aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/mm/pageattr.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/s390/mm/pageattr.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/s390/mm/pageattr.c')
-rw-r--r--arch/s390/mm/pageattr.c373
1 files changed, 373 insertions, 0 deletions
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
new file mode 100644
index 000000000..85195c18b
--- /dev/null
+++ b/arch/s390/mm/pageattr.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2011
+ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+#include <linux/hugetlb.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+#include <asm/facility.h>
+#include <asm/pgalloc.h>
+#include <asm/kfence.h>
+#include <asm/page.h>
+#include <asm/set_memory.h>
+
+static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
+{
+ asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0"
+ : [addr] "+a" (addr) : [skey] "d" (skey));
+ return addr;
+}
+
+void __storage_key_init_range(unsigned long start, unsigned long end)
+{
+ unsigned long boundary, size;
+
+ while (start < end) {
+ if (MACHINE_HAS_EDAT1) {
+ /* set storage keys for a 1MB frame */
+ size = 1UL << 20;
+ boundary = (start + size) & ~(size - 1);
+ if (boundary <= end) {
+ do {
+ start = sske_frame(start, PAGE_DEFAULT_KEY);
+ } while (start < boundary);
+ continue;
+ }
+ }
+ page_set_storage_key(start, PAGE_DEFAULT_KEY, 1);
+ start += PAGE_SIZE;
+ }
+}
+
+#ifdef CONFIG_PROC_FS
+atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
+
+void arch_report_meminfo(struct seq_file *m)
+{
+ seq_printf(m, "DirectMap4k: %8lu kB\n",
+ atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_4K]) << 2);
+ seq_printf(m, "DirectMap1M: %8lu kB\n",
+ atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_1M]) << 10);
+ seq_printf(m, "DirectMap2G: %8lu kB\n",
+ atomic_long_read(&direct_pages_count[PG_DIRECT_MAP_2G]) << 21);
+}
+#endif /* CONFIG_PROC_FS */
+
+static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr,
+ unsigned long dtt)
+{
+ unsigned long *table, mask;
+
+ mask = 0;
+ if (MACHINE_HAS_EDAT2) {
+ switch (dtt) {
+ case CRDTE_DTT_REGION3:
+ mask = ~(PTRS_PER_PUD * sizeof(pud_t) - 1);
+ break;
+ case CRDTE_DTT_SEGMENT:
+ mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+ break;
+ case CRDTE_DTT_PAGE:
+ mask = ~(PTRS_PER_PTE * sizeof(pte_t) - 1);
+ break;
+ }
+ table = (unsigned long *)((unsigned long)old & mask);
+ crdte(*old, new, table, dtt, addr, S390_lowcore.kernel_asce);
+ } else if (MACHINE_HAS_IDTE) {
+ cspg(old, *old, new);
+ } else {
+ csp((unsigned int *)old + 1, *old, new);
+ }
+}
+
+static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ pte_t *ptep, new;
+
+ if (flags == SET_MEMORY_4K)
+ return 0;
+ ptep = pte_offset_kernel(pmdp, addr);
+ do {
+ new = *ptep;
+ if (pte_none(new))
+ return -EINVAL;
+ if (flags & SET_MEMORY_RO)
+ new = pte_wrprotect(new);
+ else if (flags & SET_MEMORY_RW)
+ new = pte_mkwrite(pte_mkdirty(new));
+ if (flags & SET_MEMORY_NX)
+ new = set_pte_bit(new, __pgprot(_PAGE_NOEXEC));
+ else if (flags & SET_MEMORY_X)
+ new = clear_pte_bit(new, __pgprot(_PAGE_NOEXEC));
+ pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE);
+ ptep++;
+ addr += PAGE_SIZE;
+ cond_resched();
+ } while (addr < end);
+ return 0;
+}
+
+static int split_pmd_page(pmd_t *pmdp, unsigned long addr)
+{
+ unsigned long pte_addr, prot;
+ pte_t *pt_dir, *ptep;
+ pmd_t new;
+ int i, ro, nx;
+
+ pt_dir = vmem_pte_alloc();
+ if (!pt_dir)
+ return -ENOMEM;
+ pte_addr = pmd_pfn(*pmdp) << PAGE_SHIFT;
+ ro = !!(pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT);
+ nx = !!(pmd_val(*pmdp) & _SEGMENT_ENTRY_NOEXEC);
+ prot = pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
+ if (!nx)
+ prot &= ~_PAGE_NOEXEC;
+ ptep = pt_dir;
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ set_pte(ptep, __pte(pte_addr | prot));
+ pte_addr += PAGE_SIZE;
+ ptep++;
+ }
+ new = __pmd(__pa(pt_dir) | _SEGMENT_ENTRY);
+ pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT);
+ update_page_count(PG_DIRECT_MAP_4K, PTRS_PER_PTE);
+ update_page_count(PG_DIRECT_MAP_1M, -1);
+ return 0;
+}
+
+static void modify_pmd_page(pmd_t *pmdp, unsigned long addr,
+ unsigned long flags)
+{
+ pmd_t new = *pmdp;
+
+ if (flags & SET_MEMORY_RO)
+ new = pmd_wrprotect(new);
+ else if (flags & SET_MEMORY_RW)
+ new = pmd_mkwrite(pmd_mkdirty(new));
+ if (flags & SET_MEMORY_NX)
+ new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC));
+ else if (flags & SET_MEMORY_X)
+ new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC));
+ pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT);
+}
+
+static int walk_pmd_level(pud_t *pudp, unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ unsigned long next;
+ int need_split;
+ pmd_t *pmdp;
+ int rc = 0;
+
+ pmdp = pmd_offset(pudp, addr);
+ do {
+ if (pmd_none(*pmdp))
+ return -EINVAL;
+ next = pmd_addr_end(addr, end);
+ if (pmd_large(*pmdp)) {
+ need_split = !!(flags & SET_MEMORY_4K);
+ need_split |= !!(addr & ~PMD_MASK);
+ need_split |= !!(addr + PMD_SIZE > next);
+ if (need_split) {
+ rc = split_pmd_page(pmdp, addr);
+ if (rc)
+ return rc;
+ continue;
+ }
+ modify_pmd_page(pmdp, addr, flags);
+ } else {
+ rc = walk_pte_level(pmdp, addr, next, flags);
+ if (rc)
+ return rc;
+ }
+ pmdp++;
+ addr = next;
+ cond_resched();
+ } while (addr < end);
+ return rc;
+}
+
+static int split_pud_page(pud_t *pudp, unsigned long addr)
+{
+ unsigned long pmd_addr, prot;
+ pmd_t *pm_dir, *pmdp;
+ pud_t new;
+ int i, ro, nx;
+
+ pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
+ if (!pm_dir)
+ return -ENOMEM;
+ pmd_addr = pud_pfn(*pudp) << PAGE_SHIFT;
+ ro = !!(pud_val(*pudp) & _REGION_ENTRY_PROTECT);
+ nx = !!(pud_val(*pudp) & _REGION_ENTRY_NOEXEC);
+ prot = pgprot_val(ro ? SEGMENT_KERNEL_RO : SEGMENT_KERNEL);
+ if (!nx)
+ prot &= ~_SEGMENT_ENTRY_NOEXEC;
+ pmdp = pm_dir;
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ set_pmd(pmdp, __pmd(pmd_addr | prot));
+ pmd_addr += PMD_SIZE;
+ pmdp++;
+ }
+ new = __pud(__pa(pm_dir) | _REGION3_ENTRY);
+ pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
+ update_page_count(PG_DIRECT_MAP_1M, PTRS_PER_PMD);
+ update_page_count(PG_DIRECT_MAP_2G, -1);
+ return 0;
+}
+
+static void modify_pud_page(pud_t *pudp, unsigned long addr,
+ unsigned long flags)
+{
+ pud_t new = *pudp;
+
+ if (flags & SET_MEMORY_RO)
+ new = pud_wrprotect(new);
+ else if (flags & SET_MEMORY_RW)
+ new = pud_mkwrite(pud_mkdirty(new));
+ if (flags & SET_MEMORY_NX)
+ new = set_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC));
+ else if (flags & SET_MEMORY_X)
+ new = clear_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC));
+ pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3);
+}
+
+static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ unsigned long next;
+ int need_split;
+ pud_t *pudp;
+ int rc = 0;
+
+ pudp = pud_offset(p4d, addr);
+ do {
+ if (pud_none(*pudp))
+ return -EINVAL;
+ next = pud_addr_end(addr, end);
+ if (pud_large(*pudp)) {
+ need_split = !!(flags & SET_MEMORY_4K);
+ need_split |= !!(addr & ~PUD_MASK);
+ need_split |= !!(addr + PUD_SIZE > next);
+ if (need_split) {
+ rc = split_pud_page(pudp, addr);
+ if (rc)
+ break;
+ continue;
+ }
+ modify_pud_page(pudp, addr, flags);
+ } else {
+ rc = walk_pmd_level(pudp, addr, next, flags);
+ }
+ pudp++;
+ addr = next;
+ cond_resched();
+ } while (addr < end && !rc);
+ return rc;
+}
+
+static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ unsigned long next;
+ p4d_t *p4dp;
+ int rc = 0;
+
+ p4dp = p4d_offset(pgd, addr);
+ do {
+ if (p4d_none(*p4dp))
+ return -EINVAL;
+ next = p4d_addr_end(addr, end);
+ rc = walk_pud_level(p4dp, addr, next, flags);
+ p4dp++;
+ addr = next;
+ cond_resched();
+ } while (addr < end && !rc);
+ return rc;
+}
+
+DEFINE_MUTEX(cpa_mutex);
+
+static int change_page_attr(unsigned long addr, unsigned long end,
+ unsigned long flags)
+{
+ unsigned long next;
+ int rc = -EINVAL;
+ pgd_t *pgdp;
+
+ if (addr == end)
+ return 0;
+ if (end >= MODULES_END)
+ return -EINVAL;
+ mutex_lock(&cpa_mutex);
+ pgdp = pgd_offset_k(addr);
+ do {
+ if (pgd_none(*pgdp))
+ break;
+ next = pgd_addr_end(addr, end);
+ rc = walk_p4d_level(pgdp, addr, next, flags);
+ if (rc)
+ break;
+ cond_resched();
+ } while (pgdp++, addr = next, addr < end && !rc);
+ mutex_unlock(&cpa_mutex);
+ return rc;
+}
+
+int __set_memory(unsigned long addr, int numpages, unsigned long flags)
+{
+ if (!MACHINE_HAS_NX)
+ flags &= ~(SET_MEMORY_NX | SET_MEMORY_X);
+ if (!flags)
+ return 0;
+ addr &= PAGE_MASK;
+ return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags);
+}
+
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+
+static void ipte_range(pte_t *pte, unsigned long address, int nr)
+{
+ int i;
+
+ if (test_facility(13)) {
+ __ptep_ipte_range(address, nr - 1, pte, IPTE_GLOBAL);
+ return;
+ }
+ for (i = 0; i < nr; i++) {
+ __ptep_ipte(address, pte, 0, 0, IPTE_GLOBAL);
+ address += PAGE_SIZE;
+ pte++;
+ }
+}
+
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+ unsigned long address;
+ pte_t *ptep, pte;
+ int nr, i, j;
+
+ for (i = 0; i < numpages;) {
+ address = (unsigned long)page_to_virt(page + i);
+ ptep = virt_to_kpte(address);
+ nr = (unsigned long)ptep >> ilog2(sizeof(long));
+ nr = PTRS_PER_PTE - (nr & (PTRS_PER_PTE - 1));
+ nr = min(numpages - i, nr);
+ if (enable) {
+ for (j = 0; j < nr; j++) {
+ pte = clear_pte_bit(*ptep, __pgprot(_PAGE_INVALID));
+ set_pte(ptep, pte);
+ address += PAGE_SIZE;
+ ptep++;
+ }
+ } else {
+ ipte_range(ptep, address, nr);
+ }
+ i += nr;
+ }
+}
+
+#endif /* CONFIG_DEBUG_PAGEALLOC */