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(). ... --- arch/um/kernel/tlb.c | 602 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 602 insertions(+) create mode 100644 arch/um/kernel/tlb.c (limited to 'arch/um/kernel/tlb.c') diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c new file mode 100644 index 000000000..ad449173a --- /dev/null +++ b/arch/um/kernel/tlb.c @@ -0,0 +1,602 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + */ + +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +struct host_vm_change { + struct host_vm_op { + enum { NONE, MMAP, MUNMAP, MPROTECT } type; + union { + struct { + unsigned long addr; + unsigned long len; + unsigned int prot; + int fd; + __u64 offset; + } mmap; + struct { + unsigned long addr; + unsigned long len; + } munmap; + struct { + unsigned long addr; + unsigned long len; + unsigned int prot; + } mprotect; + } u; + } ops[1]; + int userspace; + int index; + struct mm_struct *mm; + void *data; + int force; +}; + +#define INIT_HVC(mm, force, userspace) \ + ((struct host_vm_change) \ + { .ops = { { .type = NONE } }, \ + .mm = mm, \ + .data = NULL, \ + .userspace = userspace, \ + .index = 0, \ + .force = force }) + +static void report_enomem(void) +{ + printk(KERN_ERR "UML ran out of memory on the host side! " + "This can happen due to a memory limitation or " + "vm.max_map_count has been reached.\n"); +} + +static int do_ops(struct host_vm_change *hvc, int end, + int finished) +{ + struct host_vm_op *op; + int i, ret = 0; + + for (i = 0; i < end && !ret; i++) { + op = &hvc->ops[i]; + switch (op->type) { + case MMAP: + if (hvc->userspace) + ret = map(&hvc->mm->context.id, op->u.mmap.addr, + op->u.mmap.len, op->u.mmap.prot, + op->u.mmap.fd, + op->u.mmap.offset, finished, + &hvc->data); + else + map_memory(op->u.mmap.addr, op->u.mmap.offset, + op->u.mmap.len, 1, 1, 1); + break; + case MUNMAP: + if (hvc->userspace) + ret = unmap(&hvc->mm->context.id, + op->u.munmap.addr, + op->u.munmap.len, finished, + &hvc->data); + else + ret = os_unmap_memory( + (void *) op->u.munmap.addr, + op->u.munmap.len); + + break; + case MPROTECT: + if (hvc->userspace) + ret = protect(&hvc->mm->context.id, + op->u.mprotect.addr, + op->u.mprotect.len, + op->u.mprotect.prot, + finished, &hvc->data); + else + ret = os_protect_memory( + (void *) op->u.mprotect.addr, + op->u.mprotect.len, + 1, 1, 1); + break; + default: + printk(KERN_ERR "Unknown op type %d in do_ops\n", + op->type); + BUG(); + break; + } + } + + if (ret == -ENOMEM) + report_enomem(); + + return ret; +} + +static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, + unsigned int prot, struct host_vm_change *hvc) +{ + __u64 offset; + struct host_vm_op *last; + int fd = -1, ret = 0; + + if (hvc->userspace) + fd = phys_mapping(phys, &offset); + else + offset = phys; + if (hvc->index != 0) { + last = &hvc->ops[hvc->index - 1]; + if ((last->type == MMAP) && + (last->u.mmap.addr + last->u.mmap.len == virt) && + (last->u.mmap.prot == prot) && (last->u.mmap.fd == fd) && + (last->u.mmap.offset + last->u.mmap.len == offset)) { + last->u.mmap.len += len; + return 0; + } + } + + if (hvc->index == ARRAY_SIZE(hvc->ops)) { + ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); + hvc->index = 0; + } + + hvc->ops[hvc->index++] = ((struct host_vm_op) + { .type = MMAP, + .u = { .mmap = { .addr = virt, + .len = len, + .prot = prot, + .fd = fd, + .offset = offset } + } }); + return ret; +} + +static int add_munmap(unsigned long addr, unsigned long len, + struct host_vm_change *hvc) +{ + struct host_vm_op *last; + int ret = 0; + + if (hvc->index != 0) { + last = &hvc->ops[hvc->index - 1]; + if ((last->type == MUNMAP) && + (last->u.munmap.addr + last->u.mmap.len == addr)) { + last->u.munmap.len += len; + return 0; + } + } + + if (hvc->index == ARRAY_SIZE(hvc->ops)) { + ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); + hvc->index = 0; + } + + hvc->ops[hvc->index++] = ((struct host_vm_op) + { .type = MUNMAP, + .u = { .munmap = { .addr = addr, + .len = len } } }); + return ret; +} + +static int add_mprotect(unsigned long addr, unsigned long len, + unsigned int prot, struct host_vm_change *hvc) +{ + struct host_vm_op *last; + int ret = 0; + + if (hvc->index != 0) { + last = &hvc->ops[hvc->index - 1]; + if ((last->type == MPROTECT) && + (last->u.mprotect.addr + last->u.mprotect.len == addr) && + (last->u.mprotect.prot == prot)) { + last->u.mprotect.len += len; + return 0; + } + } + + if (hvc->index == ARRAY_SIZE(hvc->ops)) { + ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); + hvc->index = 0; + } + + hvc->ops[hvc->index++] = ((struct host_vm_op) + { .type = MPROTECT, + .u = { .mprotect = { .addr = addr, + .len = len, + .prot = prot } } }); + return ret; +} + +#define ADD_ROUND(n, inc) (((n) + (inc)) & ~((inc) - 1)) + +static inline int update_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, + struct host_vm_change *hvc) +{ + pte_t *pte; + int r, w, x, prot, ret = 0; + + pte = pte_offset_kernel(pmd, addr); + do { + r = pte_read(*pte); + w = pte_write(*pte); + x = pte_exec(*pte); + if (!pte_young(*pte)) { + r = 0; + w = 0; + } else if (!pte_dirty(*pte)) + w = 0; + + prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | + (x ? UM_PROT_EXEC : 0)); + if (hvc->force || pte_newpage(*pte)) { + if (pte_present(*pte)) { + if (pte_newpage(*pte)) + ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK, + PAGE_SIZE, prot, hvc); + } else + ret = add_munmap(addr, PAGE_SIZE, hvc); + } else if (pte_newprot(*pte)) + ret = add_mprotect(addr, PAGE_SIZE, prot, hvc); + *pte = pte_mkuptodate(*pte); + } while (pte++, addr += PAGE_SIZE, ((addr < end) && !ret)); + return ret; +} + +static inline int update_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, + struct host_vm_change *hvc) +{ + pmd_t *pmd; + unsigned long next; + int ret = 0; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (!pmd_present(*pmd)) { + if (hvc->force || pmd_newpage(*pmd)) { + ret = add_munmap(addr, next - addr, hvc); + pmd_mkuptodate(*pmd); + } + } + else ret = update_pte_range(pmd, addr, next, hvc); + } while (pmd++, addr = next, ((addr < end) && !ret)); + return ret; +} + +static inline int update_pud_range(p4d_t *p4d, unsigned long addr, + unsigned long end, + struct host_vm_change *hvc) +{ + pud_t *pud; + unsigned long next; + int ret = 0; + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (!pud_present(*pud)) { + if (hvc->force || pud_newpage(*pud)) { + ret = add_munmap(addr, next - addr, hvc); + pud_mkuptodate(*pud); + } + } + else ret = update_pmd_range(pud, addr, next, hvc); + } while (pud++, addr = next, ((addr < end) && !ret)); + return ret; +} + +static inline int update_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, + struct host_vm_change *hvc) +{ + p4d_t *p4d; + unsigned long next; + int ret = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (!p4d_present(*p4d)) { + if (hvc->force || p4d_newpage(*p4d)) { + ret = add_munmap(addr, next - addr, hvc); + p4d_mkuptodate(*p4d); + } + } else + ret = update_pud_range(p4d, addr, next, hvc); + } while (p4d++, addr = next, ((addr < end) && !ret)); + return ret; +} + +void fix_range_common(struct mm_struct *mm, unsigned long start_addr, + unsigned long end_addr, int force) +{ + pgd_t *pgd; + struct host_vm_change hvc; + unsigned long addr = start_addr, next; + int ret = 0, userspace = 1; + + hvc = INIT_HVC(mm, force, userspace); + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end_addr); + if (!pgd_present(*pgd)) { + if (force || pgd_newpage(*pgd)) { + ret = add_munmap(addr, next - addr, &hvc); + pgd_mkuptodate(*pgd); + } + } else + ret = update_p4d_range(pgd, addr, next, &hvc); + } while (pgd++, addr = next, ((addr < end_addr) && !ret)); + + if (!ret) + ret = do_ops(&hvc, hvc.index, 1); + + /* This is not an else because ret is modified above */ + if (ret) { + struct mm_id *mm_idp = ¤t->mm->context.id; + + printk(KERN_ERR "fix_range_common: failed, killing current " + "process: %d\n", task_tgid_vnr(current)); + mm_idp->kill = 1; + } +} + +static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) +{ + struct mm_struct *mm; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long addr, last; + int updated = 0, err = 0, force = 0, userspace = 0; + struct host_vm_change hvc; + + mm = &init_mm; + hvc = INIT_HVC(mm, force, userspace); + for (addr = start; addr < end;) { + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) { + last = ADD_ROUND(addr, PGDIR_SIZE); + if (last > end) + last = end; + if (pgd_newpage(*pgd)) { + updated = 1; + err = add_munmap(addr, last - addr, &hvc); + if (err < 0) + panic("munmap failed, errno = %d\n", + -err); + } + addr = last; + continue; + } + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) { + last = ADD_ROUND(addr, P4D_SIZE); + if (last > end) + last = end; + if (p4d_newpage(*p4d)) { + updated = 1; + err = add_munmap(addr, last - addr, &hvc); + if (err < 0) + panic("munmap failed, errno = %d\n", + -err); + } + addr = last; + continue; + } + + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) { + last = ADD_ROUND(addr, PUD_SIZE); + if (last > end) + last = end; + if (pud_newpage(*pud)) { + updated = 1; + err = add_munmap(addr, last - addr, &hvc); + if (err < 0) + panic("munmap failed, errno = %d\n", + -err); + } + addr = last; + continue; + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + last = ADD_ROUND(addr, PMD_SIZE); + if (last > end) + last = end; + if (pmd_newpage(*pmd)) { + updated = 1; + err = add_munmap(addr, last - addr, &hvc); + if (err < 0) + panic("munmap failed, errno = %d\n", + -err); + } + addr = last; + continue; + } + + pte = pte_offset_kernel(pmd, addr); + if (!pte_present(*pte) || pte_newpage(*pte)) { + updated = 1; + err = add_munmap(addr, PAGE_SIZE, &hvc); + if (err < 0) + panic("munmap failed, errno = %d\n", + -err); + if (pte_present(*pte)) + err = add_mmap(addr, pte_val(*pte) & PAGE_MASK, + PAGE_SIZE, 0, &hvc); + } + else if (pte_newprot(*pte)) { + updated = 1; + err = add_mprotect(addr, PAGE_SIZE, 0, &hvc); + } + addr += PAGE_SIZE; + } + if (!err) + err = do_ops(&hvc, hvc.index, 1); + + if (err < 0) + panic("flush_tlb_kernel failed, errno = %d\n", err); + return updated; +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long address) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + struct mm_struct *mm = vma->vm_mm; + void *flush = NULL; + int r, w, x, prot, err = 0; + struct mm_id *mm_id; + + address &= PAGE_MASK; + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + goto kill; + + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto kill; + + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + goto kill; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + goto kill; + + pte = pte_offset_kernel(pmd, address); + + r = pte_read(*pte); + w = pte_write(*pte); + x = pte_exec(*pte); + if (!pte_young(*pte)) { + r = 0; + w = 0; + } else if (!pte_dirty(*pte)) { + w = 0; + } + + mm_id = &mm->context.id; + prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | + (x ? UM_PROT_EXEC : 0)); + if (pte_newpage(*pte)) { + if (pte_present(*pte)) { + unsigned long long offset; + int fd; + + fd = phys_mapping(pte_val(*pte) & PAGE_MASK, &offset); + err = map(mm_id, address, PAGE_SIZE, prot, fd, offset, + 1, &flush); + } + else err = unmap(mm_id, address, PAGE_SIZE, 1, &flush); + } + else if (pte_newprot(*pte)) + err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush); + + if (err) { + if (err == -ENOMEM) + report_enomem(); + + goto kill; + } + + *pte = pte_mkuptodate(*pte); + + return; + +kill: + printk(KERN_ERR "Failed to flush page for address 0x%lx\n", address); + force_sig(SIGKILL); +} + +void flush_tlb_all(void) +{ + /* + * Don't bother flushing if this address space is about to be + * destroyed. + */ + if (atomic_read(¤t->mm->mm_users) == 0) + return; + + flush_tlb_mm(current->mm); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + flush_tlb_kernel_range_common(start, end); +} + +void flush_tlb_kernel_vm(void) +{ + flush_tlb_kernel_range_common(start_vm, end_vm); +} + +void __flush_tlb_one(unsigned long addr) +{ + flush_tlb_kernel_range_common(addr, addr + PAGE_SIZE); +} + +static void fix_range(struct mm_struct *mm, unsigned long start_addr, + unsigned long end_addr, int force) +{ + /* + * Don't bother flushing if this address space is about to be + * destroyed. + */ + if (atomic_read(&mm->mm_users) == 0) + return; + + fix_range_common(mm, start_addr, end_addr, force); +} + +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + if (vma->vm_mm == NULL) + flush_tlb_kernel_range_common(start, end); + else fix_range(vma->vm_mm, start, end, 0); +} +EXPORT_SYMBOL(flush_tlb_range); + +void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + fix_range(mm, start, end, 0); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + + for_each_vma(vmi, vma) + fix_range(mm, vma->vm_start, vma->vm_end, 0); +} + +void force_flush_all(void) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + + for_each_vma(vmi, vma) + fix_range(mm, vma->vm_start, vma->vm_end, 1); +} -- cgit v1.2.3