aboutsummaryrefslogtreecommitdiff
path: root/arch/arm64/mm/kasan_init.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/arm64/mm/kasan_init.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/arm64/mm/kasan_init.c')
-rw-r--r--arch/arm64/mm/kasan_init.c317
1 files changed, 317 insertions, 0 deletions
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
new file mode 100644
index 000000000..e969e68de
--- /dev/null
+++ b/arch/arm64/mm/kasan_init.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains kasan initialization code for ARM64.
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/sched/task.h>
+#include <linux/memblock.h>
+#include <linux/start_kernel.h>
+#include <linux/mm.h>
+
+#include <asm/mmu_context.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <asm/tlbflush.h>
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
+static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). All the early functions are called too
+ * early to use lm_alias so __p*d_populate functions must be used to populate
+ * with the physical address from __pa_symbol.
+ */
+
+static phys_addr_t __init kasan_alloc_zeroed_page(int node)
+{
+ void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE,
+ __pa(MAX_DMA_ADDRESS),
+ MEMBLOCK_ALLOC_NOLEAKTRACE, node);
+ if (!p)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE, node,
+ __pa(MAX_DMA_ADDRESS));
+
+ return __pa(p);
+}
+
+static phys_addr_t __init kasan_alloc_raw_page(int node)
+{
+ void *p = memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE,
+ __pa(MAX_DMA_ADDRESS),
+ MEMBLOCK_ALLOC_NOLEAKTRACE,
+ node);
+ if (!p)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE, node,
+ __pa(MAX_DMA_ADDRESS));
+
+ return __pa(p);
+}
+
+static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
+ bool early)
+{
+ if (pmd_none(READ_ONCE(*pmdp))) {
+ phys_addr_t pte_phys = early ?
+ __pa_symbol(kasan_early_shadow_pte)
+ : kasan_alloc_zeroed_page(node);
+ __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+ }
+
+ return early ? pte_offset_kimg(pmdp, addr)
+ : pte_offset_kernel(pmdp, addr);
+}
+
+static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
+ bool early)
+{
+ if (pud_none(READ_ONCE(*pudp))) {
+ phys_addr_t pmd_phys = early ?
+ __pa_symbol(kasan_early_shadow_pmd)
+ : kasan_alloc_zeroed_page(node);
+ __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+ }
+
+ return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
+}
+
+static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node,
+ bool early)
+{
+ if (p4d_none(READ_ONCE(*p4dp))) {
+ phys_addr_t pud_phys = early ?
+ __pa_symbol(kasan_early_shadow_pud)
+ : kasan_alloc_zeroed_page(node);
+ __p4d_populate(p4dp, pud_phys, P4D_TYPE_TABLE);
+ }
+
+ return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early);
+
+ do {
+ phys_addr_t page_phys = early ?
+ __pa_symbol(kasan_early_shadow_page)
+ : kasan_alloc_raw_page(node);
+ if (!early)
+ memset(__va(page_phys), KASAN_SHADOW_INIT, PAGE_SIZE);
+ next = addr + PAGE_SIZE;
+ set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+ } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep)));
+}
+
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early);
+
+ do {
+ next = pmd_addr_end(addr, end);
+ kasan_pte_populate(pmdp, addr, next, node, early);
+ } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp)));
+}
+
+static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ pud_t *pudp = kasan_pud_offset(p4dp, addr, node, early);
+
+ do {
+ next = pud_addr_end(addr, end);
+ kasan_pmd_populate(pudp, addr, next, node, early);
+ } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
+}
+
+static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, int node, bool early)
+{
+ unsigned long next;
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+
+ do {
+ next = p4d_addr_end(addr, end);
+ kasan_pud_populate(p4dp, addr, next, node, early);
+ } while (p4dp++, addr = next, addr != end);
+}
+
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+ int node, bool early)
+{
+ unsigned long next;
+ pgd_t *pgdp;
+
+ pgdp = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ kasan_p4d_populate(pgdp, addr, next, node, early);
+ } while (pgdp++, addr = next, addr != end);
+}
+
+/* The early shadow maps everything to a single page of zeroes */
+asmlinkage void __init kasan_early_init(void)
+{
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+ BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+ kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE,
+ true);
+}
+
+/* Set up full kasan mappings, ensuring that the mapped pages are zeroed */
+static void __init kasan_map_populate(unsigned long start, unsigned long end,
+ int node)
+{
+ kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false);
+}
+
+/*
+ * Copy the current shadow region into a new pgdir.
+ */
+void __init kasan_copy_shadow(pgd_t *pgdir)
+{
+ pgd_t *pgdp, *pgdp_new, *pgdp_end;
+
+ pgdp = pgd_offset_k(KASAN_SHADOW_START);
+ pgdp_end = pgd_offset_k(KASAN_SHADOW_END);
+ pgdp_new = pgd_offset_pgd(pgdir, KASAN_SHADOW_START);
+ do {
+ set_pgd(pgdp_new, READ_ONCE(*pgdp));
+ } while (pgdp++, pgdp_new++, pgdp != pgdp_end);
+}
+
+static void __init clear_pgds(unsigned long start,
+ unsigned long end)
+{
+ /*
+ * Remove references to kasan page tables from
+ * swapper_pg_dir. pgd_clear() can't be used
+ * here because it's nop on 2,3-level pagetable setups
+ */
+ for (; start < end; start += PGDIR_SIZE)
+ set_pgd(pgd_offset_k(start), __pgd(0));
+}
+
+static void __init kasan_init_shadow(void)
+{
+ u64 kimg_shadow_start, kimg_shadow_end;
+ u64 mod_shadow_start, mod_shadow_end;
+ u64 vmalloc_shadow_end;
+ phys_addr_t pa_start, pa_end;
+ u64 i;
+
+ kimg_shadow_start = (u64)kasan_mem_to_shadow(KERNEL_START) & PAGE_MASK;
+ kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(KERNEL_END));
+
+ mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR);
+ mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END);
+
+ vmalloc_shadow_end = (u64)kasan_mem_to_shadow((void *)VMALLOC_END);
+
+ /*
+ * We are going to perform proper setup of shadow memory.
+ * At first we should unmap early shadow (clear_pgds() call below).
+ * However, instrumented code couldn't execute without shadow memory.
+ * tmp_pg_dir used to keep early shadow mapped until full shadow
+ * setup will be finished.
+ */
+ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
+ dsb(ishst);
+ cpu_replace_ttbr1(lm_alias(tmp_pg_dir), idmap_pg_dir);
+
+ clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
+ early_pfn_to_nid(virt_to_pfn(lm_alias(KERNEL_START))));
+
+ kasan_populate_early_shadow(kasan_mem_to_shadow((void *)PAGE_END),
+ (void *)mod_shadow_start);
+
+ if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+ BUILD_BUG_ON(VMALLOC_START != MODULES_END);
+ kasan_populate_early_shadow((void *)vmalloc_shadow_end,
+ (void *)KASAN_SHADOW_END);
+ } else {
+ kasan_populate_early_shadow((void *)kimg_shadow_end,
+ (void *)KASAN_SHADOW_END);
+ if (kimg_shadow_start > mod_shadow_end)
+ kasan_populate_early_shadow((void *)mod_shadow_end,
+ (void *)kimg_shadow_start);
+ }
+
+ for_each_mem_range(i, &pa_start, &pa_end) {
+ void *start = (void *)__phys_to_virt(pa_start);
+ void *end = (void *)__phys_to_virt(pa_end);
+
+ if (start >= end)
+ break;
+
+ kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
+ (unsigned long)kasan_mem_to_shadow(end),
+ early_pfn_to_nid(virt_to_pfn(start)));
+ }
+
+ /*
+ * KAsan may reuse the contents of kasan_early_shadow_pte directly,
+ * so we should make sure that it maps the zero page read-only.
+ */
+ for (i = 0; i < PTRS_PER_PTE; i++)
+ set_pte(&kasan_early_shadow_pte[i],
+ pfn_pte(sym_to_pfn(kasan_early_shadow_page),
+ PAGE_KERNEL_RO));
+
+ memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir);
+}
+
+static void __init kasan_init_depth(void)
+{
+ init_task.kasan_depth = 0;
+}
+
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+ unsigned long shadow_start, shadow_end;
+
+ if (!is_vmalloc_or_module_addr(start))
+ return;
+
+ shadow_start = (unsigned long)kasan_mem_to_shadow(start);
+ shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
+ shadow_end = (unsigned long)kasan_mem_to_shadow(start + size);
+ shadow_end = ALIGN(shadow_end, PAGE_SIZE);
+ kasan_map_populate(shadow_start, shadow_end, NUMA_NO_NODE);
+}
+#endif
+
+void __init kasan_init(void)
+{
+ kasan_init_shadow();
+ kasan_init_depth();
+#if defined(CONFIG_KASAN_GENERIC)
+ /* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */
+ pr_info("KernelAddressSanitizer initialized (generic)\n");
+#endif
+}
+
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */