[Feature]add MT2731_MP2_MR2_SVN388 baseline version
Change-Id: Ief04314834b31e27effab435d3ca8ba33b499059
diff --git a/src/kernel/linux/v4.14/arch/x86/hyperv/Makefile b/src/kernel/linux/v4.14/arch/x86/hyperv/Makefile
new file mode 100644
index 0000000..367a820
--- /dev/null
+++ b/src/kernel/linux/v4.14/arch/x86/hyperv/Makefile
@@ -0,0 +1 @@
+obj-y := hv_init.o mmu.o
diff --git a/src/kernel/linux/v4.14/arch/x86/hyperv/hv_init.c b/src/kernel/linux/v4.14/arch/x86/hyperv/hv_init.c
new file mode 100644
index 0000000..924fa9c
--- /dev/null
+++ b/src/kernel/linux/v4.14/arch/x86/hyperv/hv_init.c
@@ -0,0 +1,278 @@
+/*
+ * X86 specific Hyper-V initialization code.
+ *
+ * Copyright (C) 2016, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT. See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/types.h>
+#include <asm/hypervisor.h>
+#include <asm/hyperv.h>
+#include <asm/mshyperv.h>
+#include <linux/version.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+
+static struct ms_hyperv_tsc_page *tsc_pg;
+
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+ return tsc_pg;
+}
+
+static u64 read_hv_clock_tsc(struct clocksource *arg)
+{
+ u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+ if (current_tick == U64_MAX)
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+
+ return current_tick;
+}
+
+static struct clocksource hyperv_cs_tsc = {
+ .name = "hyperv_clocksource_tsc_page",
+ .rating = 400,
+ .read = read_hv_clock_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+#endif
+
+static u64 read_hv_clock_msr(struct clocksource *arg)
+{
+ u64 current_tick;
+ /*
+ * Read the partition counter to get the current tick count. This count
+ * is set to 0 when the partition is created and is incremented in
+ * 100 nanosecond units.
+ */
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+ return current_tick;
+}
+
+static struct clocksource hyperv_cs_msr = {
+ .name = "hyperv_clocksource_msr",
+ .rating = 400,
+ .read = read_hv_clock_msr,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+void *hv_hypercall_pg;
+EXPORT_SYMBOL_GPL(hv_hypercall_pg);
+struct clocksource *hyperv_cs;
+EXPORT_SYMBOL_GPL(hyperv_cs);
+
+u32 *hv_vp_index;
+EXPORT_SYMBOL_GPL(hv_vp_index);
+
+u32 hv_max_vp_index;
+
+static int hv_cpu_init(unsigned int cpu)
+{
+ u64 msr_vp_index;
+
+ hv_get_vp_index(msr_vp_index);
+
+ hv_vp_index[smp_processor_id()] = msr_vp_index;
+
+ if (msr_vp_index > hv_max_vp_index)
+ hv_max_vp_index = msr_vp_index;
+
+ return 0;
+}
+
+static int __init hv_pci_init(void)
+{
+ int gen2vm = efi_enabled(EFI_BOOT);
+
+ /*
+ * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
+ * The purpose is to suppress the harmless warning:
+ * "PCI: Fatal: No config space access function found"
+ */
+ if (gen2vm)
+ return 0;
+
+ /* For Generation-1 VM, we'll proceed in pci_arch_init(). */
+ return 1;
+}
+
+/*
+ * This function is to be invoked early in the boot sequence after the
+ * hypervisor has been detected.
+ *
+ * 1. Setup the hypercall page.
+ * 2. Register Hyper-V specific clocksource.
+ */
+void __init hyperv_init(void)
+{
+ u64 guest_id, required_msrs;
+ union hv_x64_msr_hypercall_contents hypercall_msr;
+
+ if (x86_hyper_type != X86_HYPER_MS_HYPERV)
+ return;
+
+ /* Absolutely required MSRs */
+ required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE |
+ HV_X64_MSR_VP_INDEX_AVAILABLE;
+
+ if ((ms_hyperv.features & required_msrs) != required_msrs)
+ return;
+
+ /* Allocate percpu VP index */
+ hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
+ GFP_KERNEL);
+ if (!hv_vp_index)
+ return;
+
+ if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
+ hv_cpu_init, NULL) < 0)
+ goto free_vp_index;
+
+ /*
+ * Setup the hypercall page and enable hypercalls.
+ * 1. Register the guest ID
+ * 2. Enable the hypercall and register the hypercall page
+ */
+ guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
+ wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+
+ hv_hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
+ if (hv_hypercall_pg == NULL) {
+ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+ goto free_vp_index;
+ }
+
+ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ hypercall_msr.enable = 1;
+ hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
+ wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+ hyper_alloc_mmu();
+
+ x86_init.pci.arch_init = hv_pci_init;
+
+ /*
+ * Register Hyper-V specific clocksource.
+ */
+#ifdef CONFIG_HYPERV_TSCPAGE
+ if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
+ union hv_x64_msr_hypercall_contents tsc_msr;
+
+ tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+ if (!tsc_pg)
+ goto register_msr_cs;
+
+ hyperv_cs = &hyperv_cs_tsc;
+
+ rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+
+ tsc_msr.enable = 1;
+ tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
+
+ wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+
+ hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
+
+ clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
+ return;
+ }
+register_msr_cs:
+#endif
+ /*
+ * For 32 bit guests just use the MSR based mechanism for reading
+ * the partition counter.
+ */
+
+ hyperv_cs = &hyperv_cs_msr;
+ if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
+ clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
+
+ return;
+
+free_vp_index:
+ kfree(hv_vp_index);
+ hv_vp_index = NULL;
+}
+
+/*
+ * This routine is called before kexec/kdump, it does the required cleanup.
+ */
+void hyperv_cleanup(void)
+{
+ union hv_x64_msr_hypercall_contents hypercall_msr;
+
+ /* Reset our OS id */
+ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+
+ /* Reset the hypercall page */
+ hypercall_msr.as_uint64 = 0;
+ wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+ /* Reset the TSC page */
+ hypercall_msr.as_uint64 = 0;
+ wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
+}
+EXPORT_SYMBOL_GPL(hyperv_cleanup);
+
+void hyperv_report_panic(struct pt_regs *regs)
+{
+ static bool panic_reported;
+
+ /*
+ * We prefer to report panic on 'die' chain as we have proper
+ * registers to report, but if we miss it (e.g. on BUG()) we need
+ * to report it on 'panic'.
+ */
+ if (panic_reported)
+ return;
+ panic_reported = true;
+
+ wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip);
+ wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax);
+ wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx);
+ wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx);
+ wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx);
+
+ /*
+ * Let Hyper-V know there is crash data available
+ */
+ wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(hyperv_report_panic);
+
+bool hv_is_hypercall_page_setup(void)
+{
+ union hv_x64_msr_hypercall_contents hypercall_msr;
+
+ /* Check if the hypercall page is setup */
+ hypercall_msr.as_uint64 = 0;
+ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+ if (!hypercall_msr.enable)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(hv_is_hypercall_page_setup);
diff --git a/src/kernel/linux/v4.14/arch/x86/hyperv/mmu.c b/src/kernel/linux/v4.14/arch/x86/hyperv/mmu.c
new file mode 100644
index 0000000..47718ff
--- /dev/null
+++ b/src/kernel/linux/v4.14/arch/x86/hyperv/mmu.c
@@ -0,0 +1,311 @@
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
+#include <linux/hyperv.h>
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/fpu/api.h>
+#include <asm/mshyperv.h>
+#include <asm/msr.h>
+#include <asm/tlbflush.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/hyperv.h>
+
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_flush_pcpu {
+ u64 address_space;
+ u64 flags;
+ u64 processor_mask;
+ u64 gva_list[];
+};
+
+/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
+struct hv_flush_pcpu_ex {
+ u64 address_space;
+ u64 flags;
+ struct {
+ u64 format;
+ u64 valid_bank_mask;
+ u64 bank_contents[];
+ } hv_vp_set;
+ u64 gva_list[];
+};
+
+/* Each gva in gva_list encodes up to 4096 pages to flush */
+#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
+
+static struct hv_flush_pcpu __percpu **pcpu_flush;
+
+static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;
+
+/*
+ * Fills in gva_list starting from offset. Returns the number of items added.
+ */
+static inline int fill_gva_list(u64 gva_list[], int offset,
+ unsigned long start, unsigned long end)
+{
+ int gva_n = offset;
+ unsigned long cur = start, diff;
+
+ do {
+ diff = end > cur ? end - cur : 0;
+
+ gva_list[gva_n] = cur & PAGE_MASK;
+ /*
+ * Lower 12 bits encode the number of additional
+ * pages to flush (in addition to the 'cur' page).
+ */
+ if (diff >= HV_TLB_FLUSH_UNIT) {
+ gva_list[gva_n] |= ~PAGE_MASK;
+ cur += HV_TLB_FLUSH_UNIT;
+ } else if (diff) {
+ gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
+ cur = end;
+ }
+
+ gva_n++;
+
+ } while (cur < end);
+
+ return gva_n - offset;
+}
+
+/* Return the number of banks in the resulting vp_set */
+static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
+ const struct cpumask *cpus)
+{
+ int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+
+ /* valid_bank_mask can represent up to 64 banks */
+ if (hv_max_vp_index / 64 >= 64)
+ return 0;
+
+ /*
+ * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+ * structs are not cleared between calls, we risk flushing unneeded
+ * vCPUs otherwise.
+ */
+ for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+ flush->hv_vp_set.bank_contents[vcpu_bank] = 0;
+
+ /*
+ * Some banks may end up being empty but this is acceptable.
+ */
+ for_each_cpu(cpu, cpus) {
+ vcpu = hv_cpu_number_to_vp_number(cpu);
+ vcpu_bank = vcpu / 64;
+ vcpu_offset = vcpu % 64;
+ __set_bit(vcpu_offset, (unsigned long *)
+ &flush->hv_vp_set.bank_contents[vcpu_bank]);
+ if (vcpu_bank >= nr_bank)
+ nr_bank = vcpu_bank + 1;
+ }
+ flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+
+ return nr_bank;
+}
+
+static void hyperv_flush_tlb_others(const struct cpumask *cpus,
+ const struct flush_tlb_info *info)
+{
+ int cpu, vcpu, gva_n, max_gvas;
+ struct hv_flush_pcpu **flush_pcpu;
+ struct hv_flush_pcpu *flush;
+ u64 status = U64_MAX;
+ unsigned long flags;
+
+ trace_hyperv_mmu_flush_tlb_others(cpus, info);
+
+ if (!pcpu_flush || !hv_hypercall_pg)
+ goto do_native;
+
+ if (cpumask_empty(cpus))
+ return;
+
+ local_irq_save(flags);
+
+ flush_pcpu = this_cpu_ptr(pcpu_flush);
+
+ if (unlikely(!*flush_pcpu))
+ *flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+ flush = *flush_pcpu;
+
+ if (unlikely(!flush)) {
+ local_irq_restore(flags);
+ goto do_native;
+ }
+
+ if (info->mm) {
+ /*
+ * AddressSpace argument must match the CR3 with PCID bits
+ * stripped out.
+ */
+ flush->address_space = virt_to_phys(info->mm->pgd);
+ flush->address_space &= CR3_ADDR_MASK;
+ flush->flags = 0;
+ } else {
+ flush->address_space = 0;
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ }
+
+ flush->processor_mask = 0;
+ if (cpumask_equal(cpus, cpu_present_mask)) {
+ flush->flags |= HV_FLUSH_ALL_PROCESSORS;
+ } else {
+ for_each_cpu(cpu, cpus) {
+ vcpu = hv_cpu_number_to_vp_number(cpu);
+ if (vcpu >= 64)
+ goto do_native;
+
+ __set_bit(vcpu, (unsigned long *)
+ &flush->processor_mask);
+ }
+ }
+
+ /*
+ * We can flush not more than max_gvas with one hypercall. Flush the
+ * whole address space if we were asked to do more.
+ */
+ max_gvas = (PAGE_SIZE - sizeof(*flush)) / sizeof(flush->gva_list[0]);
+
+ if (info->end == TLB_FLUSH_ALL) {
+ flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
+ status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
+ flush, NULL);
+ } else if (info->end &&
+ ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
+ status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
+ flush, NULL);
+ } else {
+ gva_n = fill_gva_list(flush->gva_list, 0,
+ info->start, info->end);
+ status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
+ gva_n, 0, flush, NULL);
+ }
+
+ local_irq_restore(flags);
+
+ if (!(status & HV_HYPERCALL_RESULT_MASK))
+ return;
+do_native:
+ native_flush_tlb_others(cpus, info);
+}
+
+static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+ const struct flush_tlb_info *info)
+{
+ int nr_bank = 0, max_gvas, gva_n;
+ struct hv_flush_pcpu_ex **flush_pcpu;
+ struct hv_flush_pcpu_ex *flush;
+ u64 status = U64_MAX;
+ unsigned long flags;
+
+ trace_hyperv_mmu_flush_tlb_others(cpus, info);
+
+ if (!pcpu_flush_ex || !hv_hypercall_pg)
+ goto do_native;
+
+ if (cpumask_empty(cpus))
+ return;
+
+ local_irq_save(flags);
+
+ flush_pcpu = this_cpu_ptr(pcpu_flush_ex);
+
+ if (unlikely(!*flush_pcpu))
+ *flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+
+ flush = *flush_pcpu;
+
+ if (unlikely(!flush)) {
+ local_irq_restore(flags);
+ goto do_native;
+ }
+
+ if (info->mm) {
+ /*
+ * AddressSpace argument must match the CR3 with PCID bits
+ * stripped out.
+ */
+ flush->address_space = virt_to_phys(info->mm->pgd);
+ flush->address_space &= CR3_ADDR_MASK;
+ flush->flags = 0;
+ } else {
+ flush->address_space = 0;
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ }
+
+ flush->hv_vp_set.valid_bank_mask = 0;
+
+ if (!cpumask_equal(cpus, cpu_present_mask)) {
+ flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
+ nr_bank = cpumask_to_vp_set(flush, cpus);
+ }
+
+ if (!nr_bank) {
+ flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
+ flush->flags |= HV_FLUSH_ALL_PROCESSORS;
+ }
+
+ /*
+ * We can flush not more than max_gvas with one hypercall. Flush the
+ * whole address space if we were asked to do more.
+ */
+ max_gvas =
+ (PAGE_SIZE - sizeof(*flush) - nr_bank *
+ sizeof(flush->hv_vp_set.bank_contents[0])) /
+ sizeof(flush->gva_list[0]);
+
+ if (info->end == TLB_FLUSH_ALL) {
+ flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
+ status = hv_do_rep_hypercall(
+ HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
+ 0, nr_bank, flush, NULL);
+ } else if (info->end &&
+ ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
+ status = hv_do_rep_hypercall(
+ HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
+ 0, nr_bank, flush, NULL);
+ } else {
+ gva_n = fill_gva_list(flush->gva_list, nr_bank,
+ info->start, info->end);
+ status = hv_do_rep_hypercall(
+ HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
+ gva_n, nr_bank, flush, NULL);
+ }
+
+ local_irq_restore(flags);
+
+ if (!(status & HV_HYPERCALL_RESULT_MASK))
+ return;
+do_native:
+ native_flush_tlb_others(cpus, info);
+}
+
+void hyperv_setup_mmu_ops(void)
+{
+ if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
+ return;
+
+ if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
+ pr_info("Using hypercall for remote TLB flush\n");
+ pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
+ } else {
+ pr_info("Using ext hypercall for remote TLB flush\n");
+ pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
+ }
+}
+
+void hyper_alloc_mmu(void)
+{
+ if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
+ return;
+
+ if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
+ else
+ pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
+}