -+ * without this assignment, the application -+ * would be incorrectly deemed as soft -+ * real-time if: -+ * 1) it issued a new request before the -+ * completion of all its in-flight -+ * requests, and -+ * 2) at that time, its soft_rt_next_start -+ * happened to be in the past. -+ */ -+ bfqq->soft_rt_next_start = -+ bfq_infinity_from_now(jiffies); -+ /* -+ * Schedule an update of soft_rt_next_start to when -+ * the task may be discovered to be isochronous. -+ */ -+ bfq_mark_bfqq_softrt_update(bfqq); -+ } -+ } -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "expire (%d, slow %d, num_disp %d, idle_win %d)", reason, -+ slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq)); -+ -+ /* -+ * Increase, decrease or leave budget unchanged according to -+ * reason. -+ */ -+ __bfq_bfqq_recalc_budget(bfqd, bfqq, reason); -+ __bfq_bfqq_expire(bfqd, bfqq); -+} -+ -+/* -+ * Budget timeout is not implemented through a dedicated timer, but -+ * just checked on request arrivals and completions, as well as on -+ * idle timer expirations. -+ */ -+static int bfq_bfqq_budget_timeout(struct bfq_queue *bfqq) -+{ -+ if (bfq_bfqq_budget_new(bfqq) || -+ time_before(jiffies, bfqq->budget_timeout)) -+ return 0; -+ return 1; -+} -+ -+/* -+ * If we expire a queue that is waiting for the arrival of a new -+ * request, we may prevent the fictitious timestamp back-shifting that -+ * allows the guarantees of the queue to be preserved (see [1] for -+ * this tricky aspect). Hence we return true only if this condition -+ * does not hold, or if the queue is slow enough to deserve only to be -+ * kicked off for preserving a high throughput. -+*/ -+static inline int bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq) -+{ -+ bfq_log_bfqq(bfqq->bfqd, bfqq, -+ "may_budget_timeout: wait_request %d left %d timeout %d", -+ bfq_bfqq_wait_request(bfqq), -+ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3, -+ bfq_bfqq_budget_timeout(bfqq)); -+ -+ return (!bfq_bfqq_wait_request(bfqq) || -+ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3) -+ && -+ bfq_bfqq_budget_timeout(bfqq); -+} -+ -+/* -+ * Device idling is allowed only for the queues for which this function -+ * returns true. For this reason, the return value of this function plays a -+ * critical role for both throughput boosting and service guarantees. The -+ * return value is computed through a logical expression. In this rather -+ * long comment, we try to briefly describe all the details and motivations -+ * behind the components of this logical expression. -+ * -+ * First, the expression is false if bfqq is not sync, or if: bfqq happened -+ * to become active during a large burst of queue activations, and the -+ * pattern of requests bfqq contains boosts the throughput if bfqq is -+ * expired. In fact, queues that became active during a large burst benefit -+ * only from throughput, as discussed in the comments to bfq_handle_burst. -+ * In this respect, expiring bfqq certainly boosts the throughput on NCQ- -+ * capable flash-based devices, whereas, on rotational devices, it boosts -+ * the throughput only if bfqq contains random requests. -+ * -+ * On the opposite end, if (a) bfqq is sync, (b) the above burst-related -+ * condition does not hold, and (c) bfqq is being weight-raised, then the -+ * expression always evaluates to true, as device idling is instrumental -+ * for preserving low-latency guarantees (see [1]). If, instead, conditions -+ * (a) and (b) do hold, but (c) does not, then the expression evaluates to -+ * true only if: (1) bfqq is I/O-bound and has a non-null idle window, and -+ * (2) at least one of the following two conditions holds. -+ * The first condition is that the device is not performing NCQ, because -+ * idling the device most certainly boosts the throughput if this condition -+ * holds and bfqq is I/O-bound and has been granted a non-null idle window. -+ * The second compound condition is made of the logical AND of two components. -+ * -+ * The first component is true only if there is no weight-raised busy -+ * queue. This guarantees that the device is not idled for a sync non- -+ * weight-raised queue when there are busy weight-raised queues. The former -+ * is then expired immediately if empty. Combined with the timestamping -+ * rules of BFQ (see [1] for details), this causes sync non-weight-raised -+ * queues to get a lower number of requests served, and hence to ask for a -+ * lower number of requests from the request pool, before the busy weight- -+ * raised queues get served again. -+ * -+ * This is beneficial for the processes associated with weight-raised -+ * queues, when the request pool is saturated (e.g., in the presence of -+ * write hogs). In fact, if the processes associated with the other queues -+ * ask for requests at a lower rate, then weight-raised processes have a -+ * higher probability to get a request from the pool immediately (or at -+ * least soon) when they need one. Hence they have a higher probability to -+ * actually get a fraction of the disk throughput proportional to their -+ * high weight. This is especially true with NCQ-capable drives, which -+ * enqueue several requests in advance and further reorder internally- -+ * queued requests. -+ * -+ * In the end, mistreating non-weight-raised queues when there are busy -+ * weight-raised queues seems to mitigate starvation problems in the -+ * presence of heavy write workloads and NCQ, and hence to guarantee a -+ * higher application and system responsiveness in these hostile scenarios. -+ * -+ * If the first component of the compound condition is instead true, i.e., -+ * there is no weight-raised busy queue, then the second component of the -+ * compound condition takes into account service-guarantee and throughput -+ * issues related to NCQ (recall that the compound condition is evaluated -+ * only if the device is detected as supporting NCQ). -+ * -+ * As for service guarantees, allowing the drive to enqueue more than one -+ * request at a time, and hence delegating de facto final scheduling -+ * decisions to the drive's internal scheduler, causes loss of control on -+ * the actual request service order. In this respect, when the drive is -+ * allowed to enqueue more than one request at a time, the service -+ * distribution enforced by the drive's internal scheduler is likely to -+ * coincide with the desired device-throughput distribution only in the -+ * following, perfectly symmetric, scenario: -+ * 1) all active queues have the same weight, -+ * 2) all active groups at the same level in the groups tree have the same -+ * weight, -+ * 3) all active groups at the same level in the groups tree have the same -+ * number of children. -+ * -+ * Even in such a scenario, sequential I/O may still receive a preferential -+ * treatment, but this is not likely to be a big issue with flash-based -+ * devices, because of their non-dramatic loss of throughput with random -+ * I/O. Things do differ with HDDs, for which additional care is taken, as -+ * explained after completing the discussion for flash-based devices. -+ * -+ * Unfortunately, keeping the necessary state for evaluating exactly the -+ * above symmetry conditions would be quite complex and time-consuming. -+ * Therefore BFQ evaluates instead the following stronger sub-conditions, -+ * for which it is much easier to maintain the needed state: -+ * 1) all active queues have the same weight, -+ * 2) all active groups have the same weight, -+ * 3) all active groups have at most one active child each. -+ * In particular, the last two conditions are always true if hierarchical -+ * support and the cgroups interface are not enabled, hence no state needs -+ * to be maintained in this case. -+ * -+ * According to the above considerations, the second component of the -+ * compound condition evaluates to true if any of the above symmetry -+ * sub-condition does not hold, or the device is not flash-based. Therefore, -+ * if also the first component is true, then idling is allowed for a sync -+ * queue. These are the only sub-conditions considered if the device is -+ * flash-based, as, for such a device, it is sensible to force idling only -+ * for service-guarantee issues. In fact, as for throughput, idling -+ * NCQ-capable flash-based devices would not boost the throughput even -+ * with sequential I/O; rather it would lower the throughput in proportion -+ * to how fast the device is. In the end, (only) if all the three -+ * sub-conditions hold and the device is flash-based, the compound -+ * condition evaluates to false and therefore no idling is performed. -+ * -+ * As already said, things change with a rotational device, where idling -+ * boosts the throughput with sequential I/O (even with NCQ). Hence, for -+ * such a device the second component of the compound condition evaluates -+ * to true also if the following additional sub-condition does not hold: -+ * the queue is constantly seeky. Unfortunately, this different behavior -+ * with respect to flash-based devices causes an additional asymmetry: if -+ * some sync queues enjoy idling and some other sync queues do not, then -+ * the latter get a low share of the device throughput, simply because the -+ * former get many requests served after being set as in service, whereas -+ * the latter do not. As a consequence, to guarantee the desired throughput -+ * distribution, on HDDs the compound expression evaluates to true (and -+ * hence device idling is performed) also if the following last symmetry -+ * condition does not hold: no other queue is benefiting from idling. Also -+ * this last condition is actually replaced with a simpler-to-maintain and -+ * stronger condition: there is no busy queue which is not constantly seeky -+ * (and hence may also benefit from idling). -+ * -+ * To sum up, when all the required symmetry and throughput-boosting -+ * sub-conditions hold, the second component of the compound condition -+ * evaluates to false, and hence no idling is performed. This helps to -+ * keep the drives' internal queues full on NCQ-capable devices, and hence -+ * to boost the throughput, without causing 'almost' any loss of service -+ * guarantees. The 'almost' follows from the fact that, if the internal -+ * queue of one such device is filled while all the sub-conditions hold, -+ * but at some point in time some sub-condition stops to hold, then it may -+ * become impossible to let requests be served in the new desired order -+ * until all the requests already queued in the device have been served. -+ */ -+static inline bool bfq_bfqq_must_not_expire(struct bfq_queue *bfqq) -+{ -+ struct bfq_data *bfqd = bfqq->bfqd; -+#ifdef CONFIG_CGROUP_BFQIO -+#define symmetric_scenario (!bfqd->active_numerous_groups && \ -+ !bfq_differentiated_weights(bfqd)) -+#else -+#define symmetric_scenario (!bfq_differentiated_weights(bfqd)) -+#endif -+#define cond_for_seeky_on_ncq_hdd (bfq_bfqq_constantly_seeky(bfqq) && \ -+ bfqd->busy_in_flight_queues == \ -+ bfqd->const_seeky_busy_in_flight_queues) -+ -+#define cond_for_expiring_in_burst (bfq_bfqq_in_large_burst(bfqq) && \ -+ bfqd->hw_tag && \ -+ (blk_queue_nonrot(bfqd->queue) || \ -+ bfq_bfqq_constantly_seeky(bfqq))) -+ -+/* -+ * Condition for expiring a non-weight-raised queue (and hence not idling -+ * the device). -+ */ -+#define cond_for_expiring_non_wr (bfqd->hw_tag && \ -+ (bfqd->wr_busy_queues > 0 || \ -+ (symmetric_scenario && \ -+ (blk_queue_nonrot(bfqd->queue) || \ -+ cond_for_seeky_on_ncq_hdd)))) -+ -+ return bfq_bfqq_sync(bfqq) && -+ !cond_for_expiring_in_burst && -+ (bfqq->wr_coeff > 1 || -+ (bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_idle_window(bfqq) && -+ !cond_for_expiring_non_wr) -+ ); -+} -+ -+/* -+ * If the in-service queue is empty but sync, and the function -+ * bfq_bfqq_must_not_expire returns true, then: -+ * 1) the queue must remain in service and cannot be expired, and -+ * 2) the disk must be idled to wait for the possible arrival of a new -+ * request for the queue. -+ * See the comments to the function bfq_bfqq_must_not_expire for the reasons -+ * why performing device idling is the best choice to boost the throughput -+ * and preserve service guarantees when bfq_bfqq_must_not_expire itself -+ * returns true. -+ */ -+static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) -+{ -+ struct bfq_data *bfqd = bfqq->bfqd; -+ -+ return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 && -+ bfq_bfqq_must_not_expire(bfqq); -+} -+ -+/* -+ * Select a queue for service. If we have a current queue in service, -+ * check whether to continue servicing it, or retrieve and set a new one. -+ */ -+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq, *new_bfqq = NULL; -+ struct request *next_rq; -+ enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; -+ -+ bfqq = bfqd->in_service_queue; -+ if (bfqq == NULL) -+ goto new_queue; -+ -+ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue"); -+ -+ /* -+ * If another queue has a request waiting within our mean seek -+ * distance, let it run. The expire code will check for close -+ * cooperators and put the close queue at the front of the -+ * service tree. If possible, merge the expiring queue with the -+ * new bfqq. -+ */ -+ new_bfqq = bfq_close_cooperator(bfqd, bfqq); -+ if (new_bfqq != NULL && bfqq->new_bfqq == NULL) -+ bfq_setup_merge(bfqq, new_bfqq); -+ -+ if (bfq_may_expire_for_budg_timeout(bfqq) && -+ !timer_pending(&bfqd->idle_slice_timer) && -+ !bfq_bfqq_must_idle(bfqq)) -+ goto expire; -+ -+ next_rq = bfqq->next_rq; -+ /* -+ * If bfqq has requests queued and it has enough budget left to -+ * serve them, keep the queue, otherwise expire it. -+ */ -+ if (next_rq != NULL) { -+ if (bfq_serv_to_charge(next_rq, bfqq) > -+ bfq_bfqq_budget_left(bfqq)) { -+ reason = BFQ_BFQQ_BUDGET_EXHAUSTED; -+ goto expire; -+ } else { -+ /* -+ * The idle timer may be pending because we may -+ * not disable disk idling even when a new request -+ * arrives. -+ */ -+ if (timer_pending(&bfqd->idle_slice_timer)) { -+ /* -+ * If we get here: 1) at least a new request -+ * has arrived but we have not disabled the -+ * timer because the request was too small, -+ * 2) then the block layer has unplugged -+ * the device, causing the dispatch to be -+ * invoked. -+ * -+ * Since the device is unplugged, now the -+ * requests are probably large enough to -+ * provide a reasonable throughput. -+ * So we disable idling. -+ */ -+ bfq_clear_bfqq_wait_request(bfqq); -+ del_timer(&bfqd->idle_slice_timer); -+ } -+ if (new_bfqq == NULL) -+ goto keep_queue; -+ else -+ goto expire; -+ } -+ } -+ -+ /* -+ * No requests pending. If the in-service queue still has requests -+ * in flight (possibly waiting for a completion) or is idling for a -+ * new request, then keep it. -+ */ -+ if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) || -+ (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) { -+ bfqq = NULL; -+ goto keep_queue; -+ } else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) { -+ /* -+ * Expiring the queue because there is a close cooperator, -+ * cancel timer. -+ */ -+ bfq_clear_bfqq_wait_request(bfqq); -+ del_timer(&bfqd->idle_slice_timer); -+ } -+ -+ reason = BFQ_BFQQ_NO_MORE_REQUESTS; -+expire: -+ bfq_bfqq_expire(bfqd, bfqq, 0, reason); -+new_queue: -+ bfqq = bfq_set_in_service_queue(bfqd, new_bfqq); -+ bfq_log(bfqd, "select_queue: new queue %d returned", -+ bfqq != NULL ? bfqq->pid : 0); -+keep_queue: -+ return bfqq; -+} -+ -+static void bfq_update_wr_data(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ if (bfqq->wr_coeff > 1) { /* queue is being boosted */ -+ struct bfq_entity *entity = &bfqq->entity; -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "raising period dur %u/%u msec, old coeff %u, w %d(%d)", -+ jiffies_to_msecs(jiffies - -+ bfqq->last_wr_start_finish), -+ jiffies_to_msecs(bfqq->wr_cur_max_time), -+ bfqq->wr_coeff, -+ bfqq->entity.weight, bfqq->entity.orig_weight); -+ -+ BUG_ON(bfqq != bfqd->in_service_queue && entity->weight != -+ entity->orig_weight * bfqq->wr_coeff); -+ if (entity->ioprio_changed) -+ bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); -+ /* -+ * If the queue was activated in a burst, or -+ * too much time has elapsed from the beginning -+ * of this weight-raising, then end weight raising. -+ */ -+ if (bfq_bfqq_in_large_burst(bfqq) || -+ time_is_before_jiffies(bfqq->last_wr_start_finish + -+ bfqq->wr_cur_max_time)) { -+ bfqq->last_wr_start_finish = jiffies; -+ bfq_log_bfqq(bfqd, bfqq, -+ "wrais ending at %lu, rais_max_time %u", -+ bfqq->last_wr_start_finish, -+ jiffies_to_msecs(bfqq->wr_cur_max_time)); -+ bfq_bfqq_end_wr(bfqq); -+ __bfq_entity_update_weight_prio( -+ bfq_entity_service_tree(entity), -+ entity); -+ } -+ } -+} -+ -+/* -+ * Dispatch one request from bfqq, moving it to the request queue -+ * dispatch list. -+ */ -+static int bfq_dispatch_request(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ int dispatched = 0; -+ struct request *rq; -+ unsigned long service_to_charge; -+ -+ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); -+ -+ /* Follow expired path, else get first next available. */ -+ rq = bfq_check_fifo(bfqq); -+ if (rq == NULL) -+ rq = bfqq->next_rq; -+ service_to_charge = bfq_serv_to_charge(rq, bfqq); -+ -+ if (service_to_charge > bfq_bfqq_budget_left(bfqq)) { -+ /* -+ * This may happen if the next rq is chosen in fifo order -+ * instead of sector order. The budget is properly -+ * dimensioned to be always sufficient to serve the next -+ * request only if it is chosen in sector order. The reason -+ * is that it would be quite inefficient and little useful -+ * to always make sure that the budget is large enough to -+ * serve even the possible next rq in fifo order. -+ * In fact, requests are seldom served in fifo order. -+ * -+ * Expire the queue for budget exhaustion, and make sure -+ * that the next act_budget is enough to serve the next -+ * request, even if it comes from the fifo expired path. -+ */ -+ bfqq->next_rq = rq; -+ /* -+ * Since this dispatch is failed, make sure that -+ * a new one will be performed -+ */ -+ if (!bfqd->rq_in_driver) -+ bfq_schedule_dispatch(bfqd); -+ goto expire; -+ } -+ -+ /* Finally, insert request into driver dispatch list. */ -+ bfq_bfqq_served(bfqq, service_to_charge); -+ bfq_dispatch_insert(bfqd->queue, rq); -+ -+ bfq_update_wr_data(bfqd, bfqq); -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "dispatched %u sec req (%llu), budg left %lu", -+ blk_rq_sectors(rq), -+ (long long unsigned)blk_rq_pos(rq), -+ bfq_bfqq_budget_left(bfqq)); -+ -+ dispatched++; -+ -+ if (bfqd->in_service_bic == NULL) { -+ atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount); -+ bfqd->in_service_bic = RQ_BIC(rq); -+ } -+ -+ if (bfqd->busy_queues > 1 && ((!bfq_bfqq_sync(bfqq) && -+ dispatched >= bfqd->bfq_max_budget_async_rq) || -+ bfq_class_idle(bfqq))) -+ goto expire; -+ -+ return dispatched; -+ -+expire: -+ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_EXHAUSTED); -+ return dispatched; -+} -+ -+static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq) -+{ -+ int dispatched = 0; -+ -+ while (bfqq->next_rq != NULL) { -+ bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq); -+ dispatched++; -+ } -+ -+ BUG_ON(!list_empty(&bfqq->fifo)); -+ return dispatched; -+} -+ -+/* -+ * Drain our current requests. -+ * Used for barriers and when switching io schedulers on-the-fly. -+ */ -+static int bfq_forced_dispatch(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq, *n; -+ struct bfq_service_tree *st; -+ int dispatched = 0; -+ -+ bfqq = bfqd->in_service_queue; -+ if (bfqq != NULL) -+ __bfq_bfqq_expire(bfqd, bfqq); -+ -+ /* -+ * Loop through classes, and be careful to leave the scheduler -+ * in a consistent state, as feedback mechanisms and vtime -+ * updates cannot be disabled during the process. -+ */ -+ list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) { -+ st = bfq_entity_service_tree(&bfqq->entity); -+ -+ dispatched += __bfq_forced_dispatch_bfqq(bfqq); -+ bfqq->max_budget = bfq_max_budget(bfqd); -+ -+ bfq_forget_idle(st); -+ } -+ -+ BUG_ON(bfqd->busy_queues != 0); -+ -+ return dispatched; -+} -+ -+static int bfq_dispatch_requests(struct request_queue *q, int force) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_queue *bfqq; -+ int max_dispatch; -+ -+ bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues); -+ if (bfqd->busy_queues == 0) -+ return 0; -+ -+ if (unlikely(force)) -+ return bfq_forced_dispatch(bfqd); -+ -+ bfqq = bfq_select_queue(bfqd); -+ if (bfqq == NULL) -+ return 0; -+ -+ max_dispatch = bfqd->bfq_quantum; -+ if (bfq_class_idle(bfqq)) -+ max_dispatch = 1; -+ -+ if (!bfq_bfqq_sync(bfqq)) -+ max_dispatch = bfqd->bfq_max_budget_async_rq; -+ -+ if (bfqq->dispatched >= max_dispatch) { -+ if (bfqd->busy_queues > 1) -+ return 0; -+ if (bfqq->dispatched >= 4 * max_dispatch) -+ return 0; -+ } -+ -+ if (bfqd->sync_flight != 0 && !bfq_bfqq_sync(bfqq)) -+ return 0; -+ -+ bfq_clear_bfqq_wait_request(bfqq); -+ BUG_ON(timer_pending(&bfqd->idle_slice_timer)); -+ -+ if (!bfq_dispatch_request(bfqd, bfqq)) -+ return 0; -+ -+ bfq_log_bfqq(bfqd, bfqq, "dispatched one request of %d (max_disp %d)", -+ bfqq->pid, max_dispatch); -+ -+ return 1; -+} -+ -+/* -+ * Task holds one reference to the queue, dropped when task exits. Each rq -+ * in-flight on this queue also holds a reference, dropped when rq is freed. -+ * -+ * Queue lock must be held here. -+ */ -+static void bfq_put_queue(struct bfq_queue *bfqq) -+{ -+ struct bfq_data *bfqd = bfqq->bfqd; -+ -+ BUG_ON(atomic_read(&bfqq->ref) <= 0); -+ -+ bfq_log_bfqq(bfqd, bfqq, "put_queue: %p %d", bfqq, -+ atomic_read(&bfqq->ref)); -+ if (!atomic_dec_and_test(&bfqq->ref)) -+ return; -+ -+ BUG_ON(rb_first(&bfqq->sort_list) != NULL); -+ BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0); -+ BUG_ON(bfqq->entity.tree != NULL); -+ BUG_ON(bfq_bfqq_busy(bfqq)); -+ BUG_ON(bfqd->in_service_queue == bfqq); -+ -+ if (bfq_bfqq_sync(bfqq)) -+ /* -+ * The fact that this queue is being destroyed does not -+ * invalidate the fact that this queue may have been -+ * activated during the current burst. As a consequence, -+ * although the queue does not exist anymore, and hence -+ * needs to be removed from the burst list if there, -+ * the burst size has not to be decremented. -+ */ -+ hlist_del_init(&bfqq->burst_list_node); -+ -+ bfq_log_bfqq(bfqd, bfqq, "put_queue: %p freed", bfqq); -+ -+ kmem_cache_free(bfq_pool, bfqq); -+} -+ -+static void bfq_put_cooperator(struct bfq_queue *bfqq) -+{ -+ struct bfq_queue *__bfqq, *next; -+ -+ /* -+ * If this queue was scheduled to merge with another queue, be -+ * sure to drop the reference taken on that queue (and others in -+ * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs. -+ */ -+ __bfqq = bfqq->new_bfqq; -+ while (__bfqq) { -+ if (__bfqq == bfqq) -+ break; -+ next = __bfqq->new_bfqq; -+ bfq_put_queue(__bfqq); -+ __bfqq = next; -+ } -+} -+ -+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ if (bfqq == bfqd->in_service_queue) { -+ __bfq_bfqq_expire(bfqd, bfqq); -+ bfq_schedule_dispatch(bfqd); -+ } -+ -+ bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, -+ atomic_read(&bfqq->ref)); -+ -+ bfq_put_cooperator(bfqq); -+ -+ bfq_put_queue(bfqq); -+} -+ -+static inline void bfq_init_icq(struct io_cq *icq) -+{ -+ struct bfq_io_cq *bic = icq_to_bic(icq); -+ -+ bic->ttime.last_end_request = jiffies; -+} -+ -+static void bfq_exit_icq(struct io_cq *icq) -+{ -+ struct bfq_io_cq *bic = icq_to_bic(icq); -+ struct bfq_data *bfqd = bic_to_bfqd(bic); -+ -+ if (bic->bfqq[BLK_RW_ASYNC]) { -+ bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_ASYNC]); -+ bic->bfqq[BLK_RW_ASYNC] = NULL; -+ } -+ -+ if (bic->bfqq[BLK_RW_SYNC]) { -+ bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]); -+ bic->bfqq[BLK_RW_SYNC] = NULL; -+ } -+} -+ -+/* -+ * Update the entity prio values; note that the new values will not -+ * be used until the next (re)activation. -+ */ -+static void bfq_init_prio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) -+{ -+ struct task_struct *tsk = current; -+ int ioprio_class; -+ -+ if (!bfq_bfqq_prio_changed(bfqq)) -+ return; -+ -+ ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); -+ switch (ioprio_class) { -+ default: -+ dev_err(bfqq->bfqd->queue->backing_dev_info.dev, -+ "bfq: bad prio class %d\n", ioprio_class); -+ case IOPRIO_CLASS_NONE: -+ /* -+ * No prio set, inherit CPU scheduling settings. -+ */ -+ bfqq->entity.new_ioprio = task_nice_ioprio(tsk); -+ bfqq->entity.new_ioprio_class = task_nice_ioclass(tsk); -+ break; -+ case IOPRIO_CLASS_RT: -+ bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); -+ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_RT; -+ break; -+ case IOPRIO_CLASS_BE: -+ bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); -+ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_BE; -+ break; -+ case IOPRIO_CLASS_IDLE: -+ bfqq->entity.new_ioprio_class = IOPRIO_CLASS_IDLE; -+ bfqq->entity.new_ioprio = 7; -+ bfq_clear_bfqq_idle_window(bfqq); -+ break; -+ } -+ -+ if (bfqq->entity.new_ioprio < 0 || -+ bfqq->entity.new_ioprio >= IOPRIO_BE_NR) { -+ printk(KERN_CRIT "bfq_init_prio_data: new_ioprio %d\n", -+ bfqq->entity.new_ioprio); -+ BUG(); -+ } -+ -+ bfqq->entity.ioprio_changed = 1; -+ -+ bfq_clear_bfqq_prio_changed(bfqq); -+} -+ -+static void bfq_changed_ioprio(struct bfq_io_cq *bic) -+{ -+ struct bfq_data *bfqd; -+ struct bfq_queue *bfqq, *new_bfqq; -+ struct bfq_group *bfqg; -+ unsigned long uninitialized_var(flags); -+ int ioprio = bic->icq.ioc->ioprio; -+ -+ bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data), -+ &flags); -+ /* -+ * This condition may trigger on a newly created bic, be sure to -+ * drop the lock before returning. -+ */ -+ if (unlikely(bfqd == NULL) || likely(bic->ioprio == ioprio)) -+ goto out; -+ -+ bfqq = bic->bfqq[BLK_RW_ASYNC]; -+ if (bfqq != NULL) { -+ bfqg = container_of(bfqq->entity.sched_data, struct bfq_group, -+ sched_data); -+ new_bfqq = bfq_get_queue(bfqd, bfqg, BLK_RW_ASYNC, bic, -+ GFP_ATOMIC); -+ if (new_bfqq != NULL) { -+ bic->bfqq[BLK_RW_ASYNC] = new_bfqq; -+ bfq_log_bfqq(bfqd, bfqq, -+ "changed_ioprio: bfqq %p %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ bfq_put_queue(bfqq); -+ } -+ } -+ -+ bfqq = bic->bfqq[BLK_RW_SYNC]; -+ if (bfqq != NULL) -+ bfq_mark_bfqq_prio_changed(bfqq); -+ -+ bic->ioprio = ioprio; -+ -+out: -+ bfq_put_bfqd_unlock(bfqd, &flags); -+} -+ -+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ pid_t pid, int is_sync) -+{ -+ RB_CLEAR_NODE(&bfqq->entity.rb_node); -+ INIT_LIST_HEAD(&bfqq->fifo); -+ INIT_HLIST_NODE(&bfqq->burst_list_node); -+ -+ atomic_set(&bfqq->ref, 0); -+ bfqq->bfqd = bfqd; -+ -+ bfq_mark_bfqq_prio_changed(bfqq); -+ -+ if (is_sync) { -+ if (!bfq_class_idle(bfqq)) -+ bfq_mark_bfqq_idle_window(bfqq); -+ bfq_mark_bfqq_sync(bfqq); -+ } -+ bfq_mark_bfqq_IO_bound(bfqq); -+ -+ /* Tentative initial value to trade off between thr and lat */ -+ bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3; -+ bfqq->pid = pid; -+ -+ bfqq->wr_coeff = 1; -+ bfqq->last_wr_start_finish = 0; -+ /* -+ * Set to the value for which bfqq will not be deemed as -+ * soft rt when it becomes backlogged. -+ */ -+ bfqq->soft_rt_next_start = bfq_infinity_from_now(jiffies); -+} -+ -+static struct bfq_queue *bfq_find_alloc_queue(struct bfq_data *bfqd, -+ struct bfq_group *bfqg, -+ int is_sync, -+ struct bfq_io_cq *bic, -+ gfp_t gfp_mask) -+{ -+ struct bfq_queue *bfqq, *new_bfqq = NULL; -+ -+retry: -+ /* bic always exists here */ -+ bfqq = bic_to_bfqq(bic, is_sync); -+ -+ /* -+ * Always try a new alloc if we fall back to the OOM bfqq -+ * originally, since it should just be a temporary situation. -+ */ -+ if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) { -+ bfqq = NULL; -+ if (new_bfqq != NULL) { -+ bfqq = new_bfqq; -+ new_bfqq = NULL; -+ } else if (gfp_mask & __GFP_WAIT) { -+ spin_unlock_irq(bfqd->queue->queue_lock); -+ new_bfqq = kmem_cache_alloc_node(bfq_pool, -+ gfp_mask | __GFP_ZERO, -+ bfqd->queue->node); -+ spin_lock_irq(bfqd->queue->queue_lock); -+ if (new_bfqq != NULL) -+ goto retry; -+ } else { -+ bfqq = kmem_cache_alloc_node(bfq_pool, -+ gfp_mask | __GFP_ZERO, -+ bfqd->queue->node); -+ } -+ -+ if (bfqq != NULL) { -+ bfq_init_bfqq(bfqd, bfqq, current->pid, is_sync); -+ bfq_init_prio_data(bfqq, bic); -+ bfq_init_entity(&bfqq->entity, bfqg); -+ bfq_log_bfqq(bfqd, bfqq, "allocated"); -+ } else { -+ bfqq = &bfqd->oom_bfqq; -+ bfq_log_bfqq(bfqd, bfqq, "using oom bfqq"); -+ } -+ } -+ -+ if (new_bfqq != NULL) -+ kmem_cache_free(bfq_pool, new_bfqq); -+ -+ return bfqq; -+} -+ -+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, -+ struct bfq_group *bfqg, -+ int ioprio_class, int ioprio) -+{ -+ switch (ioprio_class) { -+ case IOPRIO_CLASS_RT: -+ return &bfqg->async_bfqq[0][ioprio]; -+ case IOPRIO_CLASS_NONE: -+ ioprio = IOPRIO_NORM; -+ /* fall through */ -+ case IOPRIO_CLASS_BE: -+ return &bfqg->async_bfqq[1][ioprio]; -+ case IOPRIO_CLASS_IDLE: -+ return &bfqg->async_idle_bfqq; -+ default: -+ BUG(); -+ } -+} -+ -+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, -+ struct bfq_group *bfqg, int is_sync, -+ struct bfq_io_cq *bic, gfp_t gfp_mask) -+{ -+ const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); -+ const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); -+ struct bfq_queue **async_bfqq = NULL; -+ struct bfq_queue *bfqq = NULL; -+ -+ if (!is_sync) { -+ async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, -+ ioprio); -+ bfqq = *async_bfqq; -+ } -+ -+ if (bfqq == NULL) -+ bfqq = bfq_find_alloc_queue(bfqd, bfqg, is_sync, bic, gfp_mask); -+ -+ /* -+ * Pin the queue now that it's allocated, scheduler exit will -+ * prune it. -+ */ -+ if (!is_sync && *async_bfqq == NULL) { -+ atomic_inc(&bfqq->ref); -+ bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ *async_bfqq = bfqq; -+ } -+ -+ atomic_inc(&bfqq->ref); -+ bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, -+ atomic_read(&bfqq->ref)); -+ return bfqq; -+} -+ -+static void bfq_update_io_thinktime(struct bfq_data *bfqd, -+ struct bfq_io_cq *bic) -+{ -+ unsigned long elapsed = jiffies - bic->ttime.last_end_request; -+ unsigned long ttime = min(elapsed, 2UL * bfqd->bfq_slice_idle); -+ -+ bic->ttime.ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8; -+ bic->ttime.ttime_total = (7*bic->ttime.ttime_total + 256*ttime) / 8; -+ bic->ttime.ttime_mean = (bic->ttime.ttime_total + 128) / -+ bic->ttime.ttime_samples; -+} -+ -+static void bfq_update_io_seektime(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ struct request *rq) -+{ -+ sector_t sdist; -+ u64 total; -+ -+ if (bfqq->last_request_pos < blk_rq_pos(rq)) -+ sdist = blk_rq_pos(rq) - bfqq->last_request_pos; -+ else -+ sdist = bfqq->last_request_pos - blk_rq_pos(rq); -+ -+ /* -+ * Don't allow the seek distance to get too large from the -+ * odd fragment, pagein, etc. -+ */ -+ if (bfqq->seek_samples == 0) /* first request, not really a seek */ -+ sdist = 0; -+ else if (bfqq->seek_samples <= 60) /* second & third seek */ -+ sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*1024); -+ else -+ sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*64); -+ -+ bfqq->seek_samples = (7*bfqq->seek_samples + 256) / 8; -+ bfqq->seek_total = (7*bfqq->seek_total + (u64)256*sdist) / 8; -+ total = bfqq->seek_total + (bfqq->seek_samples/2); -+ do_div(total, bfqq->seek_samples); -+ bfqq->seek_mean = (sector_t)total; -+ -+ bfq_log_bfqq(bfqd, bfqq, "dist=%llu mean=%llu", (u64)sdist, -+ (u64)bfqq->seek_mean); -+} -+ -+/* -+ * Disable idle window if the process thinks too long or seeks so much that -+ * it doesn't matter. -+ */ -+static void bfq_update_idle_window(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq, -+ struct bfq_io_cq *bic) -+{ -+ int enable_idle; -+ -+ /* Don't idle for async or idle io prio class. */ -+ if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq)) -+ return; -+ -+ enable_idle = bfq_bfqq_idle_window(bfqq); -+ -+ if (atomic_read(&bic->icq.ioc->active_ref) == 0 || -+ bfqd->bfq_slice_idle == 0 || -+ (bfqd->hw_tag && BFQQ_SEEKY(bfqq) && -+ bfqq->wr_coeff == 1)) -+ enable_idle = 0; -+ else if (bfq_sample_valid(bic->ttime.ttime_samples)) { -+ if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle && -+ bfqq->wr_coeff == 1) -+ enable_idle = 0; -+ else -+ enable_idle = 1; -+ } -+ bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d", -+ enable_idle); -+ -+ if (enable_idle) -+ bfq_mark_bfqq_idle_window(bfqq); -+ else -+ bfq_clear_bfqq_idle_window(bfqq); -+} -+ -+/* -+ * Called when a new fs request (rq) is added to bfqq. Check if there's -+ * something we should do about it. -+ */ -+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ struct request *rq) -+{ -+ struct bfq_io_cq *bic = RQ_BIC(rq); -+ -+ if (rq->cmd_flags & REQ_META) -+ bfqq->meta_pending++; -+ -+ bfq_update_io_thinktime(bfqd, bic); -+ bfq_update_io_seektime(bfqd, bfqq, rq); -+ if (!BFQQ_SEEKY(bfqq) && bfq_bfqq_constantly_seeky(bfqq)) { -+ bfq_clear_bfqq_constantly_seeky(bfqq); -+ if (!blk_queue_nonrot(bfqd->queue)) { -+ BUG_ON(!bfqd->const_seeky_busy_in_flight_queues); -+ bfqd->const_seeky_busy_in_flight_queues--; -+ } -+ } -+ if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 || -+ !BFQQ_SEEKY(bfqq)) -+ bfq_update_idle_window(bfqd, bfqq, bic); -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "rq_enqueued: idle_window=%d (seeky %d, mean %llu)", -+ bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq), -+ (long long unsigned)bfqq->seek_mean); -+ -+ bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); -+ -+ if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) { -+ int small_req = bfqq->queued[rq_is_sync(rq)] == 1 && -+ blk_rq_sectors(rq) < 32; -+ int budget_timeout = bfq_bfqq_budget_timeout(bfqq); -+ -+ /* -+ * There is just this request queued: if the request -+ * is small and the queue is not to be expired, then -+ * just exit. -+ * -+ * In this way, if the disk is being idled to wait for -+ * a new request from the in-service queue, we avoid -+ * unplugging the device and committing the disk to serve -+ * just a small request. On the contrary, we wait for -+ * the block layer to decide when to unplug the device: -+ * hopefully, new requests will be merged to this one -+ * quickly, then the device will be unplugged and -+ * larger requests will be dispatched. -+ */ -+ if (small_req && !budget_timeout) -+ return; -+ -+ /* -+ * A large enough request arrived, or the queue is to -+ * be expired: in both cases disk idling is to be -+ * stopped, so clear wait_request flag and reset -+ * timer. -+ */ -+ bfq_clear_bfqq_wait_request(bfqq); -+ del_timer(&bfqd->idle_slice_timer); -+ -+ /* -+ * The queue is not empty, because a new request just -+ * arrived. Hence we can safely expire the queue, in -+ * case of budget timeout, without risking that the -+ * timestamps of the queue are not updated correctly. -+ * See [1] for more details. -+ */ -+ if (budget_timeout) -+ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT); -+ -+ /* -+ * Let the request rip immediately, or let a new queue be -+ * selected if bfqq has just been expired. -+ */ -+ __blk_run_queue(bfqd->queue); -+ } -+} -+ -+static void bfq_insert_request(struct request_queue *q, struct request *rq) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ -+ assert_spin_locked(bfqd->queue->queue_lock); -+ bfq_init_prio_data(bfqq, RQ_BIC(rq)); -+ -+ bfq_add_request(rq); -+ -+ rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]; -+ list_add_tail(&rq->queuelist, &bfqq->fifo); -+ -+ bfq_rq_enqueued(bfqd, bfqq, rq); -+} -+ -+static void bfq_update_hw_tag(struct bfq_data *bfqd) -+{ -+ bfqd->max_rq_in_driver = max(bfqd->max_rq_in_driver, -+ bfqd->rq_in_driver); -+ -+ if (bfqd->hw_tag == 1) -+ return; -+ -+ /* -+ * This sample is valid if the number of outstanding requests -+ * is large enough to allow a queueing behavior. Note that the -+ * sum is not exact, as it's not taking into account deactivated -+ * requests. -+ */ -+ if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD) -+ return; -+ -+ if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) -+ return; -+ -+ bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD; -+ bfqd->max_rq_in_driver = 0; -+ bfqd->hw_tag_samples = 0; -+} -+ -+static void bfq_completed_request(struct request_queue *q, struct request *rq) -+{ -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ struct bfq_data *bfqd = bfqq->bfqd; -+ bool sync = bfq_bfqq_sync(bfqq); -+ -+ bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left (%d)", -+ blk_rq_sectors(rq), sync); -+ -+ bfq_update_hw_tag(bfqd); -+ -+ BUG_ON(!bfqd->rq_in_driver); -+ BUG_ON(!bfqq->dispatched); -+ bfqd->rq_in_driver--; -+ bfqq->dispatched--; -+ -+ if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { -+ bfq_weights_tree_remove(bfqd, &bfqq->entity, -+ &bfqd->queue_weights_tree); -+ if (!blk_queue_nonrot(bfqd->queue)) { -+ BUG_ON(!bfqd->busy_in_flight_queues); -+ bfqd->busy_in_flight_queues--; -+ if (bfq_bfqq_constantly_seeky(bfqq)) { -+ BUG_ON(!bfqd-> -+ const_seeky_busy_in_flight_queues); -+ bfqd->const_seeky_busy_in_flight_queues--; -+ } -+ } -+ } -+ -+ if (sync) { -+ bfqd->sync_flight--; -+ RQ_BIC(rq)->ttime.last_end_request = jiffies; -+ } -+ -+ /* -+ * If we are waiting to discover whether the request pattern of the -+ * task associated with the queue is actually isochronous, and -+ * both requisites for this condition to hold are satisfied, then -+ * compute soft_rt_next_start (see the comments to the function -+ * bfq_bfqq_softrt_next_start()). -+ */ -+ if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 && -+ RB_EMPTY_ROOT(&bfqq->sort_list)) -+ bfqq->soft_rt_next_start = -+ bfq_bfqq_softrt_next_start(bfqd, bfqq); -+ -+ /* -+ * If this is the in-service queue, check if it needs to be expired, -+ * or if we want to idle in case it has no pending requests. -+ */ -+ if (bfqd->in_service_queue == bfqq) { -+ if (bfq_bfqq_budget_new(bfqq)) -+ bfq_set_budget_timeout(bfqd); -+ -+ if (bfq_bfqq_must_idle(bfqq)) { -+ bfq_arm_slice_timer(bfqd); -+ goto out; -+ } else if (bfq_may_expire_for_budg_timeout(bfqq)) -+ bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT); -+ else if (RB_EMPTY_ROOT(&bfqq->sort_list) && -+ (bfqq->dispatched == 0 || -+ !bfq_bfqq_must_not_expire(bfqq))) -+ bfq_bfqq_expire(bfqd, bfqq, 0, -+ BFQ_BFQQ_NO_MORE_REQUESTS); -+ } -+ -+ if (!bfqd->rq_in_driver) -+ bfq_schedule_dispatch(bfqd); -+ -+out: -+ return; -+} -+ -+static inline int __bfq_may_queue(struct bfq_queue *bfqq) -+{ -+ if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) { -+ bfq_clear_bfqq_must_alloc(bfqq); -+ return ELV_MQUEUE_MUST; -+ } -+ -+ return ELV_MQUEUE_MAY; -+} -+ -+static int bfq_may_queue(struct request_queue *q, int rw) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct task_struct *tsk = current; -+ struct bfq_io_cq *bic; -+ struct bfq_queue *bfqq; -+ -+ /* -+ * Don't force setup of a queue from here, as a call to may_queue -+ * does not necessarily imply that a request actually will be -+ * queued. So just lookup a possibly existing queue, or return -+ * 'may queue' if that fails. -+ */ -+ bic = bfq_bic_lookup(bfqd, tsk->io_context); -+ if (bic == NULL) -+ return ELV_MQUEUE_MAY; -+ -+ bfqq = bic_to_bfqq(bic, rw_is_sync(rw)); -+ if (bfqq != NULL) { -+ bfq_init_prio_data(bfqq, bic); -+ -+ return __bfq_may_queue(bfqq); -+ } -+ -+ return ELV_MQUEUE_MAY; -+} -+ -+/* -+ * Queue lock held here. -+ */ -+static void bfq_put_request(struct request *rq) -+{ -+ struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ -+ if (bfqq != NULL) { -+ const int rw = rq_data_dir(rq); -+ -+ BUG_ON(!bfqq->allocated[rw]); -+ bfqq->allocated[rw]--; -+ -+ rq->elv.priv[0] = NULL; -+ rq->elv.priv[1] = NULL; -+ -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ bfq_put_queue(bfqq); -+ } -+} -+ -+static struct bfq_queue * -+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, -+ struct bfq_queue *bfqq) -+{ -+ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", -+ (long unsigned)bfqq->new_bfqq->pid); -+ bic_set_bfqq(bic, bfqq->new_bfqq, 1); -+ bfq_mark_bfqq_coop(bfqq->new_bfqq); -+ bfq_put_queue(bfqq); -+ return bic_to_bfqq(bic, 1); -+} -+ -+/* -+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this -+ * was the last process referring to said bfqq. -+ */ -+static struct bfq_queue * -+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) -+{ -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); -+ if (bfqq_process_refs(bfqq) == 1) { -+ bfqq->pid = current->pid; -+ bfq_clear_bfqq_coop(bfqq); -+ bfq_clear_bfqq_split_coop(bfqq); -+ return bfqq; -+ } -+ -+ bic_set_bfqq(bic, NULL, 1); -+ -+ bfq_put_cooperator(bfqq); -+ -+ bfq_put_queue(bfqq); -+ return NULL; -+} -+ -+/* -+ * Allocate bfq data structures associated with this request. -+ */ -+static int bfq_set_request(struct request_queue *q, struct request *rq, -+ struct bio *bio, gfp_t gfp_mask) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq); -+ const int rw = rq_data_dir(rq); -+ const int is_sync = rq_is_sync(rq); -+ struct bfq_queue *bfqq; -+ struct bfq_group *bfqg; -+ unsigned long flags; -+ -+ might_sleep_if(gfp_mask & __GFP_WAIT); -+ -+ bfq_changed_ioprio(bic); -+ -+ spin_lock_irqsave(q->queue_lock, flags); -+ -+ if (bic == NULL) -+ goto queue_fail; -+ -+ bfqg = bfq_bic_update_cgroup(bic); -+ -+new_queue: -+ bfqq = bic_to_bfqq(bic, is_sync); -+ if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) { -+ bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask); -+ bic_set_bfqq(bic, bfqq, is_sync); -+ } else { -+ /* -+ * If the queue was seeky for too long, break it apart. -+ */ -+ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) { -+ bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq"); -+ bfqq = bfq_split_bfqq(bic, bfqq); -+ if (!bfqq) -+ goto new_queue; -+ } -+ -+ /* -+ * Check to see if this queue is scheduled to merge with -+ * another closely cooperating queue. The merging of queues -+ * happens here as it must be done in process context. -+ * The reference on new_bfqq was taken in merge_bfqqs. -+ */ -+ if (bfqq->new_bfqq != NULL) -+ bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq); -+ } -+ -+ bfqq->allocated[rw]++; -+ atomic_inc(&bfqq->ref); -+ bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq, -+ atomic_read(&bfqq->ref)); -+ -+ rq->elv.priv[0] = bic; -+ rq->elv.priv[1] = bfqq; -+ -+ spin_unlock_irqrestore(q->queue_lock, flags); -+ -+ return 0; -+ -+queue_fail: -+ bfq_schedule_dispatch(bfqd); -+ spin_unlock_irqrestore(q->queue_lock, flags); -+ -+ return 1; -+} -+ -+static void bfq_kick_queue(struct work_struct *work) -+{ -+ struct bfq_data *bfqd = -+ container_of(work, struct bfq_data, unplug_work); -+ struct request_queue *q = bfqd->queue; -+ -+ spin_lock_irq(q->queue_lock); -+ __blk_run_queue(q); -+ spin_unlock_irq(q->queue_lock); -+} -+ -+/* -+ * Handler of the expiration of the timer running if the in-service queue -+ * is idling inside its time slice. -+ */ -+static void bfq_idle_slice_timer(unsigned long data) -+{ -+ struct bfq_data *bfqd = (struct bfq_data *)data; -+ struct bfq_queue *bfqq; -+ unsigned long flags; -+ enum bfqq_expiration reason; -+ -+ spin_lock_irqsave(bfqd->queue->queue_lock, flags); -+ -+ bfqq = bfqd->in_service_queue; -+ /* -+ * Theoretical race here: the in-service queue can be NULL or -+ * different from the queue that was idling if the timer handler -+ * spins on the queue_lock and a new request arrives for the -+ * current queue and there is a full dispatch cycle that changes -+ * the in-service queue. This can hardly happen, but in the worst -+ * case we just expire a queue too early. -+ */ -+ if (bfqq != NULL) { -+ bfq_log_bfqq(bfqd, bfqq, "slice_timer expired"); -+ if (bfq_bfqq_budget_timeout(bfqq)) -+ /* -+ * Also here the queue can be safely expired -+ * for budget timeout without wasting -+ * guarantees -+ */ -+ reason = BFQ_BFQQ_BUDGET_TIMEOUT; -+ else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0) -+ /* -+ * The queue may not be empty upon timer expiration, -+ * because we may not disable the timer when the -+ * first request of the in-service queue arrives -+ * during disk idling. -+ */ -+ reason = BFQ_BFQQ_TOO_IDLE; -+ else -+ goto schedule_dispatch; -+ -+ bfq_bfqq_expire(bfqd, bfqq, 1, reason); -+ } -+ -+schedule_dispatch: -+ bfq_schedule_dispatch(bfqd); -+ -+ spin_unlock_irqrestore(bfqd->queue->queue_lock, flags); -+} -+ -+static void bfq_shutdown_timer_wq(struct bfq_data *bfqd) -+{ -+ del_timer_sync(&bfqd->idle_slice_timer); -+ cancel_work_sync(&bfqd->unplug_work); -+} -+ -+static inline void __bfq_put_async_bfqq(struct bfq_data *bfqd, -+ struct bfq_queue **bfqq_ptr) -+{ -+ struct bfq_group *root_group = bfqd->root_group; -+ struct bfq_queue *bfqq = *bfqq_ptr; -+ -+ bfq_log(bfqd, "put_async_bfqq: %p", bfqq); -+ if (bfqq != NULL) { -+ bfq_bfqq_move(bfqd, bfqq, &bfqq->entity, root_group); -+ bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ bfq_put_queue(bfqq); -+ *bfqq_ptr = NULL; -+ } -+} -+ -+/* -+ * Release all the bfqg references to its async queues. If we are -+ * deallocating the group these queues may still contain requests, so -+ * we reparent them to the root cgroup (i.e., the only one that will -+ * exist for sure until all the requests on a device are gone). -+ */ -+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) -+{ -+ int i, j; -+ -+ for (i = 0; i < 2; i++) -+ for (j = 0; j < IOPRIO_BE_NR; j++) -+ __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); -+ -+ __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); -+} -+ -+static void bfq_exit_queue(struct elevator_queue *e) -+{ -+ struct bfq_data *bfqd = e->elevator_data; -+ struct request_queue *q = bfqd->queue; -+ struct bfq_queue *bfqq, *n; -+ -+ bfq_shutdown_timer_wq(bfqd); -+ -+ spin_lock_irq(q->queue_lock); -+ -+ BUG_ON(bfqd->in_service_queue != NULL); -+ list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) -+ bfq_deactivate_bfqq(bfqd, bfqq, 0); -+ -+ bfq_disconnect_groups(bfqd); -+ spin_unlock_irq(q->queue_lock); -+ -+ bfq_shutdown_timer_wq(bfqd); -+ -+ synchronize_rcu(); -+ -+ BUG_ON(timer_pending(&bfqd->idle_slice_timer)); -+ -+ bfq_free_root_group(bfqd); -+ kfree(bfqd); -+} -+ -+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) -+{ -+ struct bfq_group *bfqg; -+ struct bfq_data *bfqd; -+ struct elevator_queue *eq; -+ -+ eq = elevator_alloc(q, e); -+ if (eq == NULL) -+ return -ENOMEM; -+ -+ bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node); -+ if (bfqd == NULL) { -+ kobject_put(&eq->kobj); -+ return -ENOMEM; -+ } -+ eq->elevator_data = bfqd; -+ -+ /* -+ * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. -+ * Grab a permanent reference to it, so that the normal code flow -+ * will not attempt to free it. -+ */ -+ bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, 1, 0); -+ atomic_inc(&bfqd->oom_bfqq.ref); -+ bfqd->oom_bfqq.entity.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; -+ bfqd->oom_bfqq.entity.new_ioprio_class = IOPRIO_CLASS_BE; -+ /* -+ * Trigger weight initialization, according to ioprio, at the -+ * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio -+ * class won't be changed any more. -+ */ -+ bfqd->oom_bfqq.entity.ioprio_changed = 1; -+ -+ bfqd->queue = q; -+ -+ spin_lock_irq(q->queue_lock); -+ q->elevator = eq; -+ spin_unlock_irq(q->queue_lock); -+ -+ bfqg = bfq_alloc_root_group(bfqd, q->node); -+ if (bfqg == NULL) { -+ kfree(bfqd); -+ kobject_put(&eq->kobj); -+ return -ENOMEM; -+ } -+ -+ bfqd->root_group = bfqg; -+ bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); -+#ifdef CONFIG_CGROUP_BFQIO -+ bfqd->active_numerous_groups = 0; -+#endif -+ -+ init_timer(&bfqd->idle_slice_timer); -+ bfqd->idle_slice_timer.function = bfq_idle_slice_timer; -+ bfqd->idle_slice_timer.data = (unsigned long)bfqd; -+ -+ bfqd->rq_pos_tree = RB_ROOT; -+ bfqd->queue_weights_tree = RB_ROOT; -+ bfqd->group_weights_tree = RB_ROOT; -+ -+ INIT_WORK(&bfqd->unplug_work, bfq_kick_queue); -+ -+ INIT_LIST_HEAD(&bfqd->active_list); -+ INIT_LIST_HEAD(&bfqd->idle_list); -+ INIT_HLIST_HEAD(&bfqd->burst_list); -+ -+ bfqd->hw_tag = -1; -+ -+ bfqd->bfq_max_budget = bfq_default_max_budget; -+ -+ bfqd->bfq_quantum = bfq_quantum; -+ bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0]; -+ bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1]; -+ bfqd->bfq_back_max = bfq_back_max; -+ bfqd->bfq_back_penalty = bfq_back_penalty; -+ bfqd->bfq_slice_idle = bfq_slice_idle; -+ bfqd->bfq_class_idle_last_service = 0; -+ bfqd->bfq_max_budget_async_rq = bfq_max_budget_async_rq; -+ bfqd->bfq_timeout[BLK_RW_ASYNC] = bfq_timeout_async; -+ bfqd->bfq_timeout[BLK_RW_SYNC] = bfq_timeout_sync; -+ -+ bfqd->bfq_coop_thresh = 2; -+ bfqd->bfq_failed_cooperations = 7000; -+ bfqd->bfq_requests_within_timer = 120; -+ -+ bfqd->bfq_large_burst_thresh = 11; -+ bfqd->bfq_burst_interval = msecs_to_jiffies(500); -+ -+ bfqd->low_latency = true; -+ -+ bfqd->bfq_wr_coeff = 20; -+ bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300); -+ bfqd->bfq_wr_max_time = 0; -+ bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000); -+ bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500); -+ bfqd->bfq_wr_max_softrt_rate = 7000; /* -+ * Approximate rate required -+ * to playback or record a -+ * high-definition compressed -+ * video. -+ */ -+ bfqd->wr_busy_queues = 0; -+ bfqd->busy_in_flight_queues = 0; -+ bfqd->const_seeky_busy_in_flight_queues = 0; -+ -+ /* -+ * Begin by assuming, optimistically, that the device peak rate is -+ * equal to the highest reference rate. -+ */ -+ bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] * -+ T_fast[blk_queue_nonrot(bfqd->queue)]; -+ bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)]; -+ bfqd->device_speed = BFQ_BFQD_FAST; -+ -+ return 0; -+} -+ -+static void bfq_slab_kill(void) -+{ -+ if (bfq_pool != NULL) -+ kmem_cache_destroy(bfq_pool); -+} -+ -+static int __init bfq_slab_setup(void) -+{ -+ bfq_pool = KMEM_CACHE(bfq_queue, 0); -+ if (bfq_pool == NULL) -+ return -ENOMEM; -+ return 0; -+} -+ -+static ssize_t bfq_var_show(unsigned int var, char *page) -+{ -+ return sprintf(page, "%d\n", var); -+} -+ -+static ssize_t bfq_var_store(unsigned long *var, const char *page, -+ size_t count) -+{ -+ unsigned long new_val; -+ int ret = kstrtoul(page, 10, &new_val); -+ -+ if (ret == 0) -+ *var = new_val; -+ -+ return count; -+} -+ -+static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page) -+{ -+ struct bfq_data *bfqd = e->elevator_data; -+ return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ? -+ jiffies_to_msecs(bfqd->bfq_wr_max_time) : -+ jiffies_to_msecs(bfq_wr_duration(bfqd))); -+} -+ -+static ssize_t bfq_weights_show(struct elevator_queue *e, char *page) -+{ -+ struct bfq_queue *bfqq; -+ struct bfq_data *bfqd = e->elevator_data; -+ ssize_t num_char = 0; -+ -+ num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n", -+ bfqd->queued); -+ -+ spin_lock_irq(bfqd->queue->queue_lock); -+ -+ num_char += sprintf(page + num_char, "Active:\n"); -+ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) { -+ num_char += sprintf(page + num_char, -+ "pid%d: weight %hu, nr_queued %d %d, dur %d/%u\n", -+ bfqq->pid, -+ bfqq->entity.weight, -+ bfqq->queued[0], -+ bfqq->queued[1], -+ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), -+ jiffies_to_msecs(bfqq->wr_cur_max_time)); -+ } -+ -+ num_char += sprintf(page + num_char, "Idle:\n"); -+ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) { -+ num_char += sprintf(page + num_char, -+ "pid%d: weight %hu, dur %d/%u\n", -+ bfqq->pid, -+ bfqq->entity.weight, -+ jiffies_to_msecs(jiffies - -+ bfqq->last_wr_start_finish), -+ jiffies_to_msecs(bfqq->wr_cur_max_time)); -+ } -+ -+ spin_unlock_irq(bfqd->queue->queue_lock); -+ -+ return num_char; -+} -+ -+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -+static ssize_t __FUNC(struct elevator_queue *e, char *page) \ -+{ \ -+ struct bfq_data *bfqd = e->elevator_data; \ -+ unsigned int __data = __VAR; \ -+ if (__CONV) \ -+ __data = jiffies_to_msecs(__data); \ -+ return bfq_var_show(__data, (page)); \ -+} -+SHOW_FUNCTION(bfq_quantum_show, bfqd->bfq_quantum, 0); -+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 1); -+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 1); -+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0); -+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0); -+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 1); -+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0); -+SHOW_FUNCTION(bfq_max_budget_async_rq_show, -+ bfqd->bfq_max_budget_async_rq, 0); -+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout[BLK_RW_SYNC], 1); -+SHOW_FUNCTION(bfq_timeout_async_show, bfqd->bfq_timeout[BLK_RW_ASYNC], 1); -+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0); -+SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0); -+SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1); -+SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1); -+SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async, -+ 1); -+SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0); -+#undef SHOW_FUNCTION -+ -+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ -+static ssize_t \ -+__FUNC(struct elevator_queue *e, const char *page, size_t count) \ -+{ \ -+ struct bfq_data *bfqd = e->elevator_data; \ -+ unsigned long uninitialized_var(__data); \ -+ int ret = bfq_var_store(&__data, (page), count); \ -+ if (__data < (MIN)) \ -+ __data = (MIN); \ -+ else if (__data > (MAX)) \ -+ __data = (MAX); \ -+ if (__CONV) \ -+ *(__PTR) = msecs_to_jiffies(__data); \ -+ else \ -+ *(__PTR) = __data; \ -+ return ret; \ -+} -+STORE_FUNCTION(bfq_quantum_store, &bfqd->bfq_quantum, 1, INT_MAX, 0); -+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1, -+ INT_MAX, 1); -+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1, -+ INT_MAX, 1); -+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0); -+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1, -+ INT_MAX, 0); -+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 1); -+STORE_FUNCTION(bfq_max_budget_async_rq_store, &bfqd->bfq_max_budget_async_rq, -+ 1, INT_MAX, 0); -+STORE_FUNCTION(bfq_timeout_async_store, &bfqd->bfq_timeout[BLK_RW_ASYNC], 0, -+ INT_MAX, 1); -+STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0); -+STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1); -+STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX, -+ 1); -+STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0, -+ INT_MAX, 1); -+STORE_FUNCTION(bfq_wr_min_inter_arr_async_store, -+ &bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1); -+STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0, -+ INT_MAX, 0); -+#undef STORE_FUNCTION -+ -+/* do nothing for the moment */ -+static ssize_t bfq_weights_store(struct elevator_queue *e, -+ const char *page, size_t count) -+{ -+ return count; -+} -+ -+static inline unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd) -+{ -+ u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]); -+ -+ if (bfqd->peak_rate_samples >= BFQ_PEAK_RATE_SAMPLES) -+ return bfq_calc_max_budget(bfqd->peak_rate, timeout); -+ else -+ return bfq_default_max_budget; -+} -+ -+static ssize_t bfq_max_budget_store(struct elevator_queue *e, -+ const char *page, size_t count) -+{ -+ struct bfq_data *bfqd = e->elevator_data; -+ unsigned long uninitialized_var(__data); -+ int ret = bfq_var_store(&__data, (page), count); -+ -+ if (__data == 0) -+ bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd); -+ else { -+ if (__data > INT_MAX) -+ __data = INT_MAX; -+ bfqd->bfq_max_budget = __data; -+ } -+ -+ bfqd->bfq_user_max_budget = __data; -+ -+ return ret; -+} -+ -+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e, -+ const char *page, size_t count) -+{ -+ struct bfq_data *bfqd = e->elevator_data; -+ unsigned long uninitialized_var(__data); -+ int ret = bfq_var_store(&__data, (page), count); -+ -+ if (__data < 1) -+ __data = 1; -+ else if (__data > INT_MAX) -+ __data = INT_MAX; -+ -+ bfqd->bfq_timeout[BLK_RW_SYNC] = msecs_to_jiffies(__data); -+ if (bfqd->bfq_user_max_budget == 0) -+ bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd); -+ -+ return ret; -+} -+ -+static ssize_t bfq_low_latency_store(struct elevator_queue *e, -+ const char *page, size_t count) -+{ -+ struct bfq_data *bfqd = e->elevator_data; -+ unsigned long uninitialized_var(__data); -+ int ret = bfq_var_store(&__data, (page), count); -+ -+ if (__data > 1) -+ __data = 1; -+ if (__data == 0 && bfqd->low_latency != 0) -+ bfq_end_wr(bfqd); -+ bfqd->low_latency = __data; -+ -+ return ret; -+} -+ -+#define BFQ_ATTR(name) \ -+ __ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store) -+ -+static struct elv_fs_entry bfq_attrs[] = { -+ BFQ_ATTR(quantum), -+ BFQ_ATTR(fifo_expire_sync), -+ BFQ_ATTR(fifo_expire_async), -+ BFQ_ATTR(back_seek_max), -+ BFQ_ATTR(back_seek_penalty), -+ BFQ_ATTR(slice_idle), -+ BFQ_ATTR(max_budget), -+ BFQ_ATTR(max_budget_async_rq), -+ BFQ_ATTR(timeout_sync), -+ BFQ_ATTR(timeout_async), -+ BFQ_ATTR(low_latency), -+ BFQ_ATTR(wr_coeff), -+ BFQ_ATTR(wr_max_time), -+ BFQ_ATTR(wr_rt_max_time), -+ BFQ_ATTR(wr_min_idle_time), -+ BFQ_ATTR(wr_min_inter_arr_async), -+ BFQ_ATTR(wr_max_softrt_rate), -+ BFQ_ATTR(weights), -+ __ATTR_NULL -+}; -+ -+static struct elevator_type iosched_bfq = { -+ .ops = { -+ .elevator_merge_fn = bfq_merge, -+ .elevator_merged_fn = bfq_merged_request, -+ .elevator_merge_req_fn = bfq_merged_requests, -+ .elevator_allow_merge_fn = bfq_allow_merge, -+ .elevator_dispatch_fn = bfq_dispatch_requests, -+ .elevator_add_req_fn = bfq_insert_request, -+ .elevator_activate_req_fn = bfq_activate_request, -+ .elevator_deactivate_req_fn = bfq_deactivate_request, -+ .elevator_completed_req_fn = bfq_completed_request, -+ .elevator_former_req_fn = elv_rb_former_request, -+ .elevator_latter_req_fn = elv_rb_latter_request, -+ .elevator_init_icq_fn = bfq_init_icq, -+ .elevator_exit_icq_fn = bfq_exit_icq, -+ .elevator_set_req_fn = bfq_set_request, -+ .elevator_put_req_fn = bfq_put_request, -+ .elevator_may_queue_fn = bfq_may_queue, -+ .elevator_init_fn = bfq_init_queue, -+ .elevator_exit_fn = bfq_exit_queue, -+ }, -+ .icq_size = sizeof(struct bfq_io_cq), -+ .icq_align = __alignof__(struct bfq_io_cq), -+ .elevator_attrs = bfq_attrs, -+ .elevator_name = "bfq", -+ .elevator_owner = THIS_MODULE, -+}; -+ -+static int __init bfq_init(void) -+{ -+ /* -+ * Can be 0 on HZ < 1000 setups. -+ */ -+ if (bfq_slice_idle == 0) -+ bfq_slice_idle = 1; -+ -+ if (bfq_timeout_async == 0) -+ bfq_timeout_async = 1; -+ -+ if (bfq_slab_setup()) -+ return -ENOMEM; -+ -+ /* -+ * Times to load large popular applications for the typical systems -+ * installed on the reference devices (see the comments before the -+ * definitions of the two arrays). -+ */ -+ T_slow[0] = msecs_to_jiffies(2600); -+ T_slow[1] = msecs_to_jiffies(1000); -+ T_fast[0] = msecs_to_jiffies(5500); -+ T_fast[1] = msecs_to_jiffies(2000); -+ -+ /* -+ * Thresholds that determine the switch between speed classes (see -+ * the comments before the definition of the array). -+ */ -+ device_speed_thresh[0] = (R_fast[0] + R_slow[0]) / 2; -+ device_speed_thresh[1] = (R_fast[1] + R_slow[1]) / 2; -+ -+ elv_register(&iosched_bfq); -+ pr_info("BFQ I/O-scheduler version: v7r7"); -+ -+ return 0; -+} -+ -+static void __exit bfq_exit(void) -+{ -+ elv_unregister(&iosched_bfq); -+ bfq_slab_kill(); -+} -+ -+module_init(bfq_init); -+module_exit(bfq_exit); -+ -+MODULE_AUTHOR("Fabio Checconi, Paolo Valente"); -+MODULE_LICENSE("GPL"); -diff --git a/block/bfq-sched.c b/block/bfq-sched.c -new file mode 100644 -index 0000000..2931563 ---- /dev/null -+++ b/block/bfq-sched.c -@@ -0,0 +1,1214 @@ -+/* -+ * BFQ: Hierarchical B-WF2Q+ scheduler. -+ * -+ * Based on ideas and code from CFQ: -+ * Copyright (C) 2003 Jens Axboe -+ * -+ * Copyright (C) 2008 Fabio Checconi -+ * Paolo Valente -+ * -+ * Copyright (C) 2010 Paolo Valente -+ */ -+ -+#ifdef CONFIG_CGROUP_BFQIO -+#define for_each_entity(entity) \ -+ for (; entity != NULL; entity = entity->parent) -+ -+#define for_each_entity_safe(entity, parent) \ -+ for (; entity && ({ parent = entity->parent; 1; }); entity = parent) -+ -+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, -+ int extract, -+ struct bfq_data *bfqd); -+ -+static inline void bfq_update_budget(struct bfq_entity *next_in_service) -+{ -+ struct bfq_entity *bfqg_entity; -+ struct bfq_group *bfqg; -+ struct bfq_sched_data *group_sd; -+ -+ BUG_ON(next_in_service == NULL); -+ -+ group_sd = next_in_service->sched_data; -+ -+ bfqg = container_of(group_sd, struct bfq_group, sched_data); -+ /* -+ * bfq_group's my_entity field is not NULL only if the group -+ * is not the root group. We must not touch the root entity -+ * as it must never become an in-service entity. -+ */ -+ bfqg_entity = bfqg->my_entity; -+ if (bfqg_entity != NULL) -+ bfqg_entity->budget = next_in_service->budget; -+} -+ -+static int bfq_update_next_in_service(struct bfq_sched_data *sd) -+{ -+ struct bfq_entity *next_in_service; -+ -+ if (sd->in_service_entity != NULL) -+ /* will update/requeue at the end of service */ -+ return 0; -+ -+ /* -+ * NOTE: this can be improved in many ways, such as returning -+ * 1 (and thus propagating upwards the update) only when the -+ * budget changes, or caching the bfqq that will be scheduled -+ * next from this subtree. By now we worry more about -+ * correctness than about performance... -+ */ -+ next_in_service = bfq_lookup_next_entity(sd, 0, NULL); -+ sd->next_in_service = next_in_service; -+ -+ if (next_in_service != NULL) -+ bfq_update_budget(next_in_service); -+ -+ return 1; -+} -+ -+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd, -+ struct bfq_entity *entity) -+{ -+ BUG_ON(sd->next_in_service != entity); -+} -+#else -+#define for_each_entity(entity) \ -+ for (; entity != NULL; entity = NULL) -+ -+#define for_each_entity_safe(entity, parent) \ -+ for (parent = NULL; entity != NULL; entity = parent) -+ -+static inline int bfq_update_next_in_service(struct bfq_sched_data *sd) -+{ -+ return 0; -+} -+ -+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd, -+ struct bfq_entity *entity) -+{ -+} -+ -+static inline void bfq_update_budget(struct bfq_entity *next_in_service) -+{ -+} -+#endif -+ -+/* -+ * Shift for timestamp calculations. This actually limits the maximum -+ * service allowed in one timestamp delta (small shift values increase it), -+ * the maximum total weight that can be used for the queues in the system -+ * (big shift values increase it), and the period of virtual time -+ * wraparounds. -+ */ -+#define WFQ_SERVICE_SHIFT 22 -+ -+/** -+ * bfq_gt - compare two timestamps. -+ * @a: first ts. -+ * @b: second ts. -+ * -+ * Return @a > @b, dealing with wrapping correctly. -+ */ -+static inline int bfq_gt(u64 a, u64 b) -+{ -+ return (s64)(a - b) > 0; -+} -+ -+static inline struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = NULL; -+ -+ BUG_ON(entity == NULL); -+ -+ if (entity->my_sched_data == NULL) -+ bfqq = container_of(entity, struct bfq_queue, entity); -+ -+ return bfqq; -+} -+ -+ -+/** -+ * bfq_delta - map service into the virtual time domain. -+ * @service: amount of service. -+ * @weight: scale factor (weight of an entity or weight sum). -+ */ -+static inline u64 bfq_delta(unsigned long service, -+ unsigned long weight) -+{ -+ u64 d = (u64)service << WFQ_SERVICE_SHIFT; -+ -+ do_div(d, weight); -+ return d; -+} -+ -+/** -+ * bfq_calc_finish - assign the finish time to an entity. -+ * @entity: the entity to act upon. -+ * @service: the service to be charged to the entity. -+ */ -+static inline void bfq_calc_finish(struct bfq_entity *entity, -+ unsigned long service) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ -+ BUG_ON(entity->weight == 0); -+ -+ entity->finish = entity->start + -+ bfq_delta(service, entity->weight); -+ -+ if (bfqq != NULL) { -+ bfq_log_bfqq(bfqq->bfqd, bfqq, -+ "calc_finish: serv %lu, w %d", -+ service, entity->weight); -+ bfq_log_bfqq(bfqq->bfqd, bfqq, -+ "calc_finish: start %llu, finish %llu, delta %llu", -+ entity->start, entity->finish, -+ bfq_delta(service, entity->weight)); -+ } -+} -+ -+/** -+ * bfq_entity_of - get an entity from a node. -+ * @node: the node field of the entity. -+ * -+ * Convert a node pointer to the relative entity. This is used only -+ * to simplify the logic of some functions and not as the generic -+ * conversion mechanism because, e.g., in the tree walking functions, -+ * the check for a %NULL value would be redundant. -+ */ -+static inline struct bfq_entity *bfq_entity_of(struct rb_node *node) -+{ -+ struct bfq_entity *entity = NULL; -+ -+ if (node != NULL) -+ entity = rb_entry(node, struct bfq_entity, rb_node); -+ -+ return entity; -+} -+ -+/** -+ * bfq_extract - remove an entity from a tree. -+ * @root: the tree root. -+ * @entity: the entity to remove. -+ */ -+static inline void bfq_extract(struct rb_root *root, -+ struct bfq_entity *entity) -+{ -+ BUG_ON(entity->tree != root); -+ -+ entity->tree = NULL; -+ rb_erase(&entity->rb_node, root); -+} -+ -+/** -+ * bfq_idle_extract - extract an entity from the idle tree. -+ * @st: the service tree of the owning @entity. -+ * @entity: the entity being removed. -+ */ -+static void bfq_idle_extract(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ struct rb_node *next; -+ -+ BUG_ON(entity->tree != &st->idle); -+ -+ if (entity == st->first_idle) { -+ next = rb_next(&entity->rb_node); -+ st->first_idle = bfq_entity_of(next); -+ } -+ -+ if (entity == st->last_idle) { -+ next = rb_prev(&entity->rb_node); -+ st->last_idle = bfq_entity_of(next); -+ } -+ -+ bfq_extract(&st->idle, entity); -+ -+ if (bfqq != NULL) -+ list_del(&bfqq->bfqq_list); -+} -+ -+/** -+ * bfq_insert - generic tree insertion. -+ * @root: tree root. -+ * @entity: entity to insert. -+ * -+ * This is used for the idle and the active tree, since they are both -+ * ordered by finish time. -+ */ -+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity) -+{ -+ struct bfq_entity *entry; -+ struct rb_node **node = &root->rb_node; -+ struct rb_node *parent = NULL; -+ -+ BUG_ON(entity->tree != NULL); -+ -+ while (*node != NULL) { -+ parent = *node; -+ entry = rb_entry(parent, struct bfq_entity, rb_node); -+ -+ if (bfq_gt(entry->finish, entity->finish)) -+ node = &parent->rb_left; -+ else -+ node = &parent->rb_right; -+ } -+ -+ rb_link_node(&entity->rb_node, parent, node); -+ rb_insert_color(&entity->rb_node, root); -+ -+ entity->tree = root; -+} -+ -+/** -+ * bfq_update_min - update the min_start field of a entity. -+ * @entity: the entity to update. -+ * @node: one of its children. -+ * -+ * This function is called when @entity may store an invalid value for -+ * min_start due to updates to the active tree. The function assumes -+ * that the subtree rooted at @node (which may be its left or its right -+ * child) has a valid min_start value. -+ */ -+static inline void bfq_update_min(struct bfq_entity *entity, -+ struct rb_node *node) -+{ -+ struct bfq_entity *child; -+ -+ if (node != NULL) { -+ child = rb_entry(node, struct bfq_entity, rb_node); -+ if (bfq_gt(entity->min_start, child->min_start)) -+ entity->min_start = child->min_start; -+ } -+} -+ -+/** -+ * bfq_update_active_node - recalculate min_start. -+ * @node: the node to update. -+ * -+ * @node may have changed position or one of its children may have moved, -+ * this function updates its min_start value. The left and right subtrees -+ * are assumed to hold a correct min_start value. -+ */ -+static inline void bfq_update_active_node(struct rb_node *node) -+{ -+ struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node); -+ -+ entity->min_start = entity->start; -+ bfq_update_min(entity, node->rb_right); -+ bfq_update_min(entity, node->rb_left); -+} -+ -+/** -+ * bfq_update_active_tree - update min_start for the whole active tree. -+ * @node: the starting node. -+ * -+ * @node must be the deepest modified node after an update. This function -+ * updates its min_start using the values held by its children, assuming -+ * that they did not change, and then updates all the nodes that may have -+ * changed in the path to the root. The only nodes that may have changed -+ * are the ones in the path or their siblings. -+ */ -+static void bfq_update_active_tree(struct rb_node *node) -+{ -+ struct rb_node *parent; -+ -+up: -+ bfq_update_active_node(node); -+ -+ parent = rb_parent(node); -+ if (parent == NULL) -+ return; -+ -+ if (node == parent->rb_left && parent->rb_right != NULL) -+ bfq_update_active_node(parent->rb_right); -+ else if (parent->rb_left != NULL) -+ bfq_update_active_node(parent->rb_left); -+ -+ node = parent; -+ goto up; -+} -+ -+static void bfq_weights_tree_add(struct bfq_data *bfqd, -+ struct bfq_entity *entity, -+ struct rb_root *root); -+ -+static void bfq_weights_tree_remove(struct bfq_data *bfqd, -+ struct bfq_entity *entity, -+ struct rb_root *root); -+ -+ -+/** -+ * bfq_active_insert - insert an entity in the active tree of its -+ * group/device. -+ * @st: the service tree of the entity. -+ * @entity: the entity being inserted. -+ * -+ * The active tree is ordered by finish time, but an extra key is kept -+ * per each node, containing the minimum value for the start times of -+ * its children (and the node itself), so it's possible to search for -+ * the eligible node with the lowest finish time in logarithmic time. -+ */ -+static void bfq_active_insert(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ struct rb_node *node = &entity->rb_node; -+#ifdef CONFIG_CGROUP_BFQIO -+ struct bfq_sched_data *sd = NULL; -+ struct bfq_group *bfqg = NULL; -+ struct bfq_data *bfqd = NULL; -+#endif -+ -+ bfq_insert(&st->active, entity); -+ -+ if (node->rb_left != NULL) -+ node = node->rb_left; -+ else if (node->rb_right != NULL) -+ node = node->rb_right; -+ -+ bfq_update_active_tree(node); -+ -+#ifdef CONFIG_CGROUP_BFQIO -+ sd = entity->sched_data; -+ bfqg = container_of(sd, struct bfq_group, sched_data); -+ BUG_ON(!bfqg); -+ bfqd = (struct bfq_data *)bfqg->bfqd; -+#endif -+ if (bfqq != NULL) -+ list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); -+#ifdef CONFIG_CGROUP_BFQIO -+ else { /* bfq_group */ -+ BUG_ON(!bfqd); -+ bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree); -+ } -+ if (bfqg != bfqd->root_group) { -+ BUG_ON(!bfqg); -+ BUG_ON(!bfqd); -+ bfqg->active_entities++; -+ if (bfqg->active_entities == 2) -+ bfqd->active_numerous_groups++; -+ } -+#endif -+} -+ -+/** -+ * bfq_ioprio_to_weight - calc a weight from an ioprio. -+ * @ioprio: the ioprio value to convert. -+ */ -+static inline unsigned short bfq_ioprio_to_weight(int ioprio) -+{ -+ BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR); -+ return IOPRIO_BE_NR - ioprio; -+} -+ -+/** -+ * bfq_weight_to_ioprio - calc an ioprio from a weight. -+ * @weight: the weight value to convert. -+ * -+ * To preserve as mush as possible the old only-ioprio user interface, -+ * 0 is used as an escape ioprio value for weights (numerically) equal or -+ * larger than IOPRIO_BE_NR -+ */ -+static inline unsigned short bfq_weight_to_ioprio(int weight) -+{ -+ BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT); -+ return IOPRIO_BE_NR - weight < 0 ? 0 : IOPRIO_BE_NR - weight; -+} -+ -+static inline void bfq_get_entity(struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ -+ if (bfqq != NULL) { -+ atomic_inc(&bfqq->ref); -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ } -+} -+ -+/** -+ * bfq_find_deepest - find the deepest node that an extraction can modify. -+ * @node: the node being removed. -+ * -+ * Do the first step of an extraction in an rb tree, looking for the -+ * node that will replace @node, and returning the deepest node that -+ * the following modifications to the tree can touch. If @node is the -+ * last node in the tree return %NULL. -+ */ -+static struct rb_node *bfq_find_deepest(struct rb_node *node) -+{ -+ struct rb_node *deepest; -+ -+ if (node->rb_right == NULL && node->rb_left == NULL) -+ deepest = rb_parent(node); -+ else if (node->rb_right == NULL) -+ deepest = node->rb_left; -+ else if (node->rb_left == NULL) -+ deepest = node->rb_right; -+ else { -+ deepest = rb_next(node); -+ if (deepest->rb_right != NULL) -+ deepest = deepest->rb_right; -+ else if (rb_parent(deepest) != node) -+ deepest = rb_parent(deepest); -+ } -+ -+ return deepest; -+} -+ -+/** -+ * bfq_active_extract - remove an entity from the active tree. -+ * @st: the service_tree containing the tree. -+ * @entity: the entity being removed. -+ */ -+static void bfq_active_extract(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ struct rb_node *node; -+#ifdef CONFIG_CGROUP_BFQIO -+ struct bfq_sched_data *sd = NULL; -+ struct bfq_group *bfqg = NULL; -+ struct bfq_data *bfqd = NULL; -+#endif -+ -+ node = bfq_find_deepest(&entity->rb_node); -+ bfq_extract(&st->active, entity); -+ -+ if (node != NULL) -+ bfq_update_active_tree(node); -+ -+#ifdef CONFIG_CGROUP_BFQIO -+ sd = entity->sched_data; -+ bfqg = container_of(sd, struct bfq_group, sched_data); -+ BUG_ON(!bfqg); -+ bfqd = (struct bfq_data *)bfqg->bfqd; -+#endif -+ if (bfqq != NULL) -+ list_del(&bfqq->bfqq_list); -+#ifdef CONFIG_CGROUP_BFQIO -+ else { /* bfq_group */ -+ BUG_ON(!bfqd); -+ bfq_weights_tree_remove(bfqd, entity, -+ &bfqd->group_weights_tree); -+ } -+ if (bfqg != bfqd->root_group) { -+ BUG_ON(!bfqg); -+ BUG_ON(!bfqd); -+ BUG_ON(!bfqg->active_entities); -+ bfqg->active_entities--; -+ if (bfqg->active_entities == 1) { -+ BUG_ON(!bfqd->active_numerous_groups); -+ bfqd->active_numerous_groups--; -+ } -+ } -+#endif -+} -+ -+/** -+ * bfq_idle_insert - insert an entity into the idle tree. -+ * @st: the service tree containing the tree. -+ * @entity: the entity to insert. -+ */ -+static void bfq_idle_insert(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ struct bfq_entity *first_idle = st->first_idle; -+ struct bfq_entity *last_idle = st->last_idle; -+ -+ if (first_idle == NULL || bfq_gt(first_idle->finish, entity->finish)) -+ st->first_idle = entity; -+ if (last_idle == NULL || bfq_gt(entity->finish, last_idle->finish)) -+ st->last_idle = entity; -+ -+ bfq_insert(&st->idle, entity); -+ -+ if (bfqq != NULL) -+ list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list); -+} -+ -+/** -+ * bfq_forget_entity - remove an entity from the wfq trees. -+ * @st: the service tree. -+ * @entity: the entity being removed. -+ * -+ * Update the device status and forget everything about @entity, putting -+ * the device reference to it, if it is a queue. Entities belonging to -+ * groups are not refcounted. -+ */ -+static void bfq_forget_entity(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ struct bfq_sched_data *sd; -+ -+ BUG_ON(!entity->on_st); -+ -+ entity->on_st = 0; -+ st->wsum -= entity->weight; -+ if (bfqq != NULL) { -+ sd = entity->sched_data; -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d", -+ bfqq, atomic_read(&bfqq->ref)); -+ bfq_put_queue(bfqq); -+ } -+} -+ -+/** -+ * bfq_put_idle_entity - release the idle tree ref of an entity. -+ * @st: service tree for the entity. -+ * @entity: the entity being released. -+ */ -+static void bfq_put_idle_entity(struct bfq_service_tree *st, -+ struct bfq_entity *entity) -+{ -+ bfq_idle_extract(st, entity); -+ bfq_forget_entity(st, entity); -+} -+ -+/** -+ * bfq_forget_idle - update the idle tree if necessary. -+ * @st: the service tree to act upon. -+ * -+ * To preserve the global O(log N) complexity we only remove one entry here; -+ * as the idle tree will not grow indefinitely this can be done safely. -+ */ -+static void bfq_forget_idle(struct bfq_service_tree *st) -+{ -+ struct bfq_entity *first_idle = st->first_idle; -+ struct bfq_entity *last_idle = st->last_idle; -+ -+ if (RB_EMPTY_ROOT(&st->active) && last_idle != NULL && -+ !bfq_gt(last_idle->finish, st->vtime)) { -+ /* -+ * Forget the whole idle tree, increasing the vtime past -+ * the last finish time of idle entities. -+ */ -+ st->vtime = last_idle->finish; -+ } -+ -+ if (first_idle != NULL && !bfq_gt(first_idle->finish, st->vtime)) -+ bfq_put_idle_entity(st, first_idle); -+} -+ -+static struct bfq_service_tree * -+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st, -+ struct bfq_entity *entity) -+{ -+ struct bfq_service_tree *new_st = old_st; -+ -+ if (entity->ioprio_changed) { -+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); -+ unsigned short prev_weight, new_weight; -+ struct bfq_data *bfqd = NULL; -+ struct rb_root *root; -+#ifdef CONFIG_CGROUP_BFQIO -+ struct bfq_sched_data *sd; -+ struct bfq_group *bfqg; -+#endif -+ -+ if (bfqq != NULL) -+ bfqd = bfqq->bfqd; -+#ifdef CONFIG_CGROUP_BFQIO -+ else { -+ sd = entity->my_sched_data; -+ bfqg = container_of(sd, struct bfq_group, sched_data); -+ BUG_ON(!bfqg); -+ bfqd = (struct bfq_data *)bfqg->bfqd; -+ BUG_ON(!bfqd); -+ } -+#endif -+ -+ BUG_ON(old_st->wsum < entity->weight); -+ old_st->wsum -= entity->weight; -+ -+ if (entity->new_weight != entity->orig_weight) { -+ if (entity->new_weight < BFQ_MIN_WEIGHT || -+ entity->new_weight > BFQ_MAX_WEIGHT) { -+ printk(KERN_CRIT "update_weight_prio: " -+ "new_weight %d\n", -+ entity->new_weight); -+ BUG(); -+ } -+ entity->orig_weight = entity->new_weight; -+ entity->ioprio = -+ bfq_weight_to_ioprio(entity->orig_weight); -+ } else if (entity->new_ioprio != entity->ioprio) { -+ entity->ioprio = entity->new_ioprio; -+ entity->orig_weight = -+ bfq_ioprio_to_weight(entity->ioprio); -+ } else -+ entity->new_weight = entity->orig_weight = -+ bfq_ioprio_to_weight(entity->ioprio); -+ -+ entity->ioprio_class = entity->new_ioprio_class; -+ entity->ioprio_changed = 0; -+ -+ /* -+ * NOTE: here we may be changing the weight too early, -+ * this will cause unfairness. The correct approach -+ * would have required additional complexity to defer -+ * weight changes to the proper time instants (i.e., -+ * when entity->finish <= old_st->vtime). -+ */ -+ new_st = bfq_entity_service_tree(entity); -+ -+ prev_weight = entity->weight; -+ new_weight = entity->orig_weight * -+ (bfqq != NULL ? bfqq->wr_coeff : 1); -+ /* -+ * If the weight of the entity changes, remove the entity -+ * from its old weight counter (if there is a counter -+ * associated with the entity), and add it to the counter -+ * associated with its new weight. -+ */ -+ if (prev_weight != new_weight) { -+ root = bfqq ? &bfqd->queue_weights_tree : -+ &bfqd->group_weights_tree; -+ bfq_weights_tree_remove(bfqd, entity, root); -+ } -+ entity->weight = new_weight; -+ /* -+ * Add the entity to its weights tree only if it is -+ * not associated with a weight-raised queue. -+ */ -+ if (prev_weight != new_weight && -+ (bfqq ? bfqq->wr_coeff == 1 : 1)) -+ /* If we get here, root has been initialized. */ -+ bfq_weights_tree_add(bfqd, entity, root); -+ -+ new_st->wsum += entity->weight; -+ -+ if (new_st != old_st) -+ entity->start = new_st->vtime; -+ } -+ -+ return new_st; -+} -+ -+/** -+ * bfq_bfqq_served - update the scheduler status after selection for -+ * service. -+ * @bfqq: the queue being served. -+ * @served: bytes to transfer. -+ * -+ * NOTE: this can be optimized, as the timestamps of upper level entities -+ * are synchronized every time a new bfqq is selected for service. By now, -+ * we keep it to better check consistency. -+ */ -+static void bfq_bfqq_served(struct bfq_queue *bfqq, unsigned long served) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ struct bfq_service_tree *st; -+ -+ for_each_entity(entity) { -+ st = bfq_entity_service_tree(entity); -+ -+ entity->service += served; -+ BUG_ON(entity->service > entity->budget); -+ BUG_ON(st->wsum == 0); -+ -+ st->vtime += bfq_delta(served, st->wsum); -+ bfq_forget_idle(st); -+ } -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %lu secs", served); -+} -+ -+/** -+ * bfq_bfqq_charge_full_budget - set the service to the entity budget. -+ * @bfqq: the queue that needs a service update. -+ * -+ * When it's not possible to be fair in the service domain, because -+ * a queue is not consuming its budget fast enough (the meaning of -+ * fast depends on the timeout parameter), we charge it a full -+ * budget. In this way we should obtain a sort of time-domain -+ * fairness among all the seeky/slow queues. -+ */ -+static inline void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget"); -+ -+ bfq_bfqq_served(bfqq, entity->budget - entity->service); -+} -+ -+/** -+ * __bfq_activate_entity - activate an entity. -+ * @entity: the entity being activated. -+ * -+ * Called whenever an entity is activated, i.e., it is not active and one -+ * of its children receives a new request, or has to be reactivated due to -+ * budget exhaustion. It uses the current budget of the entity (and the -+ * service received if @entity is active) of the queue to calculate its -+ * timestamps. -+ */ -+static void __bfq_activate_entity(struct bfq_entity *entity) -+{ -+ struct bfq_sched_data *sd = entity->sched_data; -+ struct bfq_service_tree *st = bfq_entity_service_tree(entity); -+ -+ if (entity == sd->in_service_entity) { -+ BUG_ON(entity->tree != NULL); -+ /* -+ * If we are requeueing the current entity we have -+ * to take care of not charging to it service it has -+ * not received. -+ */ -+ bfq_calc_finish(entity, entity->service); -+ entity->start = entity->finish; -+ sd->in_service_entity = NULL; -+ } else if (entity->tree == &st->active) { -+ /* -+ * Requeueing an entity due to a change of some -+ * next_in_service entity below it. We reuse the -+ * old start time. -+ */ -+ bfq_active_extract(st, entity); -+ } else if (entity->tree == &st->idle) { -+ /* -+ * Must be on the idle tree, bfq_idle_extract() will -+ * check for that. -+ */ -+ bfq_idle_extract(st, entity); -+ entity->start = bfq_gt(st->vtime, entity->finish) ? -+ st->vtime : entity->finish; -+ } else { -+ /* -+ * The finish time of the entity may be invalid, and -+ * it is in the past for sure, otherwise the queue -+ * would have been on the idle tree. -+ */ -+ entity->start = st->vtime; -+ st->wsum += entity->weight; -+ bfq_get_entity(entity); -+ -+ BUG_ON(entity->on_st); -+ entity->on_st = 1; -+ } -+ -+ st = __bfq_entity_update_weight_prio(st, entity); -+ bfq_calc_finish(entity, entity->budget); -+ bfq_active_insert(st, entity); -+} -+ -+/** -+ * bfq_activate_entity - activate an entity and its ancestors if necessary. -+ * @entity: the entity to activate. -+ * -+ * Activate @entity and all the entities on the path from it to the root. -+ */ -+static void bfq_activate_entity(struct bfq_entity *entity) -+{ -+ struct bfq_sched_data *sd; -+ -+ for_each_entity(entity) { -+ __bfq_activate_entity(entity); -+ -+ sd = entity->sched_data; -+ if (!bfq_update_next_in_service(sd)) -+ /* -+ * No need to propagate the activation to the -+ * upper entities, as they will be updated when -+ * the in-service entity is rescheduled. -+ */ -+ break; -+ } -+} -+ -+/** -+ * __bfq_deactivate_entity - deactivate an entity from its service tree. -+ * @entity: the entity to deactivate. -+ * @requeue: if false, the entity will not be put into the idle tree. -+ * -+ * Deactivate an entity, independently from its previous state. If the -+ * entity was not on a service tree just return, otherwise if it is on -+ * any scheduler tree, extract it from that tree, and if necessary -+ * and if the caller did not specify @requeue, put it on the idle tree. -+ * -+ * Return %1 if the caller should update the entity hierarchy, i.e., -+ * if the entity was in service or if it was the next_in_service for -+ * its sched_data; return %0 otherwise. -+ */ -+static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue) -+{ -+ struct bfq_sched_data *sd = entity->sched_data; -+ struct bfq_service_tree *st = bfq_entity_service_tree(entity); -+ int was_in_service = entity == sd->in_service_entity; -+ int ret = 0; -+ -+ if (!entity->on_st) -+ return 0; -+ -+ BUG_ON(was_in_service && entity->tree != NULL); -+ -+ if (was_in_service) { -+ bfq_calc_finish(entity, entity->service); -+ sd->in_service_entity = NULL; -+ } else if (entity->tree == &st->active) -+ bfq_active_extract(st, entity); -+ else if (entity->tree == &st->idle) -+ bfq_idle_extract(st, entity); -+ else if (entity->tree != NULL) -+ BUG(); -+ -+ if (was_in_service || sd->next_in_service == entity) -+ ret = bfq_update_next_in_service(sd); -+ -+ if (!requeue || !bfq_gt(entity->finish, st->vtime)) -+ bfq_forget_entity(st, entity); -+ else -+ bfq_idle_insert(st, entity); -+ -+ BUG_ON(sd->in_service_entity == entity); -+ BUG_ON(sd->next_in_service == entity); -+ -+ return ret; -+} -+ -+/** -+ * bfq_deactivate_entity - deactivate an entity. -+ * @entity: the entity to deactivate. -+ * @requeue: true if the entity can be put on the idle tree -+ */ -+static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue) -+{ -+ struct bfq_sched_data *sd; -+ struct bfq_entity *parent; -+ -+ for_each_entity_safe(entity, parent) { -+ sd = entity->sched_data; -+ -+ if (!__bfq_deactivate_entity(entity, requeue)) -+ /* -+ * The parent entity is still backlogged, and -+ * we don't need to update it as it is still -+ * in service. -+ */ -+ break; -+ -+ if (sd->next_in_service != NULL) -+ /* -+ * The parent entity is still backlogged and -+ * the budgets on the path towards the root -+ * need to be updated. -+ */ -+ goto update; -+ -+ /* -+ * If we reach there the parent is no more backlogged and -+ * we want to propagate the dequeue upwards. -+ */ -+ requeue = 1; -+ } -+ -+ return; -+ -+update: -+ entity = parent; -+ for_each_entity(entity) { -+ __bfq_activate_entity(entity); -+ -+ sd = entity->sched_data; -+ if (!bfq_update_next_in_service(sd)) -+ break; -+ } -+} -+ -+/** -+ * bfq_update_vtime - update vtime if necessary. -+ * @st: the service tree to act upon. -+ * -+ * If necessary update the service tree vtime to have at least one -+ * eligible entity, skipping to its start time. Assumes that the -+ * active tree of the device is not empty. -+ * -+ * NOTE: this hierarchical implementation updates vtimes quite often, -+ * we may end up with reactivated processes getting timestamps after a -+ * vtime skip done because we needed a ->first_active entity on some -+ * intermediate node. -+ */ -+static void bfq_update_vtime(struct bfq_service_tree *st) -+{ -+ struct bfq_entity *entry; -+ struct rb_node *node = st->active.rb_node; -+ -+ entry = rb_entry(node, struct bfq_entity, rb_node); -+ if (bfq_gt(entry->min_start, st->vtime)) { -+ st->vtime = entry->min_start; -+ bfq_forget_idle(st); -+ } -+} -+ -+/** -+ * bfq_first_active_entity - find the eligible entity with -+ * the smallest finish time -+ * @st: the service tree to select from. -+ * -+ * This function searches the first schedulable entity, starting from the -+ * root of the tree and going on the left every time on this side there is -+ * a subtree with at least one eligible (start >= vtime) entity. The path on -+ * the right is followed only if a) the left subtree contains no eligible -+ * entities and b) no eligible entity has been found yet. -+ */ -+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st) -+{ -+ struct bfq_entity *entry, *first = NULL; -+ struct rb_node *node = st->active.rb_node; -+ -+ while (node != NULL) { -+ entry = rb_entry(node, struct bfq_entity, rb_node); -+left: -+ if (!bfq_gt(entry->start, st->vtime)) -+ first = entry; -+ -+ BUG_ON(bfq_gt(entry->min_start, st->vtime)); -+ -+ if (node->rb_left != NULL) { -+ entry = rb_entry(node->rb_left, -+ struct bfq_entity, rb_node); -+ if (!bfq_gt(entry->min_start, st->vtime)) { -+ node = node->rb_left; -+ goto left; -+ } -+ } -+ if (first != NULL) -+ break; -+ node = node->rb_right; -+ } -+ -+ BUG_ON(first == NULL && !RB_EMPTY_ROOT(&st->active)); -+ return first; -+} -+ -+/** -+ * __bfq_lookup_next_entity - return the first eligible entity in @st. -+ * @st: the service tree. -+ * -+ * Update the virtual time in @st and return the first eligible entity -+ * it contains. -+ */ -+static struct bfq_entity *__bfq_lookup_next_entity(struct bfq_service_tree *st, -+ bool force) -+{ -+ struct bfq_entity *entity, *new_next_in_service = NULL; -+ -+ if (RB_EMPTY_ROOT(&st->active)) -+ return NULL; -+ -+ bfq_update_vtime(st); -+ entity = bfq_first_active_entity(st); -+ BUG_ON(bfq_gt(entity->start, st->vtime)); -+ -+ /* -+ * If the chosen entity does not match with the sched_data's -+ * next_in_service and we are forcedly serving the IDLE priority -+ * class tree, bubble up budget update. -+ */ -+ if (unlikely(force && entity != entity->sched_data->next_in_service)) { -+ new_next_in_service = entity; -+ for_each_entity(new_next_in_service) -+ bfq_update_budget(new_next_in_service); -+ } -+ -+ return entity; -+} -+ -+/** -+ * bfq_lookup_next_entity - return the first eligible entity in @sd. -+ * @sd: the sched_data. -+ * @extract: if true the returned entity will be also extracted from @sd. -+ * -+ * NOTE: since we cache the next_in_service entity at each level of the -+ * hierarchy, the complexity of the lookup can be decreased with -+ * absolutely no effort just returning the cached next_in_service value; -+ * we prefer to do full lookups to test the consistency of * the data -+ * structures. -+ */ -+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, -+ int extract, -+ struct bfq_data *bfqd) -+{ -+ struct bfq_service_tree *st = sd->service_tree; -+ struct bfq_entity *entity; -+ int i = 0; -+ -+ BUG_ON(sd->in_service_entity != NULL); -+ -+ if (bfqd != NULL && -+ jiffies - bfqd->bfq_class_idle_last_service > BFQ_CL_IDLE_TIMEOUT) { -+ entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1, -+ true); -+ if (entity != NULL) { -+ i = BFQ_IOPRIO_CLASSES - 1; -+ bfqd->bfq_class_idle_last_service = jiffies; -+ sd->next_in_service = entity; -+ } -+ } -+ for (; i < BFQ_IOPRIO_CLASSES; i++) { -+ entity = __bfq_lookup_next_entity(st + i, false); -+ if (entity != NULL) { -+ if (extract) { -+ bfq_check_next_in_service(sd, entity); -+ bfq_active_extract(st + i, entity); -+ sd->in_service_entity = entity; -+ sd->next_in_service = NULL; -+ } -+ break; -+ } -+ } -+ -+ return entity; -+} -+ -+/* -+ * Get next queue for service. -+ */ -+static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) -+{ -+ struct bfq_entity *entity = NULL; -+ struct bfq_sched_data *sd; -+ struct bfq_queue *bfqq; -+ -+ BUG_ON(bfqd->in_service_queue != NULL); -+ -+ if (bfqd->busy_queues == 0) -+ return NULL; -+ -+ sd = &bfqd->root_group->sched_data; -+ for (; sd != NULL; sd = entity->my_sched_data) { -+ entity = bfq_lookup_next_entity(sd, 1, bfqd); -+ BUG_ON(entity == NULL); -+ entity->service = 0; -+ } -+ -+ bfqq = bfq_entity_to_bfqq(entity); -+ BUG_ON(bfqq == NULL); -+ -+ return bfqq; -+} -+ -+/* -+ * Forced extraction of the given queue. -+ */ -+static void bfq_get_next_queue_forced(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ struct bfq_entity *entity; -+ struct bfq_sched_data *sd; -+ -+ BUG_ON(bfqd->in_service_queue != NULL); -+ -+ entity = &bfqq->entity; -+ /* -+ * Bubble up extraction/update from the leaf to the root. -+ */ -+ for_each_entity(entity) { -+ sd = entity->sched_data; -+ bfq_update_budget(entity); -+ bfq_update_vtime(bfq_entity_service_tree(entity)); -+ bfq_active_extract(bfq_entity_service_tree(entity), entity); -+ sd->in_service_entity = entity; -+ sd->next_in_service = NULL; -+ entity->service = 0; -+ } -+ -+ return; -+} -+ -+static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) -+{ -+ if (bfqd->in_service_bic != NULL) { -+ put_io_context(bfqd->in_service_bic->icq.ioc); -+ bfqd->in_service_bic = NULL; -+ } -+ -+ bfqd->in_service_queue = NULL; -+ del_timer(&bfqd->idle_slice_timer); -+} -+ -+static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ int requeue) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ -+ if (bfqq == bfqd->in_service_queue) -+ __bfq_bfqd_reset_in_service(bfqd); -+ -+ bfq_deactivate_entity(entity, requeue); -+} -+ -+static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ struct bfq_entity *entity = &bfqq->entity; -+ -+ bfq_activate_entity(entity); -+} -+ -+/* -+ * Called when the bfqq no longer has requests pending, remove it from -+ * the service tree. -+ */ -+static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ int requeue) -+{ -+ BUG_ON(!bfq_bfqq_busy(bfqq)); -+ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); -+ -+ bfq_log_bfqq(bfqd, bfqq, "del from busy"); -+ -+ bfq_clear_bfqq_busy(bfqq); -+ -+ BUG_ON(bfqd->busy_queues == 0); -+ bfqd->busy_queues--; -+ -+ if (!bfqq->dispatched) { -+ bfq_weights_tree_remove(bfqd, &bfqq->entity, -+ &bfqd->queue_weights_tree); -+ if (!blk_queue_nonrot(bfqd->queue)) { -+ BUG_ON(!bfqd->busy_in_flight_queues); -+ bfqd->busy_in_flight_queues--; -+ if (bfq_bfqq_constantly_seeky(bfqq)) { -+ BUG_ON(!bfqd-> -+ const_seeky_busy_in_flight_queues); -+ bfqd->const_seeky_busy_in_flight_queues--; -+ } -+ } -+ } -+ if (bfqq->wr_coeff > 1) -+ bfqd->wr_busy_queues--; -+ -+ bfq_deactivate_bfqq(bfqd, bfqq, requeue); -+} -+ -+/* -+ * Called when an inactive queue receives a new request. -+ */ -+static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq) -+{ -+ BUG_ON(bfq_bfqq_busy(bfqq)); -+ BUG_ON(bfqq == bfqd->in_service_queue); -+ -+ bfq_log_bfqq(bfqd, bfqq, "add to busy"); -+ -+ bfq_activate_bfqq(bfqd, bfqq); -+ -+ bfq_mark_bfqq_busy(bfqq); -+ bfqd->busy_queues++; -+ -+ if (!bfqq->dispatched) { -+ if (bfqq->wr_coeff == 1) -+ bfq_weights_tree_add(bfqd, &bfqq->entity, -+ &bfqd->queue_weights_tree); -+ if (!blk_queue_nonrot(bfqd->queue)) { -+ bfqd->busy_in_flight_queues++; -+ if (bfq_bfqq_constantly_seeky(bfqq)) -+ bfqd->const_seeky_busy_in_flight_queues++; -+ } -+ } -+ if (bfqq->wr_coeff > 1) -+ bfqd->wr_busy_queues++; -+} -diff --git a/block/bfq.h b/block/bfq.h -new file mode 100644 -index 0000000..518f2ac ---- /dev/null -+++ b/block/bfq.h -@@ -0,0 +1,775 @@ -+/* -+ * BFQ-v7r7 for 4.0.0: data structures and common functions prototypes. -+ * -+ * Based on ideas and code from CFQ: -+ * Copyright (C) 2003 Jens Axboe -+ * -+ * Copyright (C) 2008 Fabio Checconi -+ * Paolo Valente -+ * -+ * Copyright (C) 2010 Paolo Valente -+ */ -+ -+#ifndef _BFQ_H -+#define _BFQ_H -+ -+#include -+#include -+#include -+#include -+ -+#define BFQ_IOPRIO_CLASSES 3 -+#define BFQ_CL_IDLE_TIMEOUT (HZ/5) -+ -+#define BFQ_MIN_WEIGHT 1 -+#define BFQ_MAX_WEIGHT 1000 -+ -+#define BFQ_DEFAULT_QUEUE_IOPRIO 4 -+ -+#define BFQ_DEFAULT_GRP_WEIGHT 10 -+#define BFQ_DEFAULT_GRP_IOPRIO 0 -+#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE -+ -+struct bfq_entity; -+ -+/** -+ * struct bfq_service_tree - per ioprio_class service tree. -+ * @active: tree for active entities (i.e., those backlogged). -+ * @idle: tree for idle entities (i.e., those not backlogged, with V <= F_i). -+ * @first_idle: idle entity with minimum F_i. -+ * @last_idle: idle entity with maximum F_i. -+ * @vtime: scheduler virtual time. -+ * @wsum: scheduler weight sum; active and idle entities contribute to it. -+ * -+ * Each service tree represents a B-WF2Q+ scheduler on its own. Each -+ * ioprio_class has its own independent scheduler, and so its own -+ * bfq_service_tree. All the fields are protected by the queue lock -+ * of the containing bfqd. -+ */ -+struct bfq_service_tree { -+ struct rb_root active; -+ struct rb_root idle; -+ -+ struct bfq_entity *first_idle; -+ struct bfq_entity *last_idle; -+ -+ u64 vtime; -+ unsigned long wsum; -+}; -+ -+/** -+ * struct bfq_sched_data - multi-class scheduler. -+ * @in_service_entity: entity in service. -+ * @next_in_service: head-of-the-line entity in the scheduler. -+ * @service_tree: array of service trees, one per ioprio_class. -+ * -+ * bfq_sched_data is the basic scheduler queue. It supports three -+ * ioprio_classes, and can be used either as a toplevel queue or as -+ * an intermediate queue on a hierarchical setup. -+ * @next_in_service points to the active entity of the sched_data -+ * service trees that will be scheduled next. -+ * -+ * The supported ioprio_classes are the same as in CFQ, in descending -+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE. -+ * Requests from higher priority queues are served before all the -+ * requests from lower priority queues; among requests of the same -+ * queue requests are served according to B-WF2Q+. -+ * All the fields are protected by the queue lock of the containing bfqd. -+ */ -+struct bfq_sched_data { -+ struct bfq_entity *in_service_entity; -+ struct bfq_entity *next_in_service; -+ struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES]; -+}; -+ -+/** -+ * struct bfq_weight_counter - counter of the number of all active entities -+ * with a given weight. -+ * @weight: weight of the entities that this counter refers to. -+ * @num_active: number of active entities with this weight. -+ * @weights_node: weights tree member (see bfq_data's @queue_weights_tree -+ * and @group_weights_tree). -+ */ -+struct bfq_weight_counter { -+ short int weight; -+ unsigned int num_active; -+ struct rb_node weights_node; -+}; -+ -+/** -+ * struct bfq_entity - schedulable entity. -+ * @rb_node: service_tree member. -+ * @weight_counter: pointer to the weight counter associated with this entity. -+ * @on_st: flag, true if the entity is on a tree (either the active or -+ * the idle one of its service_tree). -+ * @finish: B-WF2Q+ finish timestamp (aka F_i). -+ * @start: B-WF2Q+ start timestamp (aka S_i). -+ * @tree: tree the entity is enqueued into; %NULL if not on a tree. -+ * @min_start: minimum start time of the (active) subtree rooted at -+ * this entity; used for O(log N) lookups into active trees. -+ * @service: service received during the last round of service. -+ * @budget: budget used to calculate F_i; F_i = S_i + @budget / @weight. -+ * @weight: weight of the queue -+ * @parent: parent entity, for hierarchical scheduling. -+ * @my_sched_data: for non-leaf nodes in the cgroup hierarchy, the -+ * associated scheduler queue, %NULL on leaf nodes. -+ * @sched_data: the scheduler queue this entity belongs to. -+ * @ioprio: the ioprio in use. -+ * @new_weight: when a weight change is requested, the new weight value. -+ * @orig_weight: original weight, used to implement weight boosting -+ * @new_ioprio: when an ioprio change is requested, the new ioprio value. -+ * @ioprio_class: the ioprio_class in use. -+ * @new_ioprio_class: when an ioprio_class change is requested, the new -+ * ioprio_class value. -+ * @ioprio_changed: flag, true when the user requested a weight, ioprio or -+ * ioprio_class change. -+ * -+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the -+ * cgroup hierarchy) or a bfq_group into the upper level scheduler. Each -+ * entity belongs to the sched_data of the parent group in the cgroup -+ * hierarchy. Non-leaf entities have also their own sched_data, stored -+ * in @my_sched_data. -+ * -+ * Each entity stores independently its priority values; this would -+ * allow different weights on different devices, but this -+ * functionality is not exported to userspace by now. Priorities and -+ * weights are updated lazily, first storing the new values into the -+ * new_* fields, then setting the @ioprio_changed flag. As soon as -+ * there is a transition in the entity state that allows the priority -+ * update to take place the effective and the requested priority -+ * values are synchronized. -+ * -+ * Unless cgroups are used, the weight value is calculated from the -+ * ioprio to export the same interface as CFQ. When dealing with -+ * ``well-behaved'' queues (i.e., queues that do not spend too much -+ * time to consume their budget and have true sequential behavior, and -+ * when there are no external factors breaking anticipation) the -+ * relative weights at each level of the cgroups hierarchy should be -+ * guaranteed. All the fields are protected by the queue lock of the -+ * containing bfqd. -+ */ -+struct bfq_entity { -+ struct rb_node rb_node; -+ struct bfq_weight_counter *weight_counter; -+ -+ int on_st; -+ -+ u64 finish; -+ u64 start; -+ -+ struct rb_root *tree; -+ -+ u64 min_start; -+ -+ unsigned long service, budget; -+ unsigned short weight, new_weight; -+ unsigned short orig_weight; -+ -+ struct bfq_entity *parent; -+ -+ struct bfq_sched_data *my_sched_data; -+ struct bfq_sched_data *sched_data; -+ -+ unsigned short ioprio, new_ioprio; -+ unsigned short ioprio_class, new_ioprio_class; -+ -+ int ioprio_changed; -+}; -+ -+struct bfq_group; -+ -+/** -+ * struct bfq_queue - leaf schedulable entity. -+ * @ref: reference counter. -+ * @bfqd: parent bfq_data. -+ * @new_bfqq: shared bfq_queue if queue is cooperating with -+ * one or more other queues. -+ * @pos_node: request-position tree member (see bfq_data's @rq_pos_tree). -+ * @pos_root: request-position tree root (see bfq_data's @rq_pos_tree). -+ * @sort_list: sorted list of pending requests. -+ * @next_rq: if fifo isn't expired, next request to serve. -+ * @queued: nr of requests queued in @sort_list. -+ * @allocated: currently allocated requests. -+ * @meta_pending: pending metadata requests. -+ * @fifo: fifo list of requests in sort_list. -+ * @entity: entity representing this queue in the scheduler. -+ * @max_budget: maximum budget allowed from the feedback mechanism. -+ * @budget_timeout: budget expiration (in jiffies). -+ * @dispatched: number of requests on the dispatch list or inside driver. -+ * @flags: status flags. -+ * @bfqq_list: node for active/idle bfqq list inside our bfqd. -+ * @burst_list_node: node for the device's burst list. -+ * @seek_samples: number of seeks sampled -+ * @seek_total: sum of the distances of the seeks sampled -+ * @seek_mean: mean seek distance -+ * @last_request_pos: position of the last request enqueued -+ * @requests_within_timer: number of consecutive pairs of request completion -+ * and arrival, such that the queue becomes idle -+ * after the completion, but the next request arrives -+ * within an idle time slice; used only if the queue's -+ * IO_bound has been cleared. -+ * @pid: pid of the process owning the queue, used for logging purposes. -+ * @last_wr_start_finish: start time of the current weight-raising period if -+ * the @bfq-queue is being weight-raised, otherwise -+ * finish time of the last weight-raising period -+ * @wr_cur_max_time: current max raising time for this queue -+ * @soft_rt_next_start: minimum time instant such that, only if a new -+ * request is enqueued after this time instant in an -+ * idle @bfq_queue with no outstanding requests, then -+ * the task associated with the queue it is deemed as -+ * soft real-time (see the comments to the function -+ * bfq_bfqq_softrt_next_start()). -+ * @last_idle_bklogged: time of the last transition of the @bfq_queue from -+ * idle to backlogged -+ * @service_from_backlogged: cumulative service received from the @bfq_queue -+ * since the last transition from idle to -+ * backlogged -+ * -+ * A bfq_queue is a leaf request queue; it can be associated with an io_context -+ * or more, if it is async or shared between cooperating processes. @cgroup -+ * holds a reference to the cgroup, to be sure that it does not disappear while -+ * a bfqq still references it (mostly to avoid races between request issuing and -+ * task migration followed by cgroup destruction). -+ * All the fields are protected by the queue lock of the containing bfqd. -+ */ -+struct bfq_queue { -+ atomic_t ref; -+ struct bfq_data *bfqd; -+ -+ /* fields for cooperating queues handling */ -+ struct bfq_queue *new_bfqq; -+ struct rb_node pos_node; -+ struct rb_root *pos_root; -+ -+ struct rb_root sort_list; -+ struct request *next_rq; -+ int queued[2]; -+ int allocated[2]; -+ int meta_pending; -+ struct list_head fifo; -+ -+ struct bfq_entity entity; -+ -+ unsigned long max_budget; -+ unsigned long budget_timeout; -+ -+ int dispatched; -+ -+ unsigned int flags; -+ -+ struct list_head bfqq_list; -+ -+ struct hlist_node burst_list_node; -+ -+ unsigned int seek_samples; -+ u64 seek_total; -+ sector_t seek_mean; -+ sector_t last_request_pos; -+ -+ unsigned int requests_within_timer; -+ -+ pid_t pid; -+ -+ /* weight-raising fields */ -+ unsigned long wr_cur_max_time; -+ unsigned long soft_rt_next_start; -+ unsigned long last_wr_start_finish; -+ unsigned int wr_coeff; -+ unsigned long last_idle_bklogged; -+ unsigned long service_from_backlogged; -+}; -+ -+/** -+ * struct bfq_ttime - per process thinktime stats. -+ * @ttime_total: total process thinktime -+ * @ttime_samples: number of thinktime samples -+ * @ttime_mean: average process thinktime -+ */ -+struct bfq_ttime { -+ unsigned long last_end_request; -+ -+ unsigned long ttime_total; -+ unsigned long ttime_samples; -+ unsigned long ttime_mean; -+}; -+ -+/** -+ * struct bfq_io_cq - per (request_queue, io_context) structure. -+ * @icq: associated io_cq structure -+ * @bfqq: array of two process queues, the sync and the async -+ * @ttime: associated @bfq_ttime struct -+ */ -+struct bfq_io_cq { -+ struct io_cq icq; /* must be the first member */ -+ struct bfq_queue *bfqq[2]; -+ struct bfq_ttime ttime; -+ int ioprio; -+}; -+ -+enum bfq_device_speed { -+ BFQ_BFQD_FAST, -+ BFQ_BFQD_SLOW, -+}; -+ -+/** -+ * struct bfq_data - per device data structure. -+ * @queue: request queue for the managed device. -+ * @root_group: root bfq_group for the device. -+ * @rq_pos_tree: rbtree sorted by next_request position, used when -+ * determining if two or more queues have interleaving -+ * requests (see bfq_close_cooperator()). -+ * @active_numerous_groups: number of bfq_groups containing more than one -+ * active @bfq_entity. -+ * @queue_weights_tree: rbtree of weight counters of @bfq_queues, sorted by -+ * weight. Used to keep track of whether all @bfq_queues -+ * have the same weight. The tree contains one counter -+ * for each distinct weight associated to some active -+ * and not weight-raised @bfq_queue (see the comments to -+ * the functions bfq_weights_tree_[add|remove] for -+ * further details). -+ * @group_weights_tree: rbtree of non-queue @bfq_entity weight counters, sorted -+ * by weight. Used to keep track of whether all -+ * @bfq_groups have the same weight. The tree contains -+ * one counter for each distinct weight associated to -+ * some active @bfq_group (see the comments to the -+ * functions bfq_weights_tree_[add|remove] for further -+ * details). -+ * @busy_queues: number of bfq_queues containing requests (including the -+ * queue in service, even if it is idling). -+ * @busy_in_flight_queues: number of @bfq_queues containing pending or -+ * in-flight requests, plus the @bfq_queue in -+ * service, even if idle but waiting for the -+ * possible arrival of its next sync request. This -+ * field is updated only if the device is rotational, -+ * but used only if the device is also NCQ-capable. -+ * The reason why the field is updated also for non- -+ * NCQ-capable rotational devices is related to the -+ * fact that the value of @hw_tag may be set also -+ * later than when busy_in_flight_queues may need to -+ * be incremented for the first time(s). Taking also -+ * this possibility into account, to avoid unbalanced -+ * increments/decrements, would imply more overhead -+ * than just updating busy_in_flight_queues -+ * regardless of the value of @hw_tag. -+ * @const_seeky_busy_in_flight_queues: number of constantly-seeky @bfq_queues -+ * (that is, seeky queues that expired -+ * for budget timeout at least once) -+ * containing pending or in-flight -+ * requests, including the in-service -+ * @bfq_queue if constantly seeky. This -+ * field is updated only if the device -+ * is rotational, but used only if the -+ * device is also NCQ-capable (see the -+ * comments to @busy_in_flight_queues). -+ * @wr_busy_queues: number of weight-raised busy @bfq_queues. -+ * @queued: number of queued requests. -+ * @rq_in_driver: number of requests dispatched and waiting for completion. -+ * @sync_flight: number of sync requests in the driver. -+ * @max_rq_in_driver: max number of reqs in driver in the last -+ * @hw_tag_samples completed requests. -+ * @hw_tag_samples: nr of samples used to calculate hw_tag. -+ * @hw_tag: flag set to one if the driver is showing a queueing behavior. -+ * @budgets_assigned: number of budgets assigned. -+ * @idle_slice_timer: timer set when idling for the next sequential request -+ * from the queue in service. -+ * @unplug_work: delayed work to restart dispatching on the request queue. -+ * @in_service_queue: bfq_queue in service. -+ * @in_service_bic: bfq_io_cq (bic) associated with the @in_service_queue. -+ * @last_position: on-disk position of the last served request. -+ * @last_budget_start: beginning of the last budget. -+ * @last_idling_start: beginning of the last idle slice. -+ * @peak_rate: peak transfer rate observed for a budget. -+ * @peak_rate_samples: number of samples used to calculate @peak_rate. -+ * @bfq_max_budget: maximum budget allotted to a bfq_queue before -+ * rescheduling. -+ * @group_list: list of all the bfq_groups active on the device. -+ * @active_list: list of all the bfq_queues active on the device. -+ * @idle_list: list of all the bfq_queues idle on the device. -+ * @bfq_quantum: max number of requests dispatched per dispatch round. -+ * @bfq_fifo_expire: timeout for async/sync requests; when it expires -+ * requests are served in fifo order. -+ * @bfq_back_penalty: weight of backward seeks wrt forward ones. -+ * @bfq_back_max: maximum allowed backward seek. -+ * @bfq_slice_idle: maximum idling time. -+ * @bfq_user_max_budget: user-configured max budget value -+ * (0 for auto-tuning). -+ * @bfq_max_budget_async_rq: maximum budget (in nr of requests) allotted to -+ * async queues. -+ * @bfq_timeout: timeout for bfq_queues to consume their budget; used to -+ * to prevent seeky queues to impose long latencies to well -+ * behaved ones (this also implies that seeky queues cannot -+ * receive guarantees in the service domain; after a timeout -+ * they are charged for the whole allocated budget, to try -+ * to preserve a behavior reasonably fair among them, but -+ * without service-domain guarantees). -+ * @bfq_coop_thresh: number of queue merges after which a @bfq_queue is -+ * no more granted any weight-raising. -+ * @bfq_failed_cooperations: number of consecutive failed cooperation -+ * chances after which weight-raising is restored -+ * to a queue subject to more than bfq_coop_thresh -+ * queue merges. -+ * @bfq_requests_within_timer: number of consecutive requests that must be -+ * issued within the idle time slice to set -+ * again idling to a queue which was marked as -+ * non-I/O-bound (see the definition of the -+ * IO_bound flag for further details). -+ * @last_ins_in_burst: last time at which a queue entered the current -+ * burst of queues being activated shortly after -+ * each other; for more details about this and the -+ * following parameters related to a burst of -+ * activations, see the comments to the function -+ * @bfq_handle_burst. -+ * @bfq_burst_interval: reference time interval used to decide whether a -+ * queue has been activated shortly after -+ * @last_ins_in_burst. -+ * @burst_size: number of queues in the current burst of queue activations. -+ * @bfq_large_burst_thresh: maximum burst size above which the current -+ * queue-activation burst is deemed as 'large'. -+ * @large_burst: true if a large queue-activation burst is in progress. -+ * @burst_list: head of the burst list (as for the above fields, more details -+ * in the comments to the function bfq_handle_burst). -+ * @low_latency: if set to true, low-latency heuristics are enabled. -+ * @bfq_wr_coeff: maximum factor by which the weight of a weight-raised -+ * queue is multiplied. -+ * @bfq_wr_max_time: maximum duration of a weight-raising period (jiffies). -+ * @bfq_wr_rt_max_time: maximum duration for soft real-time processes. -+ * @bfq_wr_min_idle_time: minimum idle period after which weight-raising -+ * may be reactivated for a queue (in jiffies). -+ * @bfq_wr_min_inter_arr_async: minimum period between request arrivals -+ * after which weight-raising may be -+ * reactivated for an already busy queue -+ * (in jiffies). -+ * @bfq_wr_max_softrt_rate: max service-rate for a soft real-time queue, -+ * sectors per seconds. -+ * @RT_prod: cached value of the product R*T used for computing the maximum -+ * duration of the weight raising automatically. -+ * @device_speed: device-speed class for the low-latency heuristic. -+ * @oom_bfqq: fallback dummy bfqq for extreme OOM conditions. -+ * -+ * All the fields are protected by the @queue lock. -+ */ -+struct bfq_data { -+ struct request_queue *queue; -+ -+ struct bfq_group *root_group; -+ struct rb_root rq_pos_tree; -+ -+#ifdef CONFIG_CGROUP_BFQIO -+ int active_numerous_groups; -+#endif -+ -+ struct rb_root queue_weights_tree; -+ struct rb_root group_weights_tree; -+ -+ int busy_queues; -+ int busy_in_flight_queues; -+ int const_seeky_busy_in_flight_queues; -+ int wr_busy_queues; -+ int queued; -+ int rq_in_driver; -+ int sync_flight; -+ -+ int max_rq_in_driver; -+ int hw_tag_samples; -+ int hw_tag; -+ -+ int budgets_assigned; -+ -+ struct timer_list idle_slice_timer; -+ struct work_struct unplug_work; -+ -+ struct bfq_queue *in_service_queue; -+ struct bfq_io_cq *in_service_bic; -+ -+ sector_t last_position; -+ -+ ktime_t last_budget_start; -+ ktime_t last_idling_start; -+ int peak_rate_samples; -+ u64 peak_rate; -+ unsigned long bfq_max_budget; -+ -+ struct hlist_head group_list; -+ struct list_head active_list; -+ struct list_head idle_list; -+ -+ unsigned int bfq_quantum; -+ unsigned int bfq_fifo_expire[2]; -+ unsigned int bfq_back_penalty; -+ unsigned int bfq_back_max; -+ unsigned int bfq_slice_idle; -+ u64 bfq_class_idle_last_service; -+ -+ unsigned int bfq_user_max_budget; -+ unsigned int bfq_max_budget_async_rq; -+ unsigned int bfq_timeout[2]; -+ -+ unsigned int bfq_coop_thresh; -+ unsigned int bfq_failed_cooperations; -+ unsigned int bfq_requests_within_timer; -+ -+ unsigned long last_ins_in_burst; -+ unsigned long bfq_burst_interval; -+ int burst_size; -+ unsigned long bfq_large_burst_thresh; -+ bool large_burst; -+ struct hlist_head burst_list; -+ -+ bool low_latency; -+ -+ /* parameters of the low_latency heuristics */ -+ unsigned int bfq_wr_coeff; -+ unsigned int bfq_wr_max_time; -+ unsigned int bfq_wr_rt_max_time; -+ unsigned int bfq_wr_min_idle_time; -+ unsigned long bfq_wr_min_inter_arr_async; -+ unsigned int bfq_wr_max_softrt_rate; -+ u64 RT_prod; -+ enum bfq_device_speed device_speed; -+ -+ struct bfq_queue oom_bfqq; -+}; -+ -+enum bfqq_state_flags { -+ BFQ_BFQQ_FLAG_busy = 0, /* has requests or is in service */ -+ BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */ -+ BFQ_BFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ -+ BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ -+ BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */ -+ BFQ_BFQQ_FLAG_prio_changed, /* task priority has changed */ -+ BFQ_BFQQ_FLAG_sync, /* synchronous queue */ -+ BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */ -+ BFQ_BFQQ_FLAG_IO_bound, /* -+ * bfqq has timed-out at least once -+ * having consumed at most 2/10 of -+ * its budget -+ */ -+ BFQ_BFQQ_FLAG_in_large_burst, /* -+ * bfqq activated in a large burst, -+ * see comments to bfq_handle_burst. -+ */ -+ BFQ_BFQQ_FLAG_constantly_seeky, /* -+ * bfqq has proved to be slow and -+ * seeky until budget timeout -+ */ -+ BFQ_BFQQ_FLAG_softrt_update, /* -+ * may need softrt-next-start -+ * update -+ */ -+ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ -+ BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be splitted */ -+}; -+ -+#define BFQ_BFQQ_FNS(name) \ -+static inline void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ -+{ \ -+ (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \ -+} \ -+static inline void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \ -+{ \ -+ (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \ -+} \ -+static inline int bfq_bfqq_##name(const struct bfq_queue *bfqq) \ -+{ \ -+ return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \ -+} -+ -+BFQ_BFQQ_FNS(busy); -+BFQ_BFQQ_FNS(wait_request); -+BFQ_BFQQ_FNS(must_alloc); -+BFQ_BFQQ_FNS(fifo_expire); -+BFQ_BFQQ_FNS(idle_window); -+BFQ_BFQQ_FNS(prio_changed); -+BFQ_BFQQ_FNS(sync); -+BFQ_BFQQ_FNS(budget_new); -+BFQ_BFQQ_FNS(IO_bound); -+BFQ_BFQQ_FNS(in_large_burst); -+BFQ_BFQQ_FNS(constantly_seeky); -+BFQ_BFQQ_FNS(coop); -+BFQ_BFQQ_FNS(split_coop); -+BFQ_BFQQ_FNS(softrt_update); -+#undef BFQ_BFQQ_FNS -+ -+/* Logging facilities. */ -+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ -+ blk_add_trace_msg((bfqd)->queue, "bfq%d " fmt, (bfqq)->pid, ##args) -+ -+#define bfq_log(bfqd, fmt, args...) \ -+ blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args) -+ -+/* Expiration reasons. */ -+enum bfqq_expiration { -+ BFQ_BFQQ_TOO_IDLE = 0, /* -+ * queue has been idling for -+ * too long -+ */ -+ BFQ_BFQQ_BUDGET_TIMEOUT, /* budget took too long to be used */ -+ BFQ_BFQQ_BUDGET_EXHAUSTED, /* budget consumed */ -+ BFQ_BFQQ_NO_MORE_REQUESTS, /* the queue has no more requests */ -+}; -+ -+#ifdef CONFIG_CGROUP_BFQIO -+/** -+ * struct bfq_group - per (device, cgroup) data structure. -+ * @entity: schedulable entity to insert into the parent group sched_data. -+ * @sched_data: own sched_data, to contain child entities (they may be -+ * both bfq_queues and bfq_groups). -+ * @group_node: node to be inserted into the bfqio_cgroup->group_data -+ * list of the containing cgroup's bfqio_cgroup. -+ * @bfqd_node: node to be inserted into the @bfqd->group_list list -+ * of the groups active on the same device; used for cleanup. -+ * @bfqd: the bfq_data for the device this group acts upon. -+ * @async_bfqq: array of async queues for all the tasks belonging to -+ * the group, one queue per ioprio value per ioprio_class, -+ * except for the idle class that has only one queue. -+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored). -+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used -+ * to avoid too many special cases during group creation/ -+ * migration. -+ * @active_entities: number of active entities belonging to the group; -+ * unused for the root group. Used to know whether there -+ * are groups with more than one active @bfq_entity -+ * (see the comments to the function -+ * bfq_bfqq_must_not_expire()). -+ * -+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup -+ * there is a set of bfq_groups, each one collecting the lower-level -+ * entities belonging to the group that are acting on the same device. -+ * -+ * Locking works as follows: -+ * o @group_node is protected by the bfqio_cgroup lock, and is accessed -+ * via RCU from its readers. -+ * o @bfqd is protected by the queue lock, RCU is used to access it -+ * from the readers. -+ * o All the other fields are protected by the @bfqd queue lock. -+ */ -+struct bfq_group { -+ struct bfq_entity entity; -+ struct bfq_sched_data sched_data; -+ -+ struct hlist_node group_node; -+ struct hlist_node bfqd_node; -+ -+ void *bfqd; -+ -+ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; -+ struct bfq_queue *async_idle_bfqq; -+ -+ struct bfq_entity *my_entity; -+ -+ int active_entities; -+}; -+ -+/** -+ * struct bfqio_cgroup - bfq cgroup data structure. -+ * @css: subsystem state for bfq in the containing cgroup. -+ * @online: flag marked when the subsystem is inserted. -+ * @weight: cgroup weight. -+ * @ioprio: cgroup ioprio. -+ * @ioprio_class: cgroup ioprio_class. -+ * @lock: spinlock that protects @ioprio, @ioprio_class and @group_data. -+ * @group_data: list containing the bfq_group belonging to this cgroup. -+ * -+ * @group_data is accessed using RCU, with @lock protecting the updates, -+ * @ioprio and @ioprio_class are protected by @lock. -+ */ -+struct bfqio_cgroup { -+ struct cgroup_subsys_state css; -+ bool online; -+ -+ unsigned short weight, ioprio, ioprio_class; -+ -+ spinlock_t lock; -+ struct hlist_head group_data; -+}; -+#else -+struct bfq_group { -+ struct bfq_sched_data sched_data; -+ -+ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; -+ struct bfq_queue *async_idle_bfqq; -+}; -+#endif -+ -+static inline struct bfq_service_tree * -+bfq_entity_service_tree(struct bfq_entity *entity) -+{ -+ struct bfq_sched_data *sched_data = entity->sched_data; -+ unsigned int idx = entity->ioprio_class - 1; -+ -+ BUG_ON(idx >= BFQ_IOPRIO_CLASSES); -+ BUG_ON(sched_data == NULL); -+ -+ return sched_data->service_tree + idx; -+} -+ -+static inline struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, -+ bool is_sync) -+{ -+ return bic->bfqq[is_sync]; -+} -+ -+static inline void bic_set_bfqq(struct bfq_io_cq *bic, -+ struct bfq_queue *bfqq, bool is_sync) -+{ -+ bic->bfqq[is_sync] = bfqq; -+} -+ -+static inline struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic) -+{ -+ return bic->icq.q->elevator->elevator_data; -+} -+ -+/** -+ * bfq_get_bfqd_locked - get a lock to a bfqd using a RCU protected pointer. -+ * @ptr: a pointer to a bfqd. -+ * @flags: storage for the flags to be saved. -+ * -+ * This function allows bfqg->bfqd to be protected by the -+ * queue lock of the bfqd they reference; the pointer is dereferenced -+ * under RCU, so the storage for bfqd is assured to be safe as long -+ * as the RCU read side critical section does not end. After the -+ * bfqd->queue->queue_lock is taken the pointer is rechecked, to be -+ * sure that no other writer accessed it. If we raced with a writer, -+ * the function returns NULL, with the queue unlocked, otherwise it -+ * returns the dereferenced pointer, with the queue locked. -+ */ -+static inline struct bfq_data *bfq_get_bfqd_locked(void **ptr, -+ unsigned long *flags) -+{ -+ struct bfq_data *bfqd; -+ -+ rcu_read_lock(); -+ bfqd = rcu_dereference(*(struct bfq_data **)ptr); -+ -+ if (bfqd != NULL) { -+ spin_lock_irqsave(bfqd->queue->queue_lock, *flags); -+ if (*ptr == bfqd) -+ goto out; -+ spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags); -+ } -+ -+ bfqd = NULL; -+out: -+ rcu_read_unlock(); -+ return bfqd; -+} -+ -+static inline void bfq_put_bfqd_unlock(struct bfq_data *bfqd, -+ unsigned long *flags) -+{ -+ spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags); -+} -+ -+static void bfq_changed_ioprio(struct bfq_io_cq *bic); -+static void bfq_put_queue(struct bfq_queue *bfqq); -+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq); -+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, -+ struct bfq_group *bfqg, int is_sync, -+ struct bfq_io_cq *bic, gfp_t gfp_mask); -+static void bfq_end_wr_async_queues(struct bfq_data *bfqd, -+ struct bfq_group *bfqg); -+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); -+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); -+ -+#endif /* _BFQ_H */ --- -2.1.0 - diff --git a/5003_block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r7-for-4.0.0.patch b/5003_block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r7-for-4.0.0.patch deleted file mode 100644 index 53267cdd..00000000 --- a/5003_block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r7-for-4.0.0.patch +++ /dev/null @@ -1,1222 +0,0 @@ -From d49cf2e7913ec1c4b86a9de657140d9ec5fa8c19 Mon Sep 17 00:00:00 2001 -From: Mauro Andreolini -Date: Thu, 18 Dec 2014 21:32:08 +0100 -Subject: [PATCH 3/3] block, bfq: add Early Queue Merge (EQM) to BFQ-v7r7 for - 4.0.0 - -A set of processes may happen to perform interleaved reads, i.e.,requests -whose union would give rise to a sequential read pattern. There are two -typical cases: in the first case, processes read fixed-size chunks of -data at a fixed distance from each other, while in the second case processes -may read variable-size chunks at variable distances. The latter case occurs -for example with QEMU, which splits the I/O generated by the guest into -multiple chunks, and lets these chunks be served by a pool of cooperating -processes, iteratively assigning the next chunk of I/O to the first -available process. CFQ uses actual queue merging for the first type of -rocesses, whereas it uses preemption to get a sequential read pattern out -of the read requests performed by the second type of processes. In the end -it uses two different mechanisms to achieve the same goal: boosting the -throughput with interleaved I/O. - -This patch introduces Early Queue Merge (EQM), a unified mechanism to get a -sequential read pattern with both types of processes. The main idea is -checking newly arrived requests against the next request of the active queue -both in case of actual request insert and in case of request merge. By doing -so, both the types of processes can be handled by just merging their queues. -EQM is then simpler and more compact than the pair of mechanisms used in -CFQ. - -Finally, EQM also preserves the typical low-latency properties of BFQ, by -properly restoring the weight-raising state of a queue when it gets back to -a non-merged state. - -Signed-off-by: Mauro Andreolini -Signed-off-by: Arianna Avanzini -Signed-off-by: Paolo Valente ---- - block/bfq-iosched.c | 751 +++++++++++++++++++++++++++++++++++++--------------- - block/bfq-sched.c | 28 -- - block/bfq.h | 54 +++- - 3 files changed, 581 insertions(+), 252 deletions(-) - -diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c -index 97ee934..328f33c 100644 ---- a/block/bfq-iosched.c -+++ b/block/bfq-iosched.c -@@ -571,6 +571,57 @@ static inline unsigned int bfq_wr_duration(struct bfq_data *bfqd) - return dur; - } - -+static inline unsigned -+bfq_bfqq_cooperations(struct bfq_queue *bfqq) -+{ -+ return bfqq->bic ? bfqq->bic->cooperations : 0; -+} -+ -+static inline void -+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) -+{ -+ if (bic->saved_idle_window) -+ bfq_mark_bfqq_idle_window(bfqq); -+ else -+ bfq_clear_bfqq_idle_window(bfqq); -+ if (bic->saved_IO_bound) -+ bfq_mark_bfqq_IO_bound(bfqq); -+ else -+ bfq_clear_bfqq_IO_bound(bfqq); -+ /* Assuming that the flag in_large_burst is already correctly set */ -+ if (bic->wr_time_left && bfqq->bfqd->low_latency && -+ !bfq_bfqq_in_large_burst(bfqq) && -+ bic->cooperations < bfqq->bfqd->bfq_coop_thresh) { -+ /* -+ * Start a weight raising period with the duration given by -+ * the raising_time_left snapshot. -+ */ -+ if (bfq_bfqq_busy(bfqq)) -+ bfqq->bfqd->wr_busy_queues++; -+ bfqq->wr_coeff = bfqq->bfqd->bfq_wr_coeff; -+ bfqq->wr_cur_max_time = bic->wr_time_left; -+ bfqq->last_wr_start_finish = jiffies; -+ bfqq->entity.ioprio_changed = 1; -+ } -+ /* -+ * Clear wr_time_left to prevent bfq_bfqq_save_state() from -+ * getting confused about the queue's need of a weight-raising -+ * period. -+ */ -+ bic->wr_time_left = 0; -+} -+ -+/* Must be called with the queue_lock held. */ -+static int bfqq_process_refs(struct bfq_queue *bfqq) -+{ -+ int process_refs, io_refs; -+ -+ io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; -+ process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st; -+ BUG_ON(process_refs < 0); -+ return process_refs; -+} -+ - /* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */ - static inline void bfq_reset_burst_list(struct bfq_data *bfqd, - struct bfq_queue *bfqq) -@@ -815,7 +866,7 @@ static void bfq_add_request(struct request *rq) - bfq_rq_pos_tree_add(bfqd, bfqq); - - if (!bfq_bfqq_busy(bfqq)) { -- bool soft_rt, -+ bool soft_rt, coop_or_in_burst, - idle_for_long_time = time_is_before_jiffies( - bfqq->budget_timeout + - bfqd->bfq_wr_min_idle_time); -@@ -839,11 +890,12 @@ static void bfq_add_request(struct request *rq) - bfqd->last_ins_in_burst = jiffies; - } - -+ coop_or_in_burst = bfq_bfqq_in_large_burst(bfqq) || -+ bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh; - soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && -- !bfq_bfqq_in_large_burst(bfqq) && -+ !coop_or_in_burst && - time_is_before_jiffies(bfqq->soft_rt_next_start); -- interactive = !bfq_bfqq_in_large_burst(bfqq) && -- idle_for_long_time; -+ interactive = !coop_or_in_burst && idle_for_long_time; - entity->budget = max_t(unsigned long, bfqq->max_budget, - bfq_serv_to_charge(next_rq, bfqq)); - -@@ -862,11 +914,20 @@ static void bfq_add_request(struct request *rq) - if (!bfqd->low_latency) - goto add_bfqq_busy; - -+ if (bfq_bfqq_just_split(bfqq)) -+ goto set_ioprio_changed; -+ - /* -- * If the queue is not being boosted and has been idle -- * for enough time, start a weight-raising period -+ * If the queue: -+ * - is not being boosted, -+ * - has been idle for enough time, -+ * - is not a sync queue or is linked to a bfq_io_cq (it is -+ * shared "for its nature" or it is not shared and its -+ * requests have not been redirected to a shared queue) -+ * start a weight-raising period. - */ -- if (old_wr_coeff == 1 && (interactive || soft_rt)) { -+ if (old_wr_coeff == 1 && (interactive || soft_rt) && -+ (!bfq_bfqq_sync(bfqq) || bfqq->bic != NULL)) { - bfqq->wr_coeff = bfqd->bfq_wr_coeff; - if (interactive) - bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); -@@ -880,7 +941,7 @@ static void bfq_add_request(struct request *rq) - } else if (old_wr_coeff > 1) { - if (interactive) - bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); -- else if (bfq_bfqq_in_large_burst(bfqq) || -+ else if (coop_or_in_burst || - (bfqq->wr_cur_max_time == - bfqd->bfq_wr_rt_max_time && - !soft_rt)) { -@@ -899,18 +960,18 @@ static void bfq_add_request(struct request *rq) - /* - * - * The remaining weight-raising time is lower -- * than bfqd->bfq_wr_rt_max_time, which -- * means that the application is enjoying -- * weight raising either because deemed soft- -- * rt in the near past, or because deemed -- * interactive a long ago. In both cases, -- * resetting now the current remaining weight- -- * raising time for the application to the -- * weight-raising duration for soft rt -- * applications would not cause any latency -- * increase for the application (as the new -- * duration would be higher than the remaining -- * time). -+ * than bfqd->bfq_wr_rt_max_time, which means -+ * that the application is enjoying weight -+ * raising either because deemed soft-rt in -+ * the near past, or because deemed interactive -+ * a long ago. -+ * In both cases, resetting now the current -+ * remaining weight-raising time for the -+ * application to the weight-raising duration -+ * for soft rt applications would not cause any -+ * latency increase for the application (as the -+ * new duration would be higher than the -+ * remaining time). - * - * In addition, the application is now meeting - * the requirements for being deemed soft rt. -@@ -945,6 +1006,7 @@ static void bfq_add_request(struct request *rq) - bfqd->bfq_wr_rt_max_time; - } - } -+set_ioprio_changed: - if (old_wr_coeff != bfqq->wr_coeff) - entity->ioprio_changed = 1; - add_bfqq_busy: -@@ -1156,90 +1218,35 @@ static void bfq_end_wr(struct bfq_data *bfqd) - spin_unlock_irq(bfqd->queue->queue_lock); - } - --static int bfq_allow_merge(struct request_queue *q, struct request *rq, -- struct bio *bio) -+static inline sector_t bfq_io_struct_pos(void *io_struct, bool request) - { -- struct bfq_data *bfqd = q->elevator->elevator_data; -- struct bfq_io_cq *bic; -- struct bfq_queue *bfqq; -- -- /* -- * Disallow merge of a sync bio into an async request. -- */ -- if (bfq_bio_sync(bio) && !rq_is_sync(rq)) -- return 0; -- -- /* -- * Lookup the bfqq that this bio will be queued with. Allow -- * merge only if rq is queued there. -- * Queue lock is held here. -- */ -- bic = bfq_bic_lookup(bfqd, current->io_context); -- if (bic == NULL) -- return 0; -- -- bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); -- return bfqq == RQ_BFQQ(rq); --} -- --static void __bfq_set_in_service_queue(struct bfq_data *bfqd, -- struct bfq_queue *bfqq) --{ -- if (bfqq != NULL) { -- bfq_mark_bfqq_must_alloc(bfqq); -- bfq_mark_bfqq_budget_new(bfqq); -- bfq_clear_bfqq_fifo_expire(bfqq); -- -- bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; -- -- bfq_log_bfqq(bfqd, bfqq, -- "set_in_service_queue, cur-budget = %lu", -- bfqq->entity.budget); -- } -- -- bfqd->in_service_queue = bfqq; --} -- --/* -- * Get and set a new queue for service. -- */ --static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd, -- struct bfq_queue *bfqq) --{ -- if (!bfqq) -- bfqq = bfq_get_next_queue(bfqd); -+ if (request) -+ return blk_rq_pos(io_struct); - else -- bfq_get_next_queue_forced(bfqd, bfqq); -- -- __bfq_set_in_service_queue(bfqd, bfqq); -- return bfqq; -+ return ((struct bio *)io_struct)->bi_iter.bi_sector; - } - --static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd, -- struct request *rq) -+static inline sector_t bfq_dist_from(sector_t pos1, -+ sector_t pos2) - { -- if (blk_rq_pos(rq) >= bfqd->last_position) -- return blk_rq_pos(rq) - bfqd->last_position; -+ if (pos1 >= pos2) -+ return pos1 - pos2; - else -- return bfqd->last_position - blk_rq_pos(rq); -+ return pos2 - pos1; - } - --/* -- * Return true if bfqq has no request pending and rq is close enough to -- * bfqd->last_position, or if rq is closer to bfqd->last_position than -- * bfqq->next_rq -- */ --static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq) -+static inline int bfq_rq_close_to_sector(void *io_struct, bool request, -+ sector_t sector) - { -- return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR; -+ return bfq_dist_from(bfq_io_struct_pos(io_struct, request), sector) <= -+ BFQQ_SEEK_THR; - } - --static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) -+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd, sector_t sector) - { - struct rb_root *root = &bfqd->rq_pos_tree; - struct rb_node *parent, *node; - struct bfq_queue *__bfqq; -- sector_t sector = bfqd->last_position; - - if (RB_EMPTY_ROOT(root)) - return NULL; -@@ -1258,7 +1265,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) - * next_request position). - */ - __bfqq = rb_entry(parent, struct bfq_queue, pos_node); -- if (bfq_rq_close(bfqd, __bfqq->next_rq)) -+ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) - return __bfqq; - - if (blk_rq_pos(__bfqq->next_rq) < sector) -@@ -1269,7 +1276,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) - return NULL; - - __bfqq = rb_entry(node, struct bfq_queue, pos_node); -- if (bfq_rq_close(bfqd, __bfqq->next_rq)) -+ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) - return __bfqq; - - return NULL; -@@ -1278,14 +1285,12 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) - /* - * bfqd - obvious - * cur_bfqq - passed in so that we don't decide that the current queue -- * is closely cooperating with itself. -- * -- * We are assuming that cur_bfqq has dispatched at least one request, -- * and that bfqd->last_position reflects a position on the disk associated -- * with the I/O issued by cur_bfqq. -+ * is closely cooperating with itself -+ * sector - used as a reference point to search for a close queue - */ - static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, -- struct bfq_queue *cur_bfqq) -+ struct bfq_queue *cur_bfqq, -+ sector_t sector) - { - struct bfq_queue *bfqq; - -@@ -1305,7 +1310,7 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, - * working closely on the same area of the disk. In that case, - * we can group them together and don't waste time idling. - */ -- bfqq = bfqq_close(bfqd); -+ bfqq = bfqq_close(bfqd, sector); - if (bfqq == NULL || bfqq == cur_bfqq) - return NULL; - -@@ -1332,6 +1337,315 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, - return bfqq; - } - -+static struct bfq_queue * -+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) -+{ -+ int process_refs, new_process_refs; -+ struct bfq_queue *__bfqq; -+ -+ /* -+ * If there are no process references on the new_bfqq, then it is -+ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain -+ * may have dropped their last reference (not just their last process -+ * reference). -+ */ -+ if (!bfqq_process_refs(new_bfqq)) -+ return NULL; -+ -+ /* Avoid a circular list and skip interim queue merges. */ -+ while ((__bfqq = new_bfqq->new_bfqq)) { -+ if (__bfqq == bfqq) -+ return NULL; -+ new_bfqq = __bfqq; -+ } -+ -+ process_refs = bfqq_process_refs(bfqq); -+ new_process_refs = bfqq_process_refs(new_bfqq); -+ /* -+ * If the process for the bfqq has gone away, there is no -+ * sense in merging the queues. -+ */ -+ if (process_refs == 0 || new_process_refs == 0) -+ return NULL; -+ -+ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", -+ new_bfqq->pid); -+ -+ /* -+ * Merging is just a redirection: the requests of the process -+ * owning one of the two queues are redirected to the other queue. -+ * The latter queue, in its turn, is set as shared if this is the -+ * first time that the requests of some process are redirected to -+ * it. -+ * -+ * We redirect bfqq to new_bfqq and not the opposite, because we -+ * are in the context of the process owning bfqq, hence we have -+ * the io_cq of this process. So we can immediately configure this -+ * io_cq to redirect the requests of the process to new_bfqq. -+ * -+ * NOTE, even if new_bfqq coincides with the in-service queue, the -+ * io_cq of new_bfqq is not available, because, if the in-service -+ * queue is shared, bfqd->in_service_bic may not point to the -+ * io_cq of the in-service queue. -+ * Redirecting the requests of the process owning bfqq to the -+ * currently in-service queue is in any case the best option, as -+ * we feed the in-service queue with new requests close to the -+ * last request served and, by doing so, hopefully increase the -+ * throughput. -+ */ -+ bfqq->new_bfqq = new_bfqq; -+ atomic_add(process_refs, &new_bfqq->ref); -+ return new_bfqq; -+} -+ -+/* -+ * Attempt to schedule a merge of bfqq with the currently in-service queue -+ * or with a close queue among the scheduled queues. -+ * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue -+ * structure otherwise. -+ * -+ * The OOM queue is not allowed to participate to cooperation: in fact, since -+ * the requests temporarily redirected to the OOM queue could be redirected -+ * again to dedicated queues at any time, the state needed to correctly -+ * handle merging with the OOM queue would be quite complex and expensive -+ * to maintain. Besides, in such a critical condition as an out of memory, -+ * the benefits of queue merging may be little relevant, or even negligible. -+ */ -+static struct bfq_queue * -+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, -+ void *io_struct, bool request) -+{ -+ struct bfq_queue *in_service_bfqq, *new_bfqq; -+ -+ if (bfqq->new_bfqq) -+ return bfqq->new_bfqq; -+ -+ if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) -+ return NULL; -+ -+ in_service_bfqq = bfqd->in_service_queue; -+ -+ if (in_service_bfqq == NULL || in_service_bfqq == bfqq || -+ !bfqd->in_service_bic || -+ unlikely(in_service_bfqq == &bfqd->oom_bfqq)) -+ goto check_scheduled; -+ -+ if (bfq_class_idle(in_service_bfqq) || bfq_class_idle(bfqq)) -+ goto check_scheduled; -+ -+ if (bfq_class_rt(in_service_bfqq) != bfq_class_rt(bfqq)) -+ goto check_scheduled; -+ -+ if (in_service_bfqq->entity.parent != bfqq->entity.parent) -+ goto check_scheduled; -+ -+ if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) && -+ bfq_bfqq_sync(in_service_bfqq) && bfq_bfqq_sync(bfqq)) { -+ new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); -+ if (new_bfqq != NULL) -+ return new_bfqq; /* Merge with in-service queue */ -+ } -+ -+ /* -+ * Check whether there is a cooperator among currently scheduled -+ * queues. The only thing we need is that the bio/request is not -+ * NULL, as we need it to establish whether a cooperator exists. -+ */ -+check_scheduled: -+ new_bfqq = bfq_close_cooperator(bfqd, bfqq, -+ bfq_io_struct_pos(io_struct, request)); -+ if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq)) -+ return bfq_setup_merge(bfqq, new_bfqq); -+ -+ return NULL; -+} -+ -+static inline void -+bfq_bfqq_save_state(struct bfq_queue *bfqq) -+{ -+ /* -+ * If bfqq->bic == NULL, the queue is already shared or its requests -+ * have already been redirected to a shared queue; both idle window -+ * and weight raising state have already been saved. Do nothing. -+ */ -+ if (bfqq->bic == NULL) -+ return; -+ if (bfqq->bic->wr_time_left) -+ /* -+ * This is the queue of a just-started process, and would -+ * deserve weight raising: we set wr_time_left to the full -+ * weight-raising duration to trigger weight-raising when -+ * and if the queue is split and the first request of the -+ * queue is enqueued. -+ */ -+ bfqq->bic->wr_time_left = bfq_wr_duration(bfqq->bfqd); -+ else if (bfqq->wr_coeff > 1) { -+ unsigned long wr_duration = -+ jiffies - bfqq->last_wr_start_finish; -+ /* -+ * It may happen that a queue's weight raising period lasts -+ * longer than its wr_cur_max_time, as weight raising is -+ * handled only when a request is enqueued or dispatched (it -+ * does not use any timer). If the weight raising period is -+ * about to end, don't save it. -+ */ -+ if (bfqq->wr_cur_max_time <= wr_duration) -+ bfqq->bic->wr_time_left = 0; -+ else -+ bfqq->bic->wr_time_left = -+ bfqq->wr_cur_max_time - wr_duration; -+ /* -+ * The bfq_queue is becoming shared or the requests of the -+ * process owning the queue are being redirected to a shared -+ * queue. Stop the weight raising period of the queue, as in -+ * both cases it should not be owned by an interactive or -+ * soft real-time application. -+ */ -+ bfq_bfqq_end_wr(bfqq); -+ } else -+ bfqq->bic->wr_time_left = 0; -+ bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq); -+ bfqq->bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); -+ bfqq->bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); -+ bfqq->bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); -+ bfqq->bic->cooperations++; -+ bfqq->bic->failed_cooperations = 0; -+} -+ -+static inline void -+bfq_get_bic_reference(struct bfq_queue *bfqq) -+{ -+ /* -+ * If bfqq->bic has a non-NULL value, the bic to which it belongs -+ * is about to begin using a shared bfq_queue. -+ */ -+ if (bfqq->bic) -+ atomic_long_inc(&bfqq->bic->icq.ioc->refcount); -+} -+ -+static void -+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, -+ struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) -+{ -+ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", -+ (long unsigned)new_bfqq->pid); -+ /* Save weight raising and idle window of the merged queues */ -+ bfq_bfqq_save_state(bfqq); -+ bfq_bfqq_save_state(new_bfqq); -+ if (bfq_bfqq_IO_bound(bfqq)) -+ bfq_mark_bfqq_IO_bound(new_bfqq); -+ bfq_clear_bfqq_IO_bound(bfqq); -+ /* -+ * Grab a reference to the bic, to prevent it from being destroyed -+ * before being possibly touched by a bfq_split_bfqq(). -+ */ -+ bfq_get_bic_reference(bfqq); -+ bfq_get_bic_reference(new_bfqq); -+ /* -+ * Merge queues (that is, let bic redirect its requests to new_bfqq) -+ */ -+ bic_set_bfqq(bic, new_bfqq, 1); -+ bfq_mark_bfqq_coop(new_bfqq); -+ /* -+ * new_bfqq now belongs to at least two bics (it is a shared queue): -+ * set new_bfqq->bic to NULL. bfqq either: -+ * - does not belong to any bic any more, and hence bfqq->bic must -+ * be set to NULL, or -+ * - is a queue whose owning bics have already been redirected to a -+ * different queue, hence the queue is destined to not belong to -+ * any bic soon and bfqq->bic is already NULL (therefore the next -+ * assignment causes no harm). -+ */ -+ new_bfqq->bic = NULL; -+ bfqq->bic = NULL; -+ bfq_put_queue(bfqq); -+} -+ -+static inline void bfq_bfqq_increase_failed_cooperations(struct bfq_queue *bfqq) -+{ -+ struct bfq_io_cq *bic = bfqq->bic; -+ struct bfq_data *bfqd = bfqq->bfqd; -+ -+ if (bic && bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh) { -+ bic->failed_cooperations++; -+ if (bic->failed_cooperations >= bfqd->bfq_failed_cooperations) -+ bic->cooperations = 0; -+ } -+} -+ -+static int bfq_allow_merge(struct request_queue *q, struct request *rq, -+ struct bio *bio) -+{ -+ struct bfq_data *bfqd = q->elevator->elevator_data; -+ struct bfq_io_cq *bic; -+ struct bfq_queue *bfqq, *new_bfqq; -+ -+ /* -+ * Disallow merge of a sync bio into an async request. -+ */ -+ if (bfq_bio_sync(bio) && !rq_is_sync(rq)) -+ return 0; -+ -+ /* -+ * Lookup the bfqq that this bio will be queued with. Allow -+ * merge only if rq is queued there. -+ * Queue lock is held here. -+ */ -+ bic = bfq_bic_lookup(bfqd, current->io_context); -+ if (bic == NULL) -+ return 0; -+ -+ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); -+ /* -+ * We take advantage of this function to perform an early merge -+ * of the queues of possible cooperating processes. -+ */ -+ if (bfqq != NULL) { -+ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); -+ if (new_bfqq != NULL) { -+ bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); -+ /* -+ * If we get here, the bio will be queued in the -+ * shared queue, i.e., new_bfqq, so use new_bfqq -+ * to decide whether bio and rq can be merged. -+ */ -+ bfqq = new_bfqq; -+ } else -+ bfq_bfqq_increase_failed_cooperations(bfqq); -+ } -+ -+ return bfqq == RQ_BFQQ(rq); -+} -+ -+static void __bfq_set_in_service_queue(struct bfq_data *bfqd, -+ struct bfq_queue *bfqq) -+{ -+ if (bfqq != NULL) { -+ bfq_mark_bfqq_must_alloc(bfqq); -+ bfq_mark_bfqq_budget_new(bfqq); -+ bfq_clear_bfqq_fifo_expire(bfqq); -+ -+ bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; -+ -+ bfq_log_bfqq(bfqd, bfqq, -+ "set_in_service_queue, cur-budget = %lu", -+ bfqq->entity.budget); -+ } -+ -+ bfqd->in_service_queue = bfqq; -+} -+ -+/* -+ * Get and set a new queue for service. -+ */ -+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd) -+{ -+ struct bfq_queue *bfqq = bfq_get_next_queue(bfqd); -+ -+ __bfq_set_in_service_queue(bfqd, bfqq); -+ return bfqq; -+} -+ - /* - * If enough samples have been computed, return the current max budget - * stored in bfqd, which is dynamically updated according to the -@@ -1475,61 +1789,6 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq) - return rq; - } - --/* Must be called with the queue_lock held. */ --static int bfqq_process_refs(struct bfq_queue *bfqq) --{ -- int process_refs, io_refs; -- -- io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; -- process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st; -- BUG_ON(process_refs < 0); -- return process_refs; --} -- --static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) --{ -- int process_refs, new_process_refs; -- struct bfq_queue *__bfqq; -- -- /* -- * If there are no process references on the new_bfqq, then it is -- * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain -- * may have dropped their last reference (not just their last process -- * reference). -- */ -- if (!bfqq_process_refs(new_bfqq)) -- return; -- -- /* Avoid a circular list and skip interim queue merges. */ -- while ((__bfqq = new_bfqq->new_bfqq)) { -- if (__bfqq == bfqq) -- return; -- new_bfqq = __bfqq; -- } -- -- process_refs = bfqq_process_refs(bfqq); -- new_process_refs = bfqq_process_refs(new_bfqq); -- /* -- * If the process for the bfqq has gone away, there is no -- * sense in merging the queues. -- */ -- if (process_refs == 0 || new_process_refs == 0) -- return; -- -- /* -- * Merge in the direction of the lesser amount of work. -- */ -- if (new_process_refs >= process_refs) { -- bfqq->new_bfqq = new_bfqq; -- atomic_add(process_refs, &new_bfqq->ref); -- } else { -- new_bfqq->new_bfqq = bfqq; -- atomic_add(new_process_refs, &bfqq->ref); -- } -- bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", -- new_bfqq->pid); --} -- - static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq) - { - struct bfq_entity *entity = &bfqq->entity; -@@ -2263,7 +2522,7 @@ static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) - */ - static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) - { -- struct bfq_queue *bfqq, *new_bfqq = NULL; -+ struct bfq_queue *bfqq; - struct request *next_rq; - enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; - -@@ -2273,17 +2532,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) - - bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue"); - -- /* -- * If another queue has a request waiting within our mean seek -- * distance, let it run. The expire code will check for close -- * cooperators and put the close queue at the front of the -- * service tree. If possible, merge the expiring queue with the -- * new bfqq. -- */ -- new_bfqq = bfq_close_cooperator(bfqd, bfqq); -- if (new_bfqq != NULL && bfqq->new_bfqq == NULL) -- bfq_setup_merge(bfqq, new_bfqq); -- - if (bfq_may_expire_for_budg_timeout(bfqq) && - !timer_pending(&bfqd->idle_slice_timer) && - !bfq_bfqq_must_idle(bfqq)) -@@ -2322,10 +2570,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) - bfq_clear_bfqq_wait_request(bfqq); - del_timer(&bfqd->idle_slice_timer); - } -- if (new_bfqq == NULL) -- goto keep_queue; -- else -- goto expire; -+ goto keep_queue; - } - } - -@@ -2334,40 +2579,30 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) - * in flight (possibly waiting for a completion) or is idling for a - * new request, then keep it. - */ -- if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) || -- (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) { -+ if (timer_pending(&bfqd->idle_slice_timer) || -+ (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq))) { - bfqq = NULL; - goto keep_queue; -- } else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) { -- /* -- * Expiring the queue because there is a close cooperator, -- * cancel timer. -- */ -- bfq_clear_bfqq_wait_request(bfqq); -- del_timer(&bfqd->idle_slice_timer); - } - - reason = BFQ_BFQQ_NO_MORE_REQUESTS; - expire: - bfq_bfqq_expire(bfqd, bfqq, 0, reason); - new_queue: -- bfqq = bfq_set_in_service_queue(bfqd, new_bfqq); -+ bfqq = bfq_set_in_service_queue(bfqd); - bfq_log(bfqd, "select_queue: new queue %d returned", - bfqq != NULL ? bfqq->pid : 0); - keep_queue: - return bfqq; - } - --static void bfq_update_wr_data(struct bfq_data *bfqd, -- struct bfq_queue *bfqq) -+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) - { -- if (bfqq->wr_coeff > 1) { /* queue is being boosted */ -- struct bfq_entity *entity = &bfqq->entity; -- -+ struct bfq_entity *entity = &bfqq->entity; -+ if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ - bfq_log_bfqq(bfqd, bfqq, - "raising period dur %u/%u msec, old coeff %u, w %d(%d)", -- jiffies_to_msecs(jiffies - -- bfqq->last_wr_start_finish), -+ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), - jiffies_to_msecs(bfqq->wr_cur_max_time), - bfqq->wr_coeff, - bfqq->entity.weight, bfqq->entity.orig_weight); -@@ -2376,12 +2611,16 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, - entity->orig_weight * bfqq->wr_coeff); - if (entity->ioprio_changed) - bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); -+ - /* - * If the queue was activated in a burst, or - * too much time has elapsed from the beginning -- * of this weight-raising, then end weight raising. -+ * of this weight-raising period, or the queue has -+ * exceeded the acceptable number of cooperations, -+ * then end weight raising. - */ - if (bfq_bfqq_in_large_burst(bfqq) || -+ bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh || - time_is_before_jiffies(bfqq->last_wr_start_finish + - bfqq->wr_cur_max_time)) { - bfqq->last_wr_start_finish = jiffies; -@@ -2390,11 +2629,13 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, - bfqq->last_wr_start_finish, - jiffies_to_msecs(bfqq->wr_cur_max_time)); - bfq_bfqq_end_wr(bfqq); -- __bfq_entity_update_weight_prio( -- bfq_entity_service_tree(entity), -- entity); - } - } -+ /* Update weight both if it must be raised and if it must be lowered */ -+ if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) -+ __bfq_entity_update_weight_prio( -+ bfq_entity_service_tree(entity), -+ entity); - } - - /* -@@ -2642,6 +2883,25 @@ static inline void bfq_init_icq(struct io_cq *icq) - struct bfq_io_cq *bic = icq_to_bic(icq); - - bic->ttime.last_end_request = jiffies; -+ /* -+ * A newly created bic indicates that the process has just -+ * started doing I/O, and is probably mapping into memory its -+ * executable and libraries: it definitely needs weight raising. -+ * There is however the possibility that the process performs, -+ * for a while, I/O close to some other process. EQM intercepts -+ * this behavior and may merge the queue corresponding to the -+ * process with some other queue, BEFORE the weight of the queue -+ * is raised. Merged queues are not weight-raised (they are assumed -+ * to belong to processes that benefit only from high throughput). -+ * If the merge is basically the consequence of an accident, then -+ * the queue will be split soon and will get back its old weight. -+ * It is then important to write down somewhere that this queue -+ * does need weight raising, even if it did not make it to get its -+ * weight raised before being merged. To this purpose, we overload -+ * the field raising_time_left and assign 1 to it, to mark the queue -+ * as needing weight raising. -+ */ -+ bic->wr_time_left = 1; - } - - static void bfq_exit_icq(struct io_cq *icq) -@@ -2655,6 +2915,13 @@ static void bfq_exit_icq(struct io_cq *icq) - } - - if (bic->bfqq[BLK_RW_SYNC]) { -+ /* -+ * If the bic is using a shared queue, put the reference -+ * taken on the io_context when the bic started using a -+ * shared bfq_queue. -+ */ -+ if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC])) -+ put_io_context(icq->ioc); - bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]); - bic->bfqq[BLK_RW_SYNC] = NULL; - } -@@ -2950,6 +3217,10 @@ static void bfq_update_idle_window(struct bfq_data *bfqd, - if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq)) - return; - -+ /* Idle window just restored, statistics are meaningless. */ -+ if (bfq_bfqq_just_split(bfqq)) -+ return; -+ - enable_idle = bfq_bfqq_idle_window(bfqq); - - if (atomic_read(&bic->icq.ioc->active_ref) == 0 || -@@ -2997,6 +3268,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, - if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 || - !BFQQ_SEEKY(bfqq)) - bfq_update_idle_window(bfqd, bfqq, bic); -+ bfq_clear_bfqq_just_split(bfqq); - - bfq_log_bfqq(bfqd, bfqq, - "rq_enqueued: idle_window=%d (seeky %d, mean %llu)", -@@ -3057,13 +3329,49 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, - static void bfq_insert_request(struct request_queue *q, struct request *rq) - { - struct bfq_data *bfqd = q->elevator->elevator_data; -- struct bfq_queue *bfqq = RQ_BFQQ(rq); -+ struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq; - - assert_spin_locked(bfqd->queue->queue_lock); -+ -+ /* -+ * An unplug may trigger a requeue of a request from the device -+ * driver: make sure we are in process context while trying to -+ * merge two bfq_queues. -+ */ -+ if (!in_interrupt()) { -+ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); -+ if (new_bfqq != NULL) { -+ if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq) -+ new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1); -+ /* -+ * Release the request's reference to the old bfqq -+ * and make sure one is taken to the shared queue. -+ */ -+ new_bfqq->allocated[rq_data_dir(rq)]++; -+ bfqq->allocated[rq_data_dir(rq)]--; -+ atomic_inc(&new_bfqq->ref); -+ bfq_put_queue(bfqq); -+ if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) -+ bfq_merge_bfqqs(bfqd, RQ_BIC(rq), -+ bfqq, new_bfqq); -+ rq->elv.priv[1] = new_bfqq; -+ bfqq = new_bfqq; -+ } else -+ bfq_bfqq_increase_failed_cooperations(bfqq); -+ } -+ - bfq_init_prio_data(bfqq, RQ_BIC(rq)); - - bfq_add_request(rq); - -+ /* -+ * Here a newly-created bfq_queue has already started a weight-raising -+ * period: clear raising_time_left to prevent bfq_bfqq_save_state() -+ * from assigning it a full weight-raising period. See the detailed -+ * comments about this field in bfq_init_icq(). -+ */ -+ if (bfqq->bic != NULL) -+ bfqq->bic->wr_time_left = 0; - rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]; - list_add_tail(&rq->queuelist, &bfqq->fifo); - -@@ -3228,18 +3536,6 @@ static void bfq_put_request(struct request *rq) - } - } - --static struct bfq_queue * --bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, -- struct bfq_queue *bfqq) --{ -- bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", -- (long unsigned)bfqq->new_bfqq->pid); -- bic_set_bfqq(bic, bfqq->new_bfqq, 1); -- bfq_mark_bfqq_coop(bfqq->new_bfqq); -- bfq_put_queue(bfqq); -- return bic_to_bfqq(bic, 1); --} -- - /* - * Returns NULL if a new bfqq should be allocated, or the old bfqq if this - * was the last process referring to said bfqq. -@@ -3248,6 +3544,9 @@ static struct bfq_queue * - bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) - { - bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); -+ -+ put_io_context(bic->icq.ioc); -+ - if (bfqq_process_refs(bfqq) == 1) { - bfqq->pid = current->pid; - bfq_clear_bfqq_coop(bfqq); -@@ -3276,6 +3575,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq, - struct bfq_queue *bfqq; - struct bfq_group *bfqg; - unsigned long flags; -+ bool split = false; - - might_sleep_if(gfp_mask & __GFP_WAIT); - -@@ -3293,25 +3593,26 @@ new_queue: - if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) { - bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask); - bic_set_bfqq(bic, bfqq, is_sync); -+ if (split && is_sync) { -+ if ((bic->was_in_burst_list && bfqd->large_burst) || -+ bic->saved_in_large_burst) -+ bfq_mark_bfqq_in_large_burst(bfqq); -+ else { -+ bfq_clear_bfqq_in_large_burst(bfqq); -+ if (bic->was_in_burst_list) -+ hlist_add_head(&bfqq->burst_list_node, -+ &bfqd->burst_list); -+ } -+ } - } else { -- /* -- * If the queue was seeky for too long, break it apart. -- */ -+ /* If the queue was seeky for too long, break it apart. */ - if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) { - bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq"); - bfqq = bfq_split_bfqq(bic, bfqq); -+ split = true; - if (!bfqq) - goto new_queue; - } -- -- /* -- * Check to see if this queue is scheduled to merge with -- * another closely cooperating queue. The merging of queues -- * happens here as it must be done in process context. -- * The reference on new_bfqq was taken in merge_bfqqs. -- */ -- if (bfqq->new_bfqq != NULL) -- bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq); - } - - bfqq->allocated[rw]++; -@@ -3322,6 +3623,26 @@ new_queue: - rq->elv.priv[0] = bic; - rq->elv.priv[1] = bfqq; - -+ /* -+ * If a bfq_queue has only one process reference, it is owned -+ * by only one bfq_io_cq: we can set the bic field of the -+ * bfq_queue to the address of that structure. Also, if the -+ * queue has just been split, mark a flag so that the -+ * information is available to the other scheduler hooks. -+ */ -+ if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { -+ bfqq->bic = bic; -+ if (split) { -+ bfq_mark_bfqq_just_split(bfqq); -+ /* -+ * If the queue has just been split from a shared -+ * queue, restore the idle window and the possible -+ * weight raising period. -+ */ -+ bfq_bfqq_resume_state(bfqq, bic); -+ } -+ } -+ - spin_unlock_irqrestore(q->queue_lock, flags); - - return 0; -diff --git a/block/bfq-sched.c b/block/bfq-sched.c -index 2931563..6764a7e 100644 ---- a/block/bfq-sched.c -+++ b/block/bfq-sched.c -@@ -1091,34 +1091,6 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) - return bfqq; - } - --/* -- * Forced extraction of the given queue. -- */ --static void bfq_get_next_queue_forced(struct bfq_data *bfqd, -- struct bfq_queue *bfqq) --{ -- struct bfq_entity *entity; -- struct bfq_sched_data *sd; -- -- BUG_ON(bfqd->in_service_queue != NULL); -- -- entity = &bfqq->entity; -- /* -- * Bubble up extraction/update from the leaf to the root. -- */ -- for_each_entity(entity) { -- sd = entity->sched_data; -- bfq_update_budget(entity); -- bfq_update_vtime(bfq_entity_service_tree(entity)); -- bfq_active_extract(bfq_entity_service_tree(entity), entity); -- sd->in_service_entity = entity; -- sd->next_in_service = NULL; -- entity->service = 0; -- } -- -- return; --} -- - static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) - { - if (bfqd->in_service_bic != NULL) { -diff --git a/block/bfq.h b/block/bfq.h -index 518f2ac..4f519ea 100644 ---- a/block/bfq.h -+++ b/block/bfq.h -@@ -218,18 +218,21 @@ struct bfq_group; - * idle @bfq_queue with no outstanding requests, then - * the task associated with the queue it is deemed as - * soft real-time (see the comments to the function -- * bfq_bfqq_softrt_next_start()). -+ * bfq_bfqq_softrt_next_start()) - * @last_idle_bklogged: time of the last transition of the @bfq_queue from - * idle to backlogged - * @service_from_backlogged: cumulative service received from the @bfq_queue - * since the last transition from idle to - * backlogged -+ * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the -+ * queue is shared - * -- * A bfq_queue is a leaf request queue; it can be associated with an io_context -- * or more, if it is async or shared between cooperating processes. @cgroup -- * holds a reference to the cgroup, to be sure that it does not disappear while -- * a bfqq still references it (mostly to avoid races between request issuing and -- * task migration followed by cgroup destruction). -+ * A bfq_queue is a leaf request queue; it can be associated with an -+ * io_context or more, if it is async or shared between cooperating -+ * processes. @cgroup holds a reference to the cgroup, to be sure that it -+ * does not disappear while a bfqq still references it (mostly to avoid -+ * races between request issuing and task migration followed by cgroup -+ * destruction). - * All the fields are protected by the queue lock of the containing bfqd. - */ - struct bfq_queue { -@@ -269,6 +272,7 @@ struct bfq_queue { - unsigned int requests_within_timer; - - pid_t pid; -+ struct bfq_io_cq *bic; - - /* weight-raising fields */ - unsigned long wr_cur_max_time; -@@ -298,12 +302,42 @@ struct bfq_ttime { - * @icq: associated io_cq structure - * @bfqq: array of two process queues, the sync and the async - * @ttime: associated @bfq_ttime struct -+ * @wr_time_left: snapshot of the time left before weight raising ends -+ * for the sync queue associated to this process; this -+ * snapshot is taken to remember this value while the weight -+ * raising is suspended because the queue is merged with a -+ * shared queue, and is used to set @raising_cur_max_time -+ * when the queue is split from the shared queue and its -+ * weight is raised again -+ * @saved_idle_window: same purpose as the previous field for the idle -+ * window -+ * @saved_IO_bound: same purpose as the previous two fields for the I/O -+ * bound classification of a queue -+ * @saved_in_large_burst: same purpose as the previous fields for the -+ * value of the field keeping the queue's belonging -+ * to a large burst -+ * @was_in_burst_list: true if the queue belonged to a burst list -+ * before its merge with another cooperating queue -+ * @cooperations: counter of consecutive successful queue merges underwent -+ * by any of the process' @bfq_queues -+ * @failed_cooperations: counter of consecutive failed queue merges of any -+ * of the process' @bfq_queues - */ - struct bfq_io_cq { - struct io_cq icq; /* must be the first member */ - struct bfq_queue *bfqq[2]; - struct bfq_ttime ttime; - int ioprio; -+ -+ unsigned int wr_time_left; -+ bool saved_idle_window; -+ bool saved_IO_bound; -+ -+ bool saved_in_large_burst; -+ bool was_in_burst_list; -+ -+ unsigned int cooperations; -+ unsigned int failed_cooperations; - }; - - enum bfq_device_speed { -@@ -539,7 +573,7 @@ enum bfqq_state_flags { - BFQ_BFQQ_FLAG_prio_changed, /* task priority has changed */ - BFQ_BFQQ_FLAG_sync, /* synchronous queue */ - BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */ -- BFQ_BFQQ_FLAG_IO_bound, /* -+ BFQ_BFQQ_FLAG_IO_bound, /* - * bfqq has timed-out at least once - * having consumed at most 2/10 of - * its budget -@@ -552,12 +586,13 @@ enum bfqq_state_flags { - * bfqq has proved to be slow and - * seeky until budget timeout - */ -- BFQ_BFQQ_FLAG_softrt_update, /* -+ BFQ_BFQQ_FLAG_softrt_update, /* - * may need softrt-next-start - * update - */ - BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ -- BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be splitted */ -+ BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be split */ -+ BFQ_BFQQ_FLAG_just_split, /* queue has just been split */ - }; - - #define BFQ_BFQQ_FNS(name) \ -@@ -587,6 +622,7 @@ BFQ_BFQQ_FNS(in_large_burst); - BFQ_BFQQ_FNS(constantly_seeky); - BFQ_BFQQ_FNS(coop); - BFQ_BFQQ_FNS(split_coop); -+BFQ_BFQQ_FNS(just_split); - BFQ_BFQQ_FNS(softrt_update); - #undef BFQ_BFQQ_FNS - --- -2.1.0 - diff --git a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch b/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch deleted file mode 100644 index c4efd06a..00000000 --- a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch +++ /dev/null @@ -1,402 +0,0 @@ -WARNING - this version of the patch works with version 4.9+ of gcc and with -kernel version 3.15.x+ and should NOT be applied when compiling on older -versions due to name changes of the flags with the 4.9 release of gcc. -Use the older version of this patch hosted on the same github for older -versions of gcc. For example: - -corei7 --> nehalem -corei7-avx --> sandybridge -core-avx-i --> ivybridge -core-avx2 --> haswell - -For more, see: https://gcc.gnu.org/gcc-4.9/changes.html - -It also changes 'atom' to 'bonnell' in accordance with the gcc v4.9 changes. -Note that upstream is using the deprecated 'match=atom' flags when I believe it -should use the newer 'march=bonnell' flag for atom processors. - -I have made that change to this patch set as well. See the following kernel -bug report to see if I'm right: https://bugzilla.kernel.org/show_bug.cgi?id=77461 - -This patch will expand the number of microarchitectures to include newer -processors including: AMD K10-family, AMD Family 10h (Barcelona), AMD Family -14h (Bobcat), AMD Family 15h (Bulldozer), AMD Family 15h (Piledriver), AMD -Family 16h (Jaguar), Intel 1st Gen Core i3/i5/i7 (Nehalem), Intel 1.5 Gen Core -i3/i5/i7 (Westmere), Intel 2nd Gen Core i3/i5/i7 (Sandybridge), Intel 3rd Gen -Core i3/i5/i7 (Ivybridge), Intel 4th Gen Core i3/i5/i7 (Haswell), Intel 5th -Gen Core i3/i5/i7 (Broadwell), and the low power Silvermont series of Atom -processors (Silvermont). It also offers the compiler the 'native' flag. - -Small but real speed increases are measurable using a make endpoint comparing -a generic kernel to one built with one of the respective microarchs. - -See the following experimental evidence supporting this statement: -https://github.com/graysky2/kernel_gcc_patch - -REQUIREMENTS -linux version >=3.15 -gcc version >=4.9 - ---- a/arch/x86/include/asm/module.h 2014-06-16 16:44:27.000000000 -0400 -+++ b/arch/x86/include/asm/module.h 2015-03-07 03:27:32.556672424 -0500 -@@ -15,6 +15,22 @@ - #define MODULE_PROC_FAMILY "586MMX " - #elif defined CONFIG_MCORE2 - #define MODULE_PROC_FAMILY "CORE2 " -+#elif defined CONFIG_MNATIVE -+#define MODULE_PROC_FAMILY "NATIVE " -+#elif defined CONFIG_MNEHALEM -+#define MODULE_PROC_FAMILY "NEHALEM " -+#elif defined CONFIG_MWESTMERE -+#define MODULE_PROC_FAMILY "WESTMERE " -+#elif defined CONFIG_MSILVERMONT -+#define MODULE_PROC_FAMILY "SILVERMONT " -+#elif defined CONFIG_MSANDYBRIDGE -+#define MODULE_PROC_FAMILY "SANDYBRIDGE " -+#elif defined CONFIG_MIVYBRIDGE -+#define MODULE_PROC_FAMILY "IVYBRIDGE " -+#elif defined CONFIG_MHASWELL -+#define MODULE_PROC_FAMILY "HASWELL " -+#elif defined CONFIG_MBROADWELL -+#define MODULE_PROC_FAMILY "BROADWELL " - #elif defined CONFIG_MATOM - #define MODULE_PROC_FAMILY "ATOM " - #elif defined CONFIG_M686 -@@ -33,6 +49,20 @@ - #define MODULE_PROC_FAMILY "K7 " - #elif defined CONFIG_MK8 - #define MODULE_PROC_FAMILY "K8 " -+#elif defined CONFIG_MK8SSE3 -+#define MODULE_PROC_FAMILY "K8SSE3 " -+#elif defined CONFIG_MK10 -+#define MODULE_PROC_FAMILY "K10 " -+#elif defined CONFIG_MBARCELONA -+#define MODULE_PROC_FAMILY "BARCELONA " -+#elif defined CONFIG_MBOBCAT -+#define MODULE_PROC_FAMILY "BOBCAT " -+#elif defined CONFIG_MBULLDOZER -+#define MODULE_PROC_FAMILY "BULLDOZER " -+#elif defined CONFIG_MPILEDRIVER -+#define MODULE_PROC_FAMILY "PILEDRIVER " -+#elif defined CONFIG_MJAGUAR -+#define MODULE_PROC_FAMILY "JAGUAR " - #elif defined CONFIG_MELAN - #define MODULE_PROC_FAMILY "ELAN " - #elif defined CONFIG_MCRUSOE ---- a/arch/x86/Kconfig.cpu 2014-06-16 16:44:27.000000000 -0400 -+++ b/arch/x86/Kconfig.cpu 2015-03-07 03:32:14.337713226 -0500 -@@ -137,9 +137,8 @@ config MPENTIUM4 - -Paxville - -Dempsey - -- - config MK6 -- bool "K6/K6-II/K6-III" -+ bool "AMD K6/K6-II/K6-III" - depends on X86_32 - ---help--- - Select this for an AMD K6-family processor. Enables use of -@@ -147,7 +146,7 @@ config MK6 - flags to GCC. - - config MK7 -- bool "Athlon/Duron/K7" -+ bool "AMD Athlon/Duron/K7" - depends on X86_32 - ---help--- - Select this for an AMD Athlon K7-family processor. Enables use of -@@ -155,12 +154,62 @@ config MK7 - flags to GCC. - - config MK8 -- bool "Opteron/Athlon64/Hammer/K8" -+ bool "AMD Opteron/Athlon64/Hammer/K8" - ---help--- - Select this for an AMD Opteron or Athlon64 Hammer-family processor. - Enables use of some extended instructions, and passes appropriate - optimization flags to GCC. - -+config MK8SSE3 -+ bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3" -+ ---help--- -+ Select this for improved AMD Opteron or Athlon64 Hammer-family processors. -+ Enables use of some extended instructions, and passes appropriate -+ optimization flags to GCC. -+ -+config MK10 -+ bool "AMD 61xx/7x50/PhenomX3/X4/II/K10" -+ ---help--- -+ Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50, -+ Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor. -+ Enables use of some extended instructions, and passes appropriate -+ optimization flags to GCC. -+ -+config MBARCELONA -+ bool "AMD Barcelona" -+ ---help--- -+ Select this for AMD Barcelona and newer processors. -+ -+ Enables -march=barcelona -+ -+config MBOBCAT -+ bool "AMD Bobcat" -+ ---help--- -+ Select this for AMD Bobcat processors. -+ -+ Enables -march=btver1 -+ -+config MBULLDOZER -+ bool "AMD Bulldozer" -+ ---help--- -+ Select this for AMD Bulldozer processors. -+ -+ Enables -march=bdver1 -+ -+config MPILEDRIVER -+ bool "AMD Piledriver" -+ ---help--- -+ Select this for AMD Piledriver processors. -+ -+ Enables -march=bdver2 -+ -+config MJAGUAR -+ bool "AMD Jaguar" -+ ---help--- -+ Select this for AMD Jaguar processors. -+ -+ Enables -march=btver2 -+ - config MCRUSOE - bool "Crusoe" - depends on X86_32 -@@ -251,8 +300,17 @@ config MPSC - using the cpu family field - in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. - -+config MATOM -+ bool "Intel Atom" -+ ---help--- -+ -+ Select this for the Intel Atom platform. Intel Atom CPUs have an -+ in-order pipelining architecture and thus can benefit from -+ accordingly optimized code. Use a recent GCC with specific Atom -+ support in order to fully benefit from selecting this option. -+ - config MCORE2 -- bool "Core 2/newer Xeon" -+ bool "Intel Core 2" - ---help--- - - Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and -@@ -260,14 +318,63 @@ config MCORE2 - family in /proc/cpuinfo. Newer ones have 6 and older ones 15 - (not a typo) - --config MATOM -- bool "Intel Atom" -+ Enables -march=core2 -+ -+config MNEHALEM -+ bool "Intel Nehalem" - ---help--- - -- Select this for the Intel Atom platform. Intel Atom CPUs have an -- in-order pipelining architecture and thus can benefit from -- accordingly optimized code. Use a recent GCC with specific Atom -- support in order to fully benefit from selecting this option. -+ Select this for 1st Gen Core processors in the Nehalem family. -+ -+ Enables -march=nehalem -+ -+config MWESTMERE -+ bool "Intel Westmere" -+ ---help--- -+ -+ Select this for the Intel Westmere formerly Nehalem-C family. -+ -+ Enables -march=westmere -+ -+config MSILVERMONT -+ bool "Intel Silvermont" -+ ---help--- -+ -+ Select this for the Intel Silvermont platform. -+ -+ Enables -march=silvermont -+ -+config MSANDYBRIDGE -+ bool "Intel Sandy Bridge" -+ ---help--- -+ -+ Select this for 2nd Gen Core processors in the Sandy Bridge family. -+ -+ Enables -march=sandybridge -+ -+config MIVYBRIDGE -+ bool "Intel Ivy Bridge" -+ ---help--- -+ -+ Select this for 3rd Gen Core processors in the Ivy Bridge family. -+ -+ Enables -march=ivybridge -+ -+config MHASWELL -+ bool "Intel Haswell" -+ ---help--- -+ -+ Select this for 4th Gen Core processors in the Haswell family. -+ -+ Enables -march=haswell -+ -+config MBROADWELL -+ bool "Intel Broadwell" -+ ---help--- -+ -+ Select this for 5th Gen Core processors in the Broadwell family. -+ -+ Enables -march=broadwell - - config GENERIC_CPU - bool "Generic-x86-64" -@@ -276,6 +383,19 @@ config GENERIC_CPU - Generic x86-64 CPU. - Run equally well on all x86-64 CPUs. - -+config MNATIVE -+ bool "Native optimizations autodetected by GCC" -+ ---help--- -+ -+ GCC 4.2 and above support -march=native, which automatically detects -+ the optimum settings to use based on your processor. -march=native -+ also detects and applies additional settings beyond -march specific -+ to your CPU, (eg. -msse4). Unless you have a specific reason not to -+ (e.g. distcc cross-compiling), you should probably be using -+ -march=native rather than anything listed below. -+ -+ Enables -march=native -+ - endchoice - - config X86_GENERIC -@@ -300,7 +420,7 @@ config X86_INTERNODE_CACHE_SHIFT - config X86_L1_CACHE_SHIFT - int - default "7" if MPENTIUM4 || MPSC -- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU -+ default "6" if MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || BROADWELL || MNATIVE || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU - default "4" if MELAN || M486 || MGEODEGX1 - default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - -@@ -331,11 +451,11 @@ config X86_ALIGNMENT_16 - - config X86_INTEL_USERCOPY - def_bool y -- depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 -+ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK8SSE3 || MK7 || MEFFICEON || MCORE2 || MK10 || MBARCELONA || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MNATIVE - - config X86_USE_PPRO_CHECKSUM - def_bool y -- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM -+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MATOM || MNATIVE - - config X86_USE_3DNOW - def_bool y -@@ -359,17 +479,17 @@ config X86_P6_NOP - - config X86_TSC - def_bool y -- depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 -+ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MNATIVE || MATOM) || X86_64 - - config X86_CMPXCHG64 - def_bool y -- depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM -+ depends on X86_PAE || X86_64 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM || MNATIVE - - # this should be set for all -march=.. options where the compiler - # generates cmov. - config X86_CMOV - def_bool y -- depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) -+ depends on (MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX) - - config X86_MINIMUM_CPU_FAMILY - int ---- a/arch/x86/Makefile 2014-06-16 16:44:27.000000000 -0400 -+++ b/arch/x86/Makefile 2015-03-07 03:33:27.650843211 -0500 -@@ -92,13 +92,35 @@ else - KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) - - # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) -+ cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) -+ cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-mtune=k8) -+ cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10) -+ cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona) -+ cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1) -+ cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1) -+ cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2) -+ cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2) - cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) - - cflags-$(CONFIG_MCORE2) += \ -- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) -- cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ -- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) -+ $(call cc-option,-march=core2,$(call cc-option,-mtune=core2)) -+ cflags-$(CONFIG_MNEHALEM) += \ -+ $(call cc-option,-march=nehalem,$(call cc-option,-mtune=nehalem)) -+ cflags-$(CONFIG_MWESTMERE) += \ -+ $(call cc-option,-march=westmere,$(call cc-option,-mtune=westmere)) -+ cflags-$(CONFIG_MSILVERMONT) += \ -+ $(call cc-option,-march=silvermont,$(call cc-option,-mtune=silvermont)) -+ cflags-$(CONFIG_MSANDYBRIDGE) += \ -+ $(call cc-option,-march=sandybridge,$(call cc-option,-mtune=sandybridge)) -+ cflags-$(CONFIG_MIVYBRIDGE) += \ -+ $(call cc-option,-march=ivybridge,$(call cc-option,-mtune=ivybridge)) -+ cflags-$(CONFIG_MHASWELL) += \ -+ $(call cc-option,-march=haswell,$(call cc-option,-mtune=haswell)) -+ cflags-$(CONFIG_MBROADWELL) += \ -+ $(call cc-option,-march=broadwell,$(call cc-option,-mtune=broadwell)) -+ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell) \ -+ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) - cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) - KBUILD_CFLAGS += $(cflags-y) - ---- a/arch/x86/Makefile_32.cpu 2014-06-16 16:44:27.000000000 -0400 -+++ b/arch/x86/Makefile_32.cpu 2015-03-07 03:34:15.203586024 -0500 -@@ -23,7 +23,15 @@ cflags-$(CONFIG_MK6) += -march=k6 - # Please note, that patches that add -march=athlon-xp and friends are pointless. - # They make zero difference whatsosever to performance at this time. - cflags-$(CONFIG_MK7) += -march=athlon -+cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -+cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-march=athlon) -+cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10,-march=athlon) -+cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona,-march=athlon) -+cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1,-march=athlon) -+cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1,-march=athlon) -+cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2,-march=athlon) -+cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2,-march=athlon) - cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 - cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 - cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) -@@ -32,8 +40,15 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc- - cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) - cflags-$(CONFIG_MVIAC7) += -march=i686 - cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) --cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ -- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) -+cflags-$(CONFIG_MNEHALEM) += -march=i686 $(call tune,nehalem) -+cflags-$(CONFIG_MWESTMERE) += -march=i686 $(call tune,westmere) -+cflags-$(CONFIG_MSILVERMONT) += -march=i686 $(call tune,silvermont) -+cflags-$(CONFIG_MSANDYBRIDGE) += -march=i686 $(call tune,sandybridge) -+cflags-$(CONFIG_MIVYBRIDGE) += -march=i686 $(call tune,ivybridge) -+cflags-$(CONFIG_MHASWELL) += -march=i686 $(call tune,haswell) -+cflags-$(CONFIG_MBROADWELL) += -march=i686 $(call tune,broadwell) -+cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell,$(call cc-option,-march=core2,-march=i686)) \ -+ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) - - # AMD Elan support - cflags-$(CONFIG_MELAN) += -march=i486 - -- cgit v1.2.3-65-gdbad