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_radix.c | 1080 +++++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 821 insertions(+), 259 deletions(-)
diff --git a/kernel/arch/powerpc/kvm/book3s_64_mmu_radix.c b/kernel/arch/powerpc/kvm/book3s_64_mmu_radix.c
index df0f08c..04028f9 100644
--- a/kernel/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/kernel/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -1,7 +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.
*
* Copyright 2016 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*/
@@ -10,14 +8,19 @@
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/debugfs.h>
+#include <linux/pgtable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/page.h>
#include <asm/mmu.h>
-#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/pte-walk.h>
+#include <asm/ultravisor.h>
+#include <asm/kvm_book3s_uvmem.h>
/*
* Supported radix tree geometry.
@@ -26,18 +29,236 @@
*/
static int p9_supported_radix_bits[4] = { 5, 9, 9, 13 };
+unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
+ gva_t eaddr, void *to, void *from,
+ unsigned long n)
+{
+ int old_pid, old_lpid;
+ unsigned long quadrant, ret = n;
+ bool is_load = !!to;
+
+ /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
+ if (kvmhv_on_pseries())
+ return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
+ (to != NULL) ? __pa(to): 0,
+ (from != NULL) ? __pa(from): 0, n);
+
+ quadrant = 1;
+ if (!pid)
+ quadrant = 2;
+ if (is_load)
+ from = (void *) (eaddr | (quadrant << 62));
+ else
+ to = (void *) (eaddr | (quadrant << 62));
+
+ preempt_disable();
+
+ /* switch the lpid first to avoid running host with unallocated pid */
+ old_lpid = mfspr(SPRN_LPID);
+ if (old_lpid != lpid)
+ mtspr(SPRN_LPID, lpid);
+ if (quadrant == 1) {
+ old_pid = mfspr(SPRN_PID);
+ if (old_pid != pid)
+ mtspr(SPRN_PID, pid);
+ }
+ isync();
+
+ pagefault_disable();
+ if (is_load)
+ ret = __copy_from_user_inatomic(to, (const void __user *)from, n);
+ else
+ ret = __copy_to_user_inatomic((void __user *)to, from, n);
+ pagefault_enable();
+
+ /* switch the pid first to avoid running host with unallocated pid */
+ if (quadrant == 1 && pid != old_pid)
+ mtspr(SPRN_PID, old_pid);
+ if (lpid != old_lpid)
+ mtspr(SPRN_LPID, old_lpid);
+ isync();
+
+ preempt_enable();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_copy_tofrom_guest_radix);
+
+static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+ void *to, void *from, unsigned long n)
+{
+ int lpid = vcpu->kvm->arch.lpid;
+ int pid = vcpu->arch.pid;
+
+ /* This would cause a data segment intr so don't allow the access */
+ if (eaddr & (0x3FFUL << 52))
+ return -EINVAL;
+
+ /* Should we be using the nested lpid */
+ if (vcpu->arch.nested)
+ lpid = vcpu->arch.nested->shadow_lpid;
+
+ /* If accessing quadrant 3 then pid is expected to be 0 */
+ if (((eaddr >> 62) & 0x3) == 0x3)
+ pid = 0;
+
+ eaddr &= ~(0xFFFUL << 52);
+
+ return __kvmhv_copy_tofrom_guest_radix(lpid, pid, eaddr, to, from, n);
+}
+
+long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *to,
+ unsigned long n)
+{
+ long ret;
+
+ ret = kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, to, NULL, n);
+ if (ret > 0)
+ memset(to + (n - ret), 0, ret);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_from_guest_radix);
+
+long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *from,
+ unsigned long n)
+{
+ return kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, NULL, from, n);
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_to_guest_radix);
+
+int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
+ struct kvmppc_pte *gpte, u64 root,
+ u64 *pte_ret_p)
+{
+ struct kvm *kvm = vcpu->kvm;
+ int ret, level, ps;
+ unsigned long rts, bits, offset, index;
+ u64 pte, base, gpa;
+ __be64 rpte;
+
+ rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
+ ((root & RTS2_MASK) >> RTS2_SHIFT);
+ bits = root & RPDS_MASK;
+ base = root & RPDB_MASK;
+
+ offset = rts + 31;
+
+ /* Current implementations only support 52-bit space */
+ if (offset != 52)
+ return -EINVAL;
+
+ /* Walk each level of the radix tree */
+ for (level = 3; level >= 0; --level) {
+ u64 addr;
+ /* Check a valid size */
+ if (level && bits != p9_supported_radix_bits[level])
+ return -EINVAL;
+ if (level == 0 && !(bits == 5 || bits == 9))
+ return -EINVAL;
+ offset -= bits;
+ index = (eaddr >> offset) & ((1UL << bits) - 1);
+ /* Check that low bits of page table base are zero */
+ if (base & ((1UL << (bits + 3)) - 1))
+ return -EINVAL;
+ /* Read the entry from guest memory */
+ addr = base + (index * sizeof(rpte));
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+ ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+ if (ret) {
+ if (pte_ret_p)
+ *pte_ret_p = addr;
+ return ret;
+ }
+ pte = __be64_to_cpu(rpte);
+ if (!(pte & _PAGE_PRESENT))
+ return -ENOENT;
+ /* Check if a leaf entry */
+ if (pte & _PAGE_PTE)
+ break;
+ /* Get ready to walk the next level */
+ base = pte & RPDB_MASK;
+ bits = pte & RPDS_MASK;
+ }
+
+ /* Need a leaf at lowest level; 512GB pages not supported */
+ if (level < 0 || level == 3)
+ return -EINVAL;
+
+ /* We found a valid leaf PTE */
+ /* Offset is now log base 2 of the page size */
+ gpa = pte & 0x01fffffffffff000ul;
+ if (gpa & ((1ul << offset) - 1))
+ return -EINVAL;
+ gpa |= eaddr & ((1ul << offset) - 1);
+ for (ps = MMU_PAGE_4K; ps < MMU_PAGE_COUNT; ++ps)
+ if (offset == mmu_psize_defs[ps].shift)
+ break;
+ gpte->page_size = ps;
+ gpte->page_shift = offset;
+
+ gpte->eaddr = eaddr;
+ gpte->raddr = gpa;
+
+ /* Work out permissions */
+ gpte->may_read = !!(pte & _PAGE_READ);
+ gpte->may_write = !!(pte & _PAGE_WRITE);
+ gpte->may_execute = !!(pte & _PAGE_EXEC);
+
+ gpte->rc = pte & (_PAGE_ACCESSED | _PAGE_DIRTY);
+
+ if (pte_ret_p)
+ *pte_ret_p = pte;
+
+ return 0;
+}
+
+/*
+ * Used to walk a partition or process table radix tree in guest memory
+ * Note: We exploit the fact that a partition table and a process
+ * table have the same layout, a partition-scoped page table and a
+ * process-scoped page table have the same layout, and the 2nd
+ * doubleword of a partition table entry has the same layout as
+ * the PTCR register.
+ */
+int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
+ struct kvmppc_pte *gpte, u64 table,
+ int table_index, u64 *pte_ret_p)
+{
+ struct kvm *kvm = vcpu->kvm;
+ int ret;
+ unsigned long size, ptbl, root;
+ struct prtb_entry entry;
+
+ if ((table & PRTS_MASK) > 24)
+ return -EINVAL;
+ size = 1ul << ((table & PRTS_MASK) + 12);
+
+ /* Is the table big enough to contain this entry? */
+ if ((table_index * sizeof(entry)) >= size)
+ return -EINVAL;
+
+ /* Read the table to find the root of the radix tree */
+ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+ ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+ if (ret)
+ return ret;
+
+ /* Root is stored in the first double word */
+ root = be64_to_cpu(entry.prtb0);
+
+ return kvmppc_mmu_walk_radix_tree(vcpu, eaddr, gpte, root, pte_ret_p);
+}
+
int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *gpte, bool data, bool iswrite)
{
- struct kvm *kvm = vcpu->kvm;
u32 pid;
- int ret, level, ps;
- __be64 prte, rpte;
- unsigned long ptbl;
- unsigned long root, pte, index;
- unsigned long rts, bits, offset;
- unsigned long gpa;
- unsigned long proc_tbl_size;
+ u64 pte;
+ int ret;
/* Work out effective PID */
switch (eaddr >> 62) {
@@ -50,71 +271,13 @@
default:
return -EINVAL;
}
- proc_tbl_size = 1 << ((kvm->arch.process_table & PRTS_MASK) + 12);
- if (pid * 16 >= proc_tbl_size)
- return -EINVAL;
- /* Read partition table to find root of tree for effective PID */
- ptbl = (kvm->arch.process_table & PRTB_MASK) + (pid * 16);
- ret = kvm_read_guest(kvm, ptbl, &prte, sizeof(prte));
+ ret = kvmppc_mmu_radix_translate_table(vcpu, eaddr, gpte,
+ vcpu->kvm->arch.process_table, pid, &pte);
if (ret)
return ret;
- root = be64_to_cpu(prte);
- rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
- ((root & RTS2_MASK) >> RTS2_SHIFT);
- bits = root & RPDS_MASK;
- root = root & RPDB_MASK;
-
- offset = rts + 31;
-
- /* current implementations only support 52-bit space */
- if (offset != 52)
- return -EINVAL;
-
- for (level = 3; level >= 0; --level) {
- if (level && bits != p9_supported_radix_bits[level])
- return -EINVAL;
- if (level == 0 && !(bits == 5 || bits == 9))
- return -EINVAL;
- offset -= bits;
- index = (eaddr >> offset) & ((1UL << bits) - 1);
- /* check that low bits of page table base are zero */
- if (root & ((1UL << (bits + 3)) - 1))
- return -EINVAL;
- ret = kvm_read_guest(kvm, root + index * 8,
- &rpte, sizeof(rpte));
- if (ret)
- return ret;
- pte = __be64_to_cpu(rpte);
- if (!(pte & _PAGE_PRESENT))
- return -ENOENT;
- if (pte & _PAGE_PTE)
- break;
- bits = pte & 0x1f;
- root = pte & 0x0fffffffffffff00ul;
- }
- /* need a leaf at lowest level; 512GB pages not supported */
- if (level < 0 || level == 3)
- return -EINVAL;
-
- /* offset is now log base 2 of the page size */
- gpa = pte & 0x01fffffffffff000ul;
- if (gpa & ((1ul << offset) - 1))
- return -EINVAL;
- gpa += eaddr & ((1ul << offset) - 1);
- for (ps = MMU_PAGE_4K; ps < MMU_PAGE_COUNT; ++ps)
- if (offset == mmu_psize_defs[ps].shift)
- break;
- gpte->page_size = ps;
-
- gpte->eaddr = eaddr;
- gpte->raddr = gpa;
-
- /* Work out permissions */
- gpte->may_read = !!(pte & _PAGE_READ);
- gpte->may_write = !!(pte & _PAGE_WRITE);
- gpte->may_execute = !!(pte & _PAGE_EXEC);
+ /* Check privilege (applies only to process scoped translations) */
if (kvmppc_get_msr(vcpu) & MSR_PR) {
if (pte & _PAGE_PRIVILEGED) {
gpte->may_read = 0;
@@ -136,21 +299,47 @@
return 0;
}
-static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
- unsigned int pshift)
+void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
+ unsigned int pshift, unsigned int lpid)
{
unsigned long psize = PAGE_SIZE;
+ int psi;
+ long rc;
+ unsigned long rb;
if (pshift)
psize = 1UL << pshift;
+ else
+ pshift = PAGE_SHIFT;
addr &= ~(psize - 1);
- radix__flush_tlb_lpid_page(kvm->arch.lpid, addr, psize);
+
+ if (!kvmhv_on_pseries()) {
+ radix__flush_tlb_lpid_page(lpid, addr, psize);
+ return;
+ }
+
+ psi = shift_to_mmu_psize(pshift);
+ rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
+ rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
+ lpid, rb);
+ if (rc)
+ pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
}
-static void kvmppc_radix_flush_pwc(struct kvm *kvm)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
{
- radix__flush_pwc_lpid(kvm->arch.lpid);
+ long rc;
+
+ if (!kvmhv_on_pseries()) {
+ radix__flush_pwc_lpid(lpid);
+ return;
+ }
+
+ rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
+ lpid, TLBIEL_INVAL_SET_LPID);
+ if (rc)
+ pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
}
static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
@@ -160,7 +349,7 @@
return __radix_pte_update(ptep, clr, set);
}
-void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
+static void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
radix__set_pte_at(kvm->mm, addr, ptep, pte, 0);
@@ -185,12 +374,6 @@
kmem_cache_free(kvm_pte_cache, ptep);
}
-/* Like pmd_huge() and pmd_large(), but works regardless of config options */
-static inline int pmd_is_leaf(pmd_t pmd)
-{
- return !!(pmd_val(pmd) & _PAGE_PTE);
-}
-
static pmd_t *kvmppc_pmd_alloc(void)
{
pmd_t *pmd;
@@ -207,23 +390,44 @@
kmem_cache_free(kvm_pmd_cache, pmdp);
}
-static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
- unsigned long gpa, unsigned int shift)
+/* Called with kvm->mmu_lock held */
+void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
+ unsigned int shift,
+ const struct kvm_memory_slot *memslot,
+ unsigned int lpid)
{
- unsigned long page_size = 1ul << shift;
unsigned long old;
+ unsigned long gfn = gpa >> PAGE_SHIFT;
+ unsigned long page_size = PAGE_SIZE;
+ unsigned long hpa;
old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
- if (old & _PAGE_DIRTY) {
- unsigned long gfn = gpa >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot;
+ kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
+ /* The following only applies to L1 entries */
+ if (lpid != kvm->arch.lpid)
+ return;
+
+ if (!memslot) {
memslot = gfn_to_memslot(kvm, gfn);
- if (memslot && memslot->dirty_bitmap)
- kvmppc_update_dirty_map(memslot, gfn, page_size);
+ if (!memslot)
+ return;
}
+ if (shift) { /* 1GB or 2MB page */
+ page_size = 1ul << shift;
+ if (shift == PMD_SHIFT)
+ kvm->stat.num_2M_pages--;
+ else if (shift == PUD_SHIFT)
+ kvm->stat.num_1G_pages--;
+ }
+
+ gpa &= ~(page_size - 1);
+ hpa = old & PTE_RPN_MASK;
+ kvmhv_remove_nest_rmap_range(kvm, memslot, gpa, hpa, page_size);
+
+ if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot, gfn, page_size);
}
/*
@@ -232,14 +436,19 @@
* Callers are responsible for flushing the PWC.
*
* When page tables are being unmapped/freed as part of page fault path
- * (full == false), ptes are not expected. There is code to unmap them
- * and emit a warning if encountered, but there may already be data
- * corruption due to the unexpected mappings.
+ * (full == false), valid ptes are generally not expected; however, there
+ * is one situation where they arise, which is when dirty page logging is
+ * turned off for a memslot while the VM is running. The new memslot
+ * becomes visible to page faults before the memslot commit function
+ * gets to flush the memslot, which can lead to a 2MB page mapping being
+ * installed for a guest physical address where there are already 64kB
+ * (or 4kB) mappings (of sub-pages of the same 2MB page).
*/
-static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
+static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
+ unsigned int lpid)
{
if (full) {
- memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
+ memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE);
} else {
pte_t *p = pte;
unsigned long it;
@@ -247,17 +456,17 @@
for (it = 0; it < PTRS_PER_PTE; ++it, ++p) {
if (pte_val(*p) == 0)
continue;
- WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, p,
pte_pfn(*p) << PAGE_SHIFT,
- PAGE_SHIFT);
+ PAGE_SHIFT, NULL, lpid);
}
}
kvmppc_pte_free(pte);
}
-static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
+static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
+ unsigned int lpid)
{
unsigned long im;
pmd_t *p = pmd;
@@ -272,20 +481,21 @@
WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, (pte_t *)p,
pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
- PMD_SHIFT);
+ PMD_SHIFT, NULL, lpid);
}
} else {
pte_t *pte;
pte = pte_offset_map(p, 0);
- kvmppc_unmap_free_pte(kvm, pte, full);
+ kvmppc_unmap_free_pte(kvm, pte, full, lpid);
pmd_clear(p);
}
}
kvmppc_pmd_free(pmd);
}
-static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
+static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
+ unsigned int lpid)
{
unsigned long iu;
pud_t *p = pud;
@@ -293,42 +503,47 @@
for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
if (!pud_present(*p))
continue;
- if (pud_huge(*p)) {
+ if (pud_is_leaf(*p)) {
pud_clear(p);
} else {
pmd_t *pmd;
pmd = pmd_offset(p, 0);
- kvmppc_unmap_free_pmd(kvm, pmd, true);
+ kvmppc_unmap_free_pmd(kvm, pmd, true, lpid);
pud_clear(p);
}
}
pud_free(kvm->mm, pud);
}
-void kvmppc_free_radix(struct kvm *kvm)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
{
unsigned long ig;
- pgd_t *pgd;
- if (!kvm->arch.pgtable)
- return;
- pgd = kvm->arch.pgtable;
for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
+ p4d_t *p4d = p4d_offset(pgd, 0);
pud_t *pud;
- if (!pgd_present(*pgd))
+ if (!p4d_present(*p4d))
continue;
- pud = pud_offset(pgd, 0);
- kvmppc_unmap_free_pud(kvm, pud);
- pgd_clear(pgd);
+ pud = pud_offset(p4d, 0);
+ kvmppc_unmap_free_pud(kvm, pud, lpid);
+ p4d_clear(p4d);
}
- pgd_free(kvm->mm, kvm->arch.pgtable);
- kvm->arch.pgtable = NULL;
+}
+
+void kvmppc_free_radix(struct kvm *kvm)
+{
+ if (kvm->arch.pgtable) {
+ kvmppc_free_pgtable_radix(kvm, kvm->arch.pgtable,
+ kvm->arch.lpid);
+ pgd_free(kvm->mm, kvm->arch.pgtable);
+ kvm->arch.pgtable = NULL;
+ }
}
static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
- unsigned long gpa)
+ unsigned long gpa, unsigned int lpid)
{
pte_t *pte = pte_offset_kernel(pmd, 0);
@@ -338,13 +553,13 @@
* flushing the PWC again.
*/
pmd_clear(pmd);
- kvmppc_radix_flush_pwc(kvm);
+ kvmppc_radix_flush_pwc(kvm, lpid);
- kvmppc_unmap_free_pte(kvm, pte, false);
+ kvmppc_unmap_free_pte(kvm, pte, false, lpid);
}
static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
- unsigned long gpa)
+ unsigned long gpa, unsigned int lpid)
{
pmd_t *pmd = pmd_offset(pud, 0);
@@ -354,9 +569,9 @@
* so can be freed without flushing the PWC again.
*/
pud_clear(pud);
- kvmppc_radix_flush_pwc(kvm);
+ kvmppc_radix_flush_pwc(kvm, lpid);
- kvmppc_unmap_free_pmd(kvm, pmd, false);
+ kvmppc_unmap_free_pmd(kvm, pmd, false, lpid);
}
/*
@@ -368,25 +583,30 @@
*/
#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
-static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
- unsigned int level, unsigned long mmu_seq)
+int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+ unsigned long gpa, unsigned int level,
+ unsigned long mmu_seq, unsigned int lpid,
+ unsigned long *rmapp, struct rmap_nested **n_rmap)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud, *new_pud = NULL;
pmd_t *pmd, *new_pmd = NULL;
pte_t *ptep, *new_ptep = NULL;
int ret;
/* Traverse the guest's 2nd-level tree, allocate new levels needed */
- pgd = kvm->arch.pgtable + pgd_index(gpa);
+ pgd = pgtable + pgd_index(gpa);
+ p4d = p4d_offset(pgd, gpa);
+
pud = NULL;
- if (pgd_present(*pgd))
- pud = pud_offset(pgd, gpa);
+ if (p4d_present(*p4d))
+ pud = pud_offset(p4d, gpa);
else
new_pud = pud_alloc_one(kvm->mm, gpa);
pmd = NULL;
- if (pud && pud_present(*pud) && !pud_huge(*pud))
+ if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
pmd = pmd_offset(pud, gpa);
else if (level <= 1)
new_pmd = kvmppc_pmd_alloc();
@@ -402,14 +622,14 @@
/* Now traverse again under the lock and change the tree */
ret = -ENOMEM;
- if (pgd_none(*pgd)) {
+ if (p4d_none(*p4d)) {
if (!new_pud)
goto out_unlock;
- pgd_populate(kvm->mm, pgd, new_pud);
+ p4d_populate(kvm->mm, p4d, new_pud);
new_pud = NULL;
}
- pud = pud_offset(pgd, gpa);
- if (pud_huge(*pud)) {
+ pud = pud_offset(p4d, gpa);
+ if (pud_is_leaf(*pud)) {
unsigned long hgpa = gpa & PUD_MASK;
/* Check if we raced and someone else has set the same thing */
@@ -435,7 +655,8 @@
goto out_unlock;
}
/* Valid 1GB page here already, remove it */
- kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT);
+ kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT, NULL,
+ lpid);
}
if (level == 2) {
if (!pud_none(*pud)) {
@@ -444,9 +665,11 @@
* install a large page, so remove and free the page
* table page.
*/
- kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa);
+ kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
goto out_unlock;
}
@@ -470,7 +693,7 @@
WARN_ON_ONCE((pmd_val(*pmd) ^ pte_val(pte)) &
PTE_BITS_MUST_MATCH);
kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
- 0, pte_val(pte), lgpa, PMD_SHIFT);
+ 0, pte_val(pte), lgpa, PMD_SHIFT);
ret = 0;
goto out_unlock;
}
@@ -484,7 +707,8 @@
goto out_unlock;
}
/* Valid 2MB page here already, remove it */
- kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT);
+ kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT, NULL,
+ lpid);
}
if (level == 1) {
if (!pmd_none(*pmd)) {
@@ -493,9 +717,11 @@
* install a large page, so remove and free the page
* table page.
*/
- kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa);
+ kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
goto out_unlock;
}
@@ -520,6 +746,8 @@
goto out_unlock;
}
kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
out_unlock:
@@ -533,95 +761,50 @@
return ret;
}
-int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
- unsigned long ea, unsigned long dsisr)
+bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
+ unsigned long gpa, unsigned int lpid)
+{
+ unsigned long pgflags;
+ unsigned int shift;
+ pte_t *ptep;
+
+ /*
+ * Need to set an R or C bit in the 2nd-level tables;
+ * since we are just helping out the hardware here,
+ * it is sufficient to do what the hardware does.
+ */
+ pgflags = _PAGE_ACCESSED;
+ if (writing)
+ pgflags |= _PAGE_DIRTY;
+
+ if (nested)
+ ptep = find_kvm_nested_guest_pte(kvm, lpid, gpa, &shift);
+ else
+ ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
+
+ if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
+ kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
+ return true;
+ }
+ return false;
+}
+
+int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+ unsigned long gpa,
+ struct kvm_memory_slot *memslot,
+ bool writing, bool kvm_ro,
+ pte_t *inserted_pte, unsigned int *levelp)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq;
- unsigned long gpa, gfn, hva;
- struct kvm_memory_slot *memslot;
struct page *page = NULL;
- long ret;
- bool writing;
+ unsigned long mmu_seq;
+ unsigned long hva, gfn = gpa >> PAGE_SHIFT;
bool upgrade_write = false;
bool *upgrade_p = &upgrade_write;
pte_t pte, *ptep;
- unsigned long pgflags;
unsigned int shift, level;
-
- /* Check for unusual errors */
- if (dsisr & DSISR_UNSUPP_MMU) {
- pr_err("KVM: Got unsupported MMU fault\n");
- return -EFAULT;
- }
- if (dsisr & DSISR_BADACCESS) {
- /* Reflect to the guest as DSI */
- pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
-
- /* Translate the logical address and get the page */
- gpa = vcpu->arch.fault_gpa & ~0xfffUL;
- gpa &= ~0xF000000000000000ul;
- gfn = gpa >> PAGE_SHIFT;
- if (!(dsisr & DSISR_PRTABLE_FAULT))
- gpa |= ea & 0xfff;
- memslot = gfn_to_memslot(kvm, gfn);
-
- /* No memslot means it's an emulated MMIO region */
- if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
- if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
- DSISR_SET_RC)) {
- /*
- * Bad address in guest page table tree, or other
- * unusual error - reflect it to the guest as DSI.
- */
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
- return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
- dsisr & DSISR_ISSTORE);
- }
-
- writing = (dsisr & DSISR_ISSTORE) != 0;
- if (memslot->flags & KVM_MEM_READONLY) {
- if (writing) {
- /* give the guest a DSI */
- dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
- upgrade_p = NULL;
- }
-
- if (dsisr & DSISR_SET_RC) {
- /*
- * Need to set an R or C bit in the 2nd-level tables;
- * since we are just helping out the hardware here,
- * it is sufficient to do what the hardware does.
- */
- pgflags = _PAGE_ACCESSED;
- if (writing)
- pgflags |= _PAGE_DIRTY;
- /*
- * We are walking the secondary page table here. We can do this
- * without disabling irq.
- */
- spin_lock(&kvm->mmu_lock);
- ptep = __find_linux_pte(kvm->arch.pgtable,
- gpa, NULL, &shift);
- if (ptep && pte_present(*ptep) &&
- (!writing || pte_write(*ptep))) {
- kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
- gpa, shift);
- dsisr &= ~DSISR_SET_RC;
- }
- spin_unlock(&kvm->mmu_lock);
- if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
- DSISR_PROTFAULT | DSISR_SET_RC)))
- return RESUME_GUEST;
- }
+ int ret;
+ bool large_enable;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_notifier_seq;
@@ -634,7 +817,7 @@
* is that the page is writable.
*/
hva = gfn_to_hva_memslot(memslot, gfn);
- if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
+ if (!kvm_ro && get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
upgrade_write = true;
} else {
unsigned long pfn;
@@ -656,27 +839,31 @@
* Read the PTE from the process' radix tree and use that
* so we get the shift and attribute bits.
*/
- local_irq_disable();
- ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ 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 (!ptep) {
- local_irq_enable();
+ if (!pte_present(pte)) {
if (page)
put_page(page);
return RESUME_GUEST;
}
- pte = *ptep;
- local_irq_enable();
+
+ /* If we're logging dirty pages, always map single pages */
+ large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
/* Get pte level from shift/size */
- if (shift == PUD_SHIFT &&
+ if (large_enable && shift == PUD_SHIFT &&
(gpa & (PUD_SIZE - PAGE_SIZE)) ==
(hva & (PUD_SIZE - PAGE_SIZE))) {
level = 2;
- } else if (shift == PMD_SHIFT &&
+ } else if (large_enable && shift == PMD_SHIFT &&
(gpa & (PMD_SIZE - PAGE_SIZE)) ==
(hva & (PMD_SIZE - PAGE_SIZE))) {
level = 1;
@@ -702,7 +889,12 @@
}
/* Allocate space in the tree and write the PTE */
- ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+ ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
+ mmu_seq, kvm->arch.lpid, NULL, NULL);
+ if (inserted_pte)
+ *inserted_pte = pte;
+ if (levelp)
+ *levelp = level;
if (page) {
if (!ret && (pte_val(pte) & _PAGE_WRITE))
@@ -710,36 +902,119 @@
put_page(page);
}
+ /* Increment number of large pages if we (successfully) inserted one */
+ if (!ret) {
+ if (level == 1)
+ kvm->stat.num_2M_pages++;
+ else if (level == 2)
+ kvm->stat.num_1G_pages++;
+ }
+
+ return ret;
+}
+
+int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
+ unsigned long ea, unsigned long dsisr)
+{
+ struct kvm *kvm = vcpu->kvm;
+ unsigned long gpa, gfn;
+ struct kvm_memory_slot *memslot;
+ long ret;
+ bool writing = !!(dsisr & DSISR_ISSTORE);
+ bool kvm_ro = false;
+
+ /* Check for unusual errors */
+ if (dsisr & DSISR_UNSUPP_MMU) {
+ pr_err("KVM: Got unsupported MMU fault\n");
+ return -EFAULT;
+ }
+ if (dsisr & DSISR_BADACCESS) {
+ /* Reflect to the guest as DSI */
+ pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+
+ /* Translate the logical address */
+ gpa = vcpu->arch.fault_gpa & ~0xfffUL;
+ gpa &= ~0xF000000000000000ul;
+ gfn = gpa >> PAGE_SHIFT;
+ if (!(dsisr & DSISR_PRTABLE_FAULT))
+ gpa |= ea & 0xfff;
+
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+ return kvmppc_send_page_to_uv(kvm, gfn);
+
+ /* Get the corresponding memslot */
+ memslot = gfn_to_memslot(kvm, gfn);
+
+ /* No memslot means it's an emulated MMIO region */
+ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+ if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
+ DSISR_SET_RC)) {
+ /*
+ * Bad address in guest page table tree, or other
+ * unusual error - reflect it to the guest as DSI.
+ */
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+ return kvmppc_hv_emulate_mmio(vcpu, gpa, ea, writing);
+ }
+
+ if (memslot->flags & KVM_MEM_READONLY) {
+ if (writing) {
+ /* give the guest a DSI */
+ kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
+ DSISR_PROTFAULT);
+ return RESUME_GUEST;
+ }
+ kvm_ro = true;
+ }
+
+ /* Failed to set the reference/change bits */
+ if (dsisr & DSISR_SET_RC) {
+ spin_lock(&kvm->mmu_lock);
+ if (kvmppc_hv_handle_set_rc(kvm, false, writing,
+ gpa, kvm->arch.lpid))
+ dsisr &= ~DSISR_SET_RC;
+ spin_unlock(&kvm->mmu_lock);
+
+ if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+ DSISR_PROTFAULT | DSISR_SET_RC)))
+ return RESUME_GUEST;
+ }
+
+ /* Try to insert a pte */
+ ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
+ kvm_ro, NULL, NULL);
+
if (ret == 0 || ret == -EAGAIN)
ret = RESUME_GUEST;
return ret;
}
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn)
{
pte_t *ptep;
unsigned long gpa = gfn << PAGE_SHIFT;
unsigned int shift;
- unsigned long old;
- ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
- if (ptep && pte_present(*ptep)) {
- old = kvmppc_radix_update_pte(kvm, ptep, ~0UL, 0,
- gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
- if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
- unsigned long psize = PAGE_SIZE;
- if (shift)
- psize = 1ul << shift;
- kvmppc_update_dirty_map(memslot, gfn, psize);
- }
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) {
+ uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT);
+ return 0;
}
- return 0;
+
+ ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
+ if (ptep && pte_present(*ptep))
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+ kvm->arch.lpid);
+ return 0;
}
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn)
{
@@ -747,18 +1022,27 @@
unsigned long gpa = gfn << PAGE_SHIFT;
unsigned int shift;
int ref = 0;
+ unsigned long old, *rmapp;
- ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+ return ref;
+
+ ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
- kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
- gpa, shift);
+ old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
+ gpa, shift);
/* XXX need to flush tlb here? */
+ /* Also clear bit in ptes in shadow pgtable for nested guests */
+ rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+ kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_ACCESSED, 0,
+ old & PTE_RPN_MASK,
+ 1UL << shift);
ref = 1;
}
return ref;
}
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn)
{
@@ -767,7 +1051,10 @@
unsigned int shift;
int ref = 0;
- ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+ return ref;
+
+ ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep))
ref = 1;
return ref;
@@ -779,18 +1066,52 @@
{
unsigned long gfn = memslot->base_gfn + pagenum;
unsigned long gpa = gfn << PAGE_SHIFT;
- pte_t *ptep;
+ pte_t *ptep, pte;
unsigned int shift;
int ret = 0;
+ unsigned long old, *rmapp;
- ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
- if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+ return ret;
+
+ /*
+ * For performance reasons we don't hold kvm->mmu_lock while walking the
+ * partition scoped table.
+ */
+ ptep = find_kvm_secondary_pte_unlocked(kvm, gpa, &shift);
+ if (!ptep)
+ return 0;
+
+ pte = READ_ONCE(*ptep);
+ if (pte_present(pte) && pte_dirty(pte)) {
+ spin_lock(&kvm->mmu_lock);
+ /*
+ * Recheck the pte again
+ */
+ if (pte_val(pte) != pte_val(*ptep)) {
+ /*
+ * We have KVM_MEM_LOG_DIRTY_PAGES enabled. Hence we can
+ * only find PAGE_SIZE pte entries here. We can continue
+ * to use the pte addr returned by above page table
+ * walk.
+ */
+ if (!pte_present(*ptep) || !pte_dirty(*ptep)) {
+ spin_unlock(&kvm->mmu_lock);
+ return 0;
+ }
+ }
+
ret = 1;
- if (shift)
- ret = 1 << (shift - PAGE_SHIFT);
- kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
- gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
+ VM_BUG_ON(shift);
+ old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
+ gpa, shift);
+ kvmppc_radix_tlbie_page(kvm, gpa, shift, kvm->arch.lpid);
+ /* Also clear bit in ptes in shadow pgtable for nested guests */
+ rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+ kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_DIRTY, 0,
+ old & PTE_RPN_MASK,
+ 1UL << shift);
+ spin_unlock(&kvm->mmu_lock);
}
return ret;
}
@@ -818,6 +1139,37 @@
}
}
return 0;
+}
+
+void kvmppc_radix_flush_memslot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ unsigned long n;
+ pte_t *ptep;
+ unsigned long gpa;
+ unsigned int shift;
+
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)
+ kvmppc_uvmem_drop_pages(memslot, kvm, true);
+
+ if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+ return;
+
+ gpa = memslot->base_gfn << PAGE_SHIFT;
+ spin_lock(&kvm->mmu_lock);
+ for (n = memslot->npages; n; --n) {
+ ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
+ if (ptep && pte_present(*ptep))
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+ kvm->arch.lpid);
+ gpa += PAGE_SIZE;
+ }
+ /*
+ * Increase the mmu notifier sequence number to prevent any page
+ * fault that read the memslot earlier from writing a PTE.
+ */
+ kvm->mmu_notifier_seq++;
+ spin_unlock(&kvm->mmu_lock);
}
static void add_rmmu_ap_encoding(struct kvm_ppc_rmmu_info *info,
@@ -875,6 +1227,216 @@
memset(addr, 0, RADIX_PMD_TABLE_SIZE);
}
+struct debugfs_radix_state {
+ struct kvm *kvm;
+ struct mutex mutex;
+ unsigned long gpa;
+ int lpid;
+ int chars_left;
+ int buf_index;
+ char buf[128];
+ u8 hdr;
+};
+
+static int debugfs_radix_open(struct inode *inode, struct file *file)
+{
+ struct kvm *kvm = inode->i_private;
+ struct debugfs_radix_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(kvm);
+ p->kvm = kvm;
+ mutex_init(&p->mutex);
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_radix_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_radix_state *p = file->private_data;
+
+ kvm_put_kvm(p->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_radix_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_radix_state *p = file->private_data;
+ ssize_t ret, r;
+ unsigned long n;
+ struct kvm *kvm;
+ unsigned long gpa;
+ pgd_t *pgt;
+ struct kvm_nested_guest *nested;
+ pgd_t *pgdp;
+ p4d_t p4d, *p4dp;
+ pud_t pud, *pudp;
+ pmd_t pmd, *pmdp;
+ pte_t *ptep;
+ int shift;
+ unsigned long pte;
+
+ kvm = p->kvm;
+ if (!kvm_is_radix(kvm))
+ return 0;
+
+ ret = mutex_lock_interruptible(&p->mutex);
+ if (ret)
+ return ret;
+
+ if (p->chars_left) {
+ n = p->chars_left;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf + p->buf_index, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index += n;
+ buf += n;
+ len -= n;
+ ret = n;
+ if (r) {
+ if (!n)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ gpa = p->gpa;
+ nested = NULL;
+ pgt = NULL;
+ while (len != 0 && p->lpid >= 0) {
+ if (gpa >= RADIX_PGTABLE_RANGE) {
+ gpa = 0;
+ pgt = NULL;
+ if (nested) {
+ kvmhv_put_nested(nested);
+ nested = NULL;
+ }
+ p->lpid = kvmhv_nested_next_lpid(kvm, p->lpid);
+ p->hdr = 0;
+ if (p->lpid < 0)
+ break;
+ }
+ if (!pgt) {
+ if (p->lpid == 0) {
+ pgt = kvm->arch.pgtable;
+ } else {
+ nested = kvmhv_get_nested(kvm, p->lpid, false);
+ if (!nested) {
+ gpa = RADIX_PGTABLE_RANGE;
+ continue;
+ }
+ pgt = nested->shadow_pgtable;
+ }
+ }
+ n = 0;
+ if (!p->hdr) {
+ if (p->lpid > 0)
+ n = scnprintf(p->buf, sizeof(p->buf),
+ "\nNested LPID %d: ", p->lpid);
+ n += scnprintf(p->buf + n, sizeof(p->buf) - n,
+ "pgdir: %lx\n", (unsigned long)pgt);
+ p->hdr = 1;
+ goto copy;
+ }
+
+ pgdp = pgt + pgd_index(gpa);
+ p4dp = p4d_offset(pgdp, gpa);
+ p4d = READ_ONCE(*p4dp);
+ if (!(p4d_val(p4d) & _PAGE_PRESENT)) {
+ gpa = (gpa & P4D_MASK) + P4D_SIZE;
+ continue;
+ }
+
+ pudp = pud_offset(&p4d, gpa);
+ pud = READ_ONCE(*pudp);
+ if (!(pud_val(pud) & _PAGE_PRESENT)) {
+ gpa = (gpa & PUD_MASK) + PUD_SIZE;
+ continue;
+ }
+ if (pud_val(pud) & _PAGE_PTE) {
+ pte = pud_val(pud);
+ shift = PUD_SHIFT;
+ goto leaf;
+ }
+
+ pmdp = pmd_offset(&pud, gpa);
+ pmd = READ_ONCE(*pmdp);
+ if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+ gpa = (gpa & PMD_MASK) + PMD_SIZE;
+ continue;
+ }
+ if (pmd_val(pmd) & _PAGE_PTE) {
+ pte = pmd_val(pmd);
+ shift = PMD_SHIFT;
+ goto leaf;
+ }
+
+ ptep = pte_offset_kernel(&pmd, gpa);
+ pte = pte_val(READ_ONCE(*ptep));
+ if (!(pte & _PAGE_PRESENT)) {
+ gpa += PAGE_SIZE;
+ continue;
+ }
+ shift = PAGE_SHIFT;
+ leaf:
+ n = scnprintf(p->buf, sizeof(p->buf),
+ " %lx: %lx %d\n", gpa, pte, shift);
+ gpa += 1ul << shift;
+ copy:
+ p->chars_left = n;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index = n;
+ buf += n;
+ len -= n;
+ ret += n;
+ if (r) {
+ if (!ret)
+ ret = -EFAULT;
+ break;
+ }
+ }
+ p->gpa = gpa;
+ if (nested)
+ kvmhv_put_nested(nested);
+
+ out:
+ mutex_unlock(&p->mutex);
+ return ret;
+}
+
+static ssize_t debugfs_radix_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_radix_fops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_radix_open,
+ .release = debugfs_radix_release,
+ .read = debugfs_radix_read,
+ .write = debugfs_radix_write,
+ .llseek = generic_file_llseek,
+};
+
+void kvmhv_radix_debugfs_init(struct kvm *kvm)
+{
+ debugfs_create_file("radix", 0400, kvm->arch.debugfs_dir, kvm,
+ &debugfs_radix_fops);
+}
+
int kvmppc_radix_init(void)
{
unsigned long size = sizeof(void *) << RADIX_PTE_INDEX_SIZE;
--
Gitblit v1.6.2