aboutsummaryrefslogtreecommitdiff
path: root/scripts/sorttable.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 /scripts/sorttable.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 'scripts/sorttable.c')
-rw-r--r--scripts/sorttable.c389
1 files changed, 389 insertions, 0 deletions
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
new file mode 100644
index 000000000..83cdb843d
--- /dev/null
+++ b/scripts/sorttable.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sorttable.c: Sort the kernel's table
+ *
+ * Added ORC unwind tables sort support and other updates:
+ * Copyright (C) 1999-2019 Alibaba Group Holding Limited. by:
+ * Shile Zhang <shile.zhang@linux.alibaba.com>
+ *
+ * Copyright 2011 - 2012 Cavium, Inc.
+ *
+ * Based on code taken from recortmcount.c which is:
+ *
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>. All rights reserved.
+ *
+ * Restructured to fit Linux format, as well as other updates:
+ * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ */
+
+/*
+ * Strategy: alter the vmlinux file in-place.
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <getopt.h>
+#include <elf.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <pthread.h>
+
+#include <tools/be_byteshift.h>
+#include <tools/le_byteshift.h>
+
+#ifndef EM_ARCOMPACT
+#define EM_ARCOMPACT 93
+#endif
+
+#ifndef EM_XTENSA
+#define EM_XTENSA 94
+#endif
+
+#ifndef EM_AARCH64
+#define EM_AARCH64 183
+#endif
+
+#ifndef EM_MICROBLAZE
+#define EM_MICROBLAZE 189
+#endif
+
+#ifndef EM_ARCV2
+#define EM_ARCV2 195
+#endif
+
+#ifndef EM_RISCV
+#define EM_RISCV 243
+#endif
+
+#ifndef EM_LOONGARCH
+#define EM_LOONGARCH 258
+#endif
+
+static uint32_t (*r)(const uint32_t *);
+static uint16_t (*r2)(const uint16_t *);
+static uint64_t (*r8)(const uint64_t *);
+static void (*w)(uint32_t, uint32_t *);
+static void (*w2)(uint16_t, uint16_t *);
+static void (*w8)(uint64_t, uint64_t *);
+typedef void (*table_sort_t)(char *, int);
+
+/*
+ * Get the whole file as a programming convenience in order to avoid
+ * malloc+lseek+read+free of many pieces. If successful, then mmap
+ * avoids copying unused pieces; else just read the whole file.
+ * Open for both read and write.
+ */
+static void *mmap_file(char const *fname, size_t *size)
+{
+ int fd;
+ struct stat sb;
+ void *addr = NULL;
+
+ fd = open(fname, O_RDWR);
+ if (fd < 0) {
+ perror(fname);
+ return NULL;
+ }
+ if (fstat(fd, &sb) < 0) {
+ perror(fname);
+ goto out;
+ }
+ if (!S_ISREG(sb.st_mode)) {
+ fprintf(stderr, "not a regular file: %s\n", fname);
+ goto out;
+ }
+
+ addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+ if (addr == MAP_FAILED) {
+ fprintf(stderr, "Could not mmap file: %s\n", fname);
+ goto out;
+ }
+
+ *size = sb.st_size;
+
+out:
+ close(fd);
+ return addr;
+}
+
+static uint32_t rbe(const uint32_t *x)
+{
+ return get_unaligned_be32(x);
+}
+
+static uint16_t r2be(const uint16_t *x)
+{
+ return get_unaligned_be16(x);
+}
+
+static uint64_t r8be(const uint64_t *x)
+{
+ return get_unaligned_be64(x);
+}
+
+static uint32_t rle(const uint32_t *x)
+{
+ return get_unaligned_le32(x);
+}
+
+static uint16_t r2le(const uint16_t *x)
+{
+ return get_unaligned_le16(x);
+}
+
+static uint64_t r8le(const uint64_t *x)
+{
+ return get_unaligned_le64(x);
+}
+
+static void wbe(uint32_t val, uint32_t *x)
+{
+ put_unaligned_be32(val, x);
+}
+
+static void w2be(uint16_t val, uint16_t *x)
+{
+ put_unaligned_be16(val, x);
+}
+
+static void w8be(uint64_t val, uint64_t *x)
+{
+ put_unaligned_be64(val, x);
+}
+
+static void wle(uint32_t val, uint32_t *x)
+{
+ put_unaligned_le32(val, x);
+}
+
+static void w2le(uint16_t val, uint16_t *x)
+{
+ put_unaligned_le16(val, x);
+}
+
+static void w8le(uint64_t val, uint64_t *x)
+{
+ put_unaligned_le64(val, x);
+}
+
+/*
+ * Move reserved section indices SHN_LORESERVE..SHN_HIRESERVE out of
+ * the way to -256..-1, to avoid conflicting with real section
+ * indices.
+ */
+#define SPECIAL(i) ((i) - (SHN_HIRESERVE + 1))
+
+static inline int is_shndx_special(unsigned int i)
+{
+ return i != SHN_XINDEX && i >= SHN_LORESERVE && i <= SHN_HIRESERVE;
+}
+
+/* Accessor for sym->st_shndx, hides ugliness of "64k sections" */
+static inline unsigned int get_secindex(unsigned int shndx,
+ unsigned int sym_offs,
+ const Elf32_Word *symtab_shndx_start)
+{
+ if (is_shndx_special(shndx))
+ return SPECIAL(shndx);
+ if (shndx != SHN_XINDEX)
+ return shndx;
+ return r(&symtab_shndx_start[sym_offs]);
+}
+
+/* 32 bit and 64 bit are very similar */
+#include "sorttable.h"
+#define SORTTABLE_64
+#include "sorttable.h"
+
+static int compare_relative_table(const void *a, const void *b)
+{
+ int32_t av = (int32_t)r(a);
+ int32_t bv = (int32_t)r(b);
+
+ if (av < bv)
+ return -1;
+ if (av > bv)
+ return 1;
+ return 0;
+}
+
+static void sort_relative_table(char *extab_image, int image_size)
+{
+ int i = 0;
+
+ /*
+ * Do the same thing the runtime sort does, first normalize to
+ * being relative to the start of the section.
+ */
+ while (i < image_size) {
+ uint32_t *loc = (uint32_t *)(extab_image + i);
+ w(r(loc) + i, loc);
+ i += 4;
+ }
+
+ qsort(extab_image, image_size / 8, 8, compare_relative_table);
+
+ /* Now denormalize. */
+ i = 0;
+ while (i < image_size) {
+ uint32_t *loc = (uint32_t *)(extab_image + i);
+ w(r(loc) - i, loc);
+ i += 4;
+ }
+}
+
+static void sort_relative_table_with_data(char *extab_image, int image_size)
+{
+ int i = 0;
+
+ while (i < image_size) {
+ uint32_t *loc = (uint32_t *)(extab_image + i);
+
+ w(r(loc) + i, loc);
+ w(r(loc + 1) + i + 4, loc + 1);
+ /* Don't touch the fixup type or data */
+
+ i += sizeof(uint32_t) * 3;
+ }
+
+ qsort(extab_image, image_size / 12, 12, compare_relative_table);
+
+ i = 0;
+ while (i < image_size) {
+ uint32_t *loc = (uint32_t *)(extab_image + i);
+
+ w(r(loc) - i, loc);
+ w(r(loc + 1) - (i + 4), loc + 1);
+ /* Don't touch the fixup type or data */
+
+ i += sizeof(uint32_t) * 3;
+ }
+}
+
+static int do_file(char const *const fname, void *addr)
+{
+ int rc = -1;
+ Elf32_Ehdr *ehdr = addr;
+ table_sort_t custom_sort = NULL;
+
+ switch (ehdr->e_ident[EI_DATA]) {
+ case ELFDATA2LSB:
+ r = rle;
+ r2 = r2le;
+ r8 = r8le;
+ w = wle;
+ w2 = w2le;
+ w8 = w8le;
+ break;
+ case ELFDATA2MSB:
+ r = rbe;
+ r2 = r2be;
+ r8 = r8be;
+ w = wbe;
+ w2 = w2be;
+ w8 = w8be;
+ break;
+ default:
+ fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
+ ehdr->e_ident[EI_DATA], fname);
+ return -1;
+ }
+
+ if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 ||
+ (r2(&ehdr->e_type) != ET_EXEC && r2(&ehdr->e_type) != ET_DYN) ||
+ ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
+ fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file %s\n", fname);
+ return -1;
+ }
+
+ switch (r2(&ehdr->e_machine)) {
+ case EM_386:
+ case EM_AARCH64:
+ case EM_LOONGARCH:
+ case EM_RISCV:
+ case EM_S390:
+ case EM_X86_64:
+ custom_sort = sort_relative_table_with_data;
+ break;
+ case EM_PARISC:
+ case EM_PPC:
+ case EM_PPC64:
+ custom_sort = sort_relative_table;
+ break;
+ case EM_ARCOMPACT:
+ case EM_ARCV2:
+ case EM_ARM:
+ case EM_MICROBLAZE:
+ case EM_MIPS:
+ case EM_XTENSA:
+ break;
+ default:
+ fprintf(stderr, "unrecognized e_machine %d %s\n",
+ r2(&ehdr->e_machine), fname);
+ return -1;
+ }
+
+ switch (ehdr->e_ident[EI_CLASS]) {
+ case ELFCLASS32:
+ if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) ||
+ r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
+ fprintf(stderr,
+ "unrecognized ET_EXEC/ET_DYN file: %s\n", fname);
+ break;
+ }
+ rc = do_sort_32(ehdr, fname, custom_sort);
+ break;
+ case ELFCLASS64:
+ {
+ Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
+ if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) ||
+ r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
+ fprintf(stderr,
+ "unrecognized ET_EXEC/ET_DYN file: %s\n",
+ fname);
+ break;
+ }
+ rc = do_sort_64(ghdr, fname, custom_sort);
+ }
+ break;
+ default:
+ fprintf(stderr, "unrecognized ELF class %d %s\n",
+ ehdr->e_ident[EI_CLASS], fname);
+ break;
+ }
+
+ return rc;
+}
+
+int main(int argc, char *argv[])
+{
+ int i, n_error = 0; /* gcc-4.3.0 false positive complaint */
+ size_t size = 0;
+ void *addr = NULL;
+
+ if (argc < 2) {
+ fprintf(stderr, "usage: sorttable vmlinux...\n");
+ return 0;
+ }
+
+ /* Process each file in turn, allowing deep failure. */
+ for (i = 1; i < argc; i++) {
+ addr = mmap_file(argv[i], &size);
+ if (!addr) {
+ ++n_error;
+ continue;
+ }
+
+ if (do_file(argv[i], addr))
+ ++n_error;
+
+ munmap(addr, size);
+ }
+
+ return !!n_error;
+}