aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/include/asm/book3s/64/radix.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/powerpc/include/asm/book3s/64/radix.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 'arch/powerpc/include/asm/book3s/64/radix.h')
-rw-r--r--arch/powerpc/include/asm/book3s/64/radix.h329
1 files changed, 329 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
new file mode 100644
index 000000000..686001eda
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -0,0 +1,329 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_PGTABLE_RADIX_H
+#define _ASM_POWERPC_PGTABLE_RADIX_H
+
+#include <asm/asm-const.h>
+
+#ifndef __ASSEMBLY__
+#include <asm/cmpxchg.h>
+#endif
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/book3s/64/radix-64k.h>
+#else
+#include <asm/book3s/64/radix-4k.h>
+#endif
+
+#ifndef __ASSEMBLY__
+#include <asm/book3s/64/tlbflush-radix.h>
+#include <asm/cpu_has_feature.h>
+#endif
+
+/* An empty PTE can still have a R or C writeback */
+#define RADIX_PTE_NONE_MASK (_PAGE_DIRTY | _PAGE_ACCESSED)
+
+/* Bits to set in a RPMD/RPUD/RPGD */
+#define RADIX_PMD_VAL_BITS (0x8000000000000000UL | RADIX_PTE_INDEX_SIZE)
+#define RADIX_PUD_VAL_BITS (0x8000000000000000UL | RADIX_PMD_INDEX_SIZE)
+#define RADIX_PGD_VAL_BITS (0x8000000000000000UL | RADIX_PUD_INDEX_SIZE)
+
+/* Don't have anything in the reserved bits and leaf bits */
+#define RADIX_PMD_BAD_BITS 0x60000000000000e0UL
+#define RADIX_PUD_BAD_BITS 0x60000000000000e0UL
+#define RADIX_P4D_BAD_BITS 0x60000000000000e0UL
+
+#define RADIX_PMD_SHIFT (PAGE_SHIFT + RADIX_PTE_INDEX_SIZE)
+#define RADIX_PUD_SHIFT (RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE)
+#define RADIX_PGD_SHIFT (RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE)
+
+#define R_PTRS_PER_PTE (1 << RADIX_PTE_INDEX_SIZE)
+#define R_PTRS_PER_PMD (1 << RADIX_PMD_INDEX_SIZE)
+#define R_PTRS_PER_PUD (1 << RADIX_PUD_INDEX_SIZE)
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define RADIX_PGTABLE_EADDR_SIZE (RADIX_PTE_INDEX_SIZE + RADIX_PMD_INDEX_SIZE + \
+ RADIX_PUD_INDEX_SIZE + RADIX_PGD_INDEX_SIZE + PAGE_SHIFT)
+#define RADIX_PGTABLE_RANGE (ASM_CONST(1) << RADIX_PGTABLE_EADDR_SIZE)
+
+/*
+ * We support 52 bit address space, Use top bit for kernel
+ * virtual mapping. Also make sure kernel fit in the top
+ * quadrant.
+ *
+ * +------------------+
+ * +------------------+ Kernel virtual map (0xc008000000000000)
+ * | |
+ * | |
+ * | |
+ * 0b11......+------------------+ Kernel linear map (0xc....)
+ * | |
+ * | 2 quadrant |
+ * | |
+ * 0b10......+------------------+
+ * | |
+ * | 1 quadrant |
+ * | |
+ * 0b01......+------------------+
+ * | |
+ * | 0 quadrant |
+ * | |
+ * 0b00......+------------------+
+ *
+ *
+ * 3rd quadrant expanded:
+ * +------------------------------+ Highest address (0xc010000000000000)
+ * +------------------------------+ KASAN shadow end (0xc00fc00000000000)
+ * | |
+ * | |
+ * +------------------------------+ Kernel vmemmap end/shadow start (0xc00e000000000000)
+ * | |
+ * | 512TB |
+ * | |
+ * +------------------------------+ Kernel IO map end/vmemap start
+ * | |
+ * | 512TB |
+ * | |
+ * +------------------------------+ Kernel vmap end/ IO map start
+ * | |
+ * | 512TB |
+ * | |
+ * +------------------------------+ Kernel virt start (0xc008000000000000)
+ * | |
+ * | |
+ * | |
+ * +------------------------------+ Kernel linear (0xc.....)
+ */
+
+/* For the sizes of the shadow area, see kasan.h */
+
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME)
+#define R_MAX_PHYSMEM_BITS 51
+#else
+#define R_MAX_PHYSMEM_BITS 46
+#endif
+
+#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000)
+/*
+ * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick
+ * the same value as hash.
+ */
+#define RADIX_KERN_MAP_SIZE (1UL << 49)
+
+#define RADIX_VMALLOC_START RADIX_KERN_VIRT_START
+#define RADIX_VMALLOC_SIZE RADIX_KERN_MAP_SIZE
+#define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE)
+
+#define RADIX_KERN_IO_START RADIX_VMALLOC_END
+#define RADIX_KERN_IO_SIZE RADIX_KERN_MAP_SIZE
+#define RADIX_KERN_IO_END (RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE)
+
+#define RADIX_VMEMMAP_START RADIX_KERN_IO_END
+#define RADIX_VMEMMAP_SIZE RADIX_KERN_MAP_SIZE
+#define RADIX_VMEMMAP_END (RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
+
+#ifndef __ASSEMBLY__
+#define RADIX_PTE_TABLE_SIZE (sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
+#define RADIX_PMD_TABLE_SIZE (sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE)
+#define RADIX_PUD_TABLE_SIZE (sizeof(pud_t) << RADIX_PUD_INDEX_SIZE)
+#define RADIX_PGD_TABLE_SIZE (sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE)
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+extern void radix__mark_rodata_ro(void);
+extern void radix__mark_initmem_nx(void);
+#endif
+
+extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
+ pte_t entry, unsigned long address,
+ int psize);
+
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte);
+
+static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
+ unsigned long set)
+{
+ __be64 old_be, tmp_be;
+
+ __asm__ __volatile__(
+ "1: ldarx %0,0,%3 # pte_update\n"
+ " andc %1,%0,%5 \n"
+ " or %1,%1,%4 \n"
+ " stdcx. %1,0,%3 \n"
+ " bne- 1b"
+ : "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep)
+ : "r" (ptep), "r" (cpu_to_be64(set)), "r" (cpu_to_be64(clr))
+ : "cc" );
+
+ return be64_to_cpu(old_be);
+}
+
+static inline unsigned long radix__pte_update(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, unsigned long clr,
+ unsigned long set,
+ int huge)
+{
+ unsigned long old_pte;
+
+ old_pte = __radix_pte_update(ptep, clr, set);
+ if (!huge)
+ assert_pte_locked(mm, addr);
+
+ return old_pte;
+}
+
+static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, int full)
+{
+ unsigned long old_pte;
+
+ if (full) {
+ old_pte = pte_val(*ptep);
+ *ptep = __pte(0);
+ } else
+ old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0);
+
+ return __pte(old_pte);
+}
+
+static inline int radix__pte_same(pte_t pte_a, pte_t pte_b)
+{
+ return ((pte_raw(pte_a) ^ pte_raw(pte_b)) == 0);
+}
+
+static inline int radix__pte_none(pte_t pte)
+{
+ return (pte_val(pte) & ~RADIX_PTE_NONE_MASK) == 0;
+}
+
+static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, int percpu)
+{
+ *ptep = pte;
+
+ /*
+ * The architecture suggests a ptesync after setting the pte, which
+ * orders the store that updates the pte with subsequent page table
+ * walk accesses which may load the pte. Without this it may be
+ * possible for a subsequent access to result in spurious fault.
+ *
+ * This is not necessary for correctness, because a spurious fault
+ * is tolerated by the page fault handler, and this store will
+ * eventually be seen. In testing, there was no noticable increase
+ * in user faults on POWER9. Avoiding ptesync here is a significant
+ * win for things like fork. If a future microarchitecture benefits
+ * from ptesync, it should probably go into update_mmu_cache, rather
+ * than set_pte_at (which is used to set ptes unrelated to faults).
+ *
+ * Spurious faults from the kernel memory are not tolerated, so there
+ * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows
+ * the pte update sequence from ISA Book III 6.10 Translation Table
+ * Update Synchronization Requirements.
+ */
+}
+
+static inline int radix__pmd_bad(pmd_t pmd)
+{
+ return !!(pmd_val(pmd) & RADIX_PMD_BAD_BITS);
+}
+
+static inline int radix__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+ return ((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) == 0);
+}
+
+static inline int radix__pud_bad(pud_t pud)
+{
+ return !!(pud_val(pud) & RADIX_PUD_BAD_BITS);
+}
+
+
+static inline int radix__p4d_bad(p4d_t p4d)
+{
+ return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+static inline int radix__pmd_trans_huge(pmd_t pmd)
+{
+ return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
+}
+
+static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
+{
+ return __pmd(pmd_val(pmd) | _PAGE_PTE);
+}
+
+extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp, unsigned long clr,
+ unsigned long set);
+extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
+extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable);
+extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pmd_t *pmdp);
+static inline int radix__has_transparent_hugepage(void)
+{
+ /* For radix 2M at PMD level means thp */
+ if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
+ return 1;
+ return 0;
+}
+#endif
+
+static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+{
+ return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
+extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
+ unsigned long page_size,
+ unsigned long phys);
+extern void radix__vmemmap_remove_mapping(unsigned long start,
+ unsigned long page_size);
+
+extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+ pgprot_t flags, unsigned int psz);
+
+static inline unsigned long radix__get_tree_size(void)
+{
+ unsigned long rts_field;
+ /*
+ * We support 52 bits, hence:
+ * bits 52 - 31 = 21, 0b10101
+ * RTS encoding details
+ * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+ * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+ */
+ rts_field = (0x5UL << 5); /* 6 - 8 bits */
+ rts_field |= (0x2UL << 61);
+
+ return rts_field;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int radix__create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot);
+int radix__remove_section_mapping(unsigned long start, unsigned long end);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+void radix__kernel_map_pages(struct page *page, int numpages, int enable);
+
+#endif /* __ASSEMBLY__ */
+#endif