aboutsummaryrefslogtreecommitdiff
path: root/arch/mips/include/asm/pgtable-64.h
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/mips/include/asm/pgtable-64.h
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 '')
-rw-r--r--arch/mips/include/asm/pgtable-64.h335
1 files changed, 335 insertions, 0 deletions
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
new file mode 100644
index 000000000..c6310192b
--- /dev/null
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -0,0 +1,335 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994, 95, 96, 97, 98, 99, 2000, 2003 Ralf Baechle
+ * Copyright (C) 1999, 2000, 2001 Silicon Graphics, Inc.
+ */
+#ifndef _ASM_PGTABLE_64_H
+#define _ASM_PGTABLE_64_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+
+#include <asm/addrspace.h>
+#include <asm/page.h>
+#include <asm/cachectl.h>
+#include <asm/fixmap.h>
+
+#if CONFIG_PGTABLE_LEVELS == 2
+#include <asm-generic/pgtable-nopmd.h>
+#elif CONFIG_PGTABLE_LEVELS == 3
+#include <asm-generic/pgtable-nopud.h>
+#else
+#include <asm-generic/pgtable-nop4d.h>
+#endif
+
+/*
+ * Each address space has 2 4K pages as its page directory, giving 1024
+ * (== PTRS_PER_PGD) 8 byte pointers to pmd tables. Each pmd table is a
+ * single 4K page, giving 512 (== PTRS_PER_PMD) 8 byte pointers to page
+ * tables. Each page table is also a single 4K page, giving 512 (==
+ * PTRS_PER_PTE) 8 byte ptes. Each pud entry is initialized to point to
+ * invalid_pmd_table, each pmd entry is initialized to point to
+ * invalid_pte_table, each pte is initialized to 0.
+ *
+ * Kernel mappings: kernel mappings are held in the swapper_pg_table.
+ * The layout is identical to userspace except it's indexed with the
+ * fault address - VMALLOC_START.
+ */
+
+
+/* PGDIR_SHIFT determines what a third-level page table entry can map */
+#ifdef __PAGETABLE_PMD_FOLDED
+#define PGDIR_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3)
+#else
+
+/* PMD_SHIFT determines the size of the area a second-level page table can map */
+#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3))
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+
+# ifdef __PAGETABLE_PUD_FOLDED
+# define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_TABLE_ORDER - 3))
+# endif
+#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_TABLE_ORDER - 3))
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
+#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT + PUD_TABLE_ORDER - 3))
+#endif
+
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+/*
+ * For 4kB page size we use a 3 level page tree and an 8kB pud, which
+ * permits us mapping 40 bits of virtual address space.
+ *
+ * We used to implement 41 bits by having an order 1 pmd level but that seemed
+ * rather pointless.
+ *
+ * For 8kB page size we use a 3 level page tree which permits a total of
+ * 8TB of address space. Alternatively a 33-bit / 8GB organization using
+ * two levels would be easy to implement.
+ *
+ * For 16kB page size we use a 2 level page tree which permits a total of
+ * 36 bits of virtual address space. We could add a third level but it seems
+ * like at the moment there's no need for this.
+ *
+ * For 64kB page size we use a 2 level page table tree for a total of 42 bits
+ * of virtual address space.
+ */
+#ifdef CONFIG_PAGE_SIZE_4KB
+# ifdef CONFIG_MIPS_VA_BITS_48
+# define PGD_TABLE_ORDER 0
+# define PUD_TABLE_ORDER 0
+# else
+# define PGD_TABLE_ORDER 1
+# define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud
+# endif
+#define PMD_TABLE_ORDER 0
+#endif
+#ifdef CONFIG_PAGE_SIZE_8KB
+#define PGD_TABLE_ORDER 0
+#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud
+#define PMD_TABLE_ORDER 0
+#endif
+#ifdef CONFIG_PAGE_SIZE_16KB
+#ifdef CONFIG_MIPS_VA_BITS_48
+#define PGD_TABLE_ORDER 1
+#else
+#define PGD_TABLE_ORDER 0
+#endif
+#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud
+#define PMD_TABLE_ORDER 0
+#endif
+#ifdef CONFIG_PAGE_SIZE_32KB
+#define PGD_TABLE_ORDER 0
+#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud
+#define PMD_TABLE_ORDER 0
+#endif
+#ifdef CONFIG_PAGE_SIZE_64KB
+#define PGD_TABLE_ORDER 0
+#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud
+#ifdef CONFIG_MIPS_VA_BITS_48
+#define PMD_TABLE_ORDER 0
+#else
+#define PMD_TABLE_ORDER aieeee_attempt_to_allocate_pmd
+#endif
+#endif
+
+#define PTRS_PER_PGD ((PAGE_SIZE << PGD_TABLE_ORDER) / sizeof(pgd_t))
+#ifndef __PAGETABLE_PUD_FOLDED
+#define PTRS_PER_PUD ((PAGE_SIZE << PUD_TABLE_ORDER) / sizeof(pud_t))
+#endif
+#ifndef __PAGETABLE_PMD_FOLDED
+#define PTRS_PER_PMD ((PAGE_SIZE << PMD_TABLE_ORDER) / sizeof(pmd_t))
+#endif
+#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
+
+#define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1)
+
+/*
+ * TLB refill handlers also map the vmalloc area into xuseg. Avoid
+ * the first couple of pages so NULL pointer dereferences will still
+ * reliably trap.
+ */
+#define VMALLOC_START (MAP_BASE + (2 * PAGE_SIZE))
+#define VMALLOC_END \
+ (MAP_BASE + \
+ min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, \
+ (1UL << cpu_vmbits)) - (1UL << 32))
+
+#if defined(CONFIG_MODULES) && defined(KBUILD_64BIT_SYM32) && \
+ VMALLOC_START != CKSSEG
+/* Load modules into 32bit-compatible segment. */
+#define MODULE_START CKSSEG
+#define MODULE_END (FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
+#endif
+#ifndef __PAGETABLE_PUD_FOLDED
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
+#endif
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+extern pte_t invalid_pte_table[PTRS_PER_PTE];
+
+#ifndef __PAGETABLE_PUD_FOLDED
+/*
+ * For 4-level pagetables we defines these ourselves, for 3-level the
+ * definitions are below, for 2-level the
+ * definitions are supplied by <asm-generic/pgtable-nopmd.h>.
+ */
+typedef struct { unsigned long pud; } pud_t;
+#define pud_val(x) ((x).pud)
+#define __pud(x) ((pud_t) { (x) })
+
+extern pud_t invalid_pud_table[PTRS_PER_PUD];
+
+/*
+ * Empty pgd entries point to the invalid_pud_table.
+ */
+static inline int p4d_none(p4d_t p4d)
+{
+ return p4d_val(p4d) == (unsigned long)invalid_pud_table;
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+ if (unlikely(p4d_val(p4d) & ~PAGE_MASK))
+ return 1;
+
+ return 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+ return p4d_val(p4d) != (unsigned long)invalid_pud_table;
+}
+
+static inline void p4d_clear(p4d_t *p4dp)
+{
+ p4d_val(*p4dp) = (unsigned long)invalid_pud_table;
+}
+
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+ return (pud_t *)p4d_val(p4d);
+}
+
+#define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d))
+#define p4d_page(p4d) (pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT))
+
+#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
+
+static inline void set_p4d(p4d_t *p4d, p4d_t p4dval)
+{
+ *p4d = p4dval;
+}
+
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+/*
+ * For 3-level pagetables we defines these ourselves, for 2-level the
+ * definitions are supplied by <asm-generic/pgtable-nopmd.h>.
+ */
+typedef struct { unsigned long pmd; } pmd_t;
+#define pmd_val(x) ((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) } )
+
+
+extern pmd_t invalid_pmd_table[PTRS_PER_PMD];
+#endif
+
+/*
+ * Empty pgd/pmd entries point to the invalid_pte_table.
+ */
+static inline int pmd_none(pmd_t pmd)
+{
+ return pmd_val(pmd) == (unsigned long) invalid_pte_table;
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+ /* pmd_huge(pmd) but inline */
+ if (unlikely(pmd_val(pmd) & _PAGE_HUGE))
+ return 0;
+#endif
+
+ if (unlikely(pmd_val(pmd) & ~PAGE_MASK))
+ return 1;
+
+ return 0;
+}
+
+static inline int pmd_present(pmd_t pmd)
+{
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+ if (unlikely(pmd_val(pmd) & _PAGE_HUGE))
+ return pmd_val(pmd) & _PAGE_PRESENT;
+#endif
+
+ return pmd_val(pmd) != (unsigned long) invalid_pte_table;
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+ pmd_val(*pmdp) = ((unsigned long) invalid_pte_table);
+}
+#ifndef __PAGETABLE_PMD_FOLDED
+
+/*
+ * Empty pud entries point to the invalid_pmd_table.
+ */
+static inline int pud_none(pud_t pud)
+{
+ return pud_val(pud) == (unsigned long) invalid_pmd_table;
+}
+
+static inline int pud_bad(pud_t pud)
+{
+ return pud_val(pud) & ~PAGE_MASK;
+}
+
+static inline int pud_present(pud_t pud)
+{
+ return pud_val(pud) != (unsigned long) invalid_pmd_table;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+ pud_val(*pudp) = ((unsigned long) invalid_pmd_table);
+}
+#endif
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+#define pte_pfn(x) ((unsigned long)((x).pte >> _PFN_SHIFT))
+#define pfn_pte(pfn, prot) __pte(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot) __pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
+
+#ifndef __PAGETABLE_PMD_FOLDED
+static inline pmd_t *pud_pgtable(pud_t pud)
+{
+ return (pmd_t *)pud_val(pud);
+}
+#define pud_phys(pud) virt_to_phys((void *)pud_val(pud))
+#define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT))
+
+#endif
+
+/*
+ * Initialize a new pgd / pud / pmd table with invalid pointers.
+ */
+extern void pgd_init(void *addr);
+extern void pud_init(void *addr);
+extern void pmd_init(void *addr);
+
+/*
+ * Non-present pages: high 40 bits are offset, next 8 bits type,
+ * low 16 bits zero.
+ */
+static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
+{ pte_t pte; pte_val(pte) = (type << 16) | (offset << 24); return pte; }
+
+#define __swp_type(x) (((x).val >> 16) & 0xff)
+#define __swp_offset(x) ((x).val >> 24)
+#define __swp_entry(type, offset) ((swp_entry_t) { pte_val(mk_swap_pte((type), (offset))) })
+#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+
+#endif /* _ASM_PGTABLE_64_H */