Linux 5.15.59

index a81dda65c576..45180a2cc47c 100644
@@ -10,7 +10,7 @@
 #else
 #define MAX_DMA_ADDRESS	({ \
 	extern phys_addr_t arm_dma_zone_size; \
-	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+	arm_dma_zone_size && arm_dma_zone_size < (0x100000000ULL - PAGE_OFFSET) ? \
 		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 

index b99dd8e1c93f..7ba6cf826162 100644
@@ -26,8 +26,9 @@ MODULE_LICENSE("GPL");
  * While older versions of GCC do not generate incorrect code, they fail to
  * recognize the parallel nature of these functions, and emit plain ARM code,
  * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ *
+ * #warning This code requires at least version 4.6 of GCC
  */
-#warning This code requires at least version 4.6 of GCC
 #endif
 
 #pragma GCC diagnostic ignored "-Wunused-variable"

index 2c6e1c6ecbe7..4120c428dc37 100644
@@ -2,7 +2,7 @@
 /*
  * Kernel interface for the s390 arch_random_* functions
  *
- * Copyright IBM Corp. 2017, 2020
+ * Copyright IBM Corp. 2017, 2022
  *
  * Author: Harald Freudenberger <[email protected]>
  *

@@ -14,6 +14,7 @@
 #ifdef CONFIG_ARCH_RANDOM
 
 #include <linux/static_key.h>
+#include <linux/preempt.h>
 #include <linux/atomic.h>
 #include <asm/cpacf.h>
 

@@ -32,7 +33,8 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
 
 static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
+	if (static_branch_likely(&s390_arch_random_available) &&
+	    in_task()) {
 		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
 		atomic64_add(sizeof(*v), &s390_arch_random_counter);
 		return true;

@@ -42,7 +44,8 @@ static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 
 static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
-	if (static_branch_likely(&s390_arch_random_available)) {
+	if (static_branch_likely(&s390_arch_random_available) &&
+	    in_task()) {
 		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
 		atomic64_add(sizeof(*v), &s390_arch_random_counter);
 		return true;

index 18a7ea1cffda..a37814c8547e 100644
@@ -1513,6 +1513,7 @@ static void __init spectre_v2_select_mitigation(void)
 	 * enable IBRS around firmware calls.
 	 */
 	if (boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+	    boot_cpu_has(X86_FEATURE_IBPB) &&
 	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	     boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) {
 

index 6d1ddecbf0da..d0a9ccf640c4 100644
@@ -101,9 +101,14 @@ static void dimm_setup_label(struct dimm_info *dimm, u16 handle)
 
 	dmi_memdev_name(handle, &bank, &device);
 
-	/* both strings must be non-zero */
-	if (bank && *bank && device && *device)
-		snprintf(dimm->label, sizeof(dimm->label), "%s %s", bank, device);
+	/*
+	 * Set to a NULL string when both bank and device are zero. In this case,
+	 * the label assigned by default will be preserved.
+	 */
+	snprintf(dimm->label, sizeof(dimm->label), "%s%s%s",
+		 (bank && *bank) ? bank : "",
+		 (bank && *bank && device && *device) ? " " : "",
+		 (device && *device) ? device : "");
 }
 
 static void assign_dmi_dimm_info(struct dimm_info *dimm, struct memdev_dmi_entry *entry)

index 92987daa5e17..5e72e6cb2f84 100644
@@ -679,7 +679,11 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 		goto out_free_dma;
 
 	for (i = 0; i < npages; i += max) {
-		args.end = start + (max << PAGE_SHIFT);
+		if (args.start + (max << PAGE_SHIFT) > end)
+			args.end = end;
+		else
+			args.end = args.start + (max << PAGE_SHIFT);
+
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out_free_pfns;

index 3e3f9ba1e885..f3c2c173ca4b 100644
@@ -614,7 +614,7 @@ static const struct drm_connector_funcs simpledrm_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static int
+static enum drm_mode_status
 simpledrm_simple_display_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
 				    const struct drm_display_mode *mode)
 {

index c801b128e5b2..b07d55c99317 100644
@@ -1908,11 +1908,15 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 		 * non-zero req_queue_pairs says that user requested a new
 		 * queue count via ethtool's set_channels, so use this
 		 * value for queues distribution across traffic classes
+		 * We need at least one queue pair for the interface
+		 * to be usable as we see in else statement.
 		 */
 		if (vsi->req_queue_pairs > 0)
 			vsi->num_queue_pairs = vsi->req_queue_pairs;
 		else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
 			vsi->num_queue_pairs = pf->num_lan_msix;
+		else
+			vsi->num_queue_pairs = 1;
 	}
 
 	/* Number of queues per enabled TC */

index 982db894754f..9b9c2b885486 100644
@@ -651,7 +651,8 @@ static int ice_lbtest_receive_frames(struct ice_ring *rx_ring)
 		rx_desc = ICE_RX_DESC(rx_ring, i);
 
 		if (!(rx_desc->wb.status_error0 &
-		    cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+		    (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) |
+		     cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)))))
 			continue;
 
 		rx_buf = &rx_ring->rx_buf[i];

index 188abf36a5b2..b9d45c7dbef1 100644
@@ -5481,10 +5481,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
 	if (vsi->netdev) {
 		ice_set_rx_mode(vsi->netdev);
 
-		err = ice_vsi_vlan_setup(vsi);
+		if (vsi->type != ICE_VSI_LB) {
+			err = ice_vsi_vlan_setup(vsi);
 
-		if (err)
-			return err;
+			if (err)
+				return err;
+		}
 	}
 	ice_vsi_cfg_dcb_rings(vsi);
 

185 lines not on this page · raw message

index 725b0f38813a..a2b4e3befa59 100644
@@ -1100,7 +1100,29 @@ static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb)
 
 	tx_queue = efx_channel_get_tx_queue(ptp_data->channel, type);
 	if (tx_queue && tx_queue->timestamping) {
+		/* This code invokes normal driver TX code which is always
+		 * protected from softirqs when called from generic TX code,
+		 * which in turn disables preemption. Look at __dev_queue_xmit
+		 * which uses rcu_read_lock_bh disabling preemption for RCU
+		 * plus disabling softirqs. We do not need RCU reader
+		 * protection here.
+		 *
+		 * Although it is theoretically safe for current PTP TX/RX code
+		 * running without disabling softirqs, there are three good
+		 * reasond for doing so:
+		 *
+		 *      1) The code invoked is mainly implemented for non-PTP
+		 *         packets and it is always executed with softirqs
+		 *         disabled.
+		 *      2) This being a single PTP packet, better to not
+		 *         interrupt its processing by softirqs which can lead
+		 *         to high latencies.
+		 *      3) netdev_xmit_more checks preemption is disabled and
+		 *         triggers a BUG_ON if not.
+		 */
+		local_bh_disable();
 		efx_enqueue_skb(tx_queue, skb);
+		local_bh_enable();
 	} else {
 		WARN_ONCE(1, "PTP channel has no timestamped tx queue\n");
 		dev_kfree_skb_any(skb);

index e53b40359fd1..354890948f8a 100644
@@ -241,6 +241,7 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
 #define DEFAULT_SEND_SCI true
 #define DEFAULT_ENCRYPT false
 #define DEFAULT_ENCODING_SA 0
+#define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1))
 
 static bool send_sci(const struct macsec_secy *secy)
 {

@@ -1695,7 +1696,7 @@ static bool validate_add_rxsa(struct nlattr **attrs)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_PN] &&
-	    *(u64 *)nla_data(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	    nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {

@@ -1751,7 +1752,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN;
-	if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
+	if (tb_sa[MACSEC_SA_ATTR_PN] &&
+	    nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
 		pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n",
 			  nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len);
 		rtnl_unlock();

@@ -1767,7 +1769,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 		if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
 			pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n",
 				  nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
-				  MACSEC_SA_ATTR_SALT);
+				  MACSEC_SALT_LEN);
 			rtnl_unlock();
 			return -EINVAL;
 		}

@@ -1840,7 +1842,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 
 cleanup:
-	kfree(rx_sa);
+	macsec_rxsa_put(rx_sa);
 	rtnl_unlock();
 	return err;
 }

@@ -1937,7 +1939,7 @@ static bool validate_add_txsa(struct nlattr **attrs)
 	if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
 		return false;
 
-	if (nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {

@@ -2009,7 +2011,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 		if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
 			pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n",
 				  nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
-				  MACSEC_SA_ATTR_SALT);
+				  MACSEC_SALT_LEN);
 			rtnl_unlock();
 			return -EINVAL;
 		}

@@ -2083,7 +2085,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 
 cleanup:
 	secy->operational = was_operational;
-	kfree(tx_sa);
+	macsec_txsa_put(tx_sa);
 	rtnl_unlock();
 	return err;
 }

@@ -2291,7 +2293,7 @@ static bool validate_upd_sa(struct nlattr **attrs)
 	if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
 		return false;
 
-	if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+	if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
 		return false;
 
 	if (attrs[MACSEC_SA_ATTR_ACTIVE]) {

@@ -3738,9 +3740,6 @@ static int macsec_changelink_common(struct net_device *dev,
 		secy->operational = tx_sa && tx_sa->active;
 	}
 
-	if (data[IFLA_MACSEC_WINDOW])
-		secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
-
 	if (data[IFLA_MACSEC_ENCRYPT])
 		tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);
 

@@ -3786,6 +3785,16 @@ static int macsec_changelink_common(struct net_device *dev,
 		}
 	}
 
+	if (data[IFLA_MACSEC_WINDOW]) {
+		secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
+
+		/* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window
+		 * for XPN cipher suites */
+		if (secy->xpn &&
+		    secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 

@@ -3815,7 +3824,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
 
 	ret = macsec_changelink_common(dev, data);
 	if (ret)
-		return ret;
+		goto cleanup;
 
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {

index 7de631f5356f..fd4cbf8a55ad 100644
@@ -890,7 +890,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
 	 */
 	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
 	if (ret < 0)
-		return false;
+		return ret;
 
 	if (ret & DW_VR_MII_C37_ANSGM_SP_LNKSTS) {
 		int speed_value;

index 291fa449993f..45f295403cb5 100644
@@ -454,6 +454,7 @@ static int bcm5421_init(struct mii_phy* phy)
 		int can_low_power = 1;
 		if (np == NULL || of_get_property(np, "no-autolowpower", NULL))
 			can_low_power = 0;
+		of_node_put(np);
 		if (can_low_power) {
 			/* Enable automatic low-power */
 			sungem_phy_write(phy, 0x1c, 0x9002);

index 318c681ad63e..53cefad2a79d 100644
@@ -213,9 +213,15 @@ struct virtnet_info {
 	/* Packet virtio header size */
 	u8 hdr_len;
 
-	/* Work struct for refilling if we run low on memory. */
+	/* Work struct for delayed refilling if we run low on memory. */
 	struct delayed_work refill;
 
+	/* Is delayed refill enabled? */
+	bool refill_enabled;
+
+	/* The lock to synchronize the access to refill_enabled */
+	spinlock_t refill_lock;
+
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 

@@ -319,6 +325,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = true;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = false;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
 static void virtqueue_napi_schedule(struct napi_struct *napi,
 				    struct virtqueue *vq)
 {

@@ -1454,8 +1474,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
-		if (!try_fill_recv(vi, rq, GFP_ATOMIC))
-			schedule_delayed_work(&vi->refill, 0);
+		if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+			spin_lock(&vi->refill_lock);
+			if (vi->refill_enabled)
+				schedule_delayed_work(&vi->refill, 0);
+			spin_unlock(&vi->refill_lock);
+		}
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);

@@ -1578,6 +1602,8 @@ static int virtnet_open(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i, err;
 
+	enable_delayed_refill(vi);
+
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (i < vi->curr_queue_pairs)
 			/* Make sure we have some buffers: if oom use wq. */

@@ -1958,6 +1984,8 @@ static int virtnet_close(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
+	/* Make sure NAPI doesn't schedule refill work */
+	disable_delayed_refill(vi);
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 

@@ -2455,6 +2483,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	enable_delayed_refill(vi);
+
 	if (netif_running(vi->dev)) {
 		err = virtnet_open(vi->dev);
 		if (err)

@@ -3162,6 +3192,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+	spin_lock_init(&vi->refill_lock);
 
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||

index af275ac42795..5351959fbaba 100644
@@ -11386,6 +11386,7 @@ scsih_shutdown(struct pci_dev *pdev)
 	_scsih_ir_shutdown(ioc);
 	_scsih_nvme_shutdown(ioc);
 	mpt3sas_base_mask_interrupts(ioc);
+	mpt3sas_base_stop_watchdog(ioc);
 	ioc->shost_recovery = 1;
 	mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
 	ioc->shost_recovery = 0;

index a06c61f22742..6e2f82152b4a 100644
@@ -457,7 +457,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk,
 		goto out_free_cdb;
 
 	ret = 0;
-	if (hdr->iovec_count) {
+	if (hdr->iovec_count && hdr->dxfer_len) {
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 

index 87975d1a21c8..adc302b1a57a 100644
@@ -107,9 +107,20 @@ static int ufshcd_parse_clock_info(struct ufs_hba *hba)
 	return ret;
 }
 
+static bool phandle_exists(const struct device_node *np,
+			   const char *phandle_name, int index)
+{
+	struct device_node *parse_np = of_parse_phandle(np, phandle_name, index);
+
+	if (parse_np)
+		of_node_put(parse_np);
+
+	return parse_np != NULL;
+}
+
 #define MAX_PROP_SIZE 32
 static int ufshcd_populate_vreg(struct device *dev, const char *name,
-		struct ufs_vreg **out_vreg)
+				struct ufs_vreg **out_vreg)
 {
 	char prop_name[MAX_PROP_SIZE];
 	struct ufs_vreg *vreg = NULL;

@@ -121,7 +132,7 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
 	}
 
 	snprintf(prop_name, MAX_PROP_SIZE, "%s-supply", name);
-	if (!of_parse_phandle(np, prop_name, 0)) {
+	if (!phandle_exists(np, prop_name, 0)) {
 		dev_info(dev, "%s: Unable to find %s regulator, assuming enabled\n",
 				__func__, prop_name);
 		goto out;

index d563abc3e136..914e99173130 100644
@@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
 		a = (ATTR_RECORD*)((u8*)ctx->attr +
 				le32_to_cpu(ctx->attr->length));
 	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
-		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_allocated))
+		u8 *mrec_end = (u8 *)ctx->mrec +
+		               le32_to_cpu(ctx->mrec->bytes_allocated);
+		u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+			       a->name_length * sizeof(ntfschar);
+		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+		    name_end > mrec_end)
 			break;
 		ctx->attr = a;
 		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||

index bb62cc2e0211..cf21aecdf547 100644
@@ -277,7 +277,6 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15,  /* Journal Async Commit */
 	OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
 	OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
-	OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001

@@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
 
 static inline int ocfs2_mount_local(struct ocfs2_super *osb)
 {
-	return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
-		|| (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+	return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
 }
 
 static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)

65 lines not on this page · raw message

index 7ba3dabe16f0..a03f0cabff0b 100644
@@ -173,7 +173,6 @@ enum {
 	Opt_dir_resv_level,
 	Opt_journal_async_commit,
 	Opt_err_cont,
-	Opt_nocluster,
 	Opt_err,
 };
 

@@ -207,7 +206,6 @@ static const match_table_t tokens = {
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_journal_async_commit, "journal_async_commit"},
 	{Opt_err_cont, "errors=continue"},
-	{Opt_nocluster, "nocluster"},
 	{Opt_err, NULL}
 };
 

@@ -619,13 +617,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 		goto out;
 	}
 
-	tmp = OCFS2_MOUNT_NOCLUSTER;
-	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
-		ret = -EINVAL;
-		mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
-		goto out;
-	}
-
 	tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
 		OCFS2_MOUNT_HB_NONE;
 	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {

@@ -866,7 +857,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
 	}
 
 	if (ocfs2_userspace_stack(osb) &&
-	    !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
 	    strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
 		    OCFS2_STACK_LABEL_LEN)) {
 		mlog(ML_ERROR,

@@ -1145,11 +1135,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	       osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
 	       "ordered");
 
-	if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
-	   !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
-		printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
-		       "without cluster aware mode.\n", osb->dev_str);
-
 	atomic_set(&osb->vol_state, VOLUME_MOUNTED);
 	wake_up(&osb->osb_mount_event);
 

@@ -1456,9 +1441,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 		case Opt_journal_async_commit:
 			mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
 			break;
-		case Opt_nocluster:
-			mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
-			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "

@@ -1570,9 +1552,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
 	if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
 		seq_printf(s, ",journal_async_commit");
 
-	if (opts & OCFS2_MOUNT_NOCLUSTER)
-		seq_printf(s, ",nocluster");
-
 	return 0;
 }
 

index c6db1a0762fa..8d3ec975514d 100644
@@ -1250,6 +1250,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 					  count, fl);
 		file_end_write(out.file);
 	} else {
+		if (out.file->f_flags & O_NONBLOCK)
+			fl |= SPLICE_F_NONBLOCK;
+
 		retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
 	}
 

index 7ce93aaf69f8..98954dda5734 100644
@@ -1125,9 +1125,7 @@ static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
 }
 #endif
 
-#ifndef CONFIG_GENERIC_DEVMEM_IS_ALLOWED
 extern int devmem_is_allowed(unsigned long pfn);
-#endif
 
 #endif /* __KERNEL__ */
 

index 59940e230b78..53627afab104 100644
@@ -403,6 +403,9 @@ static inline bool ip6_ignore_linkdown(const struct net_device *dev)
 {
 	const struct inet6_dev *idev = __in6_dev_get(dev);
 
+	if (unlikely(!idev))
+		return true;
+
 	return !!idev->cnf.ignore_routes_with_linkdown;
 }
 

index 3c4f550e5a8b..2f766e3437ce 100644
@@ -847,6 +847,7 @@ enum {
 };
 
 void l2cap_chan_hold(struct l2cap_chan *c);
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c);
 void l2cap_chan_put(struct l2cap_chan *c);
 
 static inline void l2cap_chan_lock(struct l2cap_chan *chan)

index fa6a87246a7b..695ed45841f0 100644
@@ -315,7 +315,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 
-#define TCP_PINGPONG_THRESH	3
+#define TCP_PINGPONG_THRESH	1
 
 static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
 {

@@ -332,14 +332,6 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
 	return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
 }
 
-static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	if (icsk->icsk_ack.pingpong < U8_MAX)
-		icsk->icsk_ack.pingpong++;
-}
-
 static inline bool inet_csk_has_ulp(struct sock *sk)
 {
 	return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;

index 96f51d4b1649..819c53965ef3 100644
@@ -2765,18 +2765,18 @@ static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_wmem ? */
 	if (proto->sysctl_wmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
 
-	return *proto->sysctl_wmem;
+	return READ_ONCE(*proto->sysctl_wmem);
 }
 
 static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_rmem ? */
 	if (proto->sysctl_rmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
 
-	return *proto->sysctl_rmem;
+	return READ_ONCE(*proto->sysctl_rmem);
 }
 
 /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)

index 8ce8aafeef0f..76b0d7f2b967 100644
@@ -1406,7 +1406,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
 
 static inline int tcp_win_from_space(const struct sock *sk, int space)
 {
-	int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
+	int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
 
 	return tcp_adv_win_scale <= 0 ?
 		(space>>(-tcp_adv_win_scale)) :

index e63f740c2cc8..4cc73e6f8974 100644
@@ -335,8 +335,6 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
-
-	/* Writer only, not initialized in reader */
 	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \

@@ -456,10 +454,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 			 * to give up the lock), request a HANDOFF to
 			 * force the issue.
 			 */
-			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
-			    time_after(jiffies, waiter->timeout)) {
-				adjustment -= RWSEM_FLAG_HANDOFF;
-				lockevent_inc(rwsem_rlock_handoff);
+			if (time_after(jiffies, waiter->timeout)) {
+				if (!(oldcount & RWSEM_FLAG_HANDOFF)) {
+					adjustment -= RWSEM_FLAG_HANDOFF;
+					lockevent_inc(rwsem_rlock_handoff);
+				}
+				waiter->handoff_set = true;
 			}
 
 			atomic_long_add(-adjustment, &sem->count);

@@ -569,7 +569,7 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 					struct rwsem_waiter *waiter)
 {
-	bool first = rwsem_first_waiter(sem) == waiter;
+	struct rwsem_waiter *first = rwsem_first_waiter(sem);
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);

@@ -579,11 +579,20 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
 		if (has_handoff) {
-			if (!first)
+			/*
+			 * Honor handoff bit and yield only when the first
+			 * waiter is the one that set it. Otherwisee, we
+			 * still try to acquire the rwsem.
+			 */
+			if (first->handoff_set && (waiter != first))
 				return false;
 
-			/* First waiter inherits a previously set handoff bit */
-			waiter->handoff_set = true;
+			/*
+			 * First waiter can inherit a previously set handoff
+			 * bit and spin on rwsem if lock acquisition fails.
+			 */
+			if (waiter == first)
+				waiter->handoff_set = true;
 		}
 
 		new = count;

@@ -978,6 +987,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
 	if (list_empty(&sem->wait_list)) {

76 lines not on this page · raw message

index bd56641c79d4..3af995c814a6 100644
@@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline bool hmm_is_device_private_entry(struct hmm_range *range,
-		swp_entry_t entry)
-{
-	return is_device_private_entry(entry) &&
-		pfn_swap_entry_to_page(entry)->pgmap->owner ==
-		range->dev_private_owner;
-}
-
 static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
 						 pte_t pte)
 {

@@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		swp_entry_t entry = pte_to_swp_entry(pte);
 
 		/*
-		 * Never fault in device private pages, but just report
-		 * the PFN even if not present.
+		 * Don't fault in device private pages owned by the caller,
+		 * just report the PFN.
 		 */
-		if (hmm_is_device_private_entry(range, entry)) {
+		if (is_device_private_entry(entry) &&
+		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
+		    range->dev_private_owner) {
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;

@@ -273,6 +267,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		if (!non_swap_entry(entry))
 			goto fault;
 
+		if (is_device_private_entry(entry))
+			goto fault;
+
 		if (is_device_exclusive_entry(entry))
 			goto fault;
 

index eed96302897a..405793b8cf0d 100644
@@ -5314,6 +5314,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 		page = alloc_huge_page(dst_vma, dst_addr, 0);
 		if (IS_ERR(page)) {
+			put_page(*pagep);
 			ret = -ENOMEM;
 			*pagep = NULL;
 			goto out;

index 036eb765c4e8..a4d0f744a458 100644
@@ -4071,9 +4071,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		}
 	}
 
-	/* See comment in handle_pte_fault() */
+	/*
+	 * See comment in handle_pte_fault() for how this scenario happens, we
+	 * need to return NOPAGE so that we drop this page.
+	 */
 	if (pmd_devmap_trans_unstable(vmf->pmd))
-		return 0;
+		return VM_FAULT_NOPAGE;
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				      vmf->address, &vmf->ptl);

index a0b7afae59e9..61d7967897ce 100644
@@ -3928,11 +3928,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * need to be calculated.
 	 */
 	if (!order) {
-		long fast_free;
+		long usable_free;
+		long reserved;
 
-		fast_free = free_pages;
-		fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
-		if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+		usable_free = free_pages;
+		reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+		/* reserved may over estimate high-atomic reserves. */
+		usable_free -= min(usable_free, reserved);
+		if (usable_free > mark + z->lowmem_reserve[highest_zoneidx])
 			return true;
 	}
 

index 5a62ef3bcfcf..14f49c0aa66e 100644
@@ -55,22 +55,28 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 	gfp_t gfp = vmf->gfp_mask;
 	unsigned long addr;
 	struct page *page;
+	vm_fault_t ret;
 	int err;
 
 	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
 		return vmf_error(-EINVAL);
 
+	filemap_invalidate_lock_shared(mapping);
+
 retry:
 	page = find_lock_page(mapping, offset);
 	if (!page) {
 		page = alloc_page(gfp | __GFP_ZERO);
-		if (!page)
-			return VM_FAULT_OOM;
+		if (!page) {
+			ret = VM_FAULT_OOM;
+			goto out;
+		}
 
 		err = set_direct_map_invalid_noflush(page);
 		if (err) {
 			put_page(page);
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		__SetPageUptodate(page);

@@ -86,7 +92,8 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 			if (err == -EEXIST)
 				goto retry;
 
-			return vmf_error(err);
+			ret = vmf_error(err);
+			goto out;
 		}
 
 		addr = (unsigned long)page_address(page);

@@ -94,7 +101,11 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 	}
 
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = VM_FAULT_LOCKED;
+
+out:
+	filemap_invalidate_unlock_shared(mapping);
+	return ret;
 }
 
 static const struct vm_operations_struct secretmem_vm_ops = {

@@ -162,12 +173,20 @@ static int secretmem_setattr(struct user_namespace *mnt_userns,
 			     struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct address_space *mapping = inode->i_mapping;
 	unsigned int ia_valid = iattr->ia_valid;
+	int ret;
+
+	filemap_invalidate_lock(mapping);
 
 	if ((ia_valid & ATTR_SIZE) && inode->i_size)
-		return -EINVAL;
+		ret = -EINVAL;
+	else
+		ret = simple_setattr(mnt_userns, dentry, iattr);
 
-	return simple_setattr(mnt_userns, dentry, iattr);
+	filemap_invalidate_unlock(mapping);
+
+	return ret;
 }
 
 static const struct inode_operations secretmem_iops = {

180 lines not on this page · raw message

index dc92a67baea3..7d542eb46172 100644
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 	sk->sk_family      = PF_DECnet;
 	sk->sk_protocol    = 0;
 	sk->sk_allocation  = gfp;
-	sk->sk_sndbuf	   = sysctl_decnet_wmem[1];
-	sk->sk_rcvbuf	   = sysctl_decnet_rmem[1];
+	sk->sk_sndbuf	   = READ_ONCE(sysctl_decnet_wmem[1]);
+	sk->sk_rcvbuf	   = READ_ONCE(sysctl_decnet_rmem[1]);
 
 	/* Initialization of DECnet Session Control Port		*/
 	scp = DN_SK(sk);

index a9cd9c2bd84e..19c6e7b93d3d 100644
@@ -1037,6 +1037,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
 
 void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 {
+	u8 fib_notify_on_flag_change;
 	struct fib_alias *fa_match;
 	struct sk_buff *skb;
 	int err;

@@ -1058,14 +1059,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 	WRITE_ONCE(fa_match->offload, fri->offload);
 	WRITE_ONCE(fa_match->trap, fri->trap);
 
+	fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
 	/* 2 means send notifications only if offload_failed was changed. */
-	if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+	if (fib_notify_on_flag_change == 2 &&
 	    READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
 		goto out;
 
 	WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
 
-	if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+	if (!fib_notify_on_flag_change)
 		goto out;
 
 	skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);

index 9f4674244aff..e07d10b2c486 100644
@@ -827,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
 	struct net *net = dev_net(in_dev->dev);
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
 		return;
-	WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
+	WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv));
 	igmp_ifc_start_timer(in_dev, 1);
 }
 

@@ -1009,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		 * received value was zero, use the default or statically
 		 * configured value.
 		 */
-		in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+		in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
 
 		/* RFC3376, 8.3. Query Response Interval:

@@ -1189,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im,
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
 	pmc->multiaddr = im->multiaddr;
-	pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+	pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 	pmc->sfmode = im->sfmode;
 	if (pmc->sfmode == MCAST_INCLUDE) {
 		struct ip_sf_list *psf;

@@ -1240,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 			swap(im->tomb, pmc->tomb);
 			swap(im->sources, pmc->sources);
 			for (psf = im->sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+				psf->sf_crcount = in_dev->mr_qrv ?:
+					READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		} else {
-			im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+			im->crcount = in_dev->mr_qrv ?:
+				READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		}
 		in_dev_put(pmc->interface);
 		kfree_pmc(pmc);

@@ -1349,7 +1351,7 @@ static void igmp_group_added(struct ip_mc_list *im)
 	if (in_dev->dead)
 		return;
 
-	im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
+	im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
 		spin_lock_bh(&im->lock);
 		igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);

@@ -1363,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im)
 	 * IN() to IN(A).
 	 */
 	if (im->sfmode == MCAST_EXCLUDE)
-		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 
 	igmp_ifc_event(in_dev);
 #endif

@@ -1754,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev)
 
 	in_dev->mr_qi = IGMP_QUERY_INTERVAL;
 	in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
-	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+	in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 }
 #else
 static void ip_mc_reset(struct in_device *in_dev)

@@ -1888,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		if (psf->sf_oldin &&
 		    !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
-			psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+			psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 			psf->sf_next = pmc->tomb;
 			pmc->tomb = psf;
 			rv = 1;

@@ -1952,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		/* filter mode change */
 		pmc->sfmode = MCAST_INCLUDE;
 #ifdef CONFIG_IP_MULTICAST
-		pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;

@@ -2131,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		/* else no filters; keep old mode for reports */
 
-		pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
 		WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;

index 1abdb8712655..2097eeaf30a6 100644
@@ -458,8 +458,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
-	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;

@@ -694,7 +694,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
 	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }

@@ -1722,7 +1722,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
-		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 	val = min(val, cap);
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 

142 lines not on this page · raw message

index fba02cf6b468..dae0776c4948 100644
@@ -1004,7 +1004,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
-		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
 				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
 				(inet_sk(sk)->tos & INET_ECN_MASK) :
 				inet_sk(sk)->tos;

@@ -1590,7 +1590,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
 		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
 	if (!dst) {

index a501150deaa3..d58e672be31c 100644
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
 	int m;
 
 	sk_dst_confirm(sk);
-	if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
 		return;
 
 	rcu_read_lock();

@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
 
 	if (tcp_in_initial_slowstart(tp)) {
 		/* Slow start still did not finish. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && (tcp_snd_cwnd(tp) >> 1) > val)

@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
 	} else if (!tcp_in_slow_start(tp) &&
 		   icsk->icsk_ca_state == TCP_CA_Open) {
 		/* Cong. avoidance phase, cwnd is reliable. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
 			tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
 				       max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));

@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
 			tcp_metric_set(tm, TCP_METRIC_CWND,
 				       (val + tp->snd_ssthresh) >> 1);
 		}
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && tp->snd_ssthresh > val)

@@ -463,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
 	if (tcp_metric_locked(tm, TCP_METRIC_CWND))
 		tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
 
-	val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+	val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
 	      0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 	if (val) {
 		tp->snd_ssthresh = val;

index caf9283f9b0f..9c9a0f7a3dee 100644
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	if (tcp_packets_in_flight(tp) == 0)
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
-	/* If this is the first data packet sent in response to the
-	 * previous received data,
-	 * and it is a reply for ato after last received packet,
-	 * increase pingpong count.
-	 */
-	if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
-	    (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_inc_pingpong_cnt(sk);
-
 	tp->lsndtime = now;
+
+	/* If it is a reply for ato after last received
+	 * packet, enter pingpong mode.
+	 */
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+		inet_csk_enter_pingpong_mode(sk);
 }
 
 /* Account for an ACK we sent. */

@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,

@@ -1989,7 +1986,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 
 	min_tso = ca_ops->min_tso_segs ?
 			ca_ops->min_tso_segs(sk) :
-			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 
 	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);

@@ -2506,7 +2503,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
-			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&

index 7f695c39d9a8..87c699d57b36 100644
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
 
 		if (++cnt >= MLD_MAX_QUEUE) {
 			rework = true;
-			schedule_delayed_work(&idev->mc_query_work, 0);
 			break;
 		}
 	}

@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
 		__mld_query_work(skb);
 	mutex_unlock(&idev->mc_lock);
 
-	if (!rework)
-		in6_dev_put(idev);
+	if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+		return;
+
+	in6_dev_put(idev);
 }
 
 /* called with rcu_read_lock() */

@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
 
 		if (++cnt >= MLD_MAX_QUEUE) {
 			rework = true;
-			schedule_delayed_work(&idev->mc_report_work, 0);
 			break;
 		}
 	}

@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
 		__mld_report_work(skb);
 	mutex_unlock(&idev->mc_lock);
 
-	if (!rework)
-		in6_dev_put(idev);
+	if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+		return;
+
+	in6_dev_put(idev);
 }
 
 static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,

index 6ac88fe24a8e..135e3a060caa 100644
@@ -22,6 +22,11 @@
 #include <linux/proc_fs.h>
 #include <net/ping.h>
 
+static void ping_v6_destroy(struct sock *sk)
+{
+	inet6_destroy_sock(sk);
+}
+
 /* Compatibility glue so we can support IPv6 when it's compiled as a module */
 static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 				 int *addr_len)

@@ -166,6 +171,7 @@ struct proto pingv6_prot = {
 	.owner =	THIS_MODULE,
 	.init =		ping_init_sock,
 	.close =	ping_close,
+	.destroy =	ping_v6_destroy,
 	.connect =	ip6_datagram_connect_v6_only,
 	.disconnect =	__udp_disconnect,
 	.setsockopt =	ipv6_setsockopt,

index beaa0c2ada23..8ab39cf57d43 100644
@@ -542,7 +542,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
-		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+		tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
 				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
 				(np->tclass & INET_ECN_MASK) :
 				np->tclass;

@@ -1364,7 +1364,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
 		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
 	/* Clone native IPv6 options from listening socket (if any)

index d6def23b8cba..7f96e0c42a09 100644
@@ -1881,7 +1881,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (msk->rcvq_space.copied <= msk->rcvq_space.space)
 		goto new_measure;
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;

@@ -1899,7 +1899,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 		do_div(rcvwin, advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;

@@ -2532,8 +2532,8 @@ static int mptcp_init_sock(struct sock *sk)
 	icsk->icsk_ca_ops = NULL;
 
 	sk_sockets_allocated_inc(sk);
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
 
 	return 0;
 }

index 8787d0613ad8..5329ebf19a18 100644
@@ -836,11 +836,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 }
 
 static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
+nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff)
 {
 	struct sk_buff *nskb;
 
 	if (diff < 0) {
+		unsigned int min_len = skb_transport_offset(e->skb);
+
+		if (data_len < min_len)
+			return -EINVAL;
+
 		if (pskb_trim(e->skb, data_len))
 			return -ENOMEM;
 	} else if (diff > 0) {

index be29da09cc7a..3460abceba44 100644
@@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init(
 	if (!sctp_ulpq_init(&asoc->ulpq, asoc))
 		goto fail_init;
 
-	if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams,
-			     0, gfp))
-		goto fail_init;
+	if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
+		goto stream_free;
 
 	/* Initialize default path MTU. */
 	asoc->pathmtu = sp->pathmtu;

index 6dc95dcc0ff4..ef9fceadef8d 100644
@@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 
 	ret = sctp_stream_alloc_out(stream, outcnt, gfp);
 	if (ret)
-		goto out_err;
+		return ret;
 
 	for (i = 0; i < stream->outcnt; i++)
 		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;

@@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 handle_in:
 	sctp_stream_interleave_init(stream);
 	if (!incnt)
-		goto out;
-
-	ret = sctp_stream_alloc_in(stream, incnt, gfp);
-	if (ret)
-		goto in_err;
-
-	goto out;
+		return 0;
 
-in_err:
-	sched->free(stream);
-	genradix_free(&stream->in);
-out_err:
-	genradix_free(&stream->out);
-	stream->outcnt = 0;
-out:
-	return ret;
+	return sctp_stream_alloc_in(stream, incnt, gfp);
 }
 
 int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)

index 99e5f69fbb74..a2e1d34f52c5 100644
@@ -163,7 +163,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
 		if (!SCTP_SO(&asoc->stream, i)->ext)
 			continue;
 
-		ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+		ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
 		if (ret)
 			goto err;
 	}

index 43509c7e90fc..f1c3b8eb4b3d 100644
@@ -517,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
 	sk->sk_shutdown = 0;
 	sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
-	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
 	sk->sk_destruct = tipc_sock_destruct;

index 4e33150cfb9e..cf75969375cf 100644
@@ -1351,8 +1351,13 @@ static int tls_device_down(struct net_device *netdev)
 		 * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
 		 * Now release the ref taken above.
 		 */
-		if (refcount_dec_and_test(&ctx->refcount))
+		if (refcount_dec_and_test(&ctx->refcount)) {
+			/* sk_destruct ran after tls_device_down took a ref, and
+			 * it returned early. Complete the destruction here.
+			 */
+			list_del(&ctx->list);
 			tls_device_free_ctx(ctx);
+		}
 	}
 
 	up_write(&device_offload_lock);

64 lines not on this page · raw message