[ Upstream commit 663a50ceac75c2208d2ad95365bc8382fd42f44d ]

shadow mm's pin count got increased in workload preparation phase, which is after workload scanning. it will get decreased in complete_current_workload() anyway after workload completion. Sometimes, if a workload meets a scanning error, its shadow mm pin count will not get increased but will get decreased in the end. This patch lets shadow mm's pin count not go below 0.

Fixes: 2707e4446688 ("drm/i915/gvt: vGPU graphics memory virtualization") Cc: zhenyuw@linux.intel.com Cc: stable@vger.kernel.org #4.14+ Signed-off-by: Yan Zhao yan.y.zhao@intel.com Signed-off-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/gvt/gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index c7103dd2d8d5..563ab8590061 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1942,7 +1942,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) */ void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm) { - atomic_dec(&mm->pincount); + atomic_dec_if_positive(&mm->pincount); }

/**

[ Upstream commit b8e204006340b7aaf32bd2b9806c692f6e0cb38a ]

Add .release_ops, that is called in case of error at a later stage in the expression initialization path, ie. .select_ops() has been already set up operations and that needs to be undone. This allows us to unwind .select_ops from the error path, ie. release the dynamic operations for this extension.

Moreover, allocate one single operation instead of recycling them, this comes at the cost of consuming a bit more memory per rule, but it simplifies the infrastructure.

Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_tables.h | 3 + net/netfilter/nf_tables_api.c | 7 +- net/netfilter/nft_compat.c | 281 ++++++------------------------ 3 files changed, 64 insertions(+), 227 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3d58acf94dd2..0612439909dc 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -691,10 +691,12 @@ static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, gcb->elems[gcb->head.cnt++] = elem; }

+struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type * * @select_ops: function to select nft_expr_ops + * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present * @list: used internally * @name: Identifier @@ -707,6 +709,7 @@ static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); + void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; struct list_head list; const char *name; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e1724f9d8b9d..dc3670f2860e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2129,6 +2129,7 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, { struct nft_expr_info info; struct nft_expr *expr; + struct module *owner; int err;

err = nf_tables_expr_parse(ctx, nla, &info); @@ -2148,7 +2149,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err3: kfree(expr); err2: - module_put(info.ops->type->owner); + owner = info.ops->type->owner; + if (info.ops->type->release_ops) + info.ops->type->release_ops(info.ops); + + module_put(owner); err1: return ERR_PTR(err); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 0a4bad55a8aa..469f9da5073b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -22,23 +22,6 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> -#include <net/netns/generic.h> - -struct nft_xt { - struct list_head head; - struct nft_expr_ops ops; - refcount_t refcnt; - - /* used only when transaction mutex is locked */ - unsigned int listcnt; - - /* Unlike other expressions, ops doesn't have static storage duration. - * nft core assumes they do. We use kfree_rcu so that nft core can - * can check expr->ops->size even after nft_compat->destroy() frees - * the nft_xt struct that holds the ops structure. - */ - struct rcu_head rcu_head; -};

/* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -47,46 +30,6 @@ struct nft_xt_match_priv { void *info; };

-struct nft_compat_net { - struct list_head nft_target_list; - struct list_head nft_match_list; -}; - -static unsigned int nft_compat_net_id __read_mostly; -static struct nft_expr_type nft_match_type; -static struct nft_expr_type nft_target_type; - -static struct nft_compat_net *nft_compat_pernet(struct net *net) -{ - return net_generic(net, nft_compat_net_id); -} - -static void nft_xt_get(struct nft_xt *xt) -{ - /* refcount_inc() warns on 0 -> 1 transition, but we can't - * init the reference count to 1 in .select_ops -- we can't - * undo such an increase when another expression inside the same - * rule fails afterwards. - */ - if (xt->listcnt == 0) - refcount_set(&xt->refcnt, 1); - else - refcount_inc(&xt->refcnt); - - xt->listcnt++; -} - -static bool nft_xt_put(struct nft_xt *xt) -{ - if (refcount_dec_and_test(&xt->refcnt)) { - WARN_ON_ONCE(!list_empty(&xt->head)); - kfree_rcu(xt, rcu_head); - return true; - } - - return false; -} - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -281,7 +224,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -305,8 +247,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (!target->target) return -EINVAL;

- nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt_get(nft_xt); return 0; }

@@ -325,8 +265,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par);

- if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(me); + module_put(me); + kfree(expr->ops); }

static int nft_extension_dump_info(struct sk_buff *skb, int attr, @@ -499,7 +439,6 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -515,13 +454,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,

nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);

- ret = xt_check_match(&par, size, proto, inv); - if (ret < 0) - return ret; - - nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt_get(nft_xt); - return 0; + return xt_check_match(&par, size, proto, inv); }

static int @@ -564,8 +497,8 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, if (par.match->destroy != NULL) par.match->destroy(&par);

- if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(me); + module_put(me); + kfree(expr->ops); }

static void @@ -574,18 +507,6 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); }

-static void nft_compat_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - - if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { - if (--xt->listcnt == 0) - list_del_init(&xt->head); - } -} - static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -780,19 +701,13 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, };

-static bool nft_match_cmp(const struct xt_match *match, - const char *name, u32 rev, u32 family) -{ - return strcmp(match->name, name) == 0 && match->revision == rev && - (match->family == NFPROTO_UNSPEC || match->family == family); -} +static struct nft_expr_type nft_match_type;

static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_compat_net *cn; - struct nft_xt *nft_match; + struct nft_expr_ops *ops; struct xt_match *match; unsigned int matchsize; char *mt_name; @@ -808,16 +723,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family;

- cn = nft_compat_pernet(ctx->net); - - /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &cn->nft_match_list, head) { - struct xt_match *match = nft_match->ops.data; - - if (nft_match_cmp(match, mt_name, rev, family)) - return &nft_match->ops; - } - match = xt_request_find_match(family, mt_name, rev); if (IS_ERR(match)) return ERR_PTR(-ENOENT); @@ -827,65 +732,62 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; }

- /* This is the first time we use this match, allocate operations */ - nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_match == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; }

- refcount_set(&nft_match->refcnt, 0); - nft_match->ops.type = &nft_match_type; - nft_match->ops.eval = nft_match_eval; - nft_match->ops.init = nft_match_init; - nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.deactivate = nft_compat_deactivate; - nft_match->ops.dump = nft_match_dump; - nft_match->ops.validate = nft_match_validate; - nft_match->ops.data = match; + ops->type = &nft_match_type; + ops->eval = nft_match_eval; + ops->init = nft_match_init; + ops->destroy = nft_match_destroy; + ops->dump = nft_match_dump; + ops->validate = nft_match_validate; + ops->data = match;

matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); if (matchsize > NFT_MATCH_LARGE_THRESH) { matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv));

- nft_match->ops.eval = nft_match_large_eval; - nft_match->ops.init = nft_match_large_init; - nft_match->ops.destroy = nft_match_large_destroy; - nft_match->ops.dump = nft_match_large_dump; + ops->eval = nft_match_large_eval; + ops->init = nft_match_large_init; + ops->destroy = nft_match_large_destroy; + ops->dump = nft_match_large_dump; }

- nft_match->ops.size = matchsize; + ops->size = matchsize;

- nft_match->listcnt = 0; - list_add(&nft_match->head, &cn->nft_match_list); - - return &nft_match->ops; + return ops; err: module_put(match->me); return ERR_PTR(err); }

+static void nft_match_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_match *match = ops->data; + + module_put(match->me); + kfree(ops); +} + static struct nft_expr_type nft_match_type __read_mostly = { .name = "match", .select_ops = nft_match_select_ops, + .release_ops = nft_match_release_ops, .policy = nft_match_policy, .maxattr = NFTA_MATCH_MAX, .owner = THIS_MODULE, };

-static bool nft_target_cmp(const struct xt_target *tg, - const char *name, u32 rev, u32 family) -{ - return strcmp(tg->name, name) == 0 && tg->revision == rev && - (tg->family == NFPROTO_UNSPEC || tg->family == family); -} +static struct nft_expr_type nft_target_type;

static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_compat_net *cn; - struct nft_xt *nft_target; + struct nft_expr_ops *ops; struct xt_target *target; char *tg_name; u32 rev, family; @@ -905,18 +807,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL);

- cn = nft_compat_pernet(ctx->net); - /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &cn->nft_target_list, head) { - struct xt_target *target = nft_target->ops.data; - - if (!target->target) - continue; - - if (nft_target_cmp(target, tg_name, rev, family)) - return &nft_target->ops; - } - target = xt_request_find_target(family, tg_name, rev); if (IS_ERR(target)) return ERR_PTR(-ENOENT); @@ -931,113 +821,55 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; }

- /* This is the first time we use this target, allocate operations */ - nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_target == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; }

- refcount_set(&nft_target->refcnt, 0); - nft_target->ops.type = &nft_target_type; - nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); - nft_target->ops.init = nft_target_init; - nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.deactivate = nft_compat_deactivate; - nft_target->ops.dump = nft_target_dump; - nft_target->ops.validate = nft_target_validate; - nft_target->ops.data = target; + ops->type = &nft_target_type; + ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); + ops->init = nft_target_init; + ops->destroy = nft_target_destroy; + ops->dump = nft_target_dump; + ops->validate = nft_target_validate; + ops->data = target;

if (family == NFPROTO_BRIDGE) - nft_target->ops.eval = nft_target_eval_bridge; + ops->eval = nft_target_eval_bridge; else - nft_target->ops.eval = nft_target_eval_xt; - - nft_target->listcnt = 0; - list_add(&nft_target->head, &cn->nft_target_list); + ops->eval = nft_target_eval_xt;

- return &nft_target->ops; + return ops; err: module_put(target->me); return ERR_PTR(err); }

+static void nft_target_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_target *target = ops->data; + + module_put(target->me); + kfree(ops); +} + static struct nft_expr_type nft_target_type __read_mostly = { .name = "target", .select_ops = nft_target_select_ops, + .release_ops = nft_target_release_ops, .policy = nft_target_policy, .maxattr = NFTA_TARGET_MAX, .owner = THIS_MODULE, };

-static int __net_init nft_compat_init_net(struct net *net) -{ - struct nft_compat_net *cn = nft_compat_pernet(net); - - INIT_LIST_HEAD(&cn->nft_target_list); - INIT_LIST_HEAD(&cn->nft_match_list); - - return 0; -} - -static void __net_exit nft_compat_exit_net(struct net *net) -{ - struct nft_compat_net *cn = nft_compat_pernet(net); - struct nft_xt *xt, *next; - - if (list_empty(&cn->nft_match_list) && - list_empty(&cn->nft_target_list)) - return; - - /* If there was an error that caused nft_xt expr to not be initialized - * fully and noone else requested the same expression later, the lists - * contain 0-refcount entries that still hold module reference. - * - * Clean them here. - */ - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - list_del_init(&xt->head); - - if (refcount_read(&xt->refcnt)) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - list_del_init(&xt->head); - - if (refcount_read(&xt->refcnt)) - continue; - module_put(match->me); - kfree(xt); - } - mutex_unlock(&net->nft.commit_mutex); -} - -static struct pernet_operations nft_compat_net_ops = { - .init = nft_compat_init_net, - .exit = nft_compat_exit_net, - .id = &nft_compat_net_id, - .size = sizeof(struct nft_compat_net), -}; - static int __init nft_compat_module_init(void) { int ret;

- ret = register_pernet_subsys(&nft_compat_net_ops); - if (ret < 0) - goto err_target; - ret = nft_register_expr(&nft_match_type); if (ret < 0) - goto err_pernet; + return ret;

ret = nft_register_expr(&nft_target_type); if (ret < 0) @@ -1054,8 +886,6 @@ static int __init nft_compat_module_init(void) nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); -err_pernet: - unregister_pernet_subsys(&nft_compat_net_ops); return ret; }

@@ -1064,7 +894,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - unregister_pernet_subsys(&nft_compat_net_ops); }

MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);

[ Upstream commit b25a31bf0ca091aa8bdb9ab329b0226257568bbe ]

->release_ops() callback releases resources and this is used in error path. If nf_tables_newrule() fails after ->select_ops(), it should release resources. but it can not call ->destroy() because that should be called after ->init(). At this point, ->release_ops() should be used for releasing resources.

Test commands: modprobe -rv xt_tcpudp iptables-nft -I INPUT -m tcp <-- error command lsmod

Result: Module Size Used by xt_tcpudp 20480 2 <-- it should be 0

Fixes: b8e204006340 ("netfilter: nft_compat: use .release_ops and remove list of extension") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f20b904873c6..acb124ce92ec 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2753,8 +2753,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, nf_tables_rule_release(&ctx, rule); err1: for (i = 0; i < n; i++) { - if (info[i].ops != NULL) + if (info[i].ops) { module_put(info[i].ops->type->owner); + if (info[i].ops->type->release_ops) + info[i].ops->type->release_ops(info[i].ops); + } } kvfree(info); return err;

[ Upstream commit bbd669a868bba591ffd38b7bc75a7b361bb54b04 ]

Fix device initialization completion handling for vNIC adapters. Initialize the completion structure on probe and reinitialize when needed. This also fixes a race condition during kdump where the driver can attempt to access the completion struct before it is initialized:

Unable to handle kernel paging request for data at address 0x00000000 Faulting instruction address: 0xc0000000081acbe0 Oops: Kernel access of bad area, sig: 11 [#1] LE SMP NR_CPUS=2048 NUMA pSeries Modules linked in: ibmvnic(+) ibmveth sunrpc overlay squashfs loop CPU: 19 PID: 301 Comm: systemd-udevd Not tainted 4.18.0-64.el8.ppc64le #1 NIP: c0000000081acbe0 LR: c0000000081ad964 CTR: c0000000081ad900 REGS: c000000027f3f990 TRAP: 0300 Not tainted (4.18.0-64.el8.ppc64le) MSR: 800000010280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 28228288 XER: 00000006 CFAR: c000000008008934 DAR: 0000000000000000 DSISR: 40000000 IRQMASK: 1 GPR00: c0000000081ad964 c000000027f3fc10 c0000000095b5800 c0000000221b4e58 GPR04: 0000000000000003 0000000000000001 000049a086918581 00000000000000d4 GPR08: 0000000000000007 0000000000000000 ffffffffffffffe8 d0000000014dde28 GPR12: c0000000081ad900 c000000009a00c00 0000000000000001 0000000000000100 GPR16: 0000000000000038 0000000000000007 c0000000095e2230 0000000000000006 GPR20: 0000000000400140 0000000000000001 c00000000910c880 0000000000000000 GPR24: 0000000000000000 0000000000000006 0000000000000000 0000000000000003 GPR28: 0000000000000001 0000000000000001 c0000000221b4e60 c0000000221b4e58 NIP [c0000000081acbe0] __wake_up_locked+0x50/0x100 LR [c0000000081ad964] complete+0x64/0xa0 Call Trace: [c000000027f3fc10] [c000000027f3fc60] 0xc000000027f3fc60 (unreliable) [c000000027f3fc60] [c0000000081ad964] complete+0x64/0xa0 [c000000027f3fca0] [d0000000014dad58] ibmvnic_handle_crq+0xce0/0x1160 [ibmvnic] [c000000027f3fd50] [d0000000014db270] ibmvnic_tasklet+0x98/0x130 [ibmvnic] [c000000027f3fda0] [c00000000813f334] tasklet_action_common.isra.3+0xc4/0x1a0 [c000000027f3fe00] [c000000008cd13f4] __do_softirq+0x164/0x400 [c000000027f3fef0] [c00000000813ed64] irq_exit+0x184/0x1c0 [c000000027f3ff20] [c0000000080188e8] __do_irq+0xb8/0x210 [c000000027f3ff90] [c00000000802d0a4] call_do_irq+0x14/0x24 [c000000026a5b010] [c000000008018adc] do_IRQ+0x9c/0x130 [c000000026a5b060] [c000000008008ce4] hardware_interrupt_common+0x114/0x120

Signed-off-by: Thomas Falcon tlfalcon@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/ibm/ibmvnic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5ecbb1adcf3b..51cfe95f3e24 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1885,6 +1885,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, */ adapter->state = VNIC_PROBED;

+ reinit_completion(&adapter->init_done); rc = init_crq_queue(adapter); if (rc) { netdev_err(adapter->netdev, @@ -4625,7 +4626,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) old_num_rx_queues = adapter->req_rx_queues; old_num_tx_queues = adapter->req_tx_queues;

- init_completion(&adapter->init_done); + reinit_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -4680,7 +4681,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)

adapter->from_passive_init = false;

- init_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -4759,6 +4759,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset); INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); + init_completion(&adapter->init_done); adapter->resetting = false;

adapter->mac_change_pending = false;

[ Upstream commit ef0efcd3bd3fd0589732b67fb586ffd3c8705806 ]

At the beginning of ip6_fragment func, the prevhdr pointer is obtained in the ip6_find_1stfragopt func. However, all the pointers pointing into skb header may change when calling skb_checksum_help func with skb->ip_summed = CHECKSUM_PARTIAL condition. The prevhdr pointe will be dangling if it is not reloaded after calling __skb_linearize func in skb_checksum_help func.

Here, I add a variable, nexthdr_offset, to evaluate the offset, which does not changes even after calling __skb_linearize func.

Fixes: 405c92f7a541 ("ipv6: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment") Signed-off-by: Junwei Hu hujunwei4@huawei.com Reported-by: Wenhao Zhang zhangwenhao8@huawei.com Reported-by: syzbot+e8ce541d095e486074fc@syzkaller.appspotmail.com Reviewed-by: Zhiqiang Liu liuzhiqiang26@huawei.com Acked-by: Martin KaFai Lau kafai@fb.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5f9fa0302b5a..e71227390bec 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -595,7 +595,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; - unsigned int mtu, hlen, left, len; + unsigned int mtu, hlen, left, len, nexthdr_offset; int hroom, troom; __be32 frag_id; int ptr, offset = 0, err = 0; @@ -606,6 +606,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, goto fail; hlen = err; nexthdr = *prevhdr; + nexthdr_offset = prevhdr - skb_network_header(skb);

mtu = ip6_skb_dst_mtu(skb);

@@ -640,6 +641,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, (err = skb_checksum_help(skb))) goto fail;

+ prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb);

[ Upstream commit 3c446e6f96997f2a95bf0037ef463802162d2323 ]

When kcm is loaded while many processes try to create a KCM socket, a crash occurs: BUG: unable to handle kernel NULL pointer dereference at 000000000000000e IP: mutex_lock+0x27/0x40 kernel/locking/mutex.c:240 PGD 8000000016ef2067 P4D 8000000016ef2067 PUD 3d6e9067 PMD 0 Oops: 0002 [#1] SMP KASAN PTI CPU: 0 PID: 7005 Comm: syz-executor.5 Not tainted 4.12.14-396-default #1 SLE15-SP1 (unreleased) RIP: 0010:mutex_lock+0x27/0x40 kernel/locking/mutex.c:240 RSP: 0018:ffff88000d487a00 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 000000000000000e RCX: 1ffff100082b0719 ... CR2: 000000000000000e CR3: 000000004b1bc003 CR4: 0000000000060ef0 Call Trace: kcm_create+0x600/0xbf0 [kcm] __sock_create+0x324/0x750 net/socket.c:1272 ...

This is due to race between sock_create and unfinished register_pernet_device. kcm_create tries to do "net_generic(net, kcm_net_id)". but kcm_net_id is not initialized yet.

So switch the order of the two to close the race.

This can be reproduced with mutiple processes doing socket(PF_KCM, ...) and one process doing module removal.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reviewed-by: Michal Kubecek mkubecek@suse.cz Signed-off-by: Jiri Slaby jslaby@suse.cz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/kcm/kcmsock.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 571d824e4e24..b919db02c7f9 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -2054,14 +2054,14 @@ static int __init kcm_init(void) if (err) goto fail;

- err = sock_register(&kcm_family_ops); - if (err) - goto sock_register_fail; - err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail;

+ err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + err = kcm_proc_init(); if (err) goto proc_init_fail; @@ -2069,12 +2069,12 @@ static int __init kcm_init(void) return 0;

proc_init_fail: - unregister_pernet_device(&kcm_net_ops); - -net_ops_fail: sock_unregister(PF_KCM);

sock_register_fail: + unregister_pernet_device(&kcm_net_ops); + +net_ops_fail: proto_unregister(&kcm_proto);

fail: @@ -2090,8 +2090,8 @@ static int __init kcm_init(void) static void __exit kcm_exit(void) { kcm_proc_exit(); - unregister_pernet_device(&kcm_net_ops); sock_unregister(PF_KCM); + unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq);

[ Upstream commit 0ab03f353d3613ea49d1f924faf98559003670a8 ]

Currently we may merge incorrectly a received GSO packet or a packet with frag_list into a packet sitting in the gro_hash list. skb_segment() may crash case because the assumptions on the skb layout are not met. The correct behaviour would be to flush the packet in the gro_hash list and send the received GSO packet directly afterwards. Commit d61d072e87c8e ("net-gro: avoid reorders") sets NAPI_GRO_CB(skb)->flush in this case, but this is not checked before merging. This patch makes sure to check this flag and to not merge in that case.

Fixes: d61d072e87c8e ("net-gro: avoid reorders") Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2415d9cb9b89..ef2cd5712098 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3801,7 +3801,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int delta_truesize; struct sk_buff *lp;

- if (unlikely(p->len + len >= 65536)) + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG;

lp = NAPI_GRO_CB(p)->last;

[ Upstream commit 355b98553789b646ed97ad801a619ff898471b92 ]

net_hash_mix() currently uses kernel address of a struct net, and is used in many places that could be used to reveal this address to a patient attacker, thus defeating KASLR, for the typical case (initial net namespace, &init_net is not dynamically allocated)

I believe the original implementation tried to avoid spending too many cycles in this function, but security comes first.

Also provide entropy regardless of CONFIG_NET_NS.

Fixes: 0b4419162aa6 ("netns: introduce the net_hash_mix "salt" for hashes") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: Amit Klein aksecurity@gmail.com Reported-by: Benny Pinkas benny@pinkas.net Cc: Pavel Emelyanov xemul@openvz.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/net_namespace.h | 1 + include/net/netns/hash.h | 10 ++-------- net/core/net_namespace.c | 1 + 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 99d4148e0f90..1c3126c14930 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -58,6 +58,7 @@ struct net { */ spinlock_t rules_mod_lock;

+ u32 hash_mix; atomic64_t cookie_gen;

struct list_head list; /* list of network namespaces */ diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index 16a842456189..d9b665151f3d 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -2,16 +2,10 @@ #ifndef __NET_NS_HASH_H__ #define __NET_NS_HASH_H__

-#include <asm/cache.h> - -struct net; +#include <net/net_namespace.h>

static inline u32 net_hash_mix(const struct net *net) { -#ifdef CONFIG_NET_NS - return (u32)(((unsigned long)net) >> ilog2(sizeof(*net))); -#else - return 0; -#endif + return net->hash_mix; } #endif diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b02fb19df2cc..40c249c574c1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)

refcount_set(&net->count, 1); refcount_set(&net->passive, 1); + get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids);

[ Upstream commit fae2708174ae95d98d19f194e03d6e8f688ae195 ]

the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below:

# tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1

action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q

divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt

Add a TDC selftest to document that 'rate' is now being validated.

Reported-by: Matteo Croce mcroce@redhat.com Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Signed-off-by: Davide Caratti dcaratti@redhat.com Acked-by: Yotam Gigi yotam.gi@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/act_sample.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1a0c682fd734..fd62fe6c8e73 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -43,8 +43,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate; struct tc_sample *parm; - u32 psample_group_num; struct tcf_sample *s; bool exists = false; int ret, err; @@ -80,6 +80,12 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EEXIST; }

+ rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + if (!rate) { + NL_SET_ERR_MSG(extack, "invalid sample rate"); + tcf_idr_release(*a, bind); + return -EINVAL; + } psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { @@ -91,7 +97,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,

spin_lock_bh(&s->tcf_lock); s->tcf_action = parm->action; - s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + s->rate = rate; s->psample_group_num = psample_group_num; RCU_INIT_POINTER(s->psample_group, psample_group);

[ Upstream commit f28cd2af22a0c134e4aa1c64a70f70d815d473fb ]

The flow action buffer can be resized if it's not big enough to contain all the requested flow actions. However, this resize doesn't take into account the new requested size, the buffer is only increased by a factor of 2x. This might be not enough to contain the new data, causing a buffer overflow, for example:

[ 42.044472] ============================================================================= [ 42.045608] BUG kmalloc-96 (Not tainted): Redzone overwritten [ 42.046415] -----------------------------------------------------------------------------

[ 42.047715] Disabling lock debugging due to kernel taint [ 42.047716] INFO: 0x8bf2c4a5-0x720c0928. First byte 0x0 instead of 0xcc [ 42.048677] INFO: Slab 0xbc6d2040 objects=29 used=18 fp=0xdc07dec4 flags=0x2808101 [ 42.049743] INFO: Object 0xd53a3464 @offset=2528 fp=0xccdcdebb

[ 42.050747] Redzone 76f1b237: cc cc cc cc cc cc cc cc ........ [ 42.051839] Object d53a3464: 6b 6b 6b 6b 6b 6b 6b 6b 0c 00 00 00 6c 00 00 00 kkkkkkkk....l... [ 42.053015] Object f49a30cc: 6c 00 0c 00 00 00 00 00 00 00 00 03 78 a3 15 f6 l...........x... [ 42.054203] Object acfe4220: 20 00 02 00 ff ff ff ff 00 00 00 00 00 00 00 00 ............... [ 42.055370] Object 21024e91: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.056541] Object 070e04c3: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.057797] Object 948a777a: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [ 42.059061] Redzone 8bf2c4a5: 00 00 00 00 .... [ 42.060189] Padding a681b46e: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ

Fix by making sure the new buffer is properly resized to contain all the requested data.

BugLink: https://bugs.launchpad.net/bugs/1813244 Signed-off-by: Andrea Righi andrea.righi@canonical.com Acked-by: Pravin B Shelar pshelar@ovn.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/openvswitch/flow_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 691da853bef5..4bdf5e3ac208 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,

struct sw_flow_actions *acts; int new_acts_size; - int req_size = NLA_ALIGN(attr_len); + size_t req_size = NLA_ALIGN(attr_len); int next_offset = offsetof(struct sw_flow_actions, actions) + (*sfa)->actions_len;

if (req_size <= (ksize(*sfa) - next_offset)) goto out;

- new_acts_size = ksize(*sfa) * 2; + new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);

if (new_acts_size > MAX_ACTIONS_BUFSIZE) { if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {

[ Upstream commit b75bb8a5b755d0c7bf1ac071e4df2349a7644a1e ]

There's a significant number of reports that re-enabling ASPM causes different issues, ranging from decreased performance to system not booting at all. This affects only a minority of users, but the number of affected users is big enough that we better switch off ASPM again.

This will hurt notebook users who are not affected by the issues, they may see decreased battery runtime w/o ASPM. With the PCI core folks is being discussed to add generic sysfs attributes to control ASPM. Once this is in place brave enough users can re-enable ASPM on their system.

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/realtek/r8169.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index f55d177ae894..5adb00f521db 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -28,6 +28,7 @@ #include <linux/pm_runtime.h> #include <linux/firmware.h> #include <linux/prefetch.h> +#include <linux/pci-aspm.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h>

@@ -7224,6 +7225,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; }

+ /* Disable ASPM completely as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users. + */ + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) {

[ Upstream commit aecfde23108b8e637d9f5c5e523b24fb97035dc3 ]

RFC8257 §3.5 explicitly states that "A DCTCP sender MUST react to loss episodes in the same way as conventional TCP".

Currently, Linux DCTCP performs no cwnd reduction when losses are encountered. Optionally, the dctcp_clamp_alpha_on_loss resets alpha to its maximal value if a RTO happens. This behavior is sub-optimal for at least two reasons: i) it ignores losses triggering fast retransmissions; and ii) it causes unnecessary large cwnd reduction in the future if the loss was isolated as it resets the historical term of DCTCP's alpha EWMA to its maximal value (i.e., denoting a total congestion). The second reason has an especially noticeable effect when using DCTCP in high BDP environments, where alpha normally stays at low values.

This patch replace the clamping of alpha by setting ssthresh to half of cwnd for both fast retransmissions and RTOs, at most once per RTT. Consequently, the dctcp_clamp_alpha_on_loss module parameter has been removed.

The table below shows experimental results where we measured the drop probability of a PIE AQM (not applying ECN marks) at a bottleneck in the presence of a single TCP flow with either the alpha-clamping option enabled or the cwnd halving proposed by this patch. Results using reno or cubic are given for comparison.

| Link | RTT | Drop TCP CC | speed | base+AQM | probability ==================|=========|==========|============ CUBIC | 40Mbps | 7+20ms | 0.21% RENO | | | 0.19% DCTCP-CLAMP-ALPHA | | | 25.80% DCTCP-HALVE-CWND | | | 0.22% ------------------|---------|----------|------------ CUBIC | 100Mbps | 7+20ms | 0.03% RENO | | | 0.02% DCTCP-CLAMP-ALPHA | | | 23.30% DCTCP-HALVE-CWND | | | 0.04% ------------------|---------|----------|------------ CUBIC | 800Mbps | 1+1ms | 0.04% RENO | | | 0.05% DCTCP-CLAMP-ALPHA | | | 18.70% DCTCP-HALVE-CWND | | | 0.06%

We see that, without halving its cwnd for all source of losses, DCTCP drives the AQM to large drop probabilities in order to keep the queue length under control (i.e., it repeatedly faces RTOs). Instead, if DCTCP reacts to all source of losses, it can then be controlled by the AQM using similar drop levels than cubic or reno.

Signed-off-by: Koen De Schepper koen.de_schepper@nokia-bell-labs.com Signed-off-by: Olivier Tilmans olivier.tilmans@nokia-bell-labs.com Cc: Bob Briscoe research@bobbriscoe.net Cc: Lawrence Brakmo brakmo@fb.com Cc: Florian Westphal fw@strlen.de Cc: Daniel Borkmann borkmann@iogearbox.net Cc: Yuchung Cheng ycheng@google.com Cc: Neal Cardwell ncardwell@google.com Cc: Eric Dumazet edumazet@google.com Cc: Andrew Shewmaker agshew@gmail.com Cc: Glenn Judd glenn.judd@morganstanley.com Acked-by: Florian Westphal fw@strlen.de Acked-by: Neal Cardwell ncardwell@google.com Acked-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_dctcp.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index cd4814f7e962..359da68d7c06 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -67,11 +67,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");

-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly; -module_param(dctcp_clamp_alpha_on_loss, uint, 0644); -MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss, - "parameter for clamping alpha on loss"); - static struct tcp_congestion_ops dctcp_reno;

static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) @@ -164,21 +159,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) } }

-static void dctcp_state(struct sock *sk, u8 new_state) +static void dctcp_react_to_loss(struct sock *sk) { - if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) { - struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk);

- /* If this extension is enabled, we clamp dctcp_alpha to - * max on packet loss; the motivation is that dctcp_alpha - * is an indicator to the extend of congestion and packet - * loss is an indicator of extreme congestion; setting - * this in practice turned out to be beneficial, and - * effectively assumes total congestion which reduces the - * window by half. - */ - ca->dctcp_alpha = DCTCP_MAX_ALPHA; - } + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +static void dctcp_state(struct sock *sk, u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != inet_csk(sk)->icsk_ca_state) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ }

static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) @@ -190,6 +187,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; default: /* Don't care for the rest. */ break;

[ Upstream commit 8c83f2df9c6578ea4c5b940d8238ad8a41b87e9e ]

Configuration check to accept source route IP options should be made on the incoming netdevice when the skb->dev is an l3mdev master. The route lookup for the source route next hop also needs the incoming netdev.

v2->v3: - Simplify by passing the original netdevice down the stack (per David Ahern).

Signed-off-by: Stephen Suryaputra ssuryaextr@gmail.com Reviewed-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/ip.h | 2 +- net/ipv4/ip_input.c | 7 +++---- net/ipv4/ip_options.c | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h index be3cad9c2e4c..583526aad1d0 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -677,7 +677,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp, unsigned char __user *data, int optlen); void ip_options_undo(struct ip_options *opt); void ip_forward_options(struct sk_buff *skb); -int ip_options_rcv_srr(struct sk_buff *skb); +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);

/* * Functions provided by ip_sockglue.c diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1f4737b77067..ccf0d31b6ce5 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb) ip_local_deliver_finish); }

-static inline bool ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt; const struct iphdr *iph; - struct net_device *dev = skb->dev;

/* It looks as overkill, because not all IP options require packet mangling. @@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb) } }

- if (ip_options_rcv_srr(skb)) + if (ip_options_rcv_srr(skb, dev)) goto drop; }

@@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, } #endif

- if (iph->ihl > 5 && ip_rcv_options(skb)) + if (iph->ihl > 5 && ip_rcv_options(skb, dev)) goto drop;

rt = skb_rtable(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 32a35043c9f5..3db31bb9df50 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb) } }

-int ip_options_rcv_srr(struct sk_buff *skb) +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; @@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)

orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); + err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb);

[ Upstream commit 80a2a9026b24c6bd34b8d58256973e22270bedec ]

Refresh tirs is looping over a global list of tirs while netdevs are adding and removing tirs from that list. That is why a lock is required.

Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring") Signed-off-by: Yuval Avnery yuvalav@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 +++++++ include/linux/mlx5/driver.h | 2 ++ 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 8100786f6fb5..1539cf3de5dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, if (err) return err;

+ mutex_lock(&mdev->mlx5e_res.td.list_lock); list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock);

return 0; } @@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir) { + mutex_lock(&mdev->mlx5e_res.td.list_lock); mlx5_core_destroy_tir(mdev, tir->tirn); list_del(&tir->list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); }

static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, @@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) }

INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list); + mutex_init(&mdev->mlx5e_res.td.list_lock);

return 0;

@@ -159,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)

MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);

+ mutex_lock(&mdev->mlx5e_res.td.list_lock); list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in, inlen); @@ -170,6 +176,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); + mutex_unlock(&mdev->mlx5e_res.td.list_lock);

return err; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54299251d40d..4f001619f854 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -591,6 +591,8 @@ enum mlx5_pagefault_type_flags { };

struct mlx5_td { + /* protects tirs list changes while tirs refresh */ + struct mutex list_lock; struct list_head tirs_list; u32 tdn; };

[ Upstream commit c3e1f7fff69c78169c8ac40cc74ac4307f74e36d ]

NFP reprs are software device on top of the PF's vNIC. The comment above __dev_queue_xmit() sayeth:

When calling this method, interrupts MUST be enabled. This is because the BH enable code must have IRQs enabled so that it will not deadlock.

For netconsole we can't guarantee IRQ state, let's just disable netpoll on representors to be on the safe side.

When the initial implementation of NFP reprs was added by the commit 5de73ee46704 ("nfp: general representor implementation") .ndo_poll_controller was required for netpoll to be enabled.

Fixes: ac3d9dd034e5 ("netpoll: make ndo_poll_controller() optional") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Reviewed-by: John Hurley john.hurley@netronome.com Reviewed-by: Simon Horman simon.horman@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 7d62e3698f08..73db94e55fd0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -384,7 +384,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6); netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;

- netdev->priv_flags |= IFF_NO_QUEUE; + netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; netdev->features |= NETIF_F_LLTX;

if (nfp_app_has_tc(app)) {

[ Upstream commit 8e44e96c6c8e8fb80b84a2ca11798a8554f710f2 ]

If the RX completion indicates RX buffers errors, the RX ring will be disabled by firmware and no packets will be received on that ring from that point on. Recover by resetting the device.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 351417e74ae2..40ca339ec3df 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1610,11 +1610,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,

rx_buf->data = NULL; if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) { + u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2); + bnxt_reuse_rx_data(rxr, cons, data); if (agg_bufs) bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);

rc = -EIO; + if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) { + netdev_warn(bp->dev, "RX buffer error %x\n", rx_err); + bnxt_sched_reset(bp, rxr); + } goto next_rx; }

[ Upstream commit 2a3cabae4536edbcb21d344e7aa8be7a584d2afb ]

erspan_v6 tunnels run __iptunnel_pull_header on received skbs to remove erspan header. This can determine a possible use-after-free accessing pkt_md pointer in ip6erspan_rcv since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb (e.g if the packet has been sent though a veth device). Fix it resetting pkt_md pointer after __iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code") Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_gre.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 26f25b6e2833..438f1a5fd19a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -524,11 +524,10 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) return PACKET_REJECT; }

-static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, - struct tnl_ptk_info *tpi) +static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, + int gre_hdr_len) { struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; const struct ipv6hdr *ipv6h; struct erspan_md2 *md2; struct ip6_tnl *tunnel; @@ -547,18 +546,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT;

- ershdr = (struct erspan_base_hdr *)skb->data; - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) return PACKET_REJECT;

if (tunnel->parms.collect_md) { + struct erspan_metadata *pkt_md, *md; struct metadata_dst *tun_dst; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags;

@@ -571,6 +568,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, if (!tun_dst) return PACKET_REJECT;

+ /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; @@ -607,7 +612,7 @@ static int gre_rcv(struct sk_buff *skb)

if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { - if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD) + if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; }

[ Upstream commit 2ec1ed2aa68782b342458681aa4d16b65c9014d6 ]

When a bpf program is uploaded, the driver computes the number of xdp tx queues resulting in the allocation of additional qsets. Starting from commit '2ecbe4f4a027 ("net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs to private for each of them")' the driver runs link state polling for each VF resulting in the following NULL pointer dereference:

[ 56.169256] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 [ 56.178032] Mem abort info: [ 56.180834] ESR = 0x96000005 [ 56.183877] Exception class = DABT (current EL), IL = 32 bits [ 56.189792] SET = 0, FnV = 0 [ 56.192834] EA = 0, S1PTW = 0 [ 56.195963] Data abort info: [ 56.198831] ISV = 0, ISS = 0x00000005 [ 56.202662] CM = 0, WnR = 0 [ 56.205619] user pgtable: 64k pages, 48-bit VAs, pgdp = 0000000021f0c7a0 [ 56.212315] [0000000000000020] pgd=0000000000000000, pud=0000000000000000 [ 56.219094] Internal error: Oops: 96000005 [#1] SMP [ 56.260459] CPU: 39 PID: 2034 Comm: ip Not tainted 5.1.0-rc3+ #3 [ 56.266452] Hardware name: GIGABYTE R120-T33/MT30-GS1, BIOS T49 02/02/2018 [ 56.273315] pstate: 80000005 (Nzcv daif -PAN -UAO) [ 56.278098] pc : __ll_sc___cmpxchg_case_acq_64+0x4/0x20 [ 56.283312] lr : mutex_lock+0x2c/0x50 [ 56.286962] sp : ffff0000219af1b0 [ 56.290264] x29: ffff0000219af1b0 x28: ffff800f64de49a0 [ 56.295565] x27: 0000000000000000 x26: 0000000000000015 [ 56.300865] x25: 0000000000000000 x24: 0000000000000000 [ 56.306165] x23: 0000000000000000 x22: ffff000011117000 [ 56.311465] x21: ffff800f64dfc080 x20: 0000000000000020 [ 56.316766] x19: 0000000000000020 x18: 0000000000000001 [ 56.322066] x17: 0000000000000000 x16: ffff800f2e077080 [ 56.327367] x15: 0000000000000004 x14: 0000000000000000 [ 56.332667] x13: ffff000010964438 x12: 0000000000000002 [ 56.337967] x11: 0000000000000000 x10: 0000000000000c70 [ 56.343268] x9 : ffff0000219af120 x8 : ffff800f2e077d50 [ 56.348568] x7 : 0000000000000027 x6 : 000000062a9d6a84 [ 56.353869] x5 : 0000000000000000 x4 : ffff800f2e077480 [ 56.359169] x3 : 0000000000000008 x2 : ffff800f2e077080 [ 56.364469] x1 : 0000000000000000 x0 : 0000000000000020 [ 56.369770] Process ip (pid: 2034, stack limit = 0x00000000c862da3a) [ 56.376110] Call trace: [ 56.378546] __ll_sc___cmpxchg_case_acq_64+0x4/0x20 [ 56.383414] drain_workqueue+0x34/0x198 [ 56.387247] nicvf_open+0x48/0x9e8 [nicvf] [ 56.391334] nicvf_open+0x898/0x9e8 [nicvf] [ 56.395507] nicvf_xdp+0x1bc/0x238 [nicvf] [ 56.399595] dev_xdp_install+0x68/0x90 [ 56.403333] dev_change_xdp_fd+0xc8/0x240 [ 56.407333] do_setlink+0x8e0/0xbe8 [ 56.410810] __rtnl_newlink+0x5b8/0x6d8 [ 56.414634] rtnl_newlink+0x54/0x80 [ 56.418112] rtnetlink_rcv_msg+0x22c/0x2f8 [ 56.422199] netlink_rcv_skb+0x60/0x120 [ 56.426023] rtnetlink_rcv+0x28/0x38 [ 56.429587] netlink_unicast+0x1c8/0x258 [ 56.433498] netlink_sendmsg+0x1b4/0x350 [ 56.437410] sock_sendmsg+0x4c/0x68 [ 56.440887] ___sys_sendmsg+0x240/0x280 [ 56.444711] __sys_sendmsg+0x68/0xb0 [ 56.448275] __arm64_sys_sendmsg+0x2c/0x38 [ 56.452361] el0_svc_handler+0x9c/0x128 [ 56.456186] el0_svc+0x8/0xc [ 56.459056] Code: 35ffff91 2a1003e0 d65f03c0 f9800011 (c85ffc10) [ 56.465166] ---[ end trace 4a57fdc27b0a572c ]--- [ 56.469772] Kernel panic - not syncing: Fatal exception

Fix it by checking nicvf_rx_mode_wq pointer in nicvf_open and nicvf_stop

Fixes: 2ecbe4f4a027 ("net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs to private for each of them") Fixes: 2c632ad8bc74 ("net: thunderx: move link state polling function to VF") Reported-by: Matteo Croce mcroce@redhat.com Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Tested-by: Matteo Croce mcroce@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/cavium/thunder/nicvf_main.c | 20 +++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 503cfadff4ac..d4ee9f9c8c34 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1328,10 +1328,11 @@ int nicvf_stop(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; union nic_mbx mbx = {};

- cancel_delayed_work_sync(&nic->link_change_work); - /* wait till all queued set_rx_mode tasks completes */ - drain_workqueue(nic->nicvf_rx_mode_wq); + if (nic->nicvf_rx_mode_wq) { + cancel_delayed_work_sync(&nic->link_change_work); + drain_workqueue(nic->nicvf_rx_mode_wq); + }

mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; nicvf_send_msg_to_pf(nic, &mbx); @@ -1452,7 +1453,8 @@ int nicvf_open(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL;

/* wait till all queued set_rx_mode tasks completes if any */ - drain_workqueue(nic->nicvf_rx_mode_wq); + if (nic->nicvf_rx_mode_wq) + drain_workqueue(nic->nicvf_rx_mode_wq);

netif_carrier_off(netdev);

@@ -1550,10 +1552,12 @@ int nicvf_open(struct net_device *netdev) /* Send VF config done msg to PF */ nicvf_send_cfg_done(nic);

- INIT_DELAYED_WORK(&nic->link_change_work, - nicvf_link_status_check_task); - queue_delayed_work(nic->nicvf_rx_mode_wq, - &nic->link_change_work, 0); + if (nic->nicvf_rx_mode_wq) { + INIT_DELAYED_WORK(&nic->link_change_work, + nicvf_link_status_check_task); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 0); + }

return 0; cleanup:

[ Upstream commit 9a5a90d167b0e5fe3d47af16b68fd09ce64085cd ]

__netif_receive_skb_list_ptype() leaves skb->next poisoned before passing it to pt_prev->func handler, what may produce (in certain cases, e.g. DSA setup) crashes like:

[ 88.606777] CPU 0 Unable to handle kernel paging request at virtual address 0000000e, epc == 80687078, ra == 8052cc7c [ 88.618666] Oops[#1]: [ 88.621196] CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc2-dlink-00206-g4192a172-dirty #1473 [ 88.630885] $ 0 : 00000000 10000400 00000002 864d7850 [ 88.636709] $ 4 : 87c0ddf0 864d7800 87c0ddf0 00000000 [ 88.642526] $ 8 : 00000000 49600000 00000001 00000001 [ 88.648342] $12 : 00000000 c288617b dadbee27 25d17c41 [ 88.654159] $16 : 87c0ddf0 85cff080 80790000 fffffffd [ 88.659975] $20 : 80797b20 ffffffff 00000001 864d7800 [ 88.665793] $24 : 00000000 8011e658 [ 88.671609] $28 : 80790000 87c0dbc0 87cabf00 8052cc7c [ 88.677427] Hi : 00000003 [ 88.680622] Lo : 7b5b4220 [ 88.683840] epc : 80687078 vlan_dev_hard_start_xmit+0x1c/0x1a0 [ 88.690532] ra : 8052cc7c dev_hard_start_xmit+0xac/0x188 [ 88.696734] Status: 10000404 IEp [ 88.700422] Cause : 50000008 (ExcCode 02) [ 88.704874] BadVA : 0000000e [ 88.708069] PrId : 0001a120 (MIPS interAptiv (multi)) [ 88.713005] Modules linked in: [ 88.716407] Process swapper (pid: 0, threadinfo=(ptrval), task=(ptrval), tls=00000000) [ 88.725219] Stack : 85f61c28 00000000 0000000e 80780000 87c0ddf0 85cff080 80790000 8052cc7c [ 88.734529] 87cabf00 00000000 00000001 85f5fb40 807b0000 864d7850 87cabf00 807d0000 [ 88.743839] 864d7800 8655f600 00000000 85cff080 87c1c000 0000006a 00000000 8052d96c [ 88.753149] 807a0000 8057adb8 87c0dcc8 87c0dc50 85cfff08 00000558 87cabf00 85f58c50 [ 88.762460] 00000002 85f58c00 864d7800 80543308 fffffff4 00000001 85f58c00 864d7800 [ 88.771770] ... [ 88.774483] Call Trace: [ 88.777199] [<80687078>] vlan_dev_hard_start_xmit+0x1c/0x1a0 [ 88.783504] [<8052cc7c>] dev_hard_start_xmit+0xac/0x188 [ 88.789326] [<8052d96c>] __dev_queue_xmit+0x6e8/0x7d4 [ 88.794955] [<805a8640>] ip_finish_output2+0x238/0x4d0 [ 88.800677] [<805ab6a0>] ip_output+0xc8/0x140 [ 88.805526] [<805a68f4>] ip_forward+0x364/0x560 [ 88.810567] [<805a4ff8>] ip_rcv+0x48/0xe4 [ 88.815030] [<80528d44>] __netif_receive_skb_one_core+0x44/0x58 [ 88.821635] [<8067f220>] dsa_switch_rcv+0x108/0x1ac [ 88.827067] [<80528f80>] __netif_receive_skb_list_core+0x228/0x26c [ 88.833951] [<8052ed84>] netif_receive_skb_list+0x1d4/0x394 [ 88.840160] [<80355a88>] lunar_rx_poll+0x38c/0x828 [ 88.845496] [<8052fa78>] net_rx_action+0x14c/0x3cc [ 88.850835] [<806ad300>] __do_softirq+0x178/0x338 [ 88.856077] [<8012a2d4>] irq_exit+0xbc/0x100 [ 88.860846] [<802f8b70>] plat_irq_dispatch+0xc0/0x144 [ 88.866477] [<80105974>] handle_int+0x14c/0x158 [ 88.871516] [<806acfb0>] r4k_wait+0x30/0x40 [ 88.876462] Code: afb10014 8c8200a0 00803025 <9443000c> 94a20468 00000000 10620042 00a08025 9605046a [ 88.887332] [ 88.888982] ---[ end trace eb863d007da11cf1 ]--- [ 88.894122] Kernel panic - not syncing: Fatal exception in interrupt [ 88.901202] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fix this by pulling skb off the sublist and zeroing skb->next pointer before calling ptype callback.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup") Reviewed-by: Edward Cree ecree@solarflare.com Signed-off-by: Alexander Lobakin alobakin@dlink.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c index 5d03889502eb..12824e007e06 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5014,8 +5014,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, if (pt_prev->list_func != NULL) pt_prev->list_func(head, pt_prev, orig_dev); else - list_for_each_entry_safe(skb, next, head, list) + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + } }

static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)

[ Upstream commit 8e949363f017e2011464812a714fb29710fb95b4 ]

idr_find() can return a NULL value to 'flow' which is used without a check. The patch adds a check to avoid potential NULL pointer dereference.

In case of mlx5_fpga_sbu_conn_sendmsg() failure, free buf allocated using kzalloc.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines") Signed-off-by: Aditya Pakki pakki001@umn.edu Reviewed-by: Yuval Shaia yuval.shaia@oracle.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c index 5cf5f2a9d51f..8de64e88c670 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -217,15 +217,21 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, void *cmd; int ret;

+ rcu_read_lock(); + flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); + rcu_read_unlock(); + + if (!flow) { + WARN_ONCE(1, "Received NULL pointer for handle\n"); + return -EINVAL; + } + buf = kzalloc(size, GFP_ATOMIC); if (!buf) return -ENOMEM;

cmd = (buf + 1);

- rcu_read_lock(); - flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); - rcu_read_unlock(); mlx5_fpga_tls_flow_to_cmd(flow, cmd);

MLX5_SET(tls_cmd, cmd, swid, ntohl(handle)); @@ -238,6 +244,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, buf->complete = mlx_tls_kfree_complete;

ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf); + if (ret < 0) + kfree(buf);

return ret; }

[ Upstream commit e28408e98bced123038857b6e3c81fa12a2e3e68 ]

Set xon = xoff - netdev's max_mtu. netdev's max_mtu will give enough time for the pause frame to arrive at the sender.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration") Signed-off-by: Huy Nguyen huyn@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/en/port_buffer.c | 28 +++++++++++-------- 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index f00de0c987cd..4ab0d030b544 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -143,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) }

static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, - u32 xoff, unsigned int mtu) + u32 xoff, unsigned int max_mtu) { int i;

@@ -155,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, }

if (port_buffer->buffer[i].size < - (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) + (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) return -ENOMEM;

port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff; - port_buffer->buffer[i].xon = port_buffer->buffer[i].xoff - mtu; + port_buffer->buffer[i].xon = + port_buffer->buffer[i].xoff - max_mtu; }

return 0; @@ -167,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,

/** * update_buffer_lossy() - * mtu: device's MTU + * max_mtu: netdev's max_mtu * pfc_en: <input> current pfc configuration * buffer: <input> current prio to buffer mapping * xoff: <input> xoff value @@ -184,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * Return 0 if no error. * Set change to true if buffer configuration is modified. */ -static int update_buffer_lossy(unsigned int mtu, +static int update_buffer_lossy(unsigned int max_mtu, u8 pfc_en, u8 *buffer, u32 xoff, struct mlx5e_port_buffer *port_buffer, bool *change) @@ -221,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu, }

if (changed) { - err = update_xoff_threshold(port_buffer, xoff, mtu); + err = update_xoff_threshold(port_buffer, xoff, max_mtu); if (err) return err;

@@ -231,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu, return 0; }

+#define MINIMUM_MAX_MTU 9216 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u32 change, unsigned int mtu, struct ieee_pfc *pfc, @@ -242,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, bool update_prio2buffer = false; u8 buffer[MLX5E_MAX_PRIORITY]; bool update_buffer = false; + unsigned int max_mtu; u32 total_used = 0; u8 curr_pfc_en; int err; int i;

mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change); + max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);

err = mlx5e_port_query_buffer(priv, &port_buffer); if (err) @@ -255,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,

if (change & MLX5E_PORT_BUFFER_CABLE_LEN) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -265,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err;

- err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff, + err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, &port_buffer, &update_buffer); if (err) return err; @@ -277,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err;

- err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff, - &port_buffer, &update_buffer); + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, + xoff, &port_buffer, &update_buffer); if (err) return err; } @@ -302,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, return -EINVAL;

update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -310,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, /* Need to update buffer configuration if xoff value is changed */ if (!update_buffer && xoff != priv->dcbx.xoff) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; }

[ Upstream commit 5f074f3e192f10c9fade898b9b3b8812e3d83342 ]

A recent optimization in Clang (r355672) lowers comparisons of the return value of memcmp against zero to comparisons of the return value of bcmp against zero. This helps some platforms that implement bcmp more efficiently than memcmp. glibc simply aliases bcmp to memcmp, but an optimized implementation is in the works.

This results in linkage failures for all targets with Clang due to the undefined symbol. For now, just implement bcmp as a tailcail to memcmp to unbreak the build. This routine can be further optimized in the future.

Other ideas discussed:

* A weak alias was discussed, but breaks for architectures that define their own implementations of memcmp since aliases to declarations are not permitted (only definitions). Arch-specific memcmp implementations typically declare memcmp in C headers, but implement them in assembly.

* -ffreestanding also is used sporadically throughout the kernel.

* -fno-builtin-bcmp doesn't work when doing LTO.

Link: https://bugs.llvm.org/show_bug.cgi?id=41035 Link: https://code.woboq.org/userspace/glibc/string/memcmp.c.html#bcmp Link: https://github.com/llvm/llvm-project/commit/8e16d73346f8091461319a7dfc4ddd18... Link: https://github.com/ClangBuiltLinux/linux/issues/416 Link: http://lkml.kernel.org/r/20190313211335.165605-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Reported-by: Nathan Chancellor natechancellor@gmail.com Reported-by: Adhemerval Zanella adhemerval.zanella@linaro.org Suggested-by: Arnd Bergmann arnd@arndb.de Suggested-by: James Y Knight jyknight@google.com Suggested-by: Masahiro Yamada yamada.masahiro@socionext.com Suggested-by: Nathan Chancellor natechancellor@gmail.com Suggested-by: Rasmus Villemoes linux@rasmusvillemoes.dk Acked-by: Steven Rostedt (VMware) rostedt@goodmis.org Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Masahiro Yamada yamada.masahiro@socionext.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: David Laight David.Laight@ACULAB.COM Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Namhyung Kim namhyung@kernel.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Dan Williams dan.j.williams@intel.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/string.h | 3 +++ lib/string.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+)

diff --git a/include/linux/string.h b/include/linux/string.h index 7927b875f80c..6ab0a6fa512e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -150,6 +150,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/lib/string.c b/lib/string.c index 38e4ca08e757..3ab861c1a857 100644 --- a/lib/string.c +++ b/lib/string.c @@ -866,6 +866,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count) EXPORT_SYMBOL(memcmp); #endif

+#ifndef __HAVE_ARCH_BCMP +/** + * bcmp - returns 0 if and only if the buffers have identical contents. + * @a: pointer to first buffer. + * @b: pointer to second buffer. + * @len: size of buffers. + * + * The sign or magnitude of a non-zero return value has no particular + * meaning, and architectures may implement their own more efficient bcmp(). So + * while this particular implementation is a simple (tail) call to memcmp, do + * not rely on anything but whether the return value is zero or non-zero. + */ +#undef bcmp +int bcmp(const void *a, const void *b, size_t len) +{ + return memcmp(a, b, len); +} +EXPORT_SYMBOL(bcmp); +#endif + #ifndef __HAVE_ARCH_MEMSCAN /** * memscan - Find a character in an area of memory.

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

commit c7084edc3f6d67750f50d4183134c4fb5712a5c8 upstream.

The n_r3964 line discipline driver was written in a different time, when SMP machines were rare, and users were trusted to do the right thing. Since then, the world has moved on but not this code, it has stayed rooted in the past with its lovely hand-crafted list structures and loads of "interesting" race conditions all over the place.

After attempting to clean up most of the issues, I just gave up and am now marking the driver as BROKEN so that hopefully someone who has this hardware will show up out of the woodwork (I know you are out there!) and will help with debugging a raft of changes that I had laying around for the code, but was too afraid to commit as odds are they would break things.

Many thanks to Jann and Linus for pointing out the initial problems in this codebase, as well as many reviews of my attempts to fix the issues. It was a case of whack-a-mole, and as you can see, the mole won.

Reported-by: Jann Horn jannh@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org

--- drivers/char/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -351,7 +351,7 @@ config XILINX_HWICAP

config R3964 tristate "Siemens R3964 line discipline" - depends on TTY + depends on TTY && BROKEN ---help--- This driver allows synchronous communication with devices using the Siemens R3964 packet protocol. Unless you are dealing with special

From: Axel Lin axel.lin@ingics.com

commit a165dcc923ada2ffdee1d4f41f12f81b66d04c55 upstream.

Select REGMAP_I2C to avoid below build error: ERROR: "__devm_regmap_init_i2c" [drivers/hwmon/w83773g.ko] undefined!

Fixes: ee249f271524 ("hwmon: Add W83773G driver") Cc: stable@vger.kernel.org Signed-off-by: Axel Lin axel.lin@ingics.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hwmon/Kconfig | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1759,6 +1759,7 @@ config SENSORS_VT8231 config SENSORS_W83773G tristate "Nuvoton W83773G" depends on I2C + select REGMAP_I2C help If you say yes here you get support for the Nuvoton W83773G hardware monitoring chip.

From: Steve French stfrench@microsoft.com

commit ca567eb2b3f014d5be0f44c6f68b01a522f15ca4 upstream.

Reconnecting after server or network failure can be improved (to maintain availability and protect data integrity) by allowing the client to choose the default persistent (or resilient) handle timeout in some use cases. Today we default to 0 which lets the server pick the default timeout (usually 120 seconds) but this can be problematic for some workloads. Add the new mount parameter to cifs.ko for SMB3 mounts "handletimeout" which enables the user to override the default handle timeout for persistent (mount option "persistenthandles") or resilient handles (mount option "resilienthandles"). Maximum allowed is 16 minutes (960000 ms). Units for the timeout are expressed in milliseconds. See section 2.2.14.2.12 and 2.2.31.3 of the MS-SMB2 protocol specification for more information.

Signed-off-by: Steve French stfrench@microsoft.com Reviewed-by: Pavel Shilovsky pshilov@microsoft.com Reviewed-by: Ronnie Sahlberg lsahlber@redhat.com CC: Stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/cifs/cifsfs.c | 2 ++ fs/cifs/cifsglob.h | 8 ++++++++ fs/cifs/connect.c | 30 +++++++++++++++++++++++++++++- fs/cifs/smb2file.c | 4 +++- fs/cifs/smb2pdu.c | 14 +++++++++++--- 5 files changed, 53 insertions(+), 5 deletions(-)

--- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -559,6 +559,8 @@ cifs_show_options(struct seq_file *s, st tcon->ses->server->echo_interval / HZ); if (tcon->snapshot_time) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); + if (tcon->handle_timeout) + seq_printf(s, ",handletimeout=%u", tcon->handle_timeout); /* convert actimeo and display it in seconds */ seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);

--- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -60,6 +60,12 @@ #define CIFS_MAX_ACTIMEO (1 << 30)

/* + * Max persistent and resilient handle timeout (milliseconds). + * Windows durable max was 960000 (16 minutes) + */ +#define SMB3_MAX_HANDLE_TIMEOUT 960000 + +/* * MAX_REQ is the maximum number of requests that WE will send * on one socket concurrently. */ @@ -572,6 +578,7 @@ struct smb_vol { struct nls_table *local_nls; unsigned int echo_interval; /* echo interval in secs */ __u64 snapshot_time; /* needed for timewarp tokens */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */ };

@@ -1028,6 +1035,7 @@ struct cifs_tcon { __u32 vol_serial_number; __le64 vol_create_time; __u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ __u32 ss_flags; /* sector size flags */ __u32 perf_sector_size; /* best sector size for perf */ __u32 max_chunks; --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -103,7 +103,7 @@ enum { Opt_cruid, Opt_gid, Opt_file_mode, Opt_dirmode, Opt_port, Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo, - Opt_echo_interval, Opt_max_credits, + Opt_echo_interval, Opt_max_credits, Opt_handletimeout, Opt_snapshot,

/* Mount options which take string value */ @@ -208,6 +208,7 @@ static const match_table_t cifs_mount_op { Opt_rsize, "rsize=%s" }, { Opt_wsize, "wsize=%s" }, { Opt_actimeo, "actimeo=%s" }, + { Opt_handletimeout, "handletimeout=%s" }, { Opt_echo_interval, "echo_interval=%s" }, { Opt_max_credits, "max_credits=%s" }, { Opt_snapshot, "snapshot=%s" }, @@ -1600,6 +1601,9 @@ cifs_parse_mount_options(const char *mou

vol->actimeo = CIFS_DEF_ACTIMEO;

+ /* Most clients set timeout to 0, allows server to use its default */ + vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ + /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ vol->ops = &smb30_operations; vol->vals = &smbdefault_values; @@ -1998,6 +2002,18 @@ cifs_parse_mount_options(const char *mou goto cifs_parse_mount_err; } break; + case Opt_handletimeout: + if (get_option_ul(args, &option)) { + cifs_dbg(VFS, "%s: Invalid handletimeout value\n", + __func__); + goto cifs_parse_mount_err; + } + vol->handle_timeout = option; + if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) { + cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n"); + goto cifs_parse_mount_err; + } + break; case Opt_echo_interval: if (get_option_ul(args, &option)) { cifs_dbg(VFS, "%s: Invalid echo interval value\n", @@ -3164,6 +3180,8 @@ static int match_tcon(struct cifs_tcon * return 0; if (tcon->snapshot_time != volume_info->snapshot_time) return 0; + if (tcon->handle_timeout != volume_info->handle_timeout) + return 0; return 1; }

@@ -3278,6 +3296,16 @@ cifs_get_tcon(struct cifs_ses *ses, stru tcon->snapshot_time = volume_info->snapshot_time; }

+ if (volume_info->handle_timeout) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "Use SMB2.1 or later for handle timeout option\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else + tcon->handle_timeout = volume_info->handle_timeout; + } + tcon->ses = ses; if (volume_info->password) { tcon->password = kstrdup(volume_info->password, GFP_KERNEL); --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -68,7 +68,9 @@ smb2_open_file(const unsigned int xid, s

if (oparms->tcon->use_resilient) { - nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + /* default timeout is 0, servers pick default (120 seconds) */ + nr_ioctl_req.Timeout = + cpu_to_le32(oparms->tcon->handle_timeout); nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1837,8 +1837,9 @@ add_lease_context(struct TCP_Server_Info }

static struct create_durable_v2 * -create_durable_v2_buf(struct cifs_fid *pfid) +create_durable_v2_buf(struct cifs_open_parms *oparms) { + struct cifs_fid *pfid = oparms->fid; struct create_durable_v2 *buf;

buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); @@ -1852,7 +1853,14 @@ create_durable_v2_buf(struct cifs_fid *p (struct create_durable_v2, Name)); buf->ccontext.NameLength = cpu_to_le16(4);

- buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + /* + * NB: Handle timeout defaults to 0, which allows server to choose + * (most servers default to 120 seconds) and most clients default to 0. + * This can be overridden at mount ("handletimeout=") if the user wants + * a different persistent (or resilient) handle timeout for all opens + * opens on a particular SMB3 mount. + */ + buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); generate_random_uuid(buf->dcontext.CreateGuid); memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); @@ -1905,7 +1913,7 @@ add_durable_v2_context(struct kvec *iov, struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec;

- iov[num].iov_base = create_durable_v2_buf(oparms->fid); + iov[num].iov_base = create_durable_v2_buf(oparms); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2);

From: Furquan Shaikh furquan@google.com

commit c8b1917c8987a6fa3695d479b4d60fbbbc3e537b upstream.

Commit 18996f2db918 ("ACPICA: Events: Stop unconditionally clearing ACPI IRQs during suspend/resume") was added to stop clearing event status bits unconditionally in the system-wide suspend and resume paths. This was done because of an issue with a laptop lid appaering to be closed even when it was used to wake up the system from suspend (see https://bugzilla.kernel.org/show_bug.cgi?id=196249), which happened because event status bits were cleared unconditionally on system resume. Though this change fixed the issue in the resume path, it introduced regressions in a few suspend paths.

First regression was reported and fixed in the S5 entry path by commit fa85015c0d95 ("ACPICA: Clear status of all events when entering S5"). Next regression was reported and fixed for all legacy sleep paths by commit f317c7dc12b7 ("ACPICA: Clear status of all events when entering sleep states"). However, there still is a suspend-to-idle regression, since suspend-to-idle does not follow the legacy sleep paths.

In the suspend-to-idle case, wakeup is enabled as part of device suspend. If the status bits of wakeup GPEs are set when they are enabled, it causes a premature system wakeup to occur.

To address that problem, partially revert commit 18996f2db918 to restore GPE status bits clearing before the GPE is enabled in acpi_ev_enable_gpe().

Fixes: 18996f2db918 ("ACPICA: Events: Stop unconditionally clearing ACPI IRQs during suspend/resume") Signed-off-by: Furquan Shaikh furquan@google.com Cc: 4.17+ stable@vger.kernel.org # 4.17+ [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/acpi/acpica/evgpe.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -81,8 +81,12 @@ acpi_status acpi_ev_enable_gpe(struct ac

ACPI_FUNCTION_TRACE(ev_enable_gpe);

- /* Enable the requested GPE */ + /* Clear the GPE status */ + status = acpi_hw_clear_gpe(gpe_event_info); + if (ACPI_FAILURE(status)) + return_ACPI_STATUS(status);

+ /* Enable the requested GPE */ status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE); return_ACPI_STATUS(status); }

From: Zubin Mithra zsm@chromium.org

commit 212ac181c158c09038c474ba68068be49caecebb upstream.

When ioctl calls are made with non-null-terminated userspace strings, strlcpy causes an OOB-read from within strlen. Fix by changing to use strscpy instead.

Signed-off-by: Zubin Mithra zsm@chromium.org Reviewed-by: Guenter Roeck groeck@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/seq/seq_clientmgr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1252,7 +1252,7 @@ static int snd_seq_ioctl_set_client_info

/* fill the info fields */ if (client_info->name[0]) - strlcpy(client->name, client_info->name, sizeof(client->name)); + strscpy(client->name, client_info->name, sizeof(client->name));

client->filter = client_info->filter; client->event_lost = client_info->event_lost; @@ -1530,7 +1530,7 @@ static int snd_seq_ioctl_create_queue(st /* set queue name */ if (!info->name[0]) snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue); - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); snd_use_lock_free(&q->use_lock);

return 0; @@ -1592,7 +1592,7 @@ static int snd_seq_ioctl_set_queue_info( queuefree(q); return -EPERM; } - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); queuefree(q);

return 0;

From: Richard Sailer rs@tuxedocomputers.com

commit 80690a276f444a68a332136d98bfea1c338bc263 upstream.

This adds a SND_PCI_QUIRK(...) line for the Tuxedo XC 1509.

The Tuxedo XC 1509 and the System76 oryp5 are the same barebone notebooks manufactured by Clevo. To name the fixups both use after the actual underlying hardware, this patch also changes System76_orpy5 to clevo_pb51ed in 2 enum symbols and one function name, matching the other pci_quirk entries which are also named after the device ODM.

Fixes: 7f665b1c3283 ("ALSA: hda/realtek - Headset microphone and internal speaker support for System76 oryp5") Signed-off-by: Richard Sailer rs@tuxedocomputers.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_realtek.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1864,8 +1864,8 @@ enum { ALC887_FIXUP_BASS_CHMAP, ALC1220_FIXUP_GB_DUAL_CODECS, ALC1220_FIXUP_CLEVO_P950, - ALC1220_FIXUP_SYSTEM76_ORYP5, - ALC1220_FIXUP_SYSTEM76_ORYP5_PINS, + ALC1220_FIXUP_CLEVO_PB51ED, + ALC1220_FIXUP_CLEVO_PB51ED_PINS, };

static void alc889_fixup_coef(struct hda_codec *codec, @@ -2070,7 +2070,7 @@ static void alc1220_fixup_clevo_p950(str static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec, const struct hda_fixup *fix, int action);

-static void alc1220_fixup_system76_oryp5(struct hda_codec *codec, +static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -2322,18 +2322,18 @@ static const struct hda_fixup alc882_fix .type = HDA_FIXUP_FUNC, .v.func = alc1220_fixup_clevo_p950, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5] = { + [ALC1220_FIXUP_CLEVO_PB51ED] = { .type = HDA_FIXUP_FUNC, - .v.func = alc1220_fixup_system76_oryp5, + .v.func = alc1220_fixup_clevo_pb51ed, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = { + [ALC1220_FIXUP_CLEVO_PB51ED_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ {} }, .chained = true, - .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5, + .chain_id = ALC1220_FIXUP_CLEVO_PB51ED, }, };

@@ -2411,8 +2411,9 @@ static const struct snd_pci_quirk alc882 SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), - SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), - SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), + SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d1, "Tuxedo Book XC1509", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),

From: Hui Wang hui.wang@canonical.com

commit cae30527901d9590db0e12ace994c1d58bea87fd upstream.

Recently we set CONFIG_SND_HDA_POWER_SAVE_DEFAULT to 1 when configuring the kernel, then two machines were reported to have noise after installing the new kernel. Put them in the blacklist, the noise disappears.

https://bugs.launchpad.net/bugs/1821663 Cc: stable@vger.kernel.org Signed-off-by: Hui Wang hui.wang@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/hda_intel.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2142,6 +2142,8 @@ static struct snd_pci_quirk power_save_b SND_PCI_QUIRK(0x8086, 0x2040, "Intel DZ77BH-55K", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=199607 */ SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0), + /* https://bugs.launchpad.net/bugs/1821663 */ + SND_PCI_QUIRK(0x8086, 0x2064, "Intel SDP 8086:2064", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */ SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ @@ -2150,6 +2152,8 @@ static struct snd_pci_quirk power_save_b SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0), + /* https://bugs.launchpad.net/bugs/1821663 */ + SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0), {} }; #endif /* CONFIG_PM */

From: Peter Geis pgwipeout@gmail.com

commit 09f91381fa5de1d44bc323d8bf345f5d57b3d9b5 upstream.

Various rk3328 based boards experience occasional sdmmc0 write errors. This is due to the rk3328.dtsi tx drive levels being set to 4ma, vs 8ma per the rk3328 datasheet default settings.

Fix this by setting the tx signal pins to 8ma. Inspiration from tonymac32's patch, https://github.com/ayufan-rock64/linux-kernel/commit/dc1212b347e0da17c5460bc...

Fixes issues on the rk3328-roc-cc and the rk3328-rock64 (as per the above commit message).

Tested on the rk3328-roc-cc board.

Fixes: 52e02d377a72 ("arm64: dts: rockchip: add core dtsi file for RK3328 SoCs") Cc: stable@vger.kernel.org Signed-off-by: Peter Geis pgwipeout@gmail.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328.dtsi | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1431,11 +1431,11 @@

sdmmc0 { sdmmc0_clk: sdmmc0-clk { - rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>; + rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>; };

sdmmc0_cmd: sdmmc0-cmd { - rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>; };

sdmmc0_dectn: sdmmc0-dectn { @@ -1447,14 +1447,14 @@ };

sdmmc0_bus1: sdmmc0-bus1 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>; };

sdmmc0_bus4: sdmmc0-bus4 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>, - <1 RK_PA1 1 &pcfg_pull_up_4ma>, - <1 RK_PA2 1 &pcfg_pull_up_4ma>, - <1 RK_PA3 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>, + <1 RK_PA1 1 &pcfg_pull_up_8ma>, + <1 RK_PA2 1 &pcfg_pull_up_8ma>, + <1 RK_PA3 1 &pcfg_pull_up_8ma>; };

sdmmc0_gpio: sdmmc0-gpio {

From: Faiz Abbas faiz_abbas@ti.com

commit 5c41ea6d52003b5bc77c2a82fd5ca7d480237d89 upstream.

commit 5b0d62108b46 ("mmc: sdhci-omap: Add platform specific reset callback") skips data resets during tuning operation. Because of this, a data error or data finish interrupt might still arrive after a command error has been handled and the mrq ended. This ends up with a "mmc0: Got data interrupt 0x00000002 even though no data operation was in progress" error message.

Fix this by adding a platform specific callback for sdhci_irq. Mark the mrq as a failure but wait for a data interrupt instead of calling finish_mrq().

Fixes: 5b0d62108b46 ("mmc: sdhci-omap: Add platform specific reset callback") Signed-off-by: Faiz Abbas faiz_abbas@ti.com Acked-by: Adrian Hunter adrian.hunter@intel.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/sdhci-omap.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+)

--- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -797,6 +797,43 @@ void sdhci_omap_reset(struct sdhci_host sdhci_reset(host, mask); }

+#define CMD_ERR_MASK (SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX |\ + SDHCI_INT_TIMEOUT) +#define CMD_MASK (CMD_ERR_MASK | SDHCI_INT_RESPONSE) + +static u32 sdhci_omap_irq(struct sdhci_host *host, u32 intmask) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host); + + if (omap_host->is_tuning && host->cmd && !host->data_early && + (intmask & CMD_ERR_MASK)) { + + /* + * Since we are not resetting data lines during tuning + * operation, data error or data complete interrupts + * might still arrive. Mark this request as a failure + * but still wait for the data interrupt + */ + if (intmask & SDHCI_INT_TIMEOUT) + host->cmd->error = -ETIMEDOUT; + else + host->cmd->error = -EILSEQ; + + host->cmd = NULL; + + /* + * Sometimes command error interrupts and command complete + * interrupt will arrive together. Clear all command related + * interrupts here. + */ + sdhci_writel(host, intmask & CMD_MASK, SDHCI_INT_STATUS); + intmask &= ~CMD_MASK; + } + + return intmask; +} + static struct sdhci_ops sdhci_omap_ops = { .set_clock = sdhci_omap_set_clock, .set_power = sdhci_omap_set_power, @@ -807,6 +844,7 @@ static struct sdhci_ops sdhci_omap_ops = .platform_send_init_74_clocks = sdhci_omap_init_74_clocks, .reset = sdhci_omap_reset, .set_uhs_signaling = sdhci_omap_set_uhs_signaling, + .irq = sdhci_omap_irq, };

static int sdhci_omap_set_capabilities(struct sdhci_omap_host *omap_host)

From: Sven Schnelle svens@stackframe.org

commit 45efd871bf0a47648f119d1b41467f70484de5bc upstream.

While working on kretprobes for PA-RISC I was wondering while the kprobes sanity test always fails on kretprobes. This is caused by returning gpr20 instead of gpr28.

Signed-off-by: Sven Schnelle svens@stackframe.org Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # 4.14+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/include/asm/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/parisc/include/asm/ptrace.h +++ b/arch/parisc/include/asm/ptrace.h @@ -22,7 +22,7 @@ unsigned long profile_pc(struct pt_regs

static inline unsigned long regs_return_value(struct pt_regs *regs) { - return regs->gr[20]; + return regs->gr[28]; }

static inline void instruction_pointer_set(struct pt_regs *regs,

From: Andrei Vagin avagin@gmail.com

commit 07d7e12091f4ab869cc6a4bb276399057e73b0b3 upstream.

To calculate a remaining time, it's required to subtract the current time from the expiration time. In alarm_timer_remaining() the arguments of ktime_sub are swapped.

Fixes: d653d8457c76 ("alarmtimer: Implement remaining callback") Signed-off-by: Andrei Vagin avagin@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Mukesh Ojha mojha@codeaurora.org Cc: Stephen Boyd sboyd@kernel.org Cc: John Stultz john.stultz@linaro.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190408041542.26338-1-avagin@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/time/alarmtimer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(str { struct alarm *alarm = &timr->it.alarm.alarmtimer;

- return ktime_sub(now, alarm->node.expires); + return ktime_sub(alarm->node.expires, now); }

/**

From: Jernej Skrabec jernej.skrabec@siol.net

commit cd9063757a227cf31ebf5391ccda2bf583b0806e upstream.

Currently resolutions with pixel clock higher than 340 MHz don't work with H6 HDMI controller. They just produce a blank screen.

Limit maximum pixel clock rate to 340 MHz until scrambling is supported.

Cc: stable@vger.kernel.org # 5.0 Fixes: 40bb9d3147b2 ("drm/sun4i: Add support for H6 DW HDMI controller") Signed-off-by: Jernej Skrabec jernej.skrabec@siol.net Signed-off-by: Maxime Ripard maxime.ripard@bootlin.com Link: https://patchwork.freedesktop.org/patch/msgid/20190324190609.32721-1-jernej.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -48,8 +48,13 @@ static enum drm_mode_status sun8i_dw_hdmi_mode_valid_h6(struct drm_connector *connector, const struct drm_display_mode *mode) { - /* This is max for HDMI 2.0b (4K@60Hz) */ - if (mode->clock > 594000) + /* + * Controller support maximum of 594 MHz, which correlates to + * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than + * 340 MHz scrambling has to be enabled. Because scrambling is + * not yet implemented, just limit to 340 MHz for now. + */ + if (mode->clock > 340000) return MODE_CLOCK_HIGH;

return MODE_OK;

From: David Rientjes rientjes@google.com

commit ede885ecb2cdf8a8dd5367702e3d964ec846a2d5 upstream.

get_num_contig_pages() could potentially overflow int so make its type consistent with its usage.

Reported-by: Cfir Cohen cfir@google.com Cc: stable@vger.kernel.org Signed-off-by: David Rientjes rientjes@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/svm.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6422,11 +6422,11 @@ e_free: return ret; }

-static int get_num_contig_pages(int idx, struct page **inpages, - unsigned long npages) +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) { unsigned long paddr, next_paddr; - int i = idx + 1, pages = 1; + unsigned long i = idx + 1, pages = 1;

/* find the number of contiguous pages starting from idx */ paddr = __sme_page_pa(inpages[idx]); @@ -6445,12 +6445,12 @@ static int get_num_contig_pages(int idx,

static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data *data; struct page **inpages; - int i, ret, pages; + int ret;

if (!sev_guest(kvm)) return -ENOTTY;

From: Greg Thelen gthelen@google.com

commit 0b3d6e6f2dd0a7b697b1aa8c167265908940624b upstream.

Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") memcg dirty and writeback counters are managed as:

1) per-memcg per-cpu values in range of [-32..32]

2) per-memcg atomic counter

When a per-cpu counter cannot fit in [-32..32] it's flushed to the atomic. Stat readers only check the atomic. Thus readers such as balance_dirty_pages() may see a nontrivial error margin: 32 pages per cpu.

Assuming 100 cpus: 4k x86 page_size: 13 MiB error per memcg 64k ppc page_size: 200 MiB error per memcg

Considering that dirty+writeback are used together for some decisions the errors double.

This inaccuracy can lead to undeserved oom kills. One nasty case is when all per-cpu counters hold positive values offsetting an atomic negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32). balance_dirty_pages() only consults the atomic and does not consider throttling the next n_cpu*32 dirty pages. If the file_lru is in the 13..200 MiB range then there's absolutely no dirty throttling, which burdens vmscan with only dirty+writeback pages thus resorting to oom kill.

It could be argued that tiny containers are not supported, but it's more subtle. It's the amount the space available for file lru that matters. If a container has memory.max-200MiB of non reclaimable memory, then it will also suffer such oom kills on a 100 cpu machine.

The following test reliably ooms without this patch. This patch avoids oom kills.

$ cat test mount -t cgroup2 none /dev/cgroup cd /dev/cgroup echo +io +memory > cgroup.subtree_control mkdir test cd test echo 10M > memory.max (echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo) (echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100)

$ cat memcg-writeback-stress.c /* * Dirty pages from all but one cpu. * Clean pages from the non dirtying cpu. * This is to stress per cpu counter imbalance. * On a 100 cpu machine: * - per memcg per cpu dirty count is 32 pages for each of 99 cpus * - per memcg atomic is -99*32 pages * - thus the complete dirty limit: sum of all counters 0 * - balance_dirty_pages() only sees atomic count -99*32 pages, which * it max()s to 0. * - So a workload can dirty -99*32 pages before balance_dirty_pages() * cares. */ #define _GNU_SOURCE #include <err.h> #include <fcntl.h> #include <sched.h> #include <stdlib.h> #include <stdio.h> #include <sys/stat.h> #include <sys/sysinfo.h> #include <sys/types.h> #include <unistd.h>

static char *buf; static int bufSize;

static void set_affinity(int cpu) { cpu_set_t affinity;

CPU_ZERO(&affinity); CPU_SET(cpu, &affinity); if (sched_setaffinity(0, sizeof(affinity), &affinity)) err(1, "sched_setaffinity"); }

static void dirty_on(int output_fd, int cpu) { int i, wrote;

set_affinity(cpu); for (i = 0; i < 32; i++) { for (wrote = 0; wrote < bufSize; ) { int ret = write(output_fd, buf+wrote, bufSize-wrote); if (ret == -1) err(1, "write"); wrote += ret; } } }

int main(int argc, char **argv) { int cpu, flush_cpu = 1, output_fd; const char *output;

if (argc != 2) errx(1, "usage: output_file");

output = argv[1]; bufSize = getpagesize(); buf = malloc(getpagesize()); if (buf == NULL) errx(1, "malloc failed");

output_fd = open(output, O_CREAT|O_RDWR); if (output_fd == -1) err(1, "open(%s)", output);

for (cpu = 0; cpu < get_nprocs(); cpu++) { if (cpu != flush_cpu) dirty_on(output_fd, cpu); }

set_affinity(flush_cpu); if (fsync(output_fd)) err(1, "fsync(%s)", output); if (close(output_fd)) err(1, "close(%s)", output); free(buf); }

Make balance_dirty_pages() and wb_over_bg_thresh() work harder to collect exact per memcg counters. This avoids the aforementioned oom kills.

This does not affect the overhead of memory.stat, which still reads the single atomic counter.

Why not use percpu_counter? memcg already handles cpus going offline, so no need for that overhead from percpu_counter. And the percpu_counter spinlocks are more heavyweight than is required.

It probably also makes sense to use exact dirty and writeback counters in memcg oom reports. But that is saved for later.

Link: http://lkml.kernel.org/r/20190329174609.164344-1-gthelen@google.com Signed-off-by: Greg Thelen gthelen@google.com Reviewed-by: Roman Gushchin guro@fb.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@kernel.org Cc: Vladimir Davydov vdavydov.dev@gmail.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org [4.16+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-)

--- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -561,7 +561,10 @@ struct mem_cgroup *lock_page_memcg(struc void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page);

-/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(s return &memcg->cgwb_domain; }

+/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writ struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent;

- *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);

/* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX;

From: S.j. Wang shengjiu.wang@nxp.com

commit 0ff4e8c61b794a4bf6c854ab071a1abaaa80f358 upstream.

There is very low possibility ( < 0.1% ) that channel swap happened in beginning when multi output/input pin is enabled. The issue is that hardware can't send data to correct pin in the beginning with the normal enable flow.

This is hardware issue, but there is no errata, the workaround flow is that: Each time playback/recording, firstly clear the xSMA/xSMB, then enable TE/RE, then enable xSMB and xSMA (xSMB must be enabled before xSMA). Which is to use the xSMA as the trigger start register, previously the xCR_TE or xCR_RE is the bit for starting.

Fixes commit 43d24e76b698 ("ASoC: fsl_esai: Add ESAI CPU DAI driver") Cc: stable@vger.kernel.org Reviewed-by: Fabio Estevam festevam@gmail.com Acked-by: Nicolin Chen nicoleotsuka@gmail.com Signed-off-by: Shengjiu Wang shengjiu.wang@nxp.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/soc/fsl/fsl_esai.c | 47 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 10 deletions(-)

--- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -54,6 +54,8 @@ struct fsl_esai { u32 fifo_depth; u32 slot_width; u32 slots; + u32 tx_mask; + u32 rx_mask; u32 hck_rate[2]; u32 sck_rate[2]; bool hck_dir[2]; @@ -361,21 +363,13 @@ static int fsl_esai_set_dai_tdm_slot(str regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask)); - esai_priv->slot_width = slot_width; esai_priv->slots = slots; + esai_priv->tx_mask = tx_mask; + esai_priv->rx_mask = rx_mask;

return 0; } @@ -596,6 +590,7 @@ static int fsl_esai_trigger(struct snd_p bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; u8 i, channels = substream->runtime->channels; u32 pins = DIV_ROUND_UP(channels, esai_priv->slots); + u32 mask;

switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -608,15 +603,38 @@ static int fsl_esai_trigger(struct snd_p for (i = 0; tx && i < channels; i++) regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);

+ /* + * When set the TE/RE in the end of enablement flow, there + * will be channel swap issue for multi data line case. + * In order to workaround this issue, we switch the bit + * enablement sequence to below sequence + * 1) clear the xSMB & xSMA: which is done in probe and + * stop state. + * 2) set TE/RE + * 3) set xSMB + * 4) set xSMA: xSMA is the last one in this flow, which + * will trigger esai to start. + */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins)); + mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask; + + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask)); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask)); + break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, 0);

/* Disable and reset FIFO */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx), @@ -906,6 +924,15 @@ static int fsl_esai_probe(struct platfor return ret; }

+ esai_priv->tx_mask = 0xFFFFFFFF; + esai_priv->rx_mask = 0xFFFFFFFF; + + /* Clear the TSMA, TSMB, RSMA, RSMB */ + regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0); + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) {

From: Anand Jain anand.jain@oracle.com

commit 50398fde997f6be8faebdb5f38e9c9c467370f51 upstream.

We let pass zstd compression parameter even if it is not fully valid. For example:

$ btrfs prop set /btrfs compression zst $ btrfs prop get /btrfs compression compression=zst

zlib and lzo are fine.

Fix it by checking the correct prefix length.

Fixes: 5c1aab1dd544 ("btrfs: Add zstd support") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Anand Jain anand.jain@oracle.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/props.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -396,7 +396,7 @@ static int prop_compression_apply(struct btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else {

From: Dmitry V. Levin ldv@altlinux.org

commit 10a16997db3d99fc02c026cf2c6e6c670acafab0 upstream.

RISC-V syscall arguments are located in orig_a0,a1..a5 fields of struct pt_regs.

Due to an off-by-one bug and a bug in pointer arithmetic syscall_get_arguments() was reading s3..s7 fields instead of a1..a5. Likewise, syscall_set_arguments() was writing s3..s7 fields instead of a1..a5.

Link: http://lkml.kernel.org/r/20190329171221.GA32456@altlinux.org

Fixes: e2c0cdfba7f69 ("RISC-V: User-facing API") Cc: Ingo Molnar mingo@redhat.com Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Albert Ou aou@eecs.berkeley.edu Cc: linux-riscv@lists.infradead.org Cc: stable@vger.kernel.org # v4.15+ Acked-by: Palmer Dabbelt palmer@sifive.com Signed-off-by: Dmitry V. Levin ldv@altlinux.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/riscv/include/asm/syscall.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -79,10 +79,11 @@ static inline void syscall_get_arguments if (i == 0) { args[0] = regs->orig_a0; args++; - i++; n--; + } else { + i--; } - memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0])); + memcpy(args, &regs->a1 + i, n * sizeof(args[0])); }

static inline void syscall_set_arguments(struct task_struct *task, @@ -94,10 +95,11 @@ static inline void syscall_set_arguments if (i == 0) { regs->orig_a0 = args[0]; args++; - i++; n--; - } - memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0)); + } else { + i--; + } + memcpy(&regs->a1 + i, args, n * sizeof(regs->a1)); }

static inline int syscall_get_arch(void)

From: Jérôme Glisse jglisse@redhat.com

commit a3761c3c91209b58b6f33bf69dd8bb8ec0c9d925 upstream.

When bio_add_pc_page() fails in bio_copy_user_iov() we should free the page we just allocated otherwise we are leaking it.

Cc: linux-block@vger.kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: stable@vger.kernel.org Reviewed-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Signed-off-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- block/bio.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/block/bio.c +++ b/block/bio.c @@ -1238,8 +1238,11 @@ struct bio *bio_copy_user_iov(struct req } }

- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) + if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { + if (!map_data) + __free_page(page); break; + }

len -= bytes; offset = 0;

From: Stephen Boyd swboyd@chromium.org

commit 325aa19598e410672175ed50982f902d4e3f31c5 upstream.

If a child irqchip calls irq_chip_set_wake_parent() but its parent irqchip has the IRQCHIP_SKIP_SET_WAKE flag set an error is returned.

This is inconsistent behaviour vs. set_irq_wake_real() which returns 0 when the irqchip has the IRQCHIP_SKIP_SET_WAKE flag set. It doesn't attempt to walk the chain of parents and set irq wake on any chips that don't have the flag set either. If the intent is to call the .irq_set_wake() callback of the parent irqchip, then we expect irqchip implementations to omit the IRQCHIP_SKIP_SET_WAKE flag and implement an .irq_set_wake() function that calls irq_chip_set_wake_parent().

The problem has been observed on a Qualcomm sdm845 device where set wake fails on any GPIO interrupts after applying work in progress wakeup irq patches to the GPIO driver. The chain of chips looks like this:

QCOM GPIO -> QCOM PDC (SKIP) -> ARM GIC (SKIP)

The GPIO controllers parent is the QCOM PDC irqchip which in turn has ARM GIC as parent. The QCOM PDC irqchip has the IRQCHIP_SKIP_SET_WAKE flag set, and so does the grandparent ARM GIC.

The GPIO driver doesn't know if the parent needs to set wake or not, so it unconditionally calls irq_chip_set_wake_parent() causing this function to return a failure because the parent irqchip (PDC) doesn't have the .irq_set_wake() callback set. Returning 0 instead makes everything work and irqs from the GPIO controller can be configured for wakeup.

Make it consistent by returning 0 (success) from irq_chip_set_wake_parent() when a parent chip has IRQCHIP_SKIP_SET_WAKE set.

[ tglx: Massaged changelog ]

Fixes: 08b55e2a9208e ("genirq: Add irqchip_set_wake_parent") Signed-off-by: Stephen Boyd swboyd@chromium.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Marc Zyngier marc.zyngier@arm.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-gpio@vger.kernel.org Cc: Lina Iyer ilina@codeaurora.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190325181026.247796-1-swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/irq/chip.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1384,6 +1384,10 @@ int irq_chip_set_vcpu_affinity_parent(st int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; + + if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on);

From: Cornelia Huck cohuck@redhat.com

commit cf94db21905333e610e479688add629397a4b384 upstream.

vring_create_virtqueue() allows the caller to specify via the may_reduce_num parameter whether the vring code is allowed to allocate a smaller ring than specified.

However, the split ring allocation code tries to allocate a smaller ring on allocation failure regardless of what the caller specified. This may cause trouble for e.g. virtio-pci in legacy mode, which does not support ring resizing. (The packed ring code does not resize in any case.)

Let's fix this by bailing out immediately in the split ring code if the requested size cannot be allocated and may_reduce_num has not been specified.

While at it, fix a typo in the usage instructions.

Fixes: 2a2d1382fe9d ("virtio: Add improved queue allocation API") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Reviewed-by: Halil Pasic pasic@linux.ibm.com Reviewed-by: Jens Freimann jfreimann@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/virtio/virtio_ring.c | 2 ++ include/linux/virtio_ring.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -871,6 +871,8 @@ static struct virtqueue *vring_create_vi GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO); if (queue) break; + if (!may_reduce_num) + return NULL; }

if (!num) --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -63,7 +63,7 @@ struct virtqueue; /* * Creates a virtqueue and allocates the descriptor ring. If * may_reduce_num is set, then this may allocate a smaller ring than - * expected. The caller should query virtqueue_get_ring_size to learn + * expected. The caller should query virtqueue_get_vring_size to learn * the actual size of the ring. */ struct virtqueue *vring_create_virtqueue(unsigned int index,

From: Janusz Krzysztofik jmkrzyszt@gmail.com

commit 3e2cf62efec52fb49daed437cc486c3cb9a0afa2 upstream.

In order to request dynamic allocationn of GPIO IDs, a negative number should be passed as a base GPIO ID via platform data. Unfortuntely, commit 771e53c4d1a1 ("ARM: OMAP1: ams-delta: Drop board specific global GPIO numbers") didn't follow that rule while switching to dynamically allocated GPIO IDs for Amstrad Delta latches, making their IDs overlapping with those already assigned to OMAP GPIO devices. Fix it.

Fixes: 771e53c4d1a1 ("ARM: OMAP1: ams-delta: Drop board specific global GPIO numbers") Signed-off-by: Janusz Krzysztofik jmkrzyszt@gmail.com Cc: stable@vger.kernel.org Acked-by: Aaro Koskinen aaro.koskinen@iki.fi Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/mach-omap1/board-ams-delta.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -182,6 +182,7 @@ static struct resource latch1_resources[

static struct bgpio_pdata latch1_pdata = { .label = LATCH1_LABEL, + .base = -1, .ngpio = LATCH1_NGPIO, };

@@ -219,6 +220,7 @@ static struct resource latch2_resources[

static struct bgpio_pdata latch2_pdata = { .label = LATCH2_LABEL, + .base = -1, .ngpio = LATCH2_NGPIO, };

From: Peter Ujfalusi peter.ujfalusi@ti.com

commit 6691370646e844be98bb6558c024269791d20bd7 upstream.

Correctly map the regulators used by tlv320aic3106. Both 1.8V and 3.3V for the codec is derived from VBAT via fixed regulators.

Cc: Stable@vger.kernel.org # v4.14+ Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/am335x-evmsk.dts | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-)

--- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -73,6 +73,24 @@ enable-active-high; };

+ /* TPS79518 */ + v1_8d_reg: fixedregulator-v1_8d { + compatible = "regulator-fixed"; + regulator-name = "v1_8d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* TPS78633 */ + v3_3d_reg: fixedregulator-v3_3d { + compatible = "regulator-fixed"; + regulator-name = "v3_3d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + leds { pinctrl-names = "default"; pinctrl-0 = <&user_leds_s0>; @@ -501,10 +519,10 @@ status = "okay";

/* Regulators */ - AVDD-supply = <&vaux2_reg>; - IOVDD-supply = <&vaux2_reg>; - DRVDD-supply = <&vaux2_reg>; - DVDD-supply = <&vbat>; + AVDD-supply = <&v3_3d_reg>; + IOVDD-supply = <&v3_3d_reg>; + DRVDD-supply = <&v3_3d_reg>; + DVDD-supply = <&v1_8d_reg>; }; };

From: David Summers beagleboard@davidjohnsummers.uk

commit 8dbc4d5ddb59f49cb3e85bccf42a4720b27a6576 upstream.

The Problem:

On ASUS Tinker Board S, when booting from the eMMC, and there is card in the sd slot, there are constant errors.

Also when warm reboot, uboot can not access the sd slot

Cause:

Identified by Robin Murphy @ ARM. The Card Detect on rk3288 devices is pulled up by vccio-sd; so when the regulator powers this off, card detect gives spurious errors. A second problem, is during power down, vccio-sd apprears to be powered down. This causes a problem when warm rebooting from the sd card. This was identified by Jonas Karlman.

History:

A common fault on these rk3288 board, which impliment the reference design.

When this arose before:

http://lists.infradead.org/pipermail/linux-arm-kernel/2014-August/281153.htm...

And Ulf and Jaehoon clearly said this was a broken card detect design, which should be solved via polling

Solution:

Hence broken-cd is set as a property. This cures the errors. The powering down of vccio-sd during reboot is cured by adding regulator-boot-on.

This solutions has been fairly widely reviewed and tested.

Fixes: e58c5e739d6f ("ARM: dts: rockchip: move shared tinker-board nodes to a common dtsi") Cc: stable@vger.kernel.org [Heiko: slightly inaccurate fixes but tinker is a sbc (aka like a Pi) where we can hopefully expect people not to rely on overly old stable kernels] Signed-off-by: David Summers beagleboard@davidjohnsummers.uk Reviewed-by: Jonas Karlman jonas@kwiboo.se Tested-by: Jonas Karlman jonas@kwiboo.se Reviewed-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/rk3288-tinker.dtsi | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/arm/boot/dts/rk3288-tinker.dtsi +++ b/arch/arm/boot/dts/rk3288-tinker.dtsi @@ -254,6 +254,7 @@ };

vccio_sd: LDO_REG5 { + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-name = "vccio_sd"; @@ -430,7 +431,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; - card-detect-delay = <200>; + broken-cd; disable-wp; /* wp not hooked up */ pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;

From: Will Deacon will.deacon@arm.com

commit 045afc24124d80c6998d9c770844c67912083506 upstream.

Rather embarrassingly, our futex() FUTEX_WAKE_OP implementation doesn't explicitly set the return value on the non-faulting path and instead leaves it holding the result of the underlying atomic operation. This means that any FUTEX_WAKE_OP atomic operation which computes a non-zero value will be reported as having failed. Regrettably, I wrote the buggy code back in 2011 and it was upstreamed as part of the initial arm64 support in 2012.

The reasons we appear to get away with this are:

1. FUTEX_WAKE_OP is rarely used and therefore doesn't appear to get exercised by futex() test applications

2. If the result of the atomic operation is zero, the system call behaves correctly

3. Prior to version 2.25, the only operation used by GLIBC set the futex to zero, and therefore worked as expected. From 2.25 onwards, FUTEX_WAKE_OP is not used by GLIBC at all.

Fix the implementation by ensuring that the return value is either 0 to indicate that the atomic operation completed successfully, or -EFAULT if we encountered a fault when accessing the user mapping.

Cc: stable@kernel.org Fixes: 6170a97460db ("arm64: Atomic operations") Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/include/asm/futex.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -30,8 +30,8 @@ do { \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ -"2: stlxr %w3, %w0, %2\n" \ -" cbnz %w3, 1b\n" \ +"2: stlxr %w0, %w3, %2\n" \ +" cbnz %w0, 1b\n" \ " dmb ish\n" \ "3:\n" \ " .pushsection .fixup,"ax"\n" \ @@ -50,30 +50,30 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval = 0, ret, tmp; + int oldval, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);

pagefault_disable();

switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %w0, %w4", + __futex_atomic_op("mov %w3, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %w0, %w1, %w4", + __futex_atomic_op("add %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %w0, %w1, %w4", + __futex_atomic_op("orr %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %w0, %w1, %w4", + __futex_atomic_op("and %w3, %w1, %w4", ret, oldval, uaddr, tmp, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %w0, %w1, %w4", + __futex_atomic_op("eor %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; default:

From: Peter Geis pgwipeout@gmail.com

commit 6fd8b9780ec1a49ac46e0aaf8775247205e66231 upstream.

Several rk3328 based boards experience high rgmii tx error rates. This is due to several pins in the rk3328.dtsi rgmii pinmux that are missing a defined pull strength setting. This causes the pinmux driver to default to 2ma (bit mask 00).

These pins are only defined in the rk3328.dtsi, and are not listed in the rk3328 specification. The TRM only lists them as "Reserved" (RK3328 TRM V1.1, 3.3.3 Detail Register Description, GRF_GPIO0B_IOMUX, GRF_GPIO0C_IOMUX, GRF_GPIO0D_IOMUX). However, removal of these pins from the rgmii pinmux definition causes the interface to fail to transmit.

Also, the rgmii tx and rx pins defined in the dtsi are not consistent with the rk3328 specification, with tx pins currently set to 12ma and rx pins set to 2ma.

Fix this by setting tx pins to 8ma and the rx pins to 4ma, consistent with the specification. Defining the drive strength for the undefined pins eliminated the high tx packet error rate observed under heavy data transfers. Aligning the drive strength to the TRM values eliminated the occasional packet retry errors under iperf3 testing. This allows much higher data rates with no recorded tx errors.

Tested on the rk3328-roc-cc board.

Fixes: 52e02d377a72 ("arm64: dts: rockchip: add core dtsi file for RK3328 SoCs") Cc: stable@vger.kernel.org Signed-off-by: Peter Geis pgwipeout@gmail.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328.dtsi | 44 +++++++++++++++---------------- 1 file changed, 22 insertions(+), 22 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1628,50 +1628,50 @@ rgmiim1_pins: rgmiim1-pins { rockchip,pins = /* mac_txclk */ - <1 RK_PB4 2 &pcfg_pull_none_12ma>, + <1 RK_PB4 2 &pcfg_pull_none_8ma>, /* mac_rxclk */ - <1 RK_PB5 2 &pcfg_pull_none_2ma>, + <1 RK_PB5 2 &pcfg_pull_none_4ma>, /* mac_mdio */ - <1 RK_PC3 2 &pcfg_pull_none_2ma>, + <1 RK_PC3 2 &pcfg_pull_none_4ma>, /* mac_txen */ - <1 RK_PD1 2 &pcfg_pull_none_12ma>, + <1 RK_PD1 2 &pcfg_pull_none_8ma>, /* mac_clk */ - <1 RK_PC5 2 &pcfg_pull_none_2ma>, + <1 RK_PC5 2 &pcfg_pull_none_4ma>, /* mac_rxdv */ - <1 RK_PC6 2 &pcfg_pull_none_2ma>, + <1 RK_PC6 2 &pcfg_pull_none_4ma>, /* mac_mdc */ - <1 RK_PC7 2 &pcfg_pull_none_2ma>, + <1 RK_PC7 2 &pcfg_pull_none_4ma>, /* mac_rxd1 */ - <1 RK_PB2 2 &pcfg_pull_none_2ma>, + <1 RK_PB2 2 &pcfg_pull_none_4ma>, /* mac_rxd0 */ - <1 RK_PB3 2 &pcfg_pull_none_2ma>, + <1 RK_PB3 2 &pcfg_pull_none_4ma>, /* mac_txd1 */ - <1 RK_PB0 2 &pcfg_pull_none_12ma>, + <1 RK_PB0 2 &pcfg_pull_none_8ma>, /* mac_txd0 */ - <1 RK_PB1 2 &pcfg_pull_none_12ma>, + <1 RK_PB1 2 &pcfg_pull_none_8ma>, /* mac_rxd3 */ - <1 RK_PB6 2 &pcfg_pull_none_2ma>, + <1 RK_PB6 2 &pcfg_pull_none_4ma>, /* mac_rxd2 */ - <1 RK_PB7 2 &pcfg_pull_none_2ma>, + <1 RK_PB7 2 &pcfg_pull_none_4ma>, /* mac_txd3 */ - <1 RK_PC0 2 &pcfg_pull_none_12ma>, + <1 RK_PC0 2 &pcfg_pull_none_8ma>, /* mac_txd2 */ - <1 RK_PC1 2 &pcfg_pull_none_12ma>, + <1 RK_PC1 2 &pcfg_pull_none_8ma>,

/* mac_txclk */ - <0 RK_PB0 1 &pcfg_pull_none>, + <0 RK_PB0 1 &pcfg_pull_none_8ma>, /* mac_txen */ - <0 RK_PB4 1 &pcfg_pull_none>, + <0 RK_PB4 1 &pcfg_pull_none_8ma>, /* mac_clk */ - <0 RK_PD0 1 &pcfg_pull_none>, + <0 RK_PD0 1 &pcfg_pull_none_4ma>, /* mac_txd1 */ - <0 RK_PC0 1 &pcfg_pull_none>, + <0 RK_PC0 1 &pcfg_pull_none_8ma>, /* mac_txd0 */ - <0 RK_PC1 1 &pcfg_pull_none>, + <0 RK_PC1 1 &pcfg_pull_none_8ma>, /* mac_txd3 */ - <0 RK_PC7 1 &pcfg_pull_none>, + <0 RK_PC7 1 &pcfg_pull_none_8ma>, /* mac_txd2 */ - <0 RK_PC6 1 &pcfg_pull_none>; + <0 RK_PC6 1 &pcfg_pull_none_8ma>; };

rmiim1_pins: rmiim1-pins {

From: Ard Biesheuvel ard.biesheuvel@linaro.org

commit 5a3ae7b314a2259b1188b22b392f5eba01e443ee upstream.

The ftrace trampoline code (which deals with modules loaded out of BL range of the core kernel) uses plt_entries_equal() to check whether the per-module trampoline equals a zero buffer, to decide whether the trampoline has already been initialized.

This triggers a BUG() in the opcode manipulation code, since we end up checking the ADRP offset of a 0x0 opcode, which is not an ADRP instruction.

So instead, add a helper to check whether a PLT is initialized, and call that from the frace code.

Cc: stable@vger.kernel.org # v5.0 Fixes: bdb85cd1d206 ("arm64/module: switch to ADRP/ADD sequences for PLT entries") Acked-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/include/asm/module.h | 5 +++++ arch/arm64/kernel/ftrace.c | 3 +-- 2 files changed, 6 insertions(+), 2 deletions(-)

--- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -73,4 +73,9 @@ static inline bool is_forbidden_offset_f struct plt_entry get_plt_entry(u64 dst, void *pc); bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);

+static inline bool plt_entry_is_initialized(const struct plt_entry *e) +{ + return e->adrp || e->add || e->br; +} + #endif /* __ASM_MODULE_H */ --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -107,8 +107,7 @@ int ftrace_make_call(struct dyn_ftrace * trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); if (!plt_entries_equal(mod->arch.ftrace_trampoline, &trampoline)) { - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &(struct plt_entry){})) { + if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; }

From: Dan Carpenter dan.carpenter@oracle.com

commit 42d8644bd77dd2d747e004e367cb0c895a606f39 upstream.

The "call" variable comes from the user in privcmd_ioctl_hypercall(). It's an offset into the hypercall_page[] which has (PAGE_SIZE / 32) elements. We need to put an upper bound on it to prevent an out of bounds access.

Cc: stable@vger.kernel.org Fixes: 1246ae0bb992 ("xen: add variable hypercall caller") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/xen/hypercall.h | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -206,6 +206,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5);

+ if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) + return -EINVAL; + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call])

From: Max Filippov jcmvbkbc@gmail.com

commit ada770b1e74a77fff2d5f539bf6c42c25f4784db upstream.

return_address returns the address that is one level higher in the call stack than requested in its argument, because level 0 corresponds to its caller's return address. Use requested level as the number of stack frames to skip.

This fixes the address reported by might_sleep and friends.

Cc: stable@vger.kernel.org Signed-off-by: Max Filippov jcmvbkbc@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/xtensa/kernel/stacktrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -253,10 +253,14 @@ static int return_address_cb(struct stac return 1; }

+/* + * level == 0 is for the return address from the caller of this function, + * not from this function itself. + */ unsigned long return_address(unsigned level) { struct return_addr_data r = { - .skip = level + 1, + .skip = level, }; walk_stackframe(stack_pointer(NULL), return_address_cb, &r); return r.addr;

From: Rasmus Villemoes linux@rasmusvillemoes.dk

commit 88ca66d8540ca26119b1428cddb96b37925bdf01 upstream.

The minimum supported gcc version is >= 4.6, so these can be removed.

Signed-off-by: Rasmus Villemoes linux@rasmusvillemoes.dk Signed-off-by: Borislav Petkov bp@suse.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: Dan Williams dan.j.williams@intel.com Cc: Geert Uytterhoeven geert@linux-m68k.org Cc: Ingo Molnar mingo@redhat.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: x86-ml x86@kernel.org Link: https://lkml.kernel.org/r/20190111084931.24601-1-linux@rasmusvillemoes.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/bitops.h | 6 ------ arch/x86/include/asm/string_32.h | 20 -------------------- arch/x86/include/asm/string_64.h | 15 --------------- 3 files changed, 41 deletions(-)

--- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -36,13 +36,7 @@ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */

-#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1) -/* Technically wrong, but this avoids compilation errors on some gcc - versions. */ -#define BITOP_ADDR(x) "=m" (*(volatile long *) (x)) -#else #define BITOP_ADDR(x) "+m" (*(volatile long *) (x)) -#endif

#define ADDR BITOP_ADDR(addr)

--- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -179,14 +179,7 @@ static inline void *__memcpy3d(void *to, * No 3D Now! */

-#if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) -#else -#define memcpy(t, f, n) \ - (__builtin_constant_p((n)) \ - ? __constant_memcpy((t), (f), (n)) \ - : __memcpy((t), (f), (n))) -#endif

#endif #endif /* !CONFIG_FORTIFY_SOURCE */ @@ -282,12 +275,7 @@ void *__constant_c_and_count_memset(void

{ int d0, d1; -#if __GNUC__ == 4 && __GNUC_MINOR__ == 0 - /* Workaround for broken gcc 4.0 */ - register unsigned long eax asm("%eax") = pattern; -#else unsigned long eax = pattern; -#endif

switch (count % 4) { case 0: @@ -321,15 +309,7 @@ void *__constant_c_and_count_memset(void #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, size_t); #ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) -#else -#define memset(s, c, count) \ - (__builtin_constant_p(c) \ - ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ - (count)) \ - : __memset((s), (c), (count))) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */

#define __HAVE_ARCH_MEMSET16 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -14,21 +14,6 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len);

-#ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 -#define memcpy(dst, src, len) \ -({ \ - size_t __len = (len); \ - void *__ret; \ - if (__builtin_constant_p(len) && __len >= 64) \ - __ret = __memcpy((dst), (src), __len); \ - else \ - __ret = __builtin_memcpy((dst), (src), __len); \ - __ret; \ -}) -#endif -#endif /* !CONFIG_FORTIFY_SOURCE */ - #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); void *__memset(void *s, int c, size_t n);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 914123fa39042e651d79eaf86bbf63a1b938dddf upstream.

On AMD processors, the detection of an overflowed counter in the NMI handler relies on the current value of the counter. So, for example, to check for overflow on a 48 bit counter, bit 47 is checked to see if it is 1 (not overflowed) or 0 (overflowed).

There is currently a race condition present when disabling and then updating the PMC. Increased NMI latency in newer AMD processors makes this race condition more pronounced. If the counter value has overflowed, it is possible to update the PMC value before the NMI handler can run. The updated PMC value is not an overflowed value, so when the perf NMI handler does run, it will not find an overflowed counter. This may appear as an unknown NMI resulting in either a panic or a series of messages, depending on how the kernel is configured.

To eliminate this race condition, the PMC value must be checked after disabling the counter. Add an AMD function, amd_pmu_disable_all(), that will wait for the NMI handler to reset any active and overflowed counter after calling x86_pmu_disable_all().

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 65 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 62 insertions(+), 3 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/apicdef.h>

#include "../perf_event.h" @@ -429,6 +430,64 @@ static void amd_pmu_cpu_dead(int cpu) } }

+/* + * When a PMC counter overflows, an NMI is used to process the event and + * reset the counter. NMI latency can result in the counter being updated + * before the NMI can run, which can result in what appear to be spurious + * NMIs. This function is intended to wait for the NMI to run and reset + * the counter to avoid possible unhandled NMI messages. + */ +#define OVERFLOW_WAIT_COUNT 50 + +static void amd_pmu_wait_on_overflow(int idx) +{ + unsigned int i; + u64 counter; + + /* + * Wait for the counter to be reset if it has overflowed. This loop + * should exit very, very quickly, but just in case, don't wait + * forever... + */ + for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { + rdmsrl(x86_pmu_event_addr(idx), counter); + if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + break; + + /* Might be in IRQ context, so can't sleep */ + udelay(1); + } +} + +static void amd_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + x86_pmu_disable_all(); + + /* + * This shouldn't be called from NMI context, but add a safeguard here + * to return, since if we're in NMI context we can't wait for an NMI + * to reset an overflowed counter value. + */ + if (in_nmi()) + return; + + /* + * Check each counter for overflow and wait for it to be reset by the + * NMI if it has overflowed. This relies on the fact that all active + * counters are always enabled when this function is caled and + * ARCH_PERFMON_EVENTSEL_INT is always set. + */ + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_wait_on_overflow(idx); + } +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -622,7 +681,7 @@ static ssize_t amd_event_sysfs_show(char static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, + .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, @@ -732,7 +791,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -750,7 +809,7 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 3966c3feca3fd10b2935caa0b4a08c7dd59469e5 upstream.

Spurious interrupt support was added to perf in the following commit, almost a decade ago:

63e6be6d98e1 ("perf, x86: Catch spurious interrupts after disabling counters")

The two previous patches (resolving the race condition when disabling a PMC and NMI latency mitigation) allow for the removal of this older spurious interrupt support.

Currently in x86_pmu_stop(), the bit for the PMC in the active_mask bitmap is cleared before disabling the PMC, which sets up a race condition. This race condition was mitigated by introducing the running bitmap. That race condition can be eliminated by first disabling the PMC, waiting for PMC reset on overflow and then clearing the bit for the PMC in the active_mask bitmap. The NMI handler will not re-enable a disabled counter.

If x86_pmu_stop() is called from the perf NMI handler, the NMI latency mitigation support will guard against any unhandled NMI messages.

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 21 +++++++++++++++++++-- arch/x86/events/core.c | 13 +++---------- 2 files changed, 22 insertions(+), 12 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -4,8 +4,8 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> -#include <linux/nmi.h> #include <asm/apicdef.h> +#include <asm/nmi.h>

#include "../perf_event.h"

@@ -491,6 +491,23 @@ static void amd_pmu_disable_all(void) } }

+static void amd_pmu_disable_event(struct perf_event *event) +{ + x86_pmu_disable_event(event); + + /* + * This can be called from NMI context (via x86_pmu_stop). The counter + * may have overflowed, but either way, we'll never see it get reset + * by the NMI if we're already in the NMI. And the NMI latency support + * below will take care of any pending NMI that might have been + * generated by the overflow. + */ + if (in_nmi()) + return; + + amd_pmu_wait_on_overflow(event->hw.idx); +} + /* * Because of NMI latency, if multiple PMC counters are active or other sources * of NMIs are received, the perf NMI handler can handle one or more overflowed @@ -738,7 +755,7 @@ static __initconst const struct x86_pmu .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, + .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *eve struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw;

- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); + __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *r apic_write(APIC_LVTPC, APIC_DM_NMI);

for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) { - /* - * Though we deactivated the counter some cpus - * might still deliver spurious interrupts still - * in flight. Catch them: - */ - if (__test_and_clear_bit(idx, cpuc->running)) - handled++; + if (!test_bit(idx, cpuc->active_mask)) continue; - }

event = cpuc->events[idx];

From: Sergey Miroshnichenko s.miroshnichenko@yadro.com

commit 3943af9d01e94330d0cfac6fccdbc829aad50c92 upstream.

During a safe hot remove, the OS powers off the slot, which may cause a Data Link Layer State Changed event. The slot has already been set to OFF_STATE, so that event results in re-enabling the device, making it impossible to safely remove it.

Clear out the Presence Detect Changed and Data Link Layer State Changed events when the disabled slot has settled down.

It is still possible to re-enable the device if it remains in the slot after pressing the Attention Button by pressing it again.

Fixes the problem that Micah reported below: an NVMe drive power button may not actually turn off the drive.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=203237 Reported-by: Micah Parrish micah.parrish@hpe.com Tested-by: Micah Parrish micah.parrish@hpe.com Signed-off-by: Sergey Miroshnichenko s.miroshnichenko@yadro.com [bhelgaas: changelog, add bugzilla URL] Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Lukas Wunner lukas@wunner.de Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pci/hotplug/pciehp_ctrl.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -115,6 +115,10 @@ static void remove_board(struct controll * removed from the slot/adapter. */ msleep(1000); + + /* Ignore link or presence changes caused by power off */ + atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC), + &ctrl->pending_events); }

/* turn off Green LED */

From: Nicholas Piggin npiggin@gmail.com

commit 7100e8704b61247649c50551b965e71d168df30b upstream.

Commit 48e7b76957 ("powerpc/64s/hash: Convert SLB miss handlers to C") broke the radix-mode segment exception handler. In radix mode, this is exception is not an SLB miss, rather it signals that the EA is outside the range translated by any page table.

The commit lost the radix feature alternate code patch, which can cause faults to some EAs to kernel BUG at arch/powerpc/mm/slb.c:639!

The original radix code would send faults to slb_miss_large_addr, which would end up faulting due to slb_addr_limit being 0. This patch sends radix directly to do_bad_slb_fault, which is a bit clearer.

Fixes: 48e7b7695745 ("powerpc/64s/hash: Convert SLB miss handlers to C") Cc: stable@vger.kernel.org # v4.20+ Reported-by: Anton Blanchard anton@samba.org Signed-off-by: Nicholas Piggin npiggin@gmail.com Reviewed-by: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/powerpc/kernel/exceptions-64s.S | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -612,11 +612,17 @@ EXC_COMMON_BEGIN(data_access_slb_common) ld r4,PACA_EXSLB+EX_DAR(r13) std r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) @@ -661,11 +667,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_ EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB) ld r4,_NIP(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11)

From: Mikulas Patocka mpatocka@redhat.com

commit 75ae193626de3238ca5fb895868ec91c94e63b1b upstream.

The limit was already incorporated to dm-crypt with commit 4e870e948fba ("dm crypt: fix error with too large bios"), so we don't need to apply it globally to all targets. The quantity BIO_MAX_PAGES * PAGE_SIZE is wrong anyway because the variable ti->max_io_len it is supposed to be in the units of 512-byte sectors not in bytes.

Reduction of the limit to 1048576 sectors could even cause data corruption in rare cases - suppose that we have a dm-striped device with stripe size 768MiB. The target will call dm_set_target_max_io_len with the value 1572864. The buggy code would reduce it to 1048576. Now, the dm-core will errorneously split the bios on 1048576-sector boundary insetad of 1572864-sector boundary and pass these stripe-crossing bios to the striped target.

Cc: stable@vger.kernel.org # v4.16+ Fixes: 8f50e358153d ("dm: limit the max bio size as BIO_MAX_PAGES * PAGE_SIZE") Signed-off-by: Mikulas Patocka mpatocka@redhat.com Acked-by: Ming Lei ming.lei@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)

--- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1060,15 +1060,7 @@ int dm_set_target_max_io_len(struct dm_t return -EINVAL; }

- /* - * BIO based queue uses its own splitting. When multipage bvecs - * is switched on, size of the incoming bio may be too big to - * be handled in some targets, such as crypt. - * - * When these targets are ready for the big bio, we can remove - * the limit. - */ - ti->max_io_len = min_t(uint32_t, len, BIO_MAX_PAGES * PAGE_SIZE); + ti->max_io_len = (uint32_t) len;

return 0; }

From: Mike Snitzer snitzer@redhat.com

commit bcb44433bba5eaff293888ef22ffa07f1f0347d6 upstream.

Storage devices which report supporting discard commands like WRITE_SAME_16 with unmap, but reject discard commands sent to the storage device. This is a clear storage firmware bug but it doesn't change the fact that should a program cause discards to be sent to a multipath device layered on this buggy storage, all paths can end up failed at the same time from the discards, causing possible I/O loss.

The first discard to a path will fail with Illegal Request, Invalid field in cdb, e.g.: kernel: sd 8:0:8:19: [sdfn] tag#0 FAILED Result: hostbyte=DID_OK driverbyte=DRIVER_SENSE kernel: sd 8:0:8:19: [sdfn] tag#0 Sense Key : Illegal Request [current] kernel: sd 8:0:8:19: [sdfn] tag#0 Add. Sense: Invalid field in cdb kernel: sd 8:0:8:19: [sdfn] tag#0 CDB: Write same(16) 93 08 00 00 00 00 00 a0 08 00 00 00 80 00 00 00 kernel: blk_update_request: critical target error, dev sdfn, sector 10487808

The SCSI layer converts this to the BLK_STS_TARGET error number, the sd device disables its support for discard on this path, and because of the BLK_STS_TARGET error multipath fails the discard without failing any path or retrying down a different path. But subsequent discards can cause path failures. Any discards sent to the path which already failed a discard ends up failing with EIO from blk_cloned_rq_check_limits with an "over max size limit" error since the discard limit was set to 0 by the sd driver for the path. As the error is EIO, this now fails the path and multipath tries to send the discard down the next path. This cycle continues as discards are sent until all paths fail.

Fix this by training DM core to disable DISCARD if the underlying storage already did so.

Also, fix branching in dm_done() and clone_endio() to reflect the mutually exclussive nature of the IO operations in question.

Cc: stable@vger.kernel.org Reported-by: David Jeffery djeffery@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-core.h | 1 + drivers/md/dm-rq.c | 11 +++++++---- drivers/md/dm.c | 20 ++++++++++++++++---- 3 files changed, 24 insertions(+), 8 deletions(-)

--- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -115,6 +115,7 @@ struct mapped_device { struct srcu_struct io_barrier; };

+void disable_discard(struct mapped_device *md); void disable_write_same(struct mapped_device *md); void disable_write_zeroes(struct mapped_device *md);

--- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -206,11 +206,14 @@ static void dm_done(struct request *clon }

if (unlikely(error == BLK_STS_TARGET)) { - if (req_op(clone) == REQ_OP_WRITE_SAME && - !clone->q->limits.max_write_same_sectors) + if (req_op(clone) == REQ_OP_DISCARD && + !clone->q->limits.max_discard_sectors) + disable_discard(tio->md); + else if (req_op(clone) == REQ_OP_WRITE_SAME && + !clone->q->limits.max_write_same_sectors) disable_write_same(tio->md); - if (req_op(clone) == REQ_OP_WRITE_ZEROES && - !clone->q->limits.max_write_zeroes_sectors) + else if (req_op(clone) == REQ_OP_WRITE_ZEROES && + !clone->q->limits.max_write_zeroes_sectors) disable_write_zeroes(tio->md); }

--- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -963,6 +963,15 @@ static void dec_pending(struct dm_io *io } }

+void disable_discard(struct mapped_device *md) +{ + struct queue_limits *limits = dm_get_queue_limits(md); + + /* device doesn't really support DISCARD, disable it */ + limits->max_discard_sectors = 0; + blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); +} + void disable_write_same(struct mapped_device *md) { struct queue_limits *limits = dm_get_queue_limits(md); @@ -988,11 +997,14 @@ static void clone_endio(struct bio *bio) dm_endio_fn endio = tio->ti->type->end_io;

if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) { - if (bio_op(bio) == REQ_OP_WRITE_SAME && - !bio->bi_disk->queue->limits.max_write_same_sectors) + if (bio_op(bio) == REQ_OP_DISCARD && + !bio->bi_disk->queue->limits.max_discard_sectors) + disable_discard(md); + else if (bio_op(bio) == REQ_OP_WRITE_SAME && + !bio->bi_disk->queue->limits.max_write_same_sectors) disable_write_same(md); - if (bio_op(bio) == REQ_OP_WRITE_ZEROES && - !bio->bi_disk->queue->limits.max_write_zeroes_sectors) + else if (bio_op(bio) == REQ_OP_WRITE_ZEROES && + !bio->bi_disk->queue->limits.max_write_zeroes_sectors) disable_write_zeroes(md); }

From: Marc Orr marcorr@google.com

commit acff78477b9b4f26ecdf65733a4ed77fe837e9dc upstream.

The nested_vmx_prepare_msr_bitmap() function doesn't directly guard the x2APIC MSR intercepts with the "virtualize x2APIC mode" MSR. As a result, we discovered the potential for a buggy or malicious L1 to get access to L0's x2APIC MSRs, via an L2, as follows.

1. L1 executes WRMSR(IA32_SPEC_CTRL, 1). This causes the spec_ctrl variable, in nested_vmx_prepare_msr_bitmap() to become true. 2. L1 disables "virtualize x2APIC mode" in VMCS12. 3. L1 enables "APIC-register virtualization" in VMCS12.

Now, KVM will set VMCS02's x2APIC MSR intercepts from VMCS12, and then set "virtualize x2APIC mode" to 0 in VMCS02. Oops.

This patch closes the leak by explicitly guarding VMCS02's x2APIC MSR intercepts with VMCS12's "virtualize x2APIC mode" control.

The scenario outlined above and fix prescribed here, were verified with a related patch in kvm-unit-tests titled "Add leak scenario to virt_x2apic_mode_test".

Note, it looks like this issue may have been introduced inadvertently during a merge---see 15303ba5d1cd.

Signed-off-by: Marc Orr marcorr@google.com Reviewed-by: Jim Mattson jmattson@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/vmx/nested.c | 72 ++++++++++++++++++++++++++++------------------ 1 file changed, 44 insertions(+), 28 deletions(-)

--- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept } }

+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap[word] = ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_ms return false;

msr_bitmap_l1 = (unsigned long *)kmap(page); - if (nested_cpu_has_apic_reg_virt(vmcs12)) { - /* - * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it - * just lets the processor take the value from the virtual-APIC page; - * take those 256 bits directly from the L1 bitmap. - */ - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = msr_bitmap_l1[word]; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } else { - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = ~0; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - }

- nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_TASKPRI), - MSR_TYPE_W); + /* + * To keep the control flow simple, pay eight 8-byte writes (sixteen + * 4-byte writes on 32-bit systems) up front to enable intercepts for + * the x2APIC MSR range and selectively disable them below. + */ + enable_x2apic_msr_intercepts(msr_bitmap_l0); + + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 + * and 0x8ff, it just lets the processor take the value + * from the virtual-APIC page; take those 256 bits + * directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + } + }

- if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_EOI), - MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_SELF_IPI), + X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_W); + + if (nested_cpu_has_vid(vmcs12)) { + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); + } }

if (spec_ctrl)

From: Gerd Hoffmann kraxel@redhat.com

commit 16065fcdd19ddb9e093192914ac863884f308766 upstream.

Bisected guest kernel changes crashing qemu. Landed at "6c1cd97bda drm/virtio: fix resource id handling". Looked again, and noticed we where not only leaking *some* ids, but *all* ids. The old code never ever called virtio_gpu_resource_id_put().

So, commit 6c1cd97bda effectively makes the linux kernel starting re-using IDs after releasing them, and apparently virglrenderer can't deal with that. Oops.

This patch puts a temporary stopgap into place for the 5.0 release.

Signed-off-by: Gerd Hoffmann kraxel@redhat.com Reviewed-by: Dave Airlie airlied@redhat.com Signed-off-by: Dave Airlie airlied@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20190208140409.15280-1-kraxel@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/virtio/virtgpu_object.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -28,10 +28,21 @@ static int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev, uint32_t *resid) { +#if 0 int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);

if (handle < 0) return handle; +#else + static int handle; + + /* + * FIXME: dirty hack to avoid re-using IDs, virglrenderer + * can't deal with that. Needs fixing in virglrenderer, also + * should figure a better way to handle that in the guest. + */ + handle++; +#endif

*resid = handle + 1; return 0; @@ -39,7 +50,9 @@ static int virtio_gpu_resource_id_get(st

static void virtio_gpu_resource_id_put(struct virtio_gpu_device *vgdev, uint32_t id) { +#if 0 ida_free(&vgdev->resource_ida, id - 1); +#endif }

static void virtio_gpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)