9cd6ae99b7
https://source.android.com/docs/security/bulletin/2023-11-01 * tag 'ASB-2023-11-05_4.19-stable' of https://android.googlesource.com/kernel/common: Reapply "perf: Disallow mis-matched inherited group reads" Revert "perf: Disallow mis-matched inherited group reads" Revert "xfrm: fix a data-race in xfrm_gen_index()" Revert "Bluetooth: hci_core: Fix build warnings" Revert "xfrm: interface: use DEV_STATS_INC()" Linux 4.19.297 xfrm6: fix inet6_dev refcount underflow problem Bluetooth: hci_sock: Correctly bounds check and pad HCI_MON_NEW_INDEX name Bluetooth: hci_sock: fix slab oob read in create_monitor_event phy: mapphone-mdm6600: Fix runtime PM for remove ASoC: pxa: fix a memory leak in probe() gpio: vf610: set value before the direction to avoid a glitch s390/pci: fix iommu bitmap allocation perf: Disallow mis-matched inherited group reads USB: serial: option: add Fibocom to DELL custom modem FM101R-GL USB: serial: option: add entry for Sierra EM9191 with new firmware USB: serial: option: add Telit LE910C4-WWX 0x1035 composition ACPI: irq: Fix incorrect return value in acpi_register_gsi() Revert "pinctrl: avoid unsafe code pattern in find_pinctrl()" mmc: core: Capture correct oemid-bits for eMMC cards mtd: spinand: micron: correct bitmask for ecc status mtd: rawnand: qcom: Unmap the right resource upon probe failure Bluetooth: hci_event: Fix using memcmp when comparing keys btrfs: fix some -Wmaybe-uninitialized warnings in ioctl.c drm: panel-orientation-quirks: Add quirk for One Mix 2S sky2: Make sure there is at least one frag_addr available wifi: cfg80211: avoid leaking stack data into trace wifi: mac80211: allow transmitting EAPOL frames with tainted key Bluetooth: hci_core: Fix build warnings Bluetooth: Avoid redundant authentication HID: holtek: fix slab-out-of-bounds Write in holtek_kbd_input_event tracing: relax trace_event_eval_update() execution with cond_resched() ata: libata-eh: Fix compilation warning in ata_eh_link_report() gpio: timberdale: Fix potential deadlock on &tgpio->lock overlayfs: set ctime when setting mtime and atime i2c: mux: Avoid potential false error message in i2c_mux_add_adapter btrfs: initialize start_slot in btrfs_log_prealloc_extents btrfs: return -EUCLEAN for delayed tree ref with a ref count not equals to 1 ARM: dts: ti: omap: Fix noisy serial with overrun-throttle-ms for mapphone libceph: use kernel_connect() libceph: fix unaligned accesses in ceph_entity_addr handling net: pktgen: Fix interface flags printing netfilter: nft_set_rbtree: .deactivate fails if element has expired net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve i40e: prevent crash on probe if hw registers have invalid values net: usb: smsc95xx: Fix an error code in smsc95xx_reset() tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb tcp: fix excessive TLP and RACK timeouts from HZ rounding net: rfkill: gpio: prevent value glitch during probe net: ipv6: fix return value check in esp_remove_trailer net: ipv4: fix return value check in esp_remove_trailer xfrm: interface: use DEV_STATS_INC() xfrm: fix a data-race in xfrm_gen_index() netfilter: nft_payload: fix wrong mac header matching KVM: x86: Mask LVTPC when handling a PMI regmap: fix NULL deref on lookup nfc: nci: fix possible NULL pointer dereference in send_acknowledge() Bluetooth: avoid memcmp() out of bounds warning Bluetooth: hci_event: Fix coding style Bluetooth: vhci: Fix race when opening vhci device Bluetooth: Fix a refcnt underflow problem for hci_conn Bluetooth: Reject connection with the device which has same BD_ADDR Bluetooth: hci_event: Ignore NULL link key usb: hub: Guard against accesses to uninitialized BOS descriptors dev_forward_skb: do not scrub skb mark within the same name space x86/alternatives: Disable KASAN in apply_alternatives() powerpc/64e: Fix wrong test in __ptep_test_and_clear_young() usb: gadget: ncm: Handle decoding of multiple NTB's in unwrap call usb: gadget: udc-xilinx: replace memcpy with memcpy_toio x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs pinctrl: avoid unsafe code pattern in find_pinctrl() cgroup: Remove duplicates in cgroup v1 tasks file Input: xpad - add PXN V900 support Input: psmouse - fix fast_reconnect function for PS/2 mode Input: powermate - fix use-after-free in powermate_config_complete ceph: fix incorrect revoked caps assert in ceph_fill_file_size() mcb: remove is_added flag from mcb_device struct iio: pressure: ms5611: ms5611_prom_is_valid false negative bug iio: pressure: bmp280: Fix NULL pointer exception usb: musb: Modify the "HWVers" register address usb: musb: Get the musb_qh poniter after musb_giveback usb: dwc3: Soft reset phy on probe for host net: usb: dm9601: fix uninitialized variable use in dm9601_mdio_read usb: xhci: xhci-ring: Use sysdev for mapping bounce buffer dmaengine: stm32-mdma: abort resume if no ongoing transfer sched,idle,rcu: Push rcu_idle deeper into the idle path workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask() nfc: nci: assert requested protocol is valid net: nfc: fix races in nfc_llcp_sock_get() and nfc_llcp_sock_get_sn() ixgbe: fix crash with empty VF macvlan list drm/vmwgfx: fix typo of sizeof argument xen-netback: use default TX queue size for vifs ieee802154: ca8210: Fix a potential UAF in ca8210_probe drm/msm/dsi: skip the wait for video mode done if not applicable drm: etvnaviv: fix bad backport leading to warning net: prevent address rewrite in kernel_bind() quota: Fix slow quotaoff HID: logitech-hidpp: Fix kernel crash on receiver USB disconnect RDMA/cxgb4: Check skb value for failure to allocate net: prevent rewrite of msg_name in sock_sendmsg() net: fix kernel-doc warnings for socket.c net: use indirect calls helpers at the socket layer indirect call wrappers: helpers to speed-up indirect calls of builtin Revert "net: add atomic_long_t to net_device_stats fields" Revert "net: Fix unwanted sign extension in netdev_stats_to_stats64()" Revert "net: bridge: use DEV_STATS_INC()" Linux 4.19.296 xen/events: replace evtchn_rwlock with RCU rtnetlink: Reject negative ifindexes in RTM_NEWLINK Revert "rtnetlink: Reject negative ifindexes in RTM_NEWLINK" dccp: fix dccp_v4_err()/dccp_v6_err() again parisc: Restore __ldcw_align for PA-RISC 2.0 processors RDMA/mlx5: Fix NULL string error RDMA/cma: Fix truncation compilation warning in make_cma_ports gpio: pxa: disable pinctrl calls for MMP_GPIO gpio: aspeed: fix the GPIO number passed to pinctrl_gpio_set_config() IB/mlx4: Fix the size of a buffer in add_port_entries() cpupower: add Makefile dependencies for install targets sctp: update hb timer immediately after users change hb_interval sctp: update transport state when processing a dupcook packet tcp: fix delayed ACKs for MSS boundary condition tcp: fix quick-ack counting to count actual ACKs of new data net: stmmac: dwmac-stm32: fix resume on STM32 MCU net: usb: smsc75xx: Fix uninit-value access in __smsc75xx_read_reg ipv4, ipv6: Fix handling of transhdrlen in __ip{,6}_append_data() modpost: add missing else to the "of" check scsi: target: core: Fix deadlock due to recursive locking regmap: rbtree: Fix wrong register marked as in-cache when creating new node drivers/net: process the result of hdlc_open() and add call of hdlc_close() in uhdlc_close() wifi: mwifiex: Fix oob check condition in mwifiex_process_rx_packet ubi: Refuse attaching if mtd's erasesize is 0 net: replace calls to sock->ops->connect() with kernel_connect() wifi: mwifiex: Fix tlv_buf_left calculation qed/red_ll2: Fix undefined behavior bug in struct qed_ll2_info scsi: zfcp: Fix a double put in zfcp_port_enqueue() Revert "PCI: qcom: Disable write access to read only registers for IP v2.3.3" media: dvb: symbol fixup for dvb_attach() - again Revert "drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions" ata: libata: disallow dev-initiated LPM transitions to unsupported states ext4: fix rec_len verify error fs: binfmt_elf_efpic: fix personality for ELF-FDPIC ata: libata-sata: increase PMP SRST timeout to 10s ata: libata-core: Do not register PM operations for SAS ports ata: libata-core: Fix port and device removal ata: libata-core: Fix ata_port_request_pm() locking net: thunderbolt: Fix TCPv6 GSO checksum calculation btrfs: properly report 0 avail for very full file systems i2c: i801: unregister tco_pdev in i801_probe() error path ata: libata-scsi: ignore reserved bits for REPORT SUPPORTED OPERATION CODES ALSA: hda: Disable power save for solving pop issue on Lenovo ThinkCentre M70q nilfs2: fix potential use after free in nilfs_gccache_submit_read_data() serial: 8250_port: Check IRQ data before use smack: Record transmuting in smk_transmuted smack: Retrieve transmuting information in smack_inode_getsecurity() Smack:- Use overlay inode label in smack_inode_copy_up() scsi: megaraid_sas: Enable msix_load_balance for Invader and later controllers net: Fix unwanted sign extension in netdev_stats_to_stats64() watchdog: iTCO_wdt: Set NO_REBOOT if the watchdog is not already running watchdog: iTCO_wdt: No need to stop the timer in probe nvme-pci: do not set the NUMA node of device if it has none fbdev/sh7760fb: Depend on FB=y bpf: Clarify error expectations from bpf_clone_redirect ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() ring-buffer: Avoid softlockup in ring_buffer_resize() selftests/ftrace: Correctly enable event in instance-event.tc parisc: irq: Make irq_stack_union static to avoid sparse warning parisc: drivers: Fix sparse warning parisc: iosapic.c: Fix sparse warnings parisc: sba: Fix compile warning wrt list of SBA devices gpio: pmic-eic-sprd: Add can_sleep flag for PMIC EIC chip ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot clk: tegra: fix error return case for recalc_rate MIPS: Alchemy: only build mmc support helpers if au1xmmc is enabled ext4: do not let fstrim block system suspend ext4: move setting of trimmed bit into ext4_try_to_trim_range() ext4: replace the traditional ternary conditional operator with with max()/min() ext4: mark group as trimmed only if it was fully scanned ext4: change s_last_trim_minblks type to unsigned long ext4: scope ret locally in ext4_try_to_trim_range() ext4: add new helper interface ext4_try_to_trim_range() ext4: remove the 'group' parameter of ext4_trim_extent scsi: megaraid_sas: Fix deadlock on firmware crashdump scsi: megaraid_sas: Load balance completions across all MSI-X scsi: qla2xxx: Remove unsupported ql2xenabledif option scsi: qla2xxx: Add protection mask module parameters Input: i8042 - add quirk for TUXEDO Gemini 17 Gen1/Clevo PD70PN i2c: mux: demux-pinctrl: check the return value of devm_kstrdup() gpio: tb10x: Fix an error handling path in tb10x_gpio_probe() team: fix null-ptr-deref when team device type is changed net: bridge: use DEV_STATS_INC() net: add atomic_long_t to net_device_stats fields net: hns3: add 5ms delay before clear firmware reset irq source powerpc/perf/hv-24x7: Update domain value check ipv4: fix null-deref in ipv4_link_failure selftests: tls: swap the TX and RX sockets in some tests selftests/tls: Add {} to avoid static checker warning netfilter: nf_tables: disallow element removal on anonymous sets ata: libahci: clear pending interrupt status ata: ahci: Drop pointless VPRINTK() calls and convert the remaining ones NFS/pNFS: Report EINVAL errors from connect() to the server ANDROID: ALSA: jack: Revert mismerge done in v4.19.291 Conflicts: include/net/tcp.h kernel/events/core.c kernel/sched/idle.c Change-Id: I141cc494dcfda5fbd11f8bd2f7166bf3bf157084
737 lines
18 KiB
C
737 lines
18 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* CPU subsystem support
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/device.h>
|
|
#include <linux/node.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/acpi.h>
|
|
#include <linux/of.h>
|
|
#include <linux/cpufeature.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/pm_qos.h>
|
|
#include <linux/sched/isolation.h>
|
|
|
|
#include "base.h"
|
|
|
|
static DEFINE_PER_CPU(struct device *, cpu_sys_devices);
|
|
|
|
static int cpu_subsys_match(struct device *dev, struct device_driver *drv)
|
|
{
|
|
/* ACPI style match is the only one that may succeed. */
|
|
if (acpi_driver_match_device(dev, drv))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static void change_cpu_under_node(struct cpu *cpu,
|
|
unsigned int from_nid, unsigned int to_nid)
|
|
{
|
|
int cpuid = cpu->dev.id;
|
|
unregister_cpu_under_node(cpuid, from_nid);
|
|
register_cpu_under_node(cpuid, to_nid);
|
|
cpu->node_id = to_nid;
|
|
}
|
|
|
|
static int cpu_subsys_online(struct device *dev)
|
|
{
|
|
struct cpu *cpu = container_of(dev, struct cpu, dev);
|
|
int cpuid = dev->id;
|
|
int from_nid, to_nid;
|
|
int ret;
|
|
|
|
from_nid = cpu_to_node(cpuid);
|
|
if (from_nid == NUMA_NO_NODE)
|
|
return -ENODEV;
|
|
|
|
ret = cpu_up(cpuid);
|
|
/*
|
|
* When hot adding memory to memoryless node and enabling a cpu
|
|
* on the node, node number of the cpu may internally change.
|
|
*/
|
|
to_nid = cpu_to_node(cpuid);
|
|
if (from_nid != to_nid)
|
|
change_cpu_under_node(cpu, from_nid, to_nid);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int cpu_subsys_offline(struct device *dev)
|
|
{
|
|
return cpu_down(dev->id);
|
|
}
|
|
|
|
void unregister_cpu(struct cpu *cpu)
|
|
{
|
|
int logical_cpu = cpu->dev.id;
|
|
|
|
unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu));
|
|
|
|
device_unregister(&cpu->dev);
|
|
per_cpu(cpu_sys_devices, logical_cpu) = NULL;
|
|
return;
|
|
}
|
|
|
|
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
|
|
static ssize_t cpu_probe_store(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf,
|
|
size_t count)
|
|
{
|
|
ssize_t cnt;
|
|
int ret;
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
cnt = arch_cpu_probe(buf, count);
|
|
|
|
unlock_device_hotplug();
|
|
return cnt;
|
|
}
|
|
|
|
static ssize_t cpu_release_store(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf,
|
|
size_t count)
|
|
{
|
|
ssize_t cnt;
|
|
int ret;
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
cnt = arch_cpu_release(buf, count);
|
|
|
|
unlock_device_hotplug();
|
|
return cnt;
|
|
}
|
|
|
|
static DEVICE_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
|
|
static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
|
|
#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
struct bus_type cpu_subsys = {
|
|
.name = "cpu",
|
|
.dev_name = "cpu",
|
|
.match = cpu_subsys_match,
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
.online = cpu_subsys_online,
|
|
.offline = cpu_subsys_offline,
|
|
#endif
|
|
};
|
|
EXPORT_SYMBOL_GPL(cpu_subsys);
|
|
|
|
#ifdef CONFIG_KEXEC
|
|
#include <linux/kexec.h>
|
|
|
|
static ssize_t show_crash_notes(struct device *dev, struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
struct cpu *cpu = container_of(dev, struct cpu, dev);
|
|
ssize_t rc;
|
|
unsigned long long addr;
|
|
int cpunum;
|
|
|
|
cpunum = cpu->dev.id;
|
|
|
|
/*
|
|
* Might be reading other cpu's data based on which cpu read thread
|
|
* has been scheduled. But cpu data (memory) is allocated once during
|
|
* boot up and this data does not change there after. Hence this
|
|
* operation should be safe. No locking required.
|
|
*/
|
|
addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
|
|
rc = sprintf(buf, "%Lx\n", addr);
|
|
return rc;
|
|
}
|
|
static DEVICE_ATTR(crash_notes, 0400, show_crash_notes, NULL);
|
|
|
|
static ssize_t show_crash_notes_size(struct device *dev,
|
|
struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
ssize_t rc;
|
|
|
|
rc = sprintf(buf, "%zu\n", sizeof(note_buf_t));
|
|
return rc;
|
|
}
|
|
static DEVICE_ATTR(crash_notes_size, 0400, show_crash_notes_size, NULL);
|
|
|
|
static struct attribute *crash_note_cpu_attrs[] = {
|
|
&dev_attr_crash_notes.attr,
|
|
&dev_attr_crash_notes_size.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group crash_note_cpu_attr_group = {
|
|
.attrs = crash_note_cpu_attrs,
|
|
};
|
|
#endif
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
static ssize_t isolate_show(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpu *cpu = container_of(dev, struct cpu, dev);
|
|
ssize_t rc;
|
|
int cpuid = cpu->dev.id;
|
|
unsigned int isolated = cpu_isolated(cpuid);
|
|
|
|
rc = snprintf(buf, PAGE_SIZE-2, "%d\n", isolated);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static DEVICE_ATTR_RO(isolate);
|
|
|
|
static struct attribute *cpu_isolated_attrs[] = {
|
|
&dev_attr_isolate.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group cpu_isolated_attr_group = {
|
|
.attrs = cpu_isolated_attrs,
|
|
};
|
|
|
|
#endif
|
|
|
|
static ssize_t show_sched_load_boost(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
ssize_t rc;
|
|
unsigned int boost;
|
|
struct cpu *cpu = container_of(dev, struct cpu, dev);
|
|
int cpuid = cpu->dev.id;
|
|
|
|
boost = per_cpu(sched_load_boost, cpuid);
|
|
rc = snprintf(buf, PAGE_SIZE-2, "%d\n", boost);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static ssize_t __ref store_sched_load_boost(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
int err;
|
|
int boost;
|
|
struct cpu *cpu = container_of(dev, struct cpu, dev);
|
|
int cpuid = cpu->dev.id;
|
|
|
|
err = kstrtoint(strstrip((char *)buf), 0, &boost);
|
|
if (err)
|
|
return err;
|
|
|
|
/*
|
|
* -100 is low enough to cancel out CPU's load and make it near zro.
|
|
* 1000 is close to the maximum value that cpu_util_freq_{walt,pelt}
|
|
* can take without overflow.
|
|
*/
|
|
if (boost < -100 || boost > 1000)
|
|
return -EINVAL;
|
|
|
|
per_cpu(sched_load_boost, cpuid) = boost;
|
|
|
|
return count;
|
|
}
|
|
|
|
static DEVICE_ATTR(sched_load_boost, 0644,
|
|
show_sched_load_boost,
|
|
store_sched_load_boost);
|
|
|
|
static struct attribute *sched_cpu_attrs[] = {
|
|
&dev_attr_sched_load_boost.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group sched_cpu_attr_group = {
|
|
.attrs = sched_cpu_attrs,
|
|
};
|
|
|
|
static const struct attribute_group *common_cpu_attr_groups[] = {
|
|
#ifdef CONFIG_KEXEC
|
|
&crash_note_cpu_attr_group,
|
|
#endif
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
&cpu_isolated_attr_group,
|
|
#endif
|
|
&sched_cpu_attr_group,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group *hotplugable_cpu_attr_groups[] = {
|
|
#ifdef CONFIG_KEXEC
|
|
&crash_note_cpu_attr_group,
|
|
#endif
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
&cpu_isolated_attr_group,
|
|
#endif
|
|
&sched_cpu_attr_group,
|
|
NULL
|
|
};
|
|
|
|
/*
|
|
* Print cpu online, possible, present, and system maps
|
|
*/
|
|
|
|
struct cpu_attr {
|
|
struct device_attribute attr;
|
|
const struct cpumask *const map;
|
|
};
|
|
|
|
static ssize_t show_cpus_attr(struct device *dev,
|
|
struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
struct cpu_attr *ca = container_of(attr, struct cpu_attr, attr);
|
|
|
|
return cpumap_print_to_pagebuf(true, buf, ca->map);
|
|
}
|
|
|
|
#define _CPU_ATTR(name, map) \
|
|
{ __ATTR(name, 0444, show_cpus_attr, NULL), map }
|
|
|
|
/* Keep in sync with cpu_subsys_attrs */
|
|
static struct cpu_attr cpu_attrs[] = {
|
|
_CPU_ATTR(online, &__cpu_online_mask),
|
|
_CPU_ATTR(possible, &__cpu_possible_mask),
|
|
_CPU_ATTR(present, &__cpu_present_mask),
|
|
_CPU_ATTR(core_ctl_isolated, &__cpu_isolated_mask),
|
|
};
|
|
|
|
/*
|
|
* Print values for NR_CPUS and offlined cpus
|
|
*/
|
|
static ssize_t print_cpus_kernel_max(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1);
|
|
return n;
|
|
}
|
|
static DEVICE_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL);
|
|
|
|
/* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */
|
|
unsigned int total_cpus;
|
|
|
|
static ssize_t print_cpus_offline(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
int n = 0, len = PAGE_SIZE-2;
|
|
cpumask_var_t offline;
|
|
|
|
/* display offline cpus < nr_cpu_ids */
|
|
if (!alloc_cpumask_var(&offline, GFP_KERNEL))
|
|
return -ENOMEM;
|
|
cpumask_andnot(offline, cpu_possible_mask, cpu_online_mask);
|
|
n = scnprintf(buf, len, "%*pbl", cpumask_pr_args(offline));
|
|
free_cpumask_var(offline);
|
|
|
|
/* display offline cpus >= nr_cpu_ids */
|
|
if (total_cpus && nr_cpu_ids < total_cpus) {
|
|
if (n && n < len)
|
|
buf[n++] = ',';
|
|
|
|
if (nr_cpu_ids == total_cpus-1)
|
|
n += snprintf(&buf[n], len - n, "%u", nr_cpu_ids);
|
|
else
|
|
n += snprintf(&buf[n], len - n, "%u-%d",
|
|
nr_cpu_ids, total_cpus-1);
|
|
}
|
|
|
|
n += snprintf(&buf[n], len - n, "\n");
|
|
return n;
|
|
}
|
|
static DEVICE_ATTR(offline, 0444, print_cpus_offline, NULL);
|
|
|
|
static ssize_t print_cpus_isolated(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
int n = 0, len = PAGE_SIZE-2;
|
|
cpumask_var_t isolated;
|
|
|
|
if (!alloc_cpumask_var(&isolated, GFP_KERNEL))
|
|
return -ENOMEM;
|
|
|
|
cpumask_andnot(isolated, cpu_possible_mask,
|
|
housekeeping_cpumask(HK_FLAG_DOMAIN));
|
|
n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(isolated));
|
|
|
|
free_cpumask_var(isolated);
|
|
|
|
return n;
|
|
}
|
|
static DEVICE_ATTR(isolated, 0444, print_cpus_isolated, NULL);
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
static ssize_t print_cpus_nohz_full(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
int n = 0, len = PAGE_SIZE-2;
|
|
|
|
n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(tick_nohz_full_mask));
|
|
|
|
return n;
|
|
}
|
|
static DEVICE_ATTR(nohz_full, 0444, print_cpus_nohz_full, NULL);
|
|
#endif
|
|
|
|
static void cpu_device_release(struct device *dev)
|
|
{
|
|
/*
|
|
* This is an empty function to prevent the driver core from spitting a
|
|
* warning at us. Yes, I know this is directly opposite of what the
|
|
* documentation for the driver core and kobjects say, and the author
|
|
* of this code has already been publically ridiculed for doing
|
|
* something as foolish as this. However, at this point in time, it is
|
|
* the only way to handle the issue of statically allocated cpu
|
|
* devices. The different architectures will have their cpu device
|
|
* code reworked to properly handle this in the near future, so this
|
|
* function will then be changed to correctly free up the memory held
|
|
* by the cpu device.
|
|
*
|
|
* Never copy this way of doing things, or you too will be made fun of
|
|
* on the linux-kernel list, you have been warned.
|
|
*/
|
|
}
|
|
|
|
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
|
|
static ssize_t print_cpu_modalias(struct device *dev,
|
|
struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
ssize_t n;
|
|
u32 i;
|
|
|
|
n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
|
|
CPU_FEATURE_TYPEVAL);
|
|
|
|
for (i = 0; i < MAX_CPU_FEATURES; i++)
|
|
if (cpu_have_feature(i)) {
|
|
if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
|
|
WARN(1, "CPU features overflow page\n");
|
|
break;
|
|
}
|
|
n += sprintf(&buf[n], ",%04X", i);
|
|
}
|
|
buf[n++] = '\n';
|
|
return n;
|
|
}
|
|
|
|
static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
|
|
{
|
|
char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
|
|
if (buf) {
|
|
print_cpu_modalias(NULL, NULL, buf);
|
|
add_uevent_var(env, "MODALIAS=%s", buf);
|
|
kfree(buf);
|
|
}
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* register_cpu - Setup a sysfs device for a CPU.
|
|
* @cpu - cpu->hotpluggable field set to 1 will generate a control file in
|
|
* sysfs for this CPU.
|
|
* @num - CPU number to use when creating the device.
|
|
*
|
|
* Initialize and register the CPU device.
|
|
*/
|
|
int register_cpu(struct cpu *cpu, int num)
|
|
{
|
|
int error;
|
|
|
|
cpu->node_id = cpu_to_node(num);
|
|
memset(&cpu->dev, 0x00, sizeof(struct device));
|
|
cpu->dev.id = num;
|
|
cpu->dev.bus = &cpu_subsys;
|
|
cpu->dev.release = cpu_device_release;
|
|
cpu->dev.offline_disabled = !cpu->hotpluggable;
|
|
cpu->dev.offline = !cpu_online(num);
|
|
cpu->dev.of_node = of_get_cpu_node(num, NULL);
|
|
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
|
|
cpu->dev.bus->uevent = cpu_uevent;
|
|
#endif
|
|
cpu->dev.groups = common_cpu_attr_groups;
|
|
if (cpu->hotpluggable)
|
|
cpu->dev.groups = hotplugable_cpu_attr_groups;
|
|
error = device_register(&cpu->dev);
|
|
if (error) {
|
|
put_device(&cpu->dev);
|
|
return error;
|
|
}
|
|
|
|
per_cpu(cpu_sys_devices, num) = &cpu->dev;
|
|
register_cpu_under_node(num, cpu_to_node(num));
|
|
dev_pm_qos_expose_latency_limit(&cpu->dev,
|
|
PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct device *get_cpu_device(unsigned cpu)
|
|
{
|
|
if (cpu < nr_cpu_ids && cpu_possible(cpu))
|
|
return per_cpu(cpu_sys_devices, cpu);
|
|
else
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_cpu_device);
|
|
|
|
static void device_create_release(struct device *dev)
|
|
{
|
|
kfree(dev);
|
|
}
|
|
|
|
static struct device *
|
|
__cpu_device_create(struct device *parent, void *drvdata,
|
|
const struct attribute_group **groups,
|
|
const char *fmt, va_list args)
|
|
{
|
|
struct device *dev = NULL;
|
|
int retval = -ENODEV;
|
|
|
|
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
|
|
if (!dev) {
|
|
retval = -ENOMEM;
|
|
goto error;
|
|
}
|
|
|
|
device_initialize(dev);
|
|
dev->parent = parent;
|
|
dev->groups = groups;
|
|
dev->release = device_create_release;
|
|
device_set_pm_not_required(dev);
|
|
dev_set_drvdata(dev, drvdata);
|
|
|
|
retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
|
|
if (retval)
|
|
goto error;
|
|
|
|
retval = device_add(dev);
|
|
if (retval)
|
|
goto error;
|
|
|
|
return dev;
|
|
|
|
error:
|
|
put_device(dev);
|
|
return ERR_PTR(retval);
|
|
}
|
|
|
|
struct device *cpu_device_create(struct device *parent, void *drvdata,
|
|
const struct attribute_group **groups,
|
|
const char *fmt, ...)
|
|
{
|
|
va_list vargs;
|
|
struct device *dev;
|
|
|
|
va_start(vargs, fmt);
|
|
dev = __cpu_device_create(parent, drvdata, groups, fmt, vargs);
|
|
va_end(vargs);
|
|
return dev;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_device_create);
|
|
|
|
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
|
|
static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
|
|
#endif
|
|
|
|
static struct attribute *cpu_root_attrs[] = {
|
|
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
|
|
&dev_attr_probe.attr,
|
|
&dev_attr_release.attr,
|
|
#endif
|
|
&cpu_attrs[0].attr.attr,
|
|
&cpu_attrs[1].attr.attr,
|
|
&cpu_attrs[2].attr.attr,
|
|
&cpu_attrs[3].attr.attr,
|
|
&dev_attr_kernel_max.attr,
|
|
&dev_attr_offline.attr,
|
|
&dev_attr_isolated.attr,
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
&dev_attr_nohz_full.attr,
|
|
#endif
|
|
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
|
|
&dev_attr_modalias.attr,
|
|
#endif
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group cpu_root_attr_group = {
|
|
.attrs = cpu_root_attrs,
|
|
};
|
|
|
|
static const struct attribute_group *cpu_root_attr_groups[] = {
|
|
&cpu_root_attr_group,
|
|
NULL,
|
|
};
|
|
|
|
bool cpu_is_hotpluggable(unsigned cpu)
|
|
{
|
|
struct device *dev = get_cpu_device(cpu);
|
|
return dev && container_of(dev, struct cpu, dev)->hotpluggable
|
|
&& tick_nohz_cpu_hotpluggable(cpu);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
|
|
|
|
#ifdef CONFIG_GENERIC_CPU_DEVICES
|
|
static DEFINE_PER_CPU(struct cpu, cpu_devices);
|
|
#endif
|
|
|
|
static void __init cpu_dev_register_generic(void)
|
|
{
|
|
#ifdef CONFIG_GENERIC_CPU_DEVICES
|
|
int i;
|
|
|
|
for_each_possible_cpu(i) {
|
|
if (register_cpu(&per_cpu(cpu_devices, i), i))
|
|
panic("Failed to register CPU device");
|
|
}
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
|
|
|
|
ssize_t __weak cpu_show_meltdown(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_spectre_v1(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_spectre_v2(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_l1tf(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_mds(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_tsx_async_abort(struct device *dev,
|
|
struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_srbds(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sprintf(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_mmio_stale_data(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sysfs_emit(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_retbleed(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sysfs_emit(buf, "Not affected\n");
|
|
}
|
|
|
|
ssize_t __weak cpu_show_gds(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
return sysfs_emit(buf, "Not affected\n");
|
|
}
|
|
|
|
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
|
|
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
|
|
static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
|
|
static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
|
|
static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
|
|
static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
|
|
static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
|
|
static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
|
|
static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
|
|
static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
|
|
static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
|
|
static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
|
|
|
|
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
|
|
&dev_attr_meltdown.attr,
|
|
&dev_attr_spectre_v1.attr,
|
|
&dev_attr_spectre_v2.attr,
|
|
&dev_attr_spec_store_bypass.attr,
|
|
&dev_attr_l1tf.attr,
|
|
&dev_attr_mds.attr,
|
|
&dev_attr_tsx_async_abort.attr,
|
|
&dev_attr_itlb_multihit.attr,
|
|
&dev_attr_srbds.attr,
|
|
&dev_attr_mmio_stale_data.attr,
|
|
&dev_attr_retbleed.attr,
|
|
&dev_attr_gather_data_sampling.attr,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group cpu_root_vulnerabilities_group = {
|
|
.name = "vulnerabilities",
|
|
.attrs = cpu_root_vulnerabilities_attrs,
|
|
};
|
|
|
|
static void __init cpu_register_vulnerabilities(void)
|
|
{
|
|
if (sysfs_create_group(&cpu_subsys.dev_root->kobj,
|
|
&cpu_root_vulnerabilities_group))
|
|
pr_err("Unable to register CPU vulnerabilities\n");
|
|
}
|
|
|
|
#else
|
|
static inline void cpu_register_vulnerabilities(void) { }
|
|
#endif
|
|
|
|
void __init cpu_dev_init(void)
|
|
{
|
|
if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups))
|
|
panic("Failed to register CPU subsystem");
|
|
|
|
cpu_dev_register_generic();
|
|
cpu_register_vulnerabilities();
|
|
}
|