Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 602 insertions, 0 deletions

diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
new file mode 100644
index 000000000..321af498e
--- /dev/null
+++ b/drivers/ras/cec.c
@@ -0,0 +1,602 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019 Borislav Petkov, SUSE Labs.
+ */
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/ras.h>
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+
+#include <asm/mce.h>
+
+#include "debugfs.h"
+
+/*
+ * RAS Correctable Errors Collector
+ *
+ * This is a simple gadget which collects correctable errors and counts their
+ * occurrence per physical page address.
+ *
+ * We've opted for possibly the simplest data structure to collect those - an
+ * array of the size of a memory page. It stores 512 u64's with the following
+ * structure:
+ *
+ * [63 ... PFN ... 12 | 11 ... generation ... 10 | 9 ... count ... 0]
+ *
+ * The generation in the two highest order bits is two bits which are set to 11b
+ * on every insertion. During the course of each entry's existence, the
+ * generation field gets decremented during spring cleaning to 10b, then 01b and
+ * then 00b.
+ *
+ * This way we're employing the natural numeric ordering to make sure that newly
+ * inserted/touched elements have higher 12-bit counts (which we've manufactured)
+ * and thus iterating over the array initially won't kick out those elements
+ * which were inserted last.
+ *
+ * Spring cleaning is what we do when we reach a certain number CLEAN_ELEMS of
+ * elements entered into the array, during which, we're decaying all elements.
+ * If, after decay, an element gets inserted again, its generation is set to 11b
+ * to make sure it has higher numerical count than other, older elements and
+ * thus emulate an LRU-like behavior when deleting elements to free up space
+ * in the page.
+ *
+ * When an element reaches it's max count of action_threshold, we try to poison
+ * it by assuming that errors triggered action_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. action_threshold is
+ * initialized to COUNT_MASK which is the maximum.
+ *
+ * That error event entry causes cec_add_elem() to return !0 value and thus
+ * signal to its callers to log the error.
+ *
+ * To the question why we've chosen a page and moving elements around with
+ * memmove(), it is because it is a very simple structure to handle and max data
+ * movement is 4K which on highly optimized modern CPUs is almost unnoticeable.
+ * We wanted to avoid the pointer traversal of more complex structures like a
+ * linked list or some sort of a balancing search tree.
+ *
+ * Deleting an element takes O(n) but since it is only a single page, it should
+ * be fast enough and it shouldn't happen all too often depending on error
+ * patterns.
+ */
+
+#undef pr_fmt
+#define pr_fmt(fmt) "RAS: " fmt
+
+/*
+ * We use DECAY_BITS bits of PAGE_SHIFT bits for counting decay, i.e., how long
+ * elements have stayed in the array without having been accessed again.
+ */
+#define DECAY_BITS		2
+#define DECAY_MASK		((1ULL << DECAY_BITS) - 1)
+#define MAX_ELEMS		(PAGE_SIZE / sizeof(u64))
+
+/*
+ * Threshold amount of inserted elements after which we start spring
+ * cleaning.
+ */
+#define CLEAN_ELEMS		(MAX_ELEMS >> DECAY_BITS)
+
+/* Bits which count the number of errors happened in this 4K page. */
+#define COUNT_BITS		(PAGE_SHIFT - DECAY_BITS)
+#define COUNT_MASK		((1ULL << COUNT_BITS) - 1)
+#define FULL_COUNT_MASK		(PAGE_SIZE - 1)
+
+/*
+ * u64: [ 63 ... 12 | DECAY_BITS | COUNT_BITS ]
+ */
+
+#define PFN(e)			((e) >> PAGE_SHIFT)
+#define DECAY(e)		(((e) >> COUNT_BITS) & DECAY_MASK)
+#define COUNT(e)		((unsigned int)(e) & COUNT_MASK)
+#define FULL_COUNT(e)		((e) & (PAGE_SIZE - 1))
+
+static struct ce_array {
+	u64 *array;			/* container page */
+	unsigned int n;			/* number of elements in the array */
+
+	unsigned int decay_count;	/*
+					 * number of element insertions/increments
+					 * since the last spring cleaning.
+					 */
+
+	u64 pfns_poisoned;		/*
+					 * number of PFNs which got poisoned.
+					 */
+
+	u64 ces_entered;		/*
+					 * The number of correctable errors
+					 * entered into the collector.
+					 */
+
+	u64 decays_done;		/*
+					 * Times we did spring cleaning.
+					 */
+
+	union {
+		struct {
+			__u32	disabled : 1,	/* cmdline disabled */
+			__resv   : 31;
+		};
+		__u32 flags;
+	};
+} ce_arr;
+
+static DEFINE_MUTEX(ce_mutex);
+static u64 dfs_pfn;
+
+/* Amount of errors after which we offline */
+static u64 action_threshold = COUNT_MASK;
+
+/* Each element "decays" each decay_interval which is 24hrs by default. */
+#define CEC_DECAY_DEFAULT_INTERVAL	24 * 60 * 60	/* 24 hrs */
+#define CEC_DECAY_MIN_INTERVAL		 1 * 60 * 60	/* 1h */
+#define CEC_DECAY_MAX_INTERVAL	   30 *	24 * 60 * 60	/* one month */
+static struct delayed_work cec_work;
+static u64 decay_interval = CEC_DECAY_DEFAULT_INTERVAL;
+
+/*
+ * Decrement decay value. We're using DECAY_BITS bits to denote decay of an
+ * element in the array. On insertion and any access, it gets reset to max.
+ */
+static void do_spring_cleaning(struct ce_array *ca)
+{
+	int i;
+
+	for (i = 0; i < ca->n; i++) {
+		u8 decay = DECAY(ca->array[i]);
+
+		if (!decay)
+			continue;
+
+		decay--;
+
+		ca->array[i] &= ~(DECAY_MASK << COUNT_BITS);
+		ca->array[i] |= (decay << COUNT_BITS);
+	}
+	ca->decay_count = 0;
+	ca->decays_done++;
+}
+
+/*
+ * @interval in seconds
+ */
+static void cec_mod_work(unsigned long interval)
+{
+	unsigned long iv;
+
+	iv = interval * HZ;
+	mod_delayed_work(system_wq, &cec_work, round_jiffies(iv));
+}
+
+static void cec_work_fn(struct work_struct *work)
+{
+	mutex_lock(&ce_mutex);
+	do_spring_cleaning(&ce_arr);
+	mutex_unlock(&ce_mutex);
+
+	cec_mod_work(decay_interval);
+}
+
+/*
+ * @to: index of the smallest element which is >= then @pfn.
+ *
+ * Return the index of the pfn if found, otherwise negative value.
+ */
+static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	int min = 0, max = ca->n - 1;
+	u64 this_pfn;
+
+	while (min <= max) {
+		int i = (min + max) >> 1;
+
+		this_pfn = PFN(ca->array[i]);
+
+		if (this_pfn < pfn)
+			min = i + 1;
+		else if (this_pfn > pfn)
+			max = i - 1;
+		else if (this_pfn == pfn) {
+			if (to)
+				*to = i;
+
+			return i;
+		}
+	}
+
+	/*
+	 * When the loop terminates without finding @pfn, min has the index of
+	 * the element slot where the new @pfn should be inserted. The loop
+	 * terminates when min > max, which means the min index points to the
+	 * bigger element while the max index to the smaller element, in-between
+	 * which the new @pfn belongs to.
+	 *
+	 * For more details, see exercise 1, Section 6.2.1 in TAOCP, vol. 3.
+	 */
+	if (to)
+		*to = min;
+
+	return -ENOKEY;
+}
+
+static int find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+	WARN_ON(!to);
+
+	if (!ca->n) {
+		*to = 0;
+		return -ENOKEY;
+	}
+	return __find_elem(ca, pfn, to);
+}
+
+static void del_elem(struct ce_array *ca, int idx)
+{
+	/* Save us a function call when deleting the last element. */
+	if (ca->n - (idx + 1))
+		memmove((void *)&ca->array[idx],
+			(void *)&ca->array[idx + 1],
+			(ca->n - (idx + 1)) * sizeof(u64));
+
+	ca->n--;
+}
+
+static u64 del_lru_elem_unlocked(struct ce_array *ca)
+{
+	unsigned int min = FULL_COUNT_MASK;
+	int i, min_idx = 0;
+
+	for (i = 0; i < ca->n; i++) {
+		unsigned int this = FULL_COUNT(ca->array[i]);
+
+		if (min > this) {
+			min = this;
+			min_idx = i;
+		}
+	}
+
+	del_elem(ca, min_idx);
+
+	return PFN(ca->array[min_idx]);
+}
+
+/*
+ * We return the 0th pfn in the error case under the assumption that it cannot
+ * be poisoned and excessive CEs in there are a serious deal anyway.
+ */
+static u64 __maybe_unused del_lru_elem(void)
+{
+	struct ce_array *ca = &ce_arr;
+	u64 pfn;
+
+	if (!ca->n)
+		return 0;
+
+	mutex_lock(&ce_mutex);
+	pfn = del_lru_elem_unlocked(ca);
+	mutex_unlock(&ce_mutex);
+
+	return pfn;
+}
+
+static bool sanity_check(struct ce_array *ca)
+{
+	bool ret = false;
+	u64 prev = 0;
+	int i;
+
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		if (WARN(prev > this, "prev: 0x%016llx <-> this: 0x%016llx\n", prev, this))
+			ret = true;
+
+		prev = this;
+	}
+
+	if (!ret)
+		return ret;
+
+	pr_info("Sanity check dump:\n{ n: %d\n", ca->n);
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		pr_info(" %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+	}
+	pr_info("}\n");
+
+	return ret;
+}
+
+/**
+ * cec_add_elem - Add an element to the CEC array.
+ * @pfn:	page frame number to insert
+ *
+ * Return values:
+ * - <0:	on error
+ * -  0:	on success
+ * - >0:	when the inserted pfn was offlined
+ */
+static int cec_add_elem(u64 pfn)
+{
+	struct ce_array *ca = &ce_arr;
+	int count, err, ret = 0;
+	unsigned int to = 0;
+
+	/*
+	 * We can be called very early on the identify_cpu() path where we are
+	 * not initialized yet. We ignore the error for simplicity.
+	 */
+	if (!ce_arr.array || ce_arr.disabled)
+		return -ENODEV;
+
+	mutex_lock(&ce_mutex);
+
+	ca->ces_entered++;
+
+	/* Array full, free the LRU slot. */
+	if (ca->n == MAX_ELEMS)
+		WARN_ON(!del_lru_elem_unlocked(ca));
+
+	err = find_elem(ca, pfn, &to);
+	if (err < 0) {
+		/*
+		 * Shift range [to-end] to make room for one more element.
+		 */
+		memmove((void *)&ca->array[to + 1],
+			(void *)&ca->array[to],
+			(ca->n - to) * sizeof(u64));
+
+		ca->array[to] = pfn << PAGE_SHIFT;
+		ca->n++;
+	}
+
+	/* Add/refresh element generation and increment count */
+	ca->array[to] |= DECAY_MASK << COUNT_BITS;
+	ca->array[to]++;
+
+	/* Check action threshold and soft-offline, if reached. */
+	count = COUNT(ca->array[to]);
+	if (count >= action_threshold) {
+		u64 pfn = ca->array[to] >> PAGE_SHIFT;
+
+		if (!pfn_valid(pfn)) {
+			pr_warn("CEC: Invalid pfn: 0x%llx\n", pfn);
+		} else {
+			/* We have reached max count for this page, soft-offline it. */
+			pr_err("Soft-offlining pfn: 0x%llx\n", pfn);
+			memory_failure_queue(pfn, MF_SOFT_OFFLINE);
+			ca->pfns_poisoned++;
+		}
+
+		del_elem(ca, to);
+
+		/*
+		 * Return a >0 value to callers, to denote that we've reached
+		 * the offlining threshold.
+		 */
+		ret = 1;
+
+		goto unlock;
+	}
+
+	ca->decay_count++;
+
+	if (ca->decay_count >= CLEAN_ELEMS)
+		do_spring_cleaning(ca);
+
+	WARN_ON_ONCE(sanity_check(ca));
+
+unlock:
+	mutex_unlock(&ce_mutex);
+
+	return ret;
+}
+
+static int u64_get(void *data, u64 *val)
+{
+	*val = *(u64 *)data;
+
+	return 0;
+}
+
+static int pfn_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	cec_add_elem(val);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
+
+static int decay_interval_set(void *data, u64 val)
+{
+	if (val < CEC_DECAY_MIN_INTERVAL)
+		return -EINVAL;
+
+	if (val > CEC_DECAY_MAX_INTERVAL)
+		return -EINVAL;
+
+	*(u64 *)data   = val;
+	decay_interval = val;
+
+	cec_mod_work(decay_interval);
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
+
+static int action_threshold_set(void *data, u64 val)
+{
+	*(u64 *)data = val;
+
+	if (val > COUNT_MASK)
+		val = COUNT_MASK;
+
+	action_threshold = val;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(action_threshold_ops, u64_get, action_threshold_set, "%lld\n");
+
+static const char * const bins[] = { "00", "01", "10", "11" };
+
+static int array_show(struct seq_file *m, void *v)
+{
+	struct ce_array *ca = &ce_arr;
+	int i;
+
+	mutex_lock(&ce_mutex);
+
+	seq_printf(m, "{ n: %d\n", ca->n);
+	for (i = 0; i < ca->n; i++) {
+		u64 this = PFN(ca->array[i]);
+
+		seq_printf(m, " %3d: [%016llx|%s|%03llx]\n",
+			   i, this, bins[DECAY(ca->array[i])], COUNT(ca->array[i]));
+	}
+
+	seq_printf(m, "}\n");
+
+	seq_printf(m, "Stats:\nCEs: %llu\nofflined pages: %llu\n",
+		   ca->ces_entered, ca->pfns_poisoned);
+
+	seq_printf(m, "Flags: 0x%x\n", ca->flags);
+
+	seq_printf(m, "Decay interval: %lld seconds\n", decay_interval);
+	seq_printf(m, "Decays: %lld\n", ca->decays_done);
+
+	seq_printf(m, "Action threshold: %lld\n", action_threshold);
+
+	mutex_unlock(&ce_mutex);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(array);
+
+static int __init create_debugfs_nodes(void)
+{
+	struct dentry *d, *pfn, *decay, *count, *array;
+
+	d = debugfs_create_dir("cec", ras_debugfs_dir);
+	if (!d) {
+		pr_warn("Error creating cec debugfs node!\n");
+		return -1;
+	}
+
+	decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
+				    &decay_interval, &decay_interval_ops);
+	if (!decay) {
+		pr_warn("Error creating decay_interval debugfs node!\n");
+		goto err;
+	}
+
+	count = debugfs_create_file("action_threshold", S_IRUSR | S_IWUSR, d,
+				    &action_threshold, &action_threshold_ops);
+	if (!count) {
+		pr_warn("Error creating action_threshold debugfs node!\n");
+		goto err;
+	}
+
+	if (!IS_ENABLED(CONFIG_RAS_CEC_DEBUG))
+		return 0;
+
+	pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
+	if (!pfn) {
+		pr_warn("Error creating pfn debugfs node!\n");
+		goto err;
+	}
+
+	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_fops);
+	if (!array) {
+		pr_warn("Error creating array debugfs node!\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	debugfs_remove_recursive(d);
+
+	return 1;
+}
+
+static int cec_notifier(struct notifier_block *nb, unsigned long val,
+			void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	/* We eat only correctable DRAM errors with usable addresses. */
+	if (mce_is_memory_error(m) &&
+	    mce_is_correctable(m)  &&
+	    mce_usable_address(m)) {
+		if (!cec_add_elem(m->addr >> PAGE_SHIFT)) {
+			m->kflags |= MCE_HANDLED_CEC;
+			return NOTIFY_OK;
+		}
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block cec_nb = {
+	.notifier_call	= cec_notifier,
+	.priority	= MCE_PRIO_CEC,
+};
+
+static int __init cec_init(void)
+{
+	if (ce_arr.disabled)
+		return -ENODEV;
+
+	/*
+	 * Intel systems may avoid uncorrectable errors
+	 * if pages with corrected errors are aggressively
+	 * taken offline.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		action_threshold = 2;
+
+	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!ce_arr.array) {
+		pr_err("Error allocating CE array page!\n");
+		return -ENOMEM;
+	}
+
+	if (create_debugfs_nodes()) {
+		free_page((unsigned long)ce_arr.array);
+		return -ENOMEM;
+	}
+
+	INIT_DELAYED_WORK(&cec_work, cec_work_fn);
+	schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL);
+
+	mce_register_decode_chain(&cec_nb);
+
+	pr_info("Correctable Errors collector initialized.\n");
+	return 0;
+}
+late_initcall(cec_init);
+
+int __init parse_cec_param(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (*str == '=')
+		str++;
+
+	if (!strcmp(str, "cec_disable"))
+		ce_arr.disabled = 1;
+	else
+		return 0;
+
+	return 1;
+}