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, 858 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
new file mode 100644
index 000000000..63fd925cc
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -0,0 +1,858 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PowerPC64 LPAR Configuration Information Driver
+ *
+ * Dave Engebretsen engebret@us.ibm.com
+ *    Copyright (c) 2003 Dave Engebretsen
+ * Will Schmidt willschm@us.ibm.com
+ *    SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation.
+ *    seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation.
+ * Nathan Lynch nathanl@austin.ibm.com
+ *    Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation.
+ *
+ * This driver creates a proc file at /proc/ppc64/lparcfg which contains
+ * keyword - value pairs that specify the configuration of the partition.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/hugetlb.h>
+#include <asm/lppaca.h>
+#include <asm/hvcall.h>
+#include <asm/firmware.h>
+#include <asm/rtas.h>
+#include <asm/time.h>
+#include <asm/vdso_datapage.h>
+#include <asm/vio.h>
+#include <asm/mmu.h>
+#include <asm/machdep.h>
+#include <asm/drmem.h>
+
+#include "pseries.h"
+#include "vas.h"	/* pseries_vas_dlpar_cpu() */
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
+#define MODULE_VERS "1.9"
+#define MODULE_NAME "lparcfg"
+
+/* #define LPARCFG_DEBUG */
+
+/*
+ * Track sum of all purrs across all processors. This is used to further
+ * calculate usage values by different applications
+ */
+static void cpu_get_purr(void *arg)
+{
+	atomic64_t *sum = arg;
+
+	atomic64_add(mfspr(SPRN_PURR), sum);
+}
+
+static unsigned long get_purr(void)
+{
+	atomic64_t purr = ATOMIC64_INIT(0);
+
+	on_each_cpu(cpu_get_purr, &purr, 1);
+
+	return atomic64_read(&purr);
+}
+
+/*
+ * Methods used to fetch LPAR data when running on a pSeries platform.
+ */
+
+struct hvcall_ppp_data {
+	u64	entitlement;
+	u64	unallocated_entitlement;
+	u16	group_num;
+	u16	pool_num;
+	u8	capped;
+	u8	weight;
+	u8	unallocated_weight;
+	u16	active_procs_in_pool;
+	u16	active_system_procs;
+	u16	phys_platform_procs;
+	u32	max_proc_cap_avail;
+	u32	entitled_proc_cap_avail;
+};
+
+/*
+ * H_GET_PPP hcall returns info in 4 parms.
+ *  entitled_capacity,unallocated_capacity,
+ *  aggregation, resource_capability).
+ *
+ *  R4 = Entitled Processor Capacity Percentage.
+ *  R5 = Unallocated Processor Capacity Percentage.
+ *  R6 (AABBCCDDEEFFGGHH).
+ *      XXXX - reserved (0)
+ *          XXXX - reserved (0)
+ *              XXXX - Group Number
+ *                  XXXX - Pool Number.
+ *  R7 (IIJJKKLLMMNNOOPP).
+ *      XX - reserved. (0)
+ *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
+ *          XX - variable processor Capacity Weight
+ *            XX - Unallocated Variable Processor Capacity Weight.
+ *              XXXX - Active processors in Physical Processor Pool.
+ *                  XXXX  - Processors active on platform.
+ *  R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1
+ *	XXXX - Physical platform procs allocated to virtualization.
+ *	    XXXXXX - Max procs capacity % available to the partitions pool.
+ *	          XXXXXX - Entitled procs capacity % available to the
+ *			   partitions pool.
+ */
+static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
+{
+	unsigned long rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	rc = plpar_hcall9(H_GET_PPP, retbuf);
+
+	ppp_data->entitlement = retbuf[0];
+	ppp_data->unallocated_entitlement = retbuf[1];
+
+	ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
+	ppp_data->pool_num = retbuf[2] & 0xffff;
+
+	ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
+	ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
+	ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
+	ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff;
+	ppp_data->active_system_procs = retbuf[3] & 0xffff;
+
+	ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8;
+	ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff;
+	ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff;
+
+	return rc;
+}
+
+static void show_gpci_data(struct seq_file *m)
+{
+	struct hv_gpci_request_buffer *buf;
+	unsigned int affinity_score;
+	long ret;
+
+	buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+	if (buf == NULL)
+		return;
+
+	/*
+	 * Show the local LPAR's affinity score.
+	 *
+	 * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall.
+	 * The score is at byte 0xB in the output buffer.
+	 */
+	memset(&buf->params, 0, sizeof(buf->params));
+	buf->params.counter_request = cpu_to_be32(0xB1);
+	buf->params.starting_index = cpu_to_be32(-1);	/* local LPAR */
+	buf->params.counter_info_version_in = 0x5;	/* v5+ for score */
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf),
+				 sizeof(*buf));
+	if (ret != H_SUCCESS) {
+		pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n",
+			 ret, be32_to_cpu(buf->params.detail_rc));
+		goto out;
+	}
+	affinity_score = buf->bytes[0xB];
+	seq_printf(m, "partition_affinity_score=%u\n", affinity_score);
+out:
+	kfree(buf);
+}
+
+static unsigned h_pic(unsigned long *pool_idle_time,
+		      unsigned long *num_procs)
+{
+	unsigned long rc;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	rc = plpar_hcall(H_PIC, retbuf);
+
+	*pool_idle_time = retbuf[0];
+	*num_procs = retbuf[1];
+
+	return rc;
+}
+
+/*
+ * parse_ppp_data
+ * Parse out the data returned from h_get_ppp and h_pic
+ */
+static void parse_ppp_data(struct seq_file *m)
+{
+	struct hvcall_ppp_data ppp_data;
+	struct device_node *root;
+	const __be32 *perf_level;
+	int rc;
+
+	rc = h_get_ppp(&ppp_data);
+	if (rc)
+		return;
+
+	seq_printf(m, "partition_entitled_capacity=%lld\n",
+	           ppp_data.entitlement);
+	seq_printf(m, "group=%d\n", ppp_data.group_num);
+	seq_printf(m, "system_active_processors=%d\n",
+	           ppp_data.active_system_procs);
+
+	/* pool related entries are appropriate for shared configs */
+	if (lppaca_shared_proc(get_lppaca())) {
+		unsigned long pool_idle_time, pool_procs;
+
+		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
+
+		/* report pool_capacity in percentage */
+		seq_printf(m, "pool_capacity=%d\n",
+			   ppp_data.active_procs_in_pool * 100);
+
+		h_pic(&pool_idle_time, &pool_procs);
+		seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+		seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+	}
+
+	seq_printf(m, "unallocated_capacity_weight=%d\n",
+		   ppp_data.unallocated_weight);
+	seq_printf(m, "capacity_weight=%d\n", ppp_data.weight);
+	seq_printf(m, "capped=%d\n", ppp_data.capped);
+	seq_printf(m, "unallocated_capacity=%lld\n",
+		   ppp_data.unallocated_entitlement);
+
+	/* The last bits of information returned from h_get_ppp are only
+	 * valid if the ibm,partition-performance-parameters-level
+	 * property is >= 1.
+	 */
+	root = of_find_node_by_path("/");
+	if (root) {
+		perf_level = of_get_property(root,
+				"ibm,partition-performance-parameters-level",
+					     NULL);
+		if (perf_level && (be32_to_cpup(perf_level) >= 1)) {
+			seq_printf(m,
+			    "physical_procs_allocated_to_virtualization=%d\n",
+				   ppp_data.phys_platform_procs);
+			seq_printf(m, "max_proc_capacity_available=%d\n",
+				   ppp_data.max_proc_cap_avail);
+			seq_printf(m, "entitled_proc_capacity_available=%d\n",
+				   ppp_data.entitled_proc_cap_avail);
+		}
+
+		of_node_put(root);
+	}
+}
+
+/**
+ * parse_mpp_data
+ * Parse out data returned from h_get_mpp
+ */
+static void parse_mpp_data(struct seq_file *m)
+{
+	struct hvcall_mpp_data mpp_data;
+	int rc;
+
+	rc = h_get_mpp(&mpp_data);
+	if (rc)
+		return;
+
+	seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem);
+
+	if (mpp_data.mapped_mem != -1)
+		seq_printf(m, "mapped_entitled_memory=%ld\n",
+		           mpp_data.mapped_mem);
+
+	seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num);
+	seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num);
+
+	seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight);
+	seq_printf(m, "unallocated_entitled_memory_weight=%d\n",
+	           mpp_data.unallocated_mem_weight);
+	seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n",
+	           mpp_data.unallocated_entitlement);
+
+	if (mpp_data.pool_size != -1)
+		seq_printf(m, "entitled_memory_pool_size=%ld bytes\n",
+		           mpp_data.pool_size);
+
+	seq_printf(m, "entitled_memory_loan_request=%ld\n",
+	           mpp_data.loan_request);
+
+	seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem);
+}
+
+/**
+ * parse_mpp_x_data
+ * Parse out data returned from h_get_mpp_x
+ */
+static void parse_mpp_x_data(struct seq_file *m)
+{
+	struct hvcall_mpp_x_data mpp_x_data;
+
+	if (!firmware_has_feature(FW_FEATURE_XCMO))
+		return;
+	if (h_get_mpp_x(&mpp_x_data))
+		return;
+
+	seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes);
+
+	if (mpp_x_data.pool_coalesced_bytes)
+		seq_printf(m, "pool_coalesced_bytes=%ld\n",
+			   mpp_x_data.pool_coalesced_bytes);
+	if (mpp_x_data.pool_purr_cycles)
+		seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles);
+	if (mpp_x_data.pool_spurr_cycles)
+		seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles);
+}
+
+/*
+ * PAPR defines, in section "7.3.16 System Parameters Option", the token 55 to
+ * read the LPAR name, and the largest output data to 4000 + 2 bytes length.
+ */
+#define SPLPAR_LPAR_NAME_TOKEN	55
+#define GET_SYS_PARM_BUF_SIZE	4002
+#if GET_SYS_PARM_BUF_SIZE > RTAS_DATA_BUF_SIZE
+#error "GET_SYS_PARM_BUF_SIZE is larger than RTAS_DATA_BUF_SIZE"
+#endif
+
+/*
+ * Read the lpar name using the RTAS ibm,get-system-parameter call.
+ *
+ * The name read through this call is updated if changes are made by the end
+ * user on the hypervisor side.
+ *
+ * Some hypervisor (like Qemu) may not provide this value. In that case, a non
+ * null value is returned.
+ */
+static int read_rtas_lpar_name(struct seq_file *m)
+{
+	int rc, len, token;
+	union {
+		char raw_buffer[GET_SYS_PARM_BUF_SIZE];
+		struct {
+			__be16 len;
+			char name[GET_SYS_PARM_BUF_SIZE-2];
+		};
+	} *local_buffer;
+
+	token = rtas_token("ibm,get-system-parameter");
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	local_buffer = kmalloc(sizeof(*local_buffer), GFP_KERNEL);
+	if (!local_buffer)
+		return -ENOMEM;
+
+	do {
+		spin_lock(&rtas_data_buf_lock);
+		memset(rtas_data_buf, 0, sizeof(*local_buffer));
+		rc = rtas_call(token, 3, 1, NULL, SPLPAR_LPAR_NAME_TOKEN,
+			       __pa(rtas_data_buf), sizeof(*local_buffer));
+		if (!rc)
+			memcpy(local_buffer->raw_buffer, rtas_data_buf,
+			       sizeof(local_buffer->raw_buffer));
+		spin_unlock(&rtas_data_buf_lock);
+	} while (rtas_busy_delay(rc));
+
+	if (!rc) {
+		/* Force end of string */
+		len = min((int) be16_to_cpu(local_buffer->len),
+			  (int) sizeof(local_buffer->name)-1);
+		local_buffer->name[len] = '\0';
+
+		seq_printf(m, "partition_name=%s\n", local_buffer->name);
+	} else
+		rc = -ENODATA;
+
+	kfree(local_buffer);
+	return rc;
+}
+
+/*
+ * Read the LPAR name from the Device Tree.
+ *
+ * The value read in the DT is not updated if the end-user is touching the LPAR
+ * name on the hypervisor side.
+ */
+static int read_dt_lpar_name(struct seq_file *m)
+{
+	const char *name;
+
+	if (of_property_read_string(of_root, "ibm,partition-name", &name))
+		return -ENOENT;
+
+	seq_printf(m, "partition_name=%s\n", name);
+	return 0;
+}
+
+static void read_lpar_name(struct seq_file *m)
+{
+	if (read_rtas_lpar_name(m) && read_dt_lpar_name(m))
+		pr_err_once("Error can't get the LPAR name");
+}
+
+#define SPLPAR_CHARACTERISTICS_TOKEN 20
+#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
+
+/*
+ * parse_system_parameter_string()
+ * Retrieve the potential_processors, max_entitled_capacity and friends
+ * through the get-system-parameter rtas call.  Replace keyword strings as
+ * necessary.
+ */
+static void parse_system_parameter_string(struct seq_file *m)
+{
+	int call_status;
+
+	unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+	if (!local_buffer) {
+		printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
+		       __FILE__, __func__, __LINE__);
+		return;
+	}
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_CHARACTERISTICS_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH);
+	local_buffer[SPLPAR_MAXLENGTH - 1] = '\0';
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		printk(KERN_INFO
+		       "%s %s Error calling get-system-parameter (0x%x)\n",
+		       __FILE__, __func__, call_status);
+	} else {
+		int splpar_strlen;
+		int idx, w_idx;
+		char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+		if (!workbuffer) {
+			printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
+			       __FILE__, __func__, __LINE__);
+			kfree(local_buffer);
+			return;
+		}
+#ifdef LPARCFG_DEBUG
+		printk(KERN_INFO "success calling get-system-parameter\n");
+#endif
+		splpar_strlen = local_buffer[0] * 256 + local_buffer[1];
+		local_buffer += 2;	/* step over strlen value */
+
+		w_idx = 0;
+		idx = 0;
+		while ((*local_buffer) && (idx < splpar_strlen)) {
+			workbuffer[w_idx++] = local_buffer[idx++];
+			if ((local_buffer[idx] == ',')
+			    || (local_buffer[idx] == '\0')) {
+				workbuffer[w_idx] = '\0';
+				if (w_idx) {
+					/* avoid the empty string */
+					seq_printf(m, "%s\n", workbuffer);
+				}
+				memset(workbuffer, 0, SPLPAR_MAXLENGTH);
+				idx++;	/* skip the comma */
+				w_idx = 0;
+			} else if (local_buffer[idx] == '=') {
+				/* code here to replace workbuffer contents
+				   with different keyword strings */
+				if (0 == strcmp(workbuffer, "MaxEntCap")) {
+					strcpy(workbuffer,
+					       "partition_max_entitled_capacity");
+					w_idx = strlen(workbuffer);
+				}
+				if (0 == strcmp(workbuffer, "MaxPlatProcs")) {
+					strcpy(workbuffer,
+					       "system_potential_processors");
+					w_idx = strlen(workbuffer);
+				}
+			}
+		}
+		kfree(workbuffer);
+		local_buffer -= 2;	/* back up over strlen value */
+	}
+	kfree(local_buffer);
+}
+
+/* Return the number of processors in the system.
+ * This function reads through the device tree and counts
+ * the virtual processors, this does not include threads.
+ */
+static int lparcfg_count_active_processors(void)
+{
+	struct device_node *cpus_dn;
+	int count = 0;
+
+	for_each_node_by_type(cpus_dn, "cpu") {
+#ifdef LPARCFG_DEBUG
+		printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
+#endif
+		count++;
+	}
+	return count;
+}
+
+static void pseries_cmo_data(struct seq_file *m)
+{
+	int cpu;
+	unsigned long cmo_faults = 0;
+	unsigned long cmo_fault_time = 0;
+
+	seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO));
+
+	if (!firmware_has_feature(FW_FEATURE_CMO))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		cmo_faults += be64_to_cpu(lppaca_of(cpu).cmo_faults);
+		cmo_fault_time += be64_to_cpu(lppaca_of(cpu).cmo_fault_time);
+	}
+
+	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
+	seq_printf(m, "cmo_fault_time_usec=%lu\n",
+		   cmo_fault_time / tb_ticks_per_usec);
+	seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp());
+	seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp());
+	seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size());
+}
+
+static void splpar_dispatch_data(struct seq_file *m)
+{
+	int cpu;
+	unsigned long dispatches = 0;
+	unsigned long dispatch_dispersions = 0;
+
+	for_each_possible_cpu(cpu) {
+		dispatches += be32_to_cpu(lppaca_of(cpu).yield_count);
+		dispatch_dispersions +=
+			be32_to_cpu(lppaca_of(cpu).dispersion_count);
+	}
+
+	seq_printf(m, "dispatches=%lu\n", dispatches);
+	seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions);
+}
+
+static void parse_em_data(struct seq_file *m)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
+}
+
+static void maxmem_data(struct seq_file *m)
+{
+	unsigned long maxmem = 0;
+
+	maxmem += (unsigned long)drmem_info->n_lmbs * drmem_info->lmb_size;
+	maxmem += hugetlb_total_pages() * PAGE_SIZE;
+
+	seq_printf(m, "MaxMem=%lu\n", maxmem);
+}
+
+static int pseries_lparcfg_data(struct seq_file *m, void *v)
+{
+	int partition_potential_processors;
+	int partition_active_processors;
+	struct device_node *rtas_node;
+	const __be32 *lrdrp = NULL;
+
+	rtas_node = of_find_node_by_path("/rtas");
+	if (rtas_node)
+		lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
+
+	if (lrdrp == NULL) {
+		partition_potential_processors = vdso_data->processorCount;
+	} else {
+		partition_potential_processors = be32_to_cpup(lrdrp + 4);
+	}
+	of_node_put(rtas_node);
+
+	partition_active_processors = lparcfg_count_active_processors();
+
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		/* this call handles the ibm,get-system-parameter contents */
+		read_lpar_name(m);
+		parse_system_parameter_string(m);
+		parse_ppp_data(m);
+		parse_mpp_data(m);
+		parse_mpp_x_data(m);
+		pseries_cmo_data(m);
+		splpar_dispatch_data(m);
+
+		seq_printf(m, "purr=%ld\n", get_purr());
+		seq_printf(m, "tbr=%ld\n", mftb());
+	} else {		/* non SPLPAR case */
+
+		seq_printf(m, "system_active_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "system_potential_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "partition_max_entitled_capacity=%d\n",
+			   partition_potential_processors * 100);
+
+		seq_printf(m, "partition_entitled_capacity=%d\n",
+			   partition_active_processors * 100);
+	}
+
+	show_gpci_data(m);
+
+	seq_printf(m, "partition_active_processors=%d\n",
+		   partition_active_processors);
+
+	seq_printf(m, "partition_potential_processors=%d\n",
+		   partition_potential_processors);
+
+	seq_printf(m, "shared_processor_mode=%d\n",
+		   lppaca_shared_proc(get_lppaca()));
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+	if (!radix_enabled())
+		seq_printf(m, "slb_size=%d\n", mmu_slb_size);
+#endif
+	parse_em_data(m);
+	maxmem_data(m);
+
+	seq_printf(m, "security_flavor=%u\n", pseries_security_flavor);
+
+	return 0;
+}
+
+static ssize_t update_ppp(u64 *entitlement, u8 *weight)
+{
+	struct hvcall_ppp_data ppp_data;
+	u8 new_weight;
+	u64 new_entitled;
+	ssize_t retval;
+
+	/* Get our current parameters */
+	retval = h_get_ppp(&ppp_data);
+	if (retval)
+		return retval;
+
+	if (entitlement) {
+		new_weight = ppp_data.weight;
+		new_entitled = *entitlement;
+	} else if (weight) {
+		new_weight = *weight;
+		new_entitled = ppp_data.entitlement;
+	} else
+		return -EINVAL;
+
+	pr_debug("%s: current_entitled = %llu, current_weight = %u\n",
+		 __func__, ppp_data.entitlement, ppp_data.weight);
+
+	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
+		 __func__, new_entitled, new_weight);
+
+	retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight);
+	return retval;
+}
+
+/**
+ * update_mpp
+ *
+ * Update the memory entitlement and weight for the partition.  Caller must
+ * specify either a new entitlement or weight, not both, to be updated
+ * since the h_set_mpp call takes both entitlement and weight as parameters.
+ */
+static ssize_t update_mpp(u64 *entitlement, u8 *weight)
+{
+	struct hvcall_mpp_data mpp_data;
+	u64 new_entitled;
+	u8 new_weight;
+	ssize_t rc;
+
+	if (entitlement) {
+		/* Check with vio to ensure the new memory entitlement
+		 * can be handled.
+		 */
+		rc = vio_cmo_entitlement_update(*entitlement);
+		if (rc)
+			return rc;
+	}
+
+	rc = h_get_mpp(&mpp_data);
+	if (rc)
+		return rc;
+
+	if (entitlement) {
+		new_weight = mpp_data.mem_weight;
+		new_entitled = *entitlement;
+	} else if (weight) {
+		new_weight = *weight;
+		new_entitled = mpp_data.entitled_mem;
+	} else
+		return -EINVAL;
+
+	pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
+	         __func__, mpp_data.entitled_mem, mpp_data.mem_weight);
+
+	pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
+		 __func__, new_entitled, new_weight);
+
+	rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight);
+	return rc;
+}
+
+/*
+ * Interface for changing system parameters (variable capacity weight
+ * and entitled capacity).  Format of input is "param_name=value";
+ * anything after value is ignored.  Valid parameters at this time are
+ * "partition_entitled_capacity" and "capacity_weight".  We use
+ * H_SET_PPP to alter parameters.
+ *
+ * This function should be invoked only on systems with
+ * FW_FEATURE_SPLPAR.
+ */
+static ssize_t lparcfg_write(struct file *file, const char __user * buf,
+			     size_t count, loff_t * off)
+{
+	char kbuf[64];
+	char *tmp;
+	u64 new_entitled, *new_entitled_ptr = &new_entitled;
+	u8 new_weight, *new_weight_ptr = &new_weight;
+	ssize_t retval;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return -EINVAL;
+
+	if (count > sizeof(kbuf))
+		return -EINVAL;
+
+	if (copy_from_user(kbuf, buf, count))
+		return -EFAULT;
+
+	kbuf[count - 1] = '\0';
+	tmp = strchr(kbuf, '=');
+	if (!tmp)
+		return -EINVAL;
+
+	*tmp++ = '\0';
+
+	if (!strcmp(kbuf, "partition_entitled_capacity")) {
+		char *endp;
+		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_ppp(new_entitled_ptr, NULL);
+
+		if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+			/*
+			 * The hypervisor assigns VAS resources based
+			 * on entitled capacity for shared mode.
+			 * Reconfig VAS windows based on DLPAR CPU events.
+			 */
+			if (pseries_vas_dlpar_cpu() != 0)
+				retval = H_HARDWARE;
+		}
+	} else if (!strcmp(kbuf, "capacity_weight")) {
+		char *endp;
+		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_ppp(NULL, new_weight_ptr);
+	} else if (!strcmp(kbuf, "entitled_memory")) {
+		char *endp;
+		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_mpp(new_entitled_ptr, NULL);
+	} else if (!strcmp(kbuf, "entitled_memory_weight")) {
+		char *endp;
+		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			return -EINVAL;
+
+		retval = update_mpp(NULL, new_weight_ptr);
+	} else
+		return -EINVAL;
+
+	if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+		retval = count;
+	} else if (retval == H_BUSY) {
+		retval = -EBUSY;
+	} else if (retval == H_HARDWARE) {
+		retval = -EIO;
+	} else if (retval == H_PARAMETER) {
+		retval = -EINVAL;
+	}
+
+	return retval;
+}
+
+static int lparcfg_data(struct seq_file *m, void *v)
+{
+	struct device_node *rootdn;
+	const char *model = "";
+	const char *system_id = "";
+	const char *tmp;
+	const __be32 *lp_index_ptr;
+	unsigned int lp_index = 0;
+
+	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
+
+	rootdn = of_find_node_by_path("/");
+	if (rootdn) {
+		tmp = of_get_property(rootdn, "model", NULL);
+		if (tmp)
+			model = tmp;
+		tmp = of_get_property(rootdn, "system-id", NULL);
+		if (tmp)
+			system_id = tmp;
+		lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
+					NULL);
+		if (lp_index_ptr)
+			lp_index = be32_to_cpup(lp_index_ptr);
+		of_node_put(rootdn);
+	}
+	seq_printf(m, "serial_number=%s\n", system_id);
+	seq_printf(m, "system_type=%s\n", model);
+	seq_printf(m, "partition_id=%d\n", (int)lp_index);
+
+	return pseries_lparcfg_data(m, v);
+}
+
+static int lparcfg_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, lparcfg_data, NULL);
+}
+
+static const struct proc_ops lparcfg_proc_ops = {
+	.proc_read	= seq_read,
+	.proc_write	= lparcfg_write,
+	.proc_open	= lparcfg_open,
+	.proc_release	= single_release,
+	.proc_lseek	= seq_lseek,
+};
+
+static int __init lparcfg_init(void)
+{
+	umode_t mode = 0444;
+
+	/* Allow writing if we have FW_FEATURE_SPLPAR */
+	if (firmware_has_feature(FW_FEATURE_SPLPAR))
+		mode |= 0200;
+
+	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_proc_ops)) {
+		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
+		return -EIO;
+	}
+	return 0;
+}
+machine_device_initcall(pseries, lparcfg_init);