From 04dd17822334871b23ea2862f7798fb0e0007777 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 11 May 2024 08:53:19 +0000
Subject: [PATCH] change otg to host mode
---
kernel/arch/powerpc/kvm/book3s_64_mmu_hv.c | 255 ++++++++++++++++++++++++--------------------------
1 files changed, 124 insertions(+), 131 deletions(-)
diff --git a/kernel/arch/powerpc/kvm/book3s_64_mmu_hv.c b/kernel/arch/powerpc/kvm/book3s_64_mmu_hv.c
index a488c10..38ea396 100644
--- a/kernel/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/kernel/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
- * 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. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*/
@@ -63,7 +52,7 @@
struct work_struct work;
u32 order;
- /* These fields protected by kvm->lock */
+ /* These fields protected by kvm->arch.mmu_setup_lock */
/* Possible values and their usage:
* <0 an error occurred during allocation,
@@ -73,7 +62,7 @@
int error;
/* Private to the work thread, until error != -EBUSY,
- * then protected by kvm->lock.
+ * then protected by kvm->arch.mmu_setup_lock.
*/
struct kvm_hpt_info hpt;
};
@@ -139,7 +128,7 @@
long err = -EBUSY;
struct kvm_hpt_info info;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
if (kvm->arch.mmu_ready) {
kvm->arch.mmu_ready = 0;
/* order mmu_ready vs. vcpus_running */
@@ -183,7 +172,7 @@
/* Ensure that each vcpu will flush its TLB on next entry. */
cpumask_setall(&kvm->arch.need_tlb_flush);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
return err;
}
@@ -268,15 +257,18 @@
{
unsigned long host_lpid, rsvd_lpid;
- if (!cpu_has_feature(CPU_FTR_HVMODE))
- return -EINVAL;
-
if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
return -EINVAL;
- /* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
- host_lpid = mfspr(SPRN_LPID);
- rsvd_lpid = LPID_RSVD;
+ host_lpid = 0;
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ host_lpid = mfspr(SPRN_LPID);
+
+ /* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ rsvd_lpid = LPID_RSVD;
+ else
+ rsvd_lpid = LPID_RSVD_POWER7;
kvmppc_init_lpid(rsvd_lpid + 1);
@@ -287,29 +279,16 @@
return 0;
}
-static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
-{
- unsigned long msr = vcpu->arch.intr_msr;
-
- /* If transactional, change to suspend mode on IRQ delivery */
- if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr))
- msr |= MSR_TS_S;
- else
- msr |= vcpu->arch.shregs.msr & MSR_TS_MASK;
- kvmppc_set_msr(vcpu, msr);
-}
-
static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
long pte_index, unsigned long pteh,
unsigned long ptel, unsigned long *pte_idx_ret)
{
long ret;
- /* Protect linux PTE lookup from page table destruction */
- rcu_read_lock_sched(); /* this disables preemption too */
+ preempt_disable();
ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
- current->mm->pgd, false, pte_idx_ret);
- rcu_read_unlock_sched();
+ kvm->mm->pgd, false, pte_idx_ret);
+ preempt_enable();
if (ret == H_TOO_HARD) {
/* this can't happen */
pr_err("KVM: Oops, kvmppc_h_enter returned too hard!\n");
@@ -437,10 +416,28 @@
return (instr & mask) != 0;
}
-int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu,
unsigned long gpa, gva_t ea, int is_store)
{
u32 last_inst;
+
+ /*
+ * Fast path - check if the guest physical address corresponds to a
+ * device on the FAST_MMIO_BUS, if so we can avoid loading the
+ * instruction all together, then we can just handle it and return.
+ */
+ if (is_store) {
+ int idx, ret;
+
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, (gpa_t) gpa, 0,
+ NULL);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ if (!ret) {
+ kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
+ return RESUME_GUEST;
+ }
+ }
/*
* If we fail, we just return to the guest and try executing it again.
@@ -479,10 +476,10 @@
vcpu->arch.paddr_accessed = gpa;
vcpu->arch.vaddr_accessed = ea;
- return kvmppc_emulate_mmio(run, vcpu);
+ return kvmppc_emulate_mmio(vcpu);
}
-int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
unsigned long ea, unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
@@ -491,20 +488,21 @@
__be64 *hptep;
unsigned long mmu_seq, psize, pte_size;
unsigned long gpa_base, gfn_base;
- unsigned long gpa, gfn, hva, pfn;
+ unsigned long gpa, gfn, hva, pfn, hpa;
struct kvm_memory_slot *memslot;
unsigned long *rmap;
struct revmap_entry *rev;
- struct page *page, *pages[1];
- long index, ret, npages;
+ struct page *page;
+ long index, ret;
bool is_ci;
- unsigned int writing, write_ok;
- struct vm_area_struct *vma;
+ bool writing, write_ok;
+ unsigned int shift;
unsigned long rcbits;
long mmio_update;
+ pte_t pte, *ptep;
if (kvm_is_radix(kvm))
- return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr);
+ return kvmppc_book3s_radix_page_fault(vcpu, ea, dsisr);
/*
* Real-mode code has already searched the HPT and found the
@@ -524,7 +522,7 @@
gpa_base = r & HPTE_R_RPN & ~(psize - 1);
gfn_base = gpa_base >> PAGE_SHIFT;
gpa = gpa_base | (ea & (psize - 1));
- return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
+ return kvmppc_hv_emulate_mmio(vcpu, gpa, ea,
dsisr & DSISR_ISSTORE);
}
}
@@ -560,7 +558,7 @@
/* No memslot means it's an emulated MMIO region */
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
- return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
+ return kvmppc_hv_emulate_mmio(vcpu, gpa, ea,
dsisr & DSISR_ISSTORE);
/*
@@ -575,59 +573,63 @@
smp_rmb();
ret = -EFAULT;
- is_ci = false;
- pfn = 0;
page = NULL;
- pte_size = PAGE_SIZE;
writing = (dsisr & DSISR_ISSTORE) != 0;
/* If writing != 0, then the HPTE must allow writing, if we get here */
write_ok = writing;
hva = gfn_to_hva_memslot(memslot, gfn);
- npages = get_user_pages_fast(hva, 1, writing, pages);
- if (npages < 1) {
- /* Check if it's an I/O mapping */
- down_read(¤t->mm->mmap_sem);
- vma = find_vma(current->mm, hva);
- if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
- (vma->vm_flags & VM_PFNMAP)) {
- pfn = vma->vm_pgoff +
- ((hva - vma->vm_start) >> PAGE_SHIFT);
- pte_size = psize;
- is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot))));
- write_ok = vma->vm_flags & VM_WRITE;
- }
- up_read(¤t->mm->mmap_sem);
- if (!pfn)
- goto out_put;
+
+ /*
+ * Do a fast check first, since __gfn_to_pfn_memslot doesn't
+ * do it with !atomic && !async, which is how we call it.
+ * We always ask for write permission since the common case
+ * is that the page is writable.
+ */
+ if (get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
+ write_ok = true;
} else {
- page = pages[0];
- pfn = page_to_pfn(page);
- if (PageHuge(page)) {
- page = compound_head(page);
- pte_size <<= compound_order(page);
- }
- /* if the guest wants write access, see if that is OK */
- if (!writing && hpte_is_writable(r)) {
- pte_t *ptep, pte;
- unsigned long flags;
- /*
- * We need to protect against page table destruction
- * hugepage split and collapse.
- */
- local_irq_save(flags);
- ptep = find_current_mm_pte(current->mm->pgd,
- hva, NULL, NULL);
- if (ptep) {
- pte = kvmppc_read_update_linux_pte(ptep, 1);
- if (__pte_write(pte))
- write_ok = 1;
- }
- local_irq_restore(flags);
+ /* Call KVM generic code to do the slow-path check */
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ writing, &write_ok);
+ if (is_error_noslot_pfn(pfn))
+ return -EFAULT;
+ page = NULL;
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (PageReserved(page))
+ page = NULL;
}
}
+ /*
+ * Read the PTE from the process' radix tree and use that
+ * so we get the shift and attribute bits.
+ */
+ spin_lock(&kvm->mmu_lock);
+ ptep = find_kvm_host_pte(kvm, mmu_seq, hva, &shift);
+ pte = __pte(0);
+ if (ptep)
+ pte = READ_ONCE(*ptep);
+ spin_unlock(&kvm->mmu_lock);
+ /*
+ * If the PTE disappeared temporarily due to a THP
+ * collapse, just return and let the guest try again.
+ */
+ if (!pte_present(pte)) {
+ if (page)
+ put_page(page);
+ return RESUME_GUEST;
+ }
+ hpa = pte_pfn(pte) << PAGE_SHIFT;
+ pte_size = PAGE_SIZE;
+ if (shift)
+ pte_size = 1ul << shift;
+ is_ci = pte_ci(pte);
+
if (psize > pte_size)
goto out_put;
+ if (pte_size > psize)
+ hpa |= hva & (pte_size - psize);
/* Check WIMG vs. the actual page we're accessing */
if (!hpte_cache_flags_ok(r, is_ci)) {
@@ -641,14 +643,13 @@
}
/*
- * Set the HPTE to point to pfn.
- * Since the pfn is at PAGE_SIZE granularity, make sure we
+ * Set the HPTE to point to hpa.
+ * Since the hpa is at PAGE_SIZE granularity, make sure we
* don't mask out lower-order bits if psize < PAGE_SIZE.
*/
if (psize < PAGE_SIZE)
psize = PAGE_SIZE;
- r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) |
- ((pfn << PAGE_SHIFT) & ~(psize - 1));
+ r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | hpa;
if (hpte_is_writable(r) && !write_ok)
r = hpte_make_readonly(r);
ret = RESUME_GUEST;
@@ -713,20 +714,13 @@
asm volatile("ptesync" : : : "memory");
preempt_enable();
if (page && hpte_is_writable(r))
- SetPageDirty(page);
+ set_page_dirty_lock(page);
out_put:
trace_kvm_page_fault_exit(vcpu, hpte, ret);
- if (page) {
- /*
- * We drop pages[0] here, not page because page might
- * have been set to the head page of a compound, but
- * we have to drop the reference on the correct tail
- * page to match the get inside gup()
- */
- put_page(pages[0]);
- }
+ if (page)
+ put_page(page);
return ret;
out_unlock:
@@ -900,11 +894,12 @@
gfn = memslot->base_gfn;
rmapp = memslot->arch.rmap;
+ if (kvm_is_radix(kvm)) {
+ kvmppc_radix_flush_memslot(kvm, memslot);
+ return;
+ }
+
for (n = memslot->npages; n; --n, ++gfn) {
- if (kvm_is_radix(kvm)) {
- kvm_unmap_radix(kvm, memslot, gfn);
- continue;
- }
/*
* Testing the present bit without locking is OK because
* the memslot has been marked invalid already, and hence
@@ -1175,7 +1170,7 @@
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
goto err;
hva = gfn_to_hva_memslot(memslot, gfn);
- npages = get_user_pages_fast(hva, 1, 1, pages);
+ npages = get_user_pages_fast(hva, 1, FOLL_WRITE, pages);
if (npages < 1)
goto err;
page = pages[0];
@@ -1429,7 +1424,7 @@
static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
{
- if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+ if (WARN_ON(!mutex_is_locked(&kvm->arch.mmu_setup_lock)))
return;
if (!resize)
@@ -1456,14 +1451,14 @@
if (WARN_ON(resize->error != -EBUSY))
return;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
/* Request is still current? */
if (kvm->arch.resize_hpt == resize) {
/* We may request large allocations here:
- * do not sleep with kvm->lock held for a while.
+ * do not sleep with kvm->arch.mmu_setup_lock held for a while.
*/
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
resize->order);
@@ -1476,9 +1471,9 @@
if (WARN_ON(err == -EBUSY))
err = -EINPROGRESS;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
/* It is possible that kvm->arch.resize_hpt != resize
- * after we grab kvm->lock again.
+ * after we grab kvm->arch.mmu_setup_lock again.
*/
}
@@ -1487,7 +1482,7 @@
if (kvm->arch.resize_hpt != resize)
resize_hpt_release(kvm, resize);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
}
long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
@@ -1504,7 +1499,7 @@
if (shift && ((shift < 18) || (shift > 46)))
return -EINVAL;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
resize = kvm->arch.resize_hpt;
@@ -1547,7 +1542,7 @@
ret = 100; /* estimated time in ms */
out:
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
return ret;
}
@@ -1570,7 +1565,7 @@
if (shift && ((shift < 18) || (shift > 46)))
return -EINVAL;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
resize = kvm->arch.resize_hpt;
@@ -1607,7 +1602,7 @@
smp_mb();
out_no_hpt:
resize_hpt_release(kvm, resize);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
return ret;
}
@@ -1744,7 +1739,7 @@
int first_pass;
unsigned long hpte[2];
- if (!access_ok(VERIFY_WRITE, buf, count))
+ if (!access_ok(buf, count))
return -EFAULT;
if (kvm_is_radix(kvm))
return 0;
@@ -1844,13 +1839,13 @@
int mmu_ready;
int pshift;
- if (!access_ok(VERIFY_READ, buf, count))
+ if (!access_ok(buf, count))
return -EFAULT;
if (kvm_is_radix(kvm))
return -EINVAL;
/* lock out vcpus from running while we're doing this */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.mmu_setup_lock);
mmu_ready = kvm->arch.mmu_ready;
if (mmu_ready) {
kvm->arch.mmu_ready = 0; /* temporarily */
@@ -1858,7 +1853,7 @@
smp_mb();
if (atomic_read(&kvm->arch.vcpus_running)) {
kvm->arch.mmu_ready = 1;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
return -EBUSY;
}
}
@@ -1945,7 +1940,7 @@
/* Order HPTE updates vs. mmu_ready */
smp_wmb();
kvm->arch.mmu_ready = mmu_ready;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.mmu_setup_lock);
if (err)
return err;
@@ -1993,7 +1988,7 @@
ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
if (ret < 0) {
kfree(ctx);
- kvm_put_kvm(kvm);
+ kvm_put_kvm_no_destroy(kvm);
return ret;
}
@@ -2142,9 +2137,8 @@
void kvmppc_mmu_debugfs_init(struct kvm *kvm)
{
- kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
- kvm->arch.debugfs_dir, kvm,
- &debugfs_htab_fops);
+ debugfs_create_file("htab", 0400, kvm->arch.debugfs_dir, kvm,
+ &debugfs_htab_fops);
}
void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
@@ -2154,7 +2148,6 @@
vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */
mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
- mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;
vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
}
--
Gitblit v1.6.2