aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/dump_pagetables.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 /arch/x86/mm/dump_pagetables.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 'arch/x86/mm/dump_pagetables.c')
-rw-r--r--arch/x86/mm/dump_pagetables.c471
1 files changed, 471 insertions, 0 deletions
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
new file mode 100644
index 000000000..e1b599ecb
--- /dev/null
+++ b/arch/x86/mm/dump_pagetables.c
@@ -0,0 +1,471 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Debug helper to dump the current kernel pagetables of the system
+ * so that we can see what the various memory ranges are set to.
+ *
+ * (C) Copyright 2008 Intel Corporation
+ *
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kasan.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/pci.h>
+#include <linux/ptdump.h>
+
+#include <asm/e820/types.h>
+
+/*
+ * The dumper groups pagetable entries of the same type into one, and for
+ * that it needs to keep some state when walking, and flush this state
+ * when a "break" in the continuity is found.
+ */
+struct pg_state {
+ struct ptdump_state ptdump;
+ int level;
+ pgprotval_t current_prot;
+ pgprotval_t effective_prot;
+ pgprotval_t prot_levels[5];
+ unsigned long start_address;
+ const struct addr_marker *marker;
+ unsigned long lines;
+ bool to_dmesg;
+ bool check_wx;
+ unsigned long wx_pages;
+ struct seq_file *seq;
+};
+
+struct addr_marker {
+ unsigned long start_address;
+ const char *name;
+ unsigned long max_lines;
+};
+
+/* Address space markers hints */
+
+#ifdef CONFIG_X86_64
+
+enum address_markers_idx {
+ USER_SPACE_NR = 0,
+ KERNEL_SPACE_NR,
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ LDT_NR,
+#endif
+ LOW_KERNEL_NR,
+ VMALLOC_START_NR,
+ VMEMMAP_START_NR,
+#ifdef CONFIG_KASAN
+ KASAN_SHADOW_START_NR,
+ KASAN_SHADOW_END_NR,
+#endif
+ CPU_ENTRY_AREA_NR,
+#ifdef CONFIG_X86_ESPFIX64
+ ESPFIX_START_NR,
+#endif
+#ifdef CONFIG_EFI
+ EFI_END_NR,
+#endif
+ HIGH_KERNEL_NR,
+ MODULES_VADDR_NR,
+ MODULES_END_NR,
+ FIXADDR_START_NR,
+ END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+ [USER_SPACE_NR] = { 0, "User Space" },
+ [KERNEL_SPACE_NR] = { (1UL << 63), "Kernel Space" },
+ [LOW_KERNEL_NR] = { 0UL, "Low Kernel Mapping" },
+ [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" },
+ [VMEMMAP_START_NR] = { 0UL, "Vmemmap" },
+#ifdef CONFIG_KASAN
+ /*
+ * These fields get initialized with the (dynamic)
+ * KASAN_SHADOW_{START,END} values in pt_dump_init().
+ */
+ [KASAN_SHADOW_START_NR] = { 0UL, "KASAN shadow" },
+ [KASAN_SHADOW_END_NR] = { 0UL, "KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { 0UL, "LDT remap" },
+#endif
+ [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
+#ifdef CONFIG_X86_ESPFIX64
+ [ESPFIX_START_NR] = { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
+#endif
+#ifdef CONFIG_EFI
+ [EFI_END_NR] = { EFI_VA_END, "EFI Runtime Services" },
+#endif
+ [HIGH_KERNEL_NR] = { __START_KERNEL_map, "High Kernel Mapping" },
+ [MODULES_VADDR_NR] = { MODULES_VADDR, "Modules" },
+ [MODULES_END_NR] = { MODULES_END, "End Modules" },
+ [FIXADDR_START_NR] = { FIXADDR_START, "Fixmap Area" },
+ [END_OF_SPACE_NR] = { -1, NULL }
+};
+
+#define INIT_PGD ((pgd_t *) &init_top_pgt)
+
+#else /* CONFIG_X86_64 */
+
+enum address_markers_idx {
+ USER_SPACE_NR = 0,
+ KERNEL_SPACE_NR,
+ VMALLOC_START_NR,
+ VMALLOC_END_NR,
+#ifdef CONFIG_HIGHMEM
+ PKMAP_BASE_NR,
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ LDT_NR,
+#endif
+ CPU_ENTRY_AREA_NR,
+ FIXADDR_START_NR,
+ END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+ [USER_SPACE_NR] = { 0, "User Space" },
+ [KERNEL_SPACE_NR] = { PAGE_OFFSET, "Kernel Mapping" },
+ [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" },
+ [VMALLOC_END_NR] = { 0UL, "vmalloc() End" },
+#ifdef CONFIG_HIGHMEM
+ [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { 0UL, "LDT remap" },
+#endif
+ [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" },
+ [FIXADDR_START_NR] = { 0UL, "Fixmap area" },
+ [END_OF_SPACE_NR] = { -1, NULL }
+};
+
+#define INIT_PGD (swapper_pg_dir)
+
+#endif /* !CONFIG_X86_64 */
+
+/* Multipliers for offsets within the PTEs */
+#define PTE_LEVEL_MULT (PAGE_SIZE)
+#define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
+#define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
+#define P4D_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
+#define PGD_LEVEL_MULT (PTRS_PER_P4D * P4D_LEVEL_MULT)
+
+#define pt_dump_seq_printf(m, to_dmesg, fmt, args...) \
+({ \
+ if (to_dmesg) \
+ printk(KERN_INFO fmt, ##args); \
+ else \
+ if (m) \
+ seq_printf(m, fmt, ##args); \
+})
+
+#define pt_dump_cont_printf(m, to_dmesg, fmt, args...) \
+({ \
+ if (to_dmesg) \
+ printk(KERN_CONT fmt, ##args); \
+ else \
+ if (m) \
+ seq_printf(m, fmt, ##args); \
+})
+
+/*
+ * Print a readable form of a pgprot_t to the seq_file
+ */
+static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg)
+{
+ static const char * const level_name[] =
+ { "pgd", "p4d", "pud", "pmd", "pte" };
+
+ if (!(pr & _PAGE_PRESENT)) {
+ /* Not present */
+ pt_dump_cont_printf(m, dmsg, " ");
+ } else {
+ if (pr & _PAGE_USER)
+ pt_dump_cont_printf(m, dmsg, "USR ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if (pr & _PAGE_RW)
+ pt_dump_cont_printf(m, dmsg, "RW ");
+ else
+ pt_dump_cont_printf(m, dmsg, "ro ");
+ if (pr & _PAGE_PWT)
+ pt_dump_cont_printf(m, dmsg, "PWT ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if (pr & _PAGE_PCD)
+ pt_dump_cont_printf(m, dmsg, "PCD ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+
+ /* Bit 7 has a different meaning on level 3 vs 4 */
+ if (level <= 3 && pr & _PAGE_PSE)
+ pt_dump_cont_printf(m, dmsg, "PSE ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if ((level == 4 && pr & _PAGE_PAT) ||
+ ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
+ pt_dump_cont_printf(m, dmsg, "PAT ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if (pr & _PAGE_GLOBAL)
+ pt_dump_cont_printf(m, dmsg, "GLB ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if (pr & _PAGE_NX)
+ pt_dump_cont_printf(m, dmsg, "NX ");
+ else
+ pt_dump_cont_printf(m, dmsg, "x ");
+ }
+ pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
+}
+
+static void note_wx(struct pg_state *st, unsigned long addr)
+{
+ unsigned long npages;
+
+ npages = (addr - st->start_address) / PAGE_SIZE;
+
+#ifdef CONFIG_PCI_BIOS
+ /*
+ * If PCI BIOS is enabled, the PCI BIOS area is forced to WX.
+ * Inform about it, but avoid the warning.
+ */
+ if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN &&
+ addr <= PAGE_OFFSET + BIOS_END) {
+ pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages);
+ return;
+ }
+#endif
+ /* Account the WX pages */
+ st->wx_pages += npages;
+ WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+ "x86/mm: Found insecure W+X mapping at address %pS\n",
+ (void *)st->start_address);
+}
+
+static void effective_prot(struct ptdump_state *pt_st, int level, u64 val)
+{
+ struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+ pgprotval_t prot = val & PTE_FLAGS_MASK;
+ pgprotval_t effective;
+
+ if (level > 0) {
+ pgprotval_t higher_prot = st->prot_levels[level - 1];
+
+ effective = (higher_prot & prot & (_PAGE_USER | _PAGE_RW)) |
+ ((higher_prot | prot) & _PAGE_NX);
+ } else {
+ effective = prot;
+ }
+
+ st->prot_levels[level] = effective;
+}
+
+/*
+ * This function gets called on a break in a continuous series
+ * of PTE entries; the next one is different so we need to
+ * print what we collected so far.
+ */
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+ u64 val)
+{
+ struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+ pgprotval_t new_prot, new_eff;
+ pgprotval_t cur, eff;
+ static const char units[] = "BKMGTPE";
+ struct seq_file *m = st->seq;
+
+ new_prot = val & PTE_FLAGS_MASK;
+ if (!val)
+ new_eff = 0;
+ else
+ new_eff = st->prot_levels[level];
+
+ /*
+ * If we have a "break" in the series, we need to flush the state that
+ * we have now. "break" is either changing perms, levels or
+ * address space marker.
+ */
+ cur = st->current_prot;
+ eff = st->effective_prot;
+
+ if (st->level == -1) {
+ /* First entry */
+ st->current_prot = new_prot;
+ st->effective_prot = new_eff;
+ st->level = level;
+ st->marker = address_markers;
+ st->lines = 0;
+ pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+ st->marker->name);
+ } else if (new_prot != cur || new_eff != eff || level != st->level ||
+ addr >= st->marker[1].start_address) {
+ const char *unit = units;
+ unsigned long delta;
+ int width = sizeof(unsigned long) * 2;
+
+ if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX))
+ note_wx(st, addr);
+
+ /*
+ * Now print the actual finished series
+ */
+ if (!st->marker->max_lines ||
+ st->lines < st->marker->max_lines) {
+ pt_dump_seq_printf(m, st->to_dmesg,
+ "0x%0*lx-0x%0*lx ",
+ width, st->start_address,
+ width, addr);
+
+ delta = addr - st->start_address;
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ",
+ delta, *unit);
+ printk_prot(m, st->current_prot, st->level,
+ st->to_dmesg);
+ }
+ st->lines++;
+
+ /*
+ * We print markers for special areas of address space,
+ * such as the start of vmalloc space etc.
+ * This helps in the interpretation.
+ */
+ if (addr >= st->marker[1].start_address) {
+ if (st->marker->max_lines &&
+ st->lines > st->marker->max_lines) {
+ unsigned long nskip =
+ st->lines - st->marker->max_lines;
+ pt_dump_seq_printf(m, st->to_dmesg,
+ "... %lu entr%s skipped ... \n",
+ nskip,
+ nskip == 1 ? "y" : "ies");
+ }
+ st->marker++;
+ st->lines = 0;
+ pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+ st->marker->name);
+ }
+
+ st->start_address = addr;
+ st->current_prot = new_prot;
+ st->effective_prot = new_eff;
+ st->level = level;
+ }
+}
+
+static void ptdump_walk_pgd_level_core(struct seq_file *m,
+ struct mm_struct *mm, pgd_t *pgd,
+ bool checkwx, bool dmesg)
+{
+ const struct ptdump_range ptdump_ranges[] = {
+#ifdef CONFIG_X86_64
+ {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
+ {GUARD_HOLE_END_ADDR, ~0UL},
+#else
+ {0, ~0UL},
+#endif
+ {0, 0}
+};
+
+ struct pg_state st = {
+ .ptdump = {
+ .note_page = note_page,
+ .effective_prot = effective_prot,
+ .range = ptdump_ranges
+ },
+ .level = -1,
+ .to_dmesg = dmesg,
+ .check_wx = checkwx,
+ .seq = m
+ };
+
+ ptdump_walk_pgd(&st.ptdump, mm, pgd);
+
+ if (!checkwx)
+ return;
+ if (st.wx_pages)
+ pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n",
+ st.wx_pages);
+ else
+ pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
+}
+
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
+{
+ ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+ bool user)
+{
+ pgd_t *pgd = mm->pgd;
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (user && boot_cpu_has(X86_FEATURE_PTI))
+ pgd = kernel_to_user_pgdp(pgd);
+#endif
+ ptdump_walk_pgd_level_core(m, mm, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pgd_t *pgd = INIT_PGD;
+
+ if (!(__supported_pte_mask & _PAGE_NX) ||
+ !boot_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("x86/mm: Checking user space page tables\n");
+ pgd = kernel_to_user_pgdp(pgd);
+ ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false);
+#endif
+}
+
+void ptdump_walk_pgd_level_checkwx(void)
+{
+ ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
+}
+
+static int __init pt_dump_init(void)
+{
+ /*
+ * Various markers are not compile-time constants, so assign them
+ * here.
+ */
+#ifdef CONFIG_X86_64
+ address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET;
+ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+ address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START;
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+#endif
+#ifdef CONFIG_KASAN
+ address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+ address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
+#endif
+#ifdef CONFIG_X86_32
+ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+ address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+# ifdef CONFIG_HIGHMEM
+ address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
+# endif
+ address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+ address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+ address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
+#endif
+ return 0;
+}
+__initcall(pt_dump_init);