aboutsummaryrefslogtreecommitdiff
path: root/init/do_mounts_rd.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /init/do_mounts_rd.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
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(). ...
Diffstat (limited to 'init/do_mounts_rd.c')
-rw-r--r--init/do_mounts_rd.c334
1 files changed, 334 insertions, 0 deletions
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
new file mode 100644
index 000000000..ac021ae6e
--- /dev/null
+++ b/init/do_mounts_rd.c
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/minix_fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/romfs_fs.h>
+#include <uapi/linux/cramfs_fs.h>
+#include <linux/initrd.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+#include "do_mounts.h"
+#include "../fs/squashfs/squashfs_fs.h"
+
+#include <linux/decompress/generic.h>
+
+static struct file *in_file, *out_file;
+static loff_t in_pos, out_pos;
+
+static int __init prompt_ramdisk(char *str)
+{
+ pr_warn("ignoring the deprecated prompt_ramdisk= option\n");
+ return 1;
+}
+__setup("prompt_ramdisk=", prompt_ramdisk);
+
+int __initdata rd_image_start; /* starting block # of image */
+
+static int __init ramdisk_start_setup(char *str)
+{
+ rd_image_start = simple_strtol(str,NULL,0);
+ return 1;
+}
+__setup("ramdisk_start=", ramdisk_start_setup);
+
+static int __init crd_load(decompress_fn deco);
+
+/*
+ * This routine tries to find a RAM disk image to load, and returns the
+ * number of blocks to read for a non-compressed image, 0 if the image
+ * is a compressed image, and -1 if an image with the right magic
+ * numbers could not be found.
+ *
+ * We currently check for the following magic numbers:
+ * minix
+ * ext2
+ * romfs
+ * cramfs
+ * squashfs
+ * gzip
+ * bzip2
+ * lzma
+ * xz
+ * lzo
+ * lz4
+ */
+static int __init
+identify_ramdisk_image(struct file *file, loff_t pos,
+ decompress_fn *decompressor)
+{
+ const int size = 512;
+ struct minix_super_block *minixsb;
+ struct romfs_super_block *romfsb;
+ struct cramfs_super *cramfsb;
+ struct squashfs_super_block *squashfsb;
+ int nblocks = -1;
+ unsigned char *buf;
+ const char *compress_name;
+ unsigned long n;
+ int start_block = rd_image_start;
+
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ minixsb = (struct minix_super_block *) buf;
+ romfsb = (struct romfs_super_block *) buf;
+ cramfsb = (struct cramfs_super *) buf;
+ squashfsb = (struct squashfs_super_block *) buf;
+ memset(buf, 0xe5, size);
+
+ /*
+ * Read block 0 to test for compressed kernel
+ */
+ pos = start_block * BLOCK_SIZE;
+ kernel_read(file, buf, size, &pos);
+
+ *decompressor = decompress_method(buf, size, &compress_name);
+ if (compress_name) {
+ printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n",
+ compress_name, start_block);
+ if (!*decompressor)
+ printk(KERN_EMERG
+ "RAMDISK: %s decompressor not configured!\n",
+ compress_name);
+ nblocks = 0;
+ goto done;
+ }
+
+ /* romfs is at block zero too */
+ if (romfsb->word0 == ROMSB_WORD0 &&
+ romfsb->word1 == ROMSB_WORD1) {
+ printk(KERN_NOTICE
+ "RAMDISK: romfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ if (cramfsb->magic == CRAMFS_MAGIC) {
+ printk(KERN_NOTICE
+ "RAMDISK: cramfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /* squashfs is at block zero too */
+ if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) {
+ printk(KERN_NOTICE
+ "RAMDISK: squashfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1)
+ >> BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /*
+ * Read 512 bytes further to check if cramfs is padded
+ */
+ pos = start_block * BLOCK_SIZE + 0x200;
+ kernel_read(file, buf, size, &pos);
+
+ if (cramfsb->magic == CRAMFS_MAGIC) {
+ printk(KERN_NOTICE
+ "RAMDISK: cramfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /*
+ * Read block 1 to test for minix and ext2 superblock
+ */
+ pos = (start_block + 1) * BLOCK_SIZE;
+ kernel_read(file, buf, size, &pos);
+
+ /* Try minix */
+ if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
+ minixsb->s_magic == MINIX_SUPER_MAGIC2) {
+ printk(KERN_NOTICE
+ "RAMDISK: Minix filesystem found at block %d\n",
+ start_block);
+ nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
+ goto done;
+ }
+
+ /* Try ext2 */
+ n = ext2_image_size(buf);
+ if (n) {
+ printk(KERN_NOTICE
+ "RAMDISK: ext2 filesystem found at block %d\n",
+ start_block);
+ nblocks = n;
+ goto done;
+ }
+
+ printk(KERN_NOTICE
+ "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
+ start_block);
+
+done:
+ kfree(buf);
+ return nblocks;
+}
+
+static unsigned long nr_blocks(struct file *file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ if (!S_ISBLK(inode->i_mode))
+ return 0;
+ return i_size_read(inode) >> 10;
+}
+
+int __init rd_load_image(char *from)
+{
+ int res = 0;
+ unsigned long rd_blocks, devblocks;
+ int nblocks, i;
+ char *buf = NULL;
+ unsigned short rotate = 0;
+ decompress_fn decompressor = NULL;
+#if !defined(CONFIG_S390)
+ char rotator[4] = { '|' , '/' , '-' , '\\' };
+#endif
+
+ out_file = filp_open("/dev/ram", O_RDWR, 0);
+ if (IS_ERR(out_file))
+ goto out;
+
+ in_file = filp_open(from, O_RDONLY, 0);
+ if (IS_ERR(in_file))
+ goto noclose_input;
+
+ in_pos = rd_image_start * BLOCK_SIZE;
+ nblocks = identify_ramdisk_image(in_file, in_pos, &decompressor);
+ if (nblocks < 0)
+ goto done;
+
+ if (nblocks == 0) {
+ if (crd_load(decompressor) == 0)
+ goto successful_load;
+ goto done;
+ }
+
+ /*
+ * NOTE NOTE: nblocks is not actually blocks but
+ * the number of kibibytes of data to load into a ramdisk.
+ */
+ rd_blocks = nr_blocks(out_file);
+ if (nblocks > rd_blocks) {
+ printk("RAMDISK: image too big! (%dKiB/%ldKiB)\n",
+ nblocks, rd_blocks);
+ goto done;
+ }
+
+ /*
+ * OK, time to copy in the data
+ */
+ if (strcmp(from, "/initrd.image") == 0)
+ devblocks = nblocks;
+ else
+ devblocks = nr_blocks(in_file);
+
+ if (devblocks == 0) {
+ printk(KERN_ERR "RAMDISK: could not determine device size\n");
+ goto done;
+ }
+
+ buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
+ if (!buf) {
+ printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
+ goto done;
+ }
+
+ printk(KERN_NOTICE "RAMDISK: Loading %dKiB [%ld disk%s] into ram disk... ",
+ nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
+ for (i = 0; i < nblocks; i++) {
+ if (i && (i % devblocks == 0)) {
+ pr_cont("done disk #1.\n");
+ rotate = 0;
+ fput(in_file);
+ break;
+ }
+ kernel_read(in_file, buf, BLOCK_SIZE, &in_pos);
+ kernel_write(out_file, buf, BLOCK_SIZE, &out_pos);
+#if !defined(CONFIG_S390)
+ if (!(i % 16)) {
+ pr_cont("%c\b", rotator[rotate & 0x3]);
+ rotate++;
+ }
+#endif
+ }
+ pr_cont("done.\n");
+
+successful_load:
+ res = 1;
+done:
+ fput(in_file);
+noclose_input:
+ fput(out_file);
+out:
+ kfree(buf);
+ init_unlink("/dev/ram");
+ return res;
+}
+
+int __init rd_load_disk(int n)
+{
+ create_dev("/dev/root", ROOT_DEV);
+ create_dev("/dev/ram", MKDEV(RAMDISK_MAJOR, n));
+ return rd_load_image("/dev/root");
+}
+
+static int exit_code;
+static int decompress_error;
+
+static long __init compr_fill(void *buf, unsigned long len)
+{
+ long r = kernel_read(in_file, buf, len, &in_pos);
+ if (r < 0)
+ printk(KERN_ERR "RAMDISK: error while reading compressed data");
+ else if (r == 0)
+ printk(KERN_ERR "RAMDISK: EOF while reading compressed data");
+ return r;
+}
+
+static long __init compr_flush(void *window, unsigned long outcnt)
+{
+ long written = kernel_write(out_file, window, outcnt, &out_pos);
+ if (written != outcnt) {
+ if (decompress_error == 0)
+ printk(KERN_ERR
+ "RAMDISK: incomplete write (%ld != %ld)\n",
+ written, outcnt);
+ decompress_error = 1;
+ return -1;
+ }
+ return outcnt;
+}
+
+static void __init error(char *x)
+{
+ printk(KERN_ERR "%s\n", x);
+ exit_code = 1;
+ decompress_error = 1;
+}
+
+static int __init crd_load(decompress_fn deco)
+{
+ int result;
+
+ if (!deco) {
+ pr_emerg("Invalid ramdisk decompression routine. "
+ "Select appropriate config option.\n");
+ panic("Could not decompress initial ramdisk image.");
+ }
+
+ result = deco(NULL, 0, compr_fill, compr_flush, NULL, NULL, error);
+ if (decompress_error)
+ result = 1;
+ return result;
+}