From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/misc/lkdtm/bugs.c | 630 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 630 insertions(+) create mode 100644 drivers/misc/lkdtm/bugs.c (limited to 'drivers/misc/lkdtm/bugs.c') diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c new file mode 100644 index 000000000..48821f4c2 --- /dev/null +++ b/drivers/misc/lkdtm/bugs.c @@ -0,0 +1,630 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This is for all the tests related to logic bugs (e.g. bad dereferences, + * bad alignment, bad loops, bad locking, bad scheduling, deep stacks, and + * lockups) along with other things that don't fit well into existing LKDTM + * test source files. + */ +#include "lkdtm.h" +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_UML) +#include +#endif + +struct lkdtm_list { + struct list_head node; +}; + +/* + * Make sure our attempts to over run the kernel stack doesn't trigger + * a compiler warning when CONFIG_FRAME_WARN is set. Then make sure we + * recurse past the end of THREAD_SIZE by default. + */ +#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN > 0) +#define REC_STACK_SIZE (_AC(CONFIG_FRAME_WARN, UL) / 2) +#else +#define REC_STACK_SIZE (THREAD_SIZE / 8UL) +#endif +#define REC_NUM_DEFAULT ((THREAD_SIZE / REC_STACK_SIZE) * 2) + +static int recur_count = REC_NUM_DEFAULT; + +static DEFINE_SPINLOCK(lock_me_up); + +/* + * Make sure compiler does not optimize this function or stack frame away: + * - function marked noinline + * - stack variables are marked volatile + * - stack variables are written (memset()) and read (buf[..] passed as arg) + * - function may have external effects (memzero_explicit()) + * - no tail recursion possible + */ +static int noinline recursive_loop(int remaining) +{ + volatile char buf[REC_STACK_SIZE]; + volatile int ret; + + memset((void *)buf, remaining & 0xFF, sizeof(buf)); + if (!remaining) + ret = 0; + else + ret = recursive_loop((int)buf[remaining % sizeof(buf)] - 1); + memzero_explicit((void *)buf, sizeof(buf)); + return ret; +} + +/* If the depth is negative, use the default, otherwise keep parameter. */ +void __init lkdtm_bugs_init(int *recur_param) +{ + if (*recur_param < 0) + *recur_param = recur_count; + else + recur_count = *recur_param; +} + +static void lkdtm_PANIC(void) +{ + panic("dumptest"); +} + +static void lkdtm_BUG(void) +{ + BUG(); +} + +static int warn_counter; + +static void lkdtm_WARNING(void) +{ + WARN_ON(++warn_counter); +} + +static void lkdtm_WARNING_MESSAGE(void) +{ + WARN(1, "Warning message trigger count: %d\n", ++warn_counter); +} + +static void lkdtm_EXCEPTION(void) +{ + *((volatile int *) 0) = 0; +} + +static void lkdtm_LOOP(void) +{ + for (;;) + ; +} + +static void lkdtm_EXHAUST_STACK(void) +{ + pr_info("Calling function with %lu frame size to depth %d ...\n", + REC_STACK_SIZE, recur_count); + recursive_loop(recur_count); + pr_info("FAIL: survived without exhausting stack?!\n"); +} + +static noinline void __lkdtm_CORRUPT_STACK(void *stack) +{ + memset(stack, '\xff', 64); +} + +/* This should trip the stack canary, not corrupt the return address. */ +static noinline void lkdtm_CORRUPT_STACK(void) +{ + /* Use default char array length that triggers stack protection. */ + char data[8] __aligned(sizeof(void *)); + + pr_info("Corrupting stack containing char array ...\n"); + __lkdtm_CORRUPT_STACK((void *)&data); +} + +/* Same as above but will only get a canary with -fstack-protector-strong */ +static noinline void lkdtm_CORRUPT_STACK_STRONG(void) +{ + union { + unsigned short shorts[4]; + unsigned long *ptr; + } data __aligned(sizeof(void *)); + + pr_info("Corrupting stack containing union ...\n"); + __lkdtm_CORRUPT_STACK((void *)&data); +} + +static pid_t stack_pid; +static unsigned long stack_addr; + +static void lkdtm_REPORT_STACK(void) +{ + volatile uintptr_t magic; + pid_t pid = task_pid_nr(current); + + if (pid != stack_pid) { + pr_info("Starting stack offset tracking for pid %d\n", pid); + stack_pid = pid; + stack_addr = (uintptr_t)&magic; + } + + pr_info("Stack offset: %d\n", (int)(stack_addr - (uintptr_t)&magic)); +} + +static pid_t stack_canary_pid; +static unsigned long stack_canary; +static unsigned long stack_canary_offset; + +static noinline void __lkdtm_REPORT_STACK_CANARY(void *stack) +{ + int i = 0; + pid_t pid = task_pid_nr(current); + unsigned long *canary = (unsigned long *)stack; + unsigned long current_offset = 0, init_offset = 0; + + /* Do our best to find the canary in a 16 word window ... */ + for (i = 1; i < 16; i++) { + canary = (unsigned long *)stack + i; +#ifdef CONFIG_STACKPROTECTOR + if (*canary == current->stack_canary) + current_offset = i; + if (*canary == init_task.stack_canary) + init_offset = i; +#endif + } + + if (current_offset == 0) { + /* + * If the canary doesn't match what's in the task_struct, + * we're either using a global canary or the stack frame + * layout changed. + */ + if (init_offset != 0) { + pr_err("FAIL: global stack canary found at offset %ld (canary for pid %d matches init_task's)!\n", + init_offset, pid); + } else { + pr_warn("FAIL: did not correctly locate stack canary :(\n"); + pr_expected_config(CONFIG_STACKPROTECTOR); + } + + return; + } else if (init_offset != 0) { + pr_warn("WARNING: found both current and init_task canaries nearby?!\n"); + } + + canary = (unsigned long *)stack + current_offset; + if (stack_canary_pid == 0) { + stack_canary = *canary; + stack_canary_pid = pid; + stack_canary_offset = current_offset; + pr_info("Recorded stack canary for pid %d at offset %ld\n", + stack_canary_pid, stack_canary_offset); + } else if (pid == stack_canary_pid) { + pr_warn("ERROR: saw pid %d again -- please use a new pid\n", pid); + } else { + if (current_offset != stack_canary_offset) { + pr_warn("ERROR: canary offset changed from %ld to %ld!?\n", + stack_canary_offset, current_offset); + return; + } + + if (*canary == stack_canary) { + pr_warn("FAIL: canary identical for pid %d and pid %d at offset %ld!\n", + stack_canary_pid, pid, current_offset); + } else { + pr_info("ok: stack canaries differ between pid %d and pid %d at offset %ld.\n", + stack_canary_pid, pid, current_offset); + /* Reset the test. */ + stack_canary_pid = 0; + } + } +} + +static void lkdtm_REPORT_STACK_CANARY(void) +{ + /* Use default char array length that triggers stack protection. */ + char data[8] __aligned(sizeof(void *)) = { }; + + __lkdtm_REPORT_STACK_CANARY((void *)&data); +} + +static void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void) +{ + static u8 data[5] __attribute__((aligned(4))) = {1, 2, 3, 4, 5}; + u32 *p; + u32 val = 0x12345678; + + p = (u32 *)(data + 1); + if (*p == 0) + val = 0x87654321; + *p = val; + + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + pr_err("XFAIL: arch has CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS\n"); +} + +static void lkdtm_SOFTLOCKUP(void) +{ + preempt_disable(); + for (;;) + cpu_relax(); +} + +static void lkdtm_HARDLOCKUP(void) +{ + local_irq_disable(); + for (;;) + cpu_relax(); +} + +static void lkdtm_SPINLOCKUP(void) +{ + /* Must be called twice to trigger. */ + spin_lock(&lock_me_up); + /* Let sparse know we intended to exit holding the lock. */ + __release(&lock_me_up); +} + +static void lkdtm_HUNG_TASK(void) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + schedule(); +} + +volatile unsigned int huge = INT_MAX - 2; +volatile unsigned int ignored; + +static void lkdtm_OVERFLOW_SIGNED(void) +{ + int value; + + value = huge; + pr_info("Normal signed addition ...\n"); + value += 1; + ignored = value; + + pr_info("Overflowing signed addition ...\n"); + value += 4; + ignored = value; +} + + +static void lkdtm_OVERFLOW_UNSIGNED(void) +{ + unsigned int value; + + value = huge; + pr_info("Normal unsigned addition ...\n"); + value += 1; + ignored = value; + + pr_info("Overflowing unsigned addition ...\n"); + value += 4; + ignored = value; +} + +/* Intentionally using old-style flex array definition of 1 byte. */ +struct array_bounds_flex_array { + int one; + int two; + char data[1]; +}; + +struct array_bounds { + int one; + int two; + char data[8]; + int three; +}; + +static void lkdtm_ARRAY_BOUNDS(void) +{ + struct array_bounds_flex_array *not_checked; + struct array_bounds *checked; + volatile int i; + + not_checked = kmalloc(sizeof(*not_checked) * 2, GFP_KERNEL); + checked = kmalloc(sizeof(*checked) * 2, GFP_KERNEL); + if (!not_checked || !checked) { + kfree(not_checked); + kfree(checked); + return; + } + + pr_info("Array access within bounds ...\n"); + /* For both, touch all bytes in the actual member size. */ + for (i = 0; i < sizeof(checked->data); i++) + checked->data[i] = 'A'; + /* + * For the uninstrumented flex array member, also touch 1 byte + * beyond to verify it is correctly uninstrumented. + */ + for (i = 0; i < sizeof(not_checked->data) + 1; i++) + not_checked->data[i] = 'A'; + + pr_info("Array access beyond bounds ...\n"); + for (i = 0; i < sizeof(checked->data) + 1; i++) + checked->data[i] = 'B'; + + kfree(not_checked); + kfree(checked); + pr_err("FAIL: survived array bounds overflow!\n"); + if (IS_ENABLED(CONFIG_UBSAN_BOUNDS)) + pr_expected_config(CONFIG_UBSAN_TRAP); + else + pr_expected_config(CONFIG_UBSAN_BOUNDS); +} + +static void lkdtm_CORRUPT_LIST_ADD(void) +{ + /* + * Initially, an empty list via LIST_HEAD: + * test_head.next = &test_head + * test_head.prev = &test_head + */ + LIST_HEAD(test_head); + struct lkdtm_list good, bad; + void *target[2] = { }; + void *redirection = ⌖ + + pr_info("attempting good list addition\n"); + + /* + * Adding to the list performs these actions: + * test_head.next->prev = &good.node + * good.node.next = test_head.next + * good.node.prev = test_head + * test_head.next = good.node + */ + list_add(&good.node, &test_head); + + pr_info("attempting corrupted list addition\n"); + /* + * In simulating this "write what where" primitive, the "what" is + * the address of &bad.node, and the "where" is the address held + * by "redirection". + */ + test_head.next = redirection; + list_add(&bad.node, &test_head); + + if (target[0] == NULL && target[1] == NULL) + pr_err("Overwrite did not happen, but no BUG?!\n"); + else { + pr_err("list_add() corruption not detected!\n"); + pr_expected_config(CONFIG_DEBUG_LIST); + } +} + +static void lkdtm_CORRUPT_LIST_DEL(void) +{ + LIST_HEAD(test_head); + struct lkdtm_list item; + void *target[2] = { }; + void *redirection = ⌖ + + list_add(&item.node, &test_head); + + pr_info("attempting good list removal\n"); + list_del(&item.node); + + pr_info("attempting corrupted list removal\n"); + list_add(&item.node, &test_head); + + /* As with the list_add() test above, this corrupts "next". */ + item.node.next = redirection; + list_del(&item.node); + + if (target[0] == NULL && target[1] == NULL) + pr_err("Overwrite did not happen, but no BUG?!\n"); + else { + pr_err("list_del() corruption not detected!\n"); + pr_expected_config(CONFIG_DEBUG_LIST); + } +} + +/* Test that VMAP_STACK is actually allocating with a leading guard page */ +static void lkdtm_STACK_GUARD_PAGE_LEADING(void) +{ + const unsigned char *stack = task_stack_page(current); + const unsigned char *ptr = stack - 1; + volatile unsigned char byte; + + pr_info("attempting bad read from page below current stack\n"); + + byte = *ptr; + + pr_err("FAIL: accessed page before stack! (byte: %x)\n", byte); +} + +/* Test that VMAP_STACK is actually allocating with a trailing guard page */ +static void lkdtm_STACK_GUARD_PAGE_TRAILING(void) +{ + const unsigned char *stack = task_stack_page(current); + const unsigned char *ptr = stack + THREAD_SIZE; + volatile unsigned char byte; + + pr_info("attempting bad read from page above current stack\n"); + + byte = *ptr; + + pr_err("FAIL: accessed page after stack! (byte: %x)\n", byte); +} + +static void lkdtm_UNSET_SMEP(void) +{ +#if IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_UML) +#define MOV_CR4_DEPTH 64 + void (*direct_write_cr4)(unsigned long val); + unsigned char *insn; + unsigned long cr4; + int i; + + cr4 = native_read_cr4(); + + if ((cr4 & X86_CR4_SMEP) != X86_CR4_SMEP) { + pr_err("FAIL: SMEP not in use\n"); + return; + } + cr4 &= ~(X86_CR4_SMEP); + + pr_info("trying to clear SMEP normally\n"); + native_write_cr4(cr4); + if (cr4 == native_read_cr4()) { + pr_err("FAIL: pinning SMEP failed!\n"); + cr4 |= X86_CR4_SMEP; + pr_info("restoring SMEP\n"); + native_write_cr4(cr4); + return; + } + pr_info("ok: SMEP did not get cleared\n"); + + /* + * To test the post-write pinning verification we need to call + * directly into the middle of native_write_cr4() where the + * cr4 write happens, skipping any pinning. This searches for + * the cr4 writing instruction. + */ + insn = (unsigned char *)native_write_cr4; + for (i = 0; i < MOV_CR4_DEPTH; i++) { + /* mov %rdi, %cr4 */ + if (insn[i] == 0x0f && insn[i+1] == 0x22 && insn[i+2] == 0xe7) + break; + /* mov %rdi,%rax; mov %rax, %cr4 */ + if (insn[i] == 0x48 && insn[i+1] == 0x89 && + insn[i+2] == 0xf8 && insn[i+3] == 0x0f && + insn[i+4] == 0x22 && insn[i+5] == 0xe0) + break; + } + if (i >= MOV_CR4_DEPTH) { + pr_info("ok: cannot locate cr4 writing call gadget\n"); + return; + } + direct_write_cr4 = (void *)(insn + i); + + pr_info("trying to clear SMEP with call gadget\n"); + direct_write_cr4(cr4); + if (native_read_cr4() & X86_CR4_SMEP) { + pr_info("ok: SMEP removal was reverted\n"); + } else { + pr_err("FAIL: cleared SMEP not detected!\n"); + cr4 |= X86_CR4_SMEP; + pr_info("restoring SMEP\n"); + native_write_cr4(cr4); + } +#else + pr_err("XFAIL: this test is x86_64-only\n"); +#endif +} + +static void lkdtm_DOUBLE_FAULT(void) +{ +#if IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_UML) + /* + * Trigger #DF by setting the stack limit to zero. This clobbers + * a GDT TLS slot, which is okay because the current task will die + * anyway due to the double fault. + */ + struct desc_struct d = { + .type = 3, /* expand-up, writable, accessed data */ + .p = 1, /* present */ + .d = 1, /* 32-bit */ + .g = 0, /* limit in bytes */ + .s = 1, /* not system */ + }; + + local_irq_disable(); + write_gdt_entry(get_cpu_gdt_rw(smp_processor_id()), + GDT_ENTRY_TLS_MIN, &d, DESCTYPE_S); + + /* + * Put our zero-limit segment in SS and then trigger a fault. The + * 4-byte access to (%esp) will fault with #SS, and the attempt to + * deliver the fault will recursively cause #SS and result in #DF. + * This whole process happens while NMIs and MCEs are blocked by the + * MOV SS window. This is nice because an NMI with an invalid SS + * would also double-fault, resulting in the NMI or MCE being lost. + */ + asm volatile ("movw %0, %%ss; addl $0, (%%esp)" :: + "r" ((unsigned short)(GDT_ENTRY_TLS_MIN << 3))); + + pr_err("FAIL: tried to double fault but didn't die\n"); +#else + pr_err("XFAIL: this test is ia32-only\n"); +#endif +} + +#ifdef CONFIG_ARM64 +static noinline void change_pac_parameters(void) +{ + if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) { + /* Reset the keys of current task */ + ptrauth_thread_init_kernel(current); + ptrauth_thread_switch_kernel(current); + } +} +#endif + +static noinline void lkdtm_CORRUPT_PAC(void) +{ +#ifdef CONFIG_ARM64 +#define CORRUPT_PAC_ITERATE 10 + int i; + + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) + pr_err("FAIL: kernel not built with CONFIG_ARM64_PTR_AUTH_KERNEL\n"); + + if (!system_supports_address_auth()) { + pr_err("FAIL: CPU lacks pointer authentication feature\n"); + return; + } + + pr_info("changing PAC parameters to force function return failure...\n"); + /* + * PAC is a hash value computed from input keys, return address and + * stack pointer. As pac has fewer bits so there is a chance of + * collision, so iterate few times to reduce the collision probability. + */ + for (i = 0; i < CORRUPT_PAC_ITERATE; i++) + change_pac_parameters(); + + pr_err("FAIL: survived PAC changes! Kernel may be unstable from here\n"); +#else + pr_err("XFAIL: this test is arm64-only\n"); +#endif +} + +static struct crashtype crashtypes[] = { + CRASHTYPE(PANIC), + CRASHTYPE(BUG), + CRASHTYPE(WARNING), + CRASHTYPE(WARNING_MESSAGE), + CRASHTYPE(EXCEPTION), + CRASHTYPE(LOOP), + CRASHTYPE(EXHAUST_STACK), + CRASHTYPE(CORRUPT_STACK), + CRASHTYPE(CORRUPT_STACK_STRONG), + CRASHTYPE(REPORT_STACK), + CRASHTYPE(REPORT_STACK_CANARY), + CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE), + CRASHTYPE(SOFTLOCKUP), + CRASHTYPE(HARDLOCKUP), + CRASHTYPE(SPINLOCKUP), + CRASHTYPE(HUNG_TASK), + CRASHTYPE(OVERFLOW_SIGNED), + CRASHTYPE(OVERFLOW_UNSIGNED), + CRASHTYPE(ARRAY_BOUNDS), + CRASHTYPE(CORRUPT_LIST_ADD), + CRASHTYPE(CORRUPT_LIST_DEL), + CRASHTYPE(STACK_GUARD_PAGE_LEADING), + CRASHTYPE(STACK_GUARD_PAGE_TRAILING), + CRASHTYPE(UNSET_SMEP), + CRASHTYPE(DOUBLE_FAULT), + CRASHTYPE(CORRUPT_PAC), +}; + +struct crashtype_category bugs_crashtypes = { + .crashtypes = crashtypes, + .len = ARRAY_SIZE(crashtypes), +}; -- cgit v1.2.3