Files
android_kernel_xiaomi_sm8450/arch/arm/xen/enlighten.c
Greg Kroah-Hartman bdd8d64f36 Merge 5.10.203 into android12-5.10-lts
Changes in 5.10.203
	RDMA/irdma: Prevent zero-length STAG registration
	PCI: keystone: Drop __init from ks_pcie_add_pcie_{ep,port}()
	afs: Fix afs_server_list to be cleaned up with RCU
	afs: Make error on cell lookup failure consistent with OpenAFS
	drm/panel: boe-tv101wum-nl6: Fine tune the panel power sequence
	drm/panel: auo,b101uan08.3: Fine tune the panel power sequence
	drm/panel: simple: Fix Innolux G101ICE-L01 bus flags
	drm/panel: simple: Fix Innolux G101ICE-L01 timings
	wireguard: use DEV_STATS_INC()
	ata: pata_isapnp: Add missing error check for devm_ioport_map()
	drm/rockchip: vop: Fix color for RGB888/BGR888 format on VOP full
	HID: core: store the unique system identifier in hid_device
	HID: fix HID device resource race between HID core and debugging support
	ipv4: Correct/silence an endian warning in __ip_do_redirect
	net: usb: ax88179_178a: fix failed operations during ax88179_reset
	net/smc: avoid data corruption caused by decline
	arm/xen: fix xen_vcpu_info allocation alignment
	amd-xgbe: handle corner-case during sfp hotplug
	amd-xgbe: handle the corner-case during tx completion
	amd-xgbe: propagate the correct speed and duplex status
	net: axienet: Fix check for partial TX checksum
	afs: Return ENOENT if no cell DNS record can be found
	afs: Fix file locking on R/O volumes to operate in local mode
	nvmet: remove unnecessary ctrl parameter
	nvmet: nul-terminate the NQNs passed in the connect command
	USB: dwc3: qcom: fix resource leaks on probe deferral
	USB: dwc3: qcom: fix ACPI platform device leak
	lockdep: Fix block chain corruption
	media: ccs: Correctly initialise try compose rectangle
	MIPS: KVM: Fix a build warning about variable set but not used
	ext4: add a new helper to check if es must be kept
	ext4: factor out __es_alloc_extent() and __es_free_extent()
	ext4: use pre-allocated es in __es_insert_extent()
	ext4: use pre-allocated es in __es_remove_extent()
	ext4: using nofail preallocation in ext4_es_remove_extent()
	ext4: using nofail preallocation in ext4_es_insert_delayed_block()
	ext4: using nofail preallocation in ext4_es_insert_extent()
	ext4: fix slab-use-after-free in ext4_es_insert_extent()
	ext4: make sure allocate pending entry not fail
	nfsd: lock_rename() needs both directories to live on the same fs
	ASoC: simple-card: fixup asoc_simple_probe() error handling
	ACPI: resource: Skip IRQ override on ASUS ExpertBook B1402CVA
	swiotlb-xen: provide the "max_mapping_size" method
	bcache: replace a mistaken IS_ERR() by IS_ERR_OR_NULL() in btree_gc_coalesce()
	bcache: fixup multi-threaded bch_sectors_dirty_init() wake-up race
	s390/dasd: protect device queue against concurrent access
	USB: serial: option: add Luat Air72*U series products
	hv_netvsc: Fix race of register_netdevice_notifier and VF register
	hv_netvsc: Mark VF as slave before exposing it to user-mode
	dm-delay: fix a race between delay_presuspend and delay_bio
	bcache: check return value from btree_node_alloc_replacement()
	bcache: prevent potential division by zero error
	bcache: fixup init dirty data errors
	bcache: fixup lock c->root error
	USB: serial: option: add Fibocom L7xx modules
	USB: serial: option: fix FM101R-GL defines
	USB: serial: option: don't claim interface 4 for ZTE MF290
	USB: dwc2: write HCINT with INTMASK applied
	usb: dwc3: Fix default mode initialization
	usb: dwc3: set the dma max_seg_size
	USB: dwc3: qcom: fix wakeup after probe deferral
	io_uring: fix off-by one bvec index
	pinctrl: avoid reload of p state in list iteration
	firewire: core: fix possible memory leak in create_units()
	mmc: block: Do not lose cache flush during CQE error recovery
	ALSA: hda: Disable power-save on KONTRON SinglePC
	ALSA: hda/realtek: Headset Mic VREF to 100%
	ALSA: hda/realtek: Add supported ALC257 for ChromeOS
	dm-verity: align struct dm_verity_fec_io properly
	dm verity: don't perform FEC for failed readahead IO
	bcache: revert replacing IS_ERR_OR_NULL with IS_ERR
	iommu/vt-d: Add MTL to quirk list to skip TE disabling
	powerpc: Don't clobber f0/vs0 during fp|altivec register save
	parisc: Drop the HP-UX ENOSYM and EREMOTERELEASE error codes
	btrfs: add dmesg output for first mount and last unmount of a filesystem
	btrfs: ref-verify: fix memory leaks in btrfs_ref_tree_mod()
	btrfs: fix off-by-one when checking chunk map includes logical address
	btrfs: send: ensure send_fd is writable
	btrfs: make error messages more clear when getting a chunk map
	Input: xpad - add HyperX Clutch Gladiate Support
	hv_netvsc: fix race of netvsc and VF register_netdevice
	USB: core: Change configuration warnings to notices
	usb: config: fix iteration issue in 'usb_get_bos_descriptor()'
	ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet
	dpaa2-eth: increase the needed headroom to account for alignment
	selftests/net: ipsec: fix constant out of range
	selftests/net: mptcp: fix uninitialized variable warnings
	net: stmmac: xgmac: Disable FPE MMC interrupts
	octeontx2-pf: Fix adding mbox work queue entry when num_vfs > 64
	Revert "workqueue: remove unused cancel_work()"
	r8169: prevent potential deadlock in rtl8169_close
	ravb: Fix races between ravb_tx_timeout_work() and net related ops
	net: ravb: Use pm_runtime_resume_and_get()
	net: ravb: Start TX queues after HW initialization succeeded
	smb3: fix touch -h of symlink
	ASoC: Intel: Move soc_intel_is_foo() helpers to a generic header
	ASoC: SOF: sof-pci-dev: use community key on all Up boards
	ASoC: SOF: sof-pci-dev: add parameter to override topology filename
	ASoC: SOF: sof-pci-dev: don't use the community key on APL Chromebooks
	ASoC: SOF: sof-pci-dev: Fix community key quirk detection
	s390/mm: fix phys vs virt confusion in mark_kernel_pXd() functions family
	s390/cmma: fix detection of DAT pages
	misc: pci_endpoint_test: Add deviceID for AM64 and J7200
	misc: pci_endpoint_test: Add deviceID for J721S2 PCIe EP device support
	fbdev: stifb: Make the STI next font pointer a 32-bit signed offset
	ima: annotate iint mutex to avoid lockdep false positive warnings
	driver core: Move the "removable" attribute from USB to core
	drm/amdgpu: don't use ATRM for external devices
	fs: add ctime accessors infrastructure
	smb3: fix caching of ctime on setxattr
	scsi: core: Introduce the scsi_cmd_to_rq() function
	scsi: qla2xxx: Use scsi_cmd_to_rq() instead of scsi_cmnd.request
	scsi: qla2xxx: Fix system crash due to bad pointer access
	cpufreq: imx6q: don't warn for disabling a non-existing frequency
	cpufreq: imx6q: Don't disable 792 Mhz OPP unnecessarily
	mmc: cqhci: Increase recovery halt timeout
	mmc: cqhci: Warn of halt or task clear failure
	mmc: cqhci: Fix task clearing in CQE error recovery
	mmc: core: convert comma to semicolon
	mmc: block: Retry commands in CQE error recovery
	mmc: core: add helpers mmc_regulator_enable/disable_vqmmc
	mmc: sdhci-sprd: Fix vqmmc not shutting down after the card was pulled
	r8169: disable ASPM in case of tx timeout
	r8169: fix deadlock on RTL8125 in jumbo mtu mode
	driver core: Release all resources during unbind before updating device links
	Linux 5.10.203

Change-Id: I7feccd8526f0286020be24411be0e6113129ff65
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2023-12-11 16:34:56 +00:00

452 lines
12 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
#include <xen/xen.h>
#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/hvm.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/xen.h>
#include <xen/interface/memory.h>
#include <xen/interface/hvm/params.h>
#include <xen/features.h>
#include <xen/platform_pci.h>
#include <xen/xenbus.h>
#include <xen/page.h>
#include <xen/interface/sched.h>
#include <xen/xen-ops.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <asm/system_misc.h>
#include <asm/efi.h>
#include <linux/interrupt.h>
#include <linux/irqreturn.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/cpuidle.h>
#include <linux/cpufreq.h>
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/pvclock_gtod.h>
#include <linux/reboot.h>
#include <linux/time64.h>
#include <linux/timekeeping.h>
#include <linux/timekeeper_internal.h>
#include <linux/acpi.h>
#include <linux/mm.h>
static struct start_info _xen_start_info;
struct start_info *xen_start_info = &_xen_start_info;
EXPORT_SYMBOL(xen_start_info);
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL(xen_domain_type);
struct shared_info xen_dummy_shared_info;
struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
static struct vcpu_info __percpu *xen_vcpu_info;
/* Linux <-> Xen vCPU id mapping */
DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
/* These are unused until we support booting "pre-ballooned" */
unsigned long xen_released_pages;
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
static __read_mostly unsigned int xen_events_irq;
uint32_t xen_start_flags;
EXPORT_SYMBOL(xen_start_flags);
int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
int nr, struct page **pages)
{
return xen_xlate_unmap_gfn_range(vma, nr, pages);
}
EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
static void xen_read_wallclock(struct timespec64 *ts)
{
u32 version;
struct timespec64 now, ts_monotonic;
struct shared_info *s = HYPERVISOR_shared_info;
struct pvclock_wall_clock *wall_clock = &(s->wc);
/* get wallclock at system boot */
do {
version = wall_clock->version;
rmb(); /* fetch version before time */
now.tv_sec = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
now.tv_nsec = wall_clock->nsec;
rmb(); /* fetch time before checking version */
} while ((wall_clock->version & 1) || (version != wall_clock->version));
/* time since system boot */
ktime_get_ts64(&ts_monotonic);
*ts = timespec64_add(now, ts_monotonic);
}
static int xen_pvclock_gtod_notify(struct notifier_block *nb,
unsigned long was_set, void *priv)
{
/* Protected by the calling core code serialization */
static struct timespec64 next_sync;
struct xen_platform_op op;
struct timespec64 now, system_time;
struct timekeeper *tk = priv;
now.tv_sec = tk->xtime_sec;
now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
system_time = timespec64_add(now, tk->wall_to_monotonic);
/*
* We only take the expensive HV call when the clock was set
* or when the 11 minutes RTC synchronization time elapsed.
*/
if (!was_set && timespec64_compare(&now, &next_sync) < 0)
return NOTIFY_OK;
op.cmd = XENPF_settime64;
op.u.settime64.mbz = 0;
op.u.settime64.secs = now.tv_sec;
op.u.settime64.nsecs = now.tv_nsec;
op.u.settime64.system_time = timespec64_to_ns(&system_time);
(void)HYPERVISOR_platform_op(&op);
/*
* Move the next drift compensation time 11 minutes
* ahead. That's emulating the sync_cmos_clock() update for
* the hardware RTC.
*/
next_sync = now;
next_sync.tv_sec += 11 * 60;
return NOTIFY_OK;
}
static struct notifier_block xen_pvclock_gtod_notifier = {
.notifier_call = xen_pvclock_gtod_notify,
};
static int xen_starting_cpu(unsigned int cpu)
{
struct vcpu_register_vcpu_info info;
struct vcpu_info *vcpup;
int err;
/*
* VCPUOP_register_vcpu_info cannot be called twice for the same
* vcpu, so if vcpu_info is already registered, just get out. This
* can happen with cpu-hotplug.
*/
if (per_cpu(xen_vcpu, cpu) != NULL)
goto after_register_vcpu_info;
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
info.mfn = percpu_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
&info);
BUG_ON(err);
per_cpu(xen_vcpu, cpu) = vcpup;
if (!xen_kernel_unmapped_at_usr())
xen_setup_runstate_info(cpu);
after_register_vcpu_info:
enable_percpu_irq(xen_events_irq, 0);
return 0;
}
static int xen_dying_cpu(unsigned int cpu)
{
disable_percpu_irq(xen_events_irq);
return 0;
}
void xen_reboot(int reason)
{
struct sched_shutdown r = { .reason = reason };
int rc;
rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
BUG_ON(rc);
}
static int xen_restart(struct notifier_block *nb, unsigned long action,
void *data)
{
xen_reboot(SHUTDOWN_reboot);
return NOTIFY_DONE;
}
static struct notifier_block xen_restart_nb = {
.notifier_call = xen_restart,
.priority = 192,
};
static void xen_power_off(void)
{
xen_reboot(SHUTDOWN_poweroff);
}
static irqreturn_t xen_arm_callback(int irq, void *arg)
{
xen_hvm_evtchn_do_upcall();
return IRQ_HANDLED;
}
static __initdata struct {
const char *compat;
const char *prefix;
const char *version;
bool found;
} hyper_node = {"xen,xen", "xen,xen-", NULL, false};
static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
int depth, void *data)
{
const void *s = NULL;
int len;
if (depth != 1 || strcmp(uname, "hypervisor") != 0)
return 0;
if (of_flat_dt_is_compatible(node, hyper_node.compat))
hyper_node.found = true;
s = of_get_flat_dt_prop(node, "compatible", &len);
if (strlen(hyper_node.prefix) + 3 < len &&
!strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
hyper_node.version = s + strlen(hyper_node.prefix);
/*
* Check if Xen supports EFI by checking whether there is the
* "/hypervisor/uefi" node in DT. If so, runtime services are available
* through proxy functions (e.g. in case of Xen dom0 EFI implementation
* they call special hypercall which executes relevant EFI functions)
* and that is why they are always enabled.
*/
if (IS_ENABLED(CONFIG_XEN_EFI)) {
if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
!efi_runtime_disabled())
set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
}
return 0;
}
/*
* see Documentation/devicetree/bindings/arm/xen.txt for the
* documentation of the Xen Device Tree format.
*/
void __init xen_early_init(void)
{
of_scan_flat_dt(fdt_find_hyper_node, NULL);
if (!hyper_node.found) {
pr_debug("No Xen support\n");
return;
}
if (hyper_node.version == NULL) {
pr_debug("Xen version not found\n");
return;
}
pr_info("Xen %s support found\n", hyper_node.version);
xen_domain_type = XEN_HVM_DOMAIN;
xen_setup_features();
if (xen_feature(XENFEAT_dom0))
xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
if (!console_set_on_cmdline && !xen_initial_domain())
add_preferred_console("hvc", 0, NULL);
}
static void __init xen_acpi_guest_init(void)
{
#ifdef CONFIG_ACPI
struct xen_hvm_param a;
int interrupt, trigger, polarity;
a.domid = DOMID_SELF;
a.index = HVM_PARAM_CALLBACK_IRQ;
if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
|| (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
xen_events_irq = 0;
return;
}
interrupt = a.value & 0xff;
trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
: ACPI_LEVEL_SENSITIVE;
polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
: ACPI_ACTIVE_HIGH;
xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
#endif
}
static void __init xen_dt_guest_init(void)
{
struct device_node *xen_node;
xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
if (!xen_node) {
pr_err("Xen support was detected before, but it has disappeared\n");
return;
}
xen_events_irq = irq_of_parse_and_map(xen_node, 0);
}
static int __init xen_guest_init(void)
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
int cpu;
if (!xen_domain())
return 0;
if (!acpi_disabled)
xen_acpi_guest_init();
else
xen_dt_guest_init();
if (!xen_events_irq) {
pr_err("Xen event channel interrupt not found\n");
return -ENODEV;
}
/*
* The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
* parameters are found. Force enable runtime services.
*/
if (efi_enabled(EFI_RUNTIME_SERVICES))
xen_efi_runtime_setup();
shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
if (!shared_info_page) {
pr_err("not enough memory\n");
return -ENOMEM;
}
xatp.domid = DOMID_SELF;
xatp.idx = 0;
xatp.space = XENMAPSPACE_shared_info;
xatp.gpfn = virt_to_gfn(shared_info_page);
if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
BUG();
HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
* page, we use it in the event channel upcall and in some pvclock
* related functions.
* The shared info contains exactly 1 CPU (the boot CPU). The guest
* is required to use VCPUOP_register_vcpu_info to place vcpu info
* for secondary CPUs as they are brought up.
* For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
*/
xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
1 << fls(sizeof(struct vcpu_info) - 1));
if (xen_vcpu_info == NULL)
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
for_each_possible_cpu(cpu)
per_cpu(xen_vcpu_id, cpu) = cpu;
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
&xen_auto_xlat_grant_frames.vaddr,
xen_auto_xlat_grant_frames.count)) {
free_percpu(xen_vcpu_info);
return -ENOMEM;
}
gnttab_init();
/*
* Making sure board specific code will not set up ops for
* cpu idle and cpu freq.
*/
disable_cpuidle();
disable_cpufreq();
xen_init_IRQ();
if (request_percpu_irq(xen_events_irq, xen_arm_callback,
"events", &xen_vcpu)) {
pr_err("Error request IRQ %d\n", xen_events_irq);
return -EINVAL;
}
if (!xen_kernel_unmapped_at_usr())
xen_time_setup_guest();
if (xen_initial_domain())
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
"arm/xen:starting", xen_starting_cpu,
xen_dying_cpu);
}
early_initcall(xen_guest_init);
static int __init xen_pm_init(void)
{
if (!xen_domain())
return -ENODEV;
pm_power_off = xen_power_off;
register_restart_handler(&xen_restart_nb);
if (!xen_initial_domain()) {
struct timespec64 ts;
xen_read_wallclock(&ts);
do_settimeofday64(&ts);
}
return 0;
}
late_initcall(xen_pm_init);
/* empty stubs */
void xen_arch_pre_suspend(void) { }
void xen_arch_post_suspend(int suspend_cancelled) { }
void xen_timer_resume(void) { }
void xen_arch_resume(void) { }
void xen_arch_suspend(void) { }
/* In the hypercall.S file. */
EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);
EXPORT_SYMBOL_GPL(HYPERVISOR_console_io);
EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
EXPORT_SYMBOL_GPL(privcmd_call);