OpenCloudOS-Kernel/arch/powerpc/kvm/book3s_64_mmu_host.c

408 lines
9.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2009 SUSE Linux Products GmbH. All rights reserved.
*
* Authors:
* Alexander Graf <agraf@suse.de>
* Kevin Wolf <mail@kevin-wolf.de>
*/
#include <linux/kvm_host.h>
#include <linux/pkeys.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/machdep.h>
#include <asm/mmu_context.h>
#include <asm/hw_irq.h>
#include "trace_pr.h"
#include "book3s.h"
#define PTE_SIZE 12
void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
mmu_hash_ops.hpte_invalidate(pte->slot, pte->host_vpn,
pte->pagesize, pte->pagesize,
MMU_SEGSIZE_256M, false);
}
/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
* a hash, so we don't waste cycles on looping */
static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
{
return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
}
static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
{
struct kvmppc_sid_map *map;
u16 sid_map_mask;
if (kvmppc_get_msr(vcpu) & MSR_PR)
gvsid |= VSID_PR;
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
map = &to_book3s(vcpu)->sid_map[sid_map_mask];
if (map->valid && (map->guest_vsid == gvsid)) {
trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
return map;
}
map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
if (map->valid && (map->guest_vsid == gvsid)) {
trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
return map;
}
trace_kvm_book3s_slb_fail(sid_map_mask, gvsid);
return NULL;
}
KVM: PPC: Book3S PR: Better handling of host-side read-only pages Currently we request write access to all pages that get mapped into the guest, even if the guest is only loading from the page. This reduces the effectiveness of KSM because it means that we unshare every page we access. Also, we always set the changed (C) bit in the guest HPTE if it allows writing, even for a guest load. This fixes both these problems. We pass an 'iswrite' flag to the mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether the access is a load or a store. The mmu.xlate() functions now only set C for stores. kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot() instead of gfn_to_pfn() so that it can indicate whether we need write access to the page, and get back a 'writable' flag to indicate whether the page is writable or not. If that 'writable' flag is clear, we then make the host HPTE read-only even if the guest HPTE allowed writing. This means that we can get a protection fault when the guest writes to a page that it has mapped read-write but which is read-only on the host side (perhaps due to KSM having merged the page). Thus we now call kvmppc_handle_pagefault() for protection faults as well as HPTE not found faults. In kvmppc_handle_pagefault(), if the access was allowed by the guest HPTE and we thus need to install a new host HPTE, we then need to remove the old host HPTE if there is one. This is done with a new function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to find and remove the old host HPTE. Since the memslot-related functions require the KVM SRCU read lock to be held, this adds srcu_read_lock/unlock pairs around the calls to kvmppc_handle_pagefault(). Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore guest HPTEs that don't permit access, and to return -EPERM for accesses that are not permitted by the page protections. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:51 +08:00
int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
bool iswrite)
{
unsigned long vpn;
kvm: rename pfn_t to kvm_pfn_t To date, we have implemented two I/O usage models for persistent memory, PMEM (a persistent "ram disk") and DAX (mmap persistent memory into userspace). This series adds a third, DAX-GUP, that allows DAX mappings to be the target of direct-i/o. It allows userspace to coordinate DMA/RDMA from/to persistent memory. The implementation leverages the ZONE_DEVICE mm-zone that went into 4.3-rc1 (also discussed at kernel summit) to flag pages that are owned and dynamically mapped by a device driver. The pmem driver, after mapping a persistent memory range into the system memmap via devm_memremap_pages(), arranges for DAX to distinguish pfn-only versus page-backed pmem-pfns via flags in the new pfn_t type. The DAX code, upon seeing a PFN_DEV+PFN_MAP flagged pfn, flags the resulting pte(s) inserted into the process page tables with a new _PAGE_DEVMAP flag. Later, when get_user_pages() is walking ptes it keys off _PAGE_DEVMAP to pin the device hosting the page range active. Finally, get_page() and put_page() are modified to take references against the device driver established page mapping. Finally, this need for "struct page" for persistent memory requires memory capacity to store the memmap array. Given the memmap array for a large pool of persistent may exhaust available DRAM introduce a mechanism to allocate the memmap from persistent memory. The new "struct vmem_altmap *" parameter to devm_memremap_pages() enables arch_add_memory() to use reserved pmem capacity rather than the page allocator. This patch (of 18): The core has developed a need for a "pfn_t" type [1]. Move the existing pfn_t in KVM to kvm_pfn_t [2]. [1]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002199.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002218.html Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Christoffer Dall <christoffer.dall@linaro.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:56:11 +08:00
kvm_pfn_t hpaddr;
ulong hash, hpteg;
u64 vsid;
int ret;
int rflags = 0x192;
int vflags = 0;
int attempt = 0;
struct kvmppc_sid_map *map;
int r = 0;
int hpsize = MMU_PAGE_4K;
KVM: PPC: Book3S PR: Better handling of host-side read-only pages Currently we request write access to all pages that get mapped into the guest, even if the guest is only loading from the page. This reduces the effectiveness of KSM because it means that we unshare every page we access. Also, we always set the changed (C) bit in the guest HPTE if it allows writing, even for a guest load. This fixes both these problems. We pass an 'iswrite' flag to the mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether the access is a load or a store. The mmu.xlate() functions now only set C for stores. kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot() instead of gfn_to_pfn() so that it can indicate whether we need write access to the page, and get back a 'writable' flag to indicate whether the page is writable or not. If that 'writable' flag is clear, we then make the host HPTE read-only even if the guest HPTE allowed writing. This means that we can get a protection fault when the guest writes to a page that it has mapped read-write but which is read-only on the host side (perhaps due to KSM having merged the page). Thus we now call kvmppc_handle_pagefault() for protection faults as well as HPTE not found faults. In kvmppc_handle_pagefault(), if the access was allowed by the guest HPTE and we thus need to install a new host HPTE, we then need to remove the old host HPTE if there is one. This is done with a new function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to find and remove the old host HPTE. Since the memslot-related functions require the KVM SRCU read lock to be held, this adds srcu_read_lock/unlock pairs around the calls to kvmppc_handle_pagefault(). Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore guest HPTEs that don't permit access, and to return -EPERM for accesses that are not permitted by the page protections. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:51 +08:00
bool writable;
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
unsigned long mmu_seq;
struct kvm *kvm = vcpu->kvm;
struct hpte_cache *cpte;
unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT;
unsigned long pfn;
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_notifier_seq;
smp_rmb();
/* Get host physical address for gpa */
pfn = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable);
if (is_error_noslot_pfn(pfn)) {
printk(KERN_INFO "Couldn't get guest page for gpa %lx!\n",
orig_pte->raddr);
r = -EINVAL;
goto out;
}
hpaddr = pfn << PAGE_SHIFT;
/* and write the mapping ea -> hpa into the pt */
vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
map = find_sid_vsid(vcpu, vsid);
if (!map) {
ret = kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr);
WARN_ON(ret < 0);
map = find_sid_vsid(vcpu, vsid);
}
if (!map) {
printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n",
vsid, orig_pte->eaddr);
WARN_ON(true);
r = -EINVAL;
goto out;
}
vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
kvm_set_pfn_accessed(pfn);
KVM: PPC: Book3S PR: Better handling of host-side read-only pages Currently we request write access to all pages that get mapped into the guest, even if the guest is only loading from the page. This reduces the effectiveness of KSM because it means that we unshare every page we access. Also, we always set the changed (C) bit in the guest HPTE if it allows writing, even for a guest load. This fixes both these problems. We pass an 'iswrite' flag to the mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether the access is a load or a store. The mmu.xlate() functions now only set C for stores. kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot() instead of gfn_to_pfn() so that it can indicate whether we need write access to the page, and get back a 'writable' flag to indicate whether the page is writable or not. If that 'writable' flag is clear, we then make the host HPTE read-only even if the guest HPTE allowed writing. This means that we can get a protection fault when the guest writes to a page that it has mapped read-write but which is read-only on the host side (perhaps due to KSM having merged the page). Thus we now call kvmppc_handle_pagefault() for protection faults as well as HPTE not found faults. In kvmppc_handle_pagefault(), if the access was allowed by the guest HPTE and we thus need to install a new host HPTE, we then need to remove the old host HPTE if there is one. This is done with a new function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to find and remove the old host HPTE. Since the memslot-related functions require the KVM SRCU read lock to be held, this adds srcu_read_lock/unlock pairs around the calls to kvmppc_handle_pagefault(). Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore guest HPTEs that don't permit access, and to return -EPERM for accesses that are not permitted by the page protections. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:51 +08:00
if (!orig_pte->may_write || !writable)
rflags |= PP_RXRX;
else {
mark_page_dirty(vcpu->kvm, gfn);
kvm_set_pfn_dirty(pfn);
}
if (!orig_pte->may_execute)
rflags |= HPTE_R_N;
else
kvmppc_mmu_flush_icache(pfn);
powerpc/kvm: Fix PR KVM with KUAP/MEM_KEYS enabled The changes to add KUAP support with the hash MMU broke booting of KVM PR guests. The symptom is no visible progress of the guest, or possibly just "SLOF" being printed to the qemu console. Host code is still executing, but breaking into xmon might show a stack trace such as: __might_fault+0x84/0xe0 (unreliable) kvm_read_guest+0x1c8/0x2f0 [kvm] kvmppc_ld+0x1b8/0x2d0 [kvm] kvmppc_load_last_inst+0x50/0xa0 [kvm] kvmppc_exit_pr_progint+0x178/0x220 [kvm_pr] kvmppc_handle_exit_pr+0x31c/0xe30 [kvm_pr] after_sprg3_load+0x80/0x90 [kvm_pr] kvmppc_vcpu_run_pr+0x104/0x260 [kvm_pr] kvmppc_vcpu_run+0x34/0x48 [kvm] kvm_arch_vcpu_ioctl_run+0x340/0x450 [kvm] kvm_vcpu_ioctl+0x2ac/0x8c0 [kvm] sys_ioctl+0x320/0x1060 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c Bisect points to commit b2ff33a10c8b ("powerpc/book3s64/hash/kuap: Enable kuap on hash"), but that's just the commit that enabled KUAP with hash and made the bug visible. The root cause seems to be that KVM PR is creating kernel mappings that don't use the correct key, since we switched to using key 3. We have a helper for adding the right key value, however it's designed to take a pteflags variable, which the KVM code doesn't have. But we can make it work by passing 0 for the pteflags, and tell it explicitly that it should use the kernel key. With that changed guests boot successfully. Fixes: d94b827e89dc ("powerpc/book3s64/kuap: Use Key 3 for kernel mapping with hash translation") Cc: stable@vger.kernel.org # v5.11+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20210419120139.1455937-1-mpe@ellerman.id.au
2021-04-19 20:01:39 +08:00
rflags |= pte_to_hpte_pkey_bits(0, HPTE_USE_KERNEL_KEY);
rflags = (rflags & ~HPTE_R_WIMG) | orig_pte->wimg;
/*
* Use 64K pages if possible; otherwise, on 64K page kernels,
* we need to transfer 4 more bits from guest real to host real addr.
*/
if (vsid & VSID_64K)
hpsize = MMU_PAGE_64K;
else
hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M);
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
cpte = kvmppc_mmu_hpte_cache_next(vcpu);
spin_lock(&kvm->mmu_lock);
if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
r = -EAGAIN;
goto out_unlock;
}
map_again:
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
/* In case we tried normal mapping already, let's nuke old entries */
if (attempt > 1)
if (mmu_hash_ops.hpte_remove(hpteg) < 0) {
r = -1;
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
goto out_unlock;
}
ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
hpsize, hpsize, MMU_SEGSIZE_256M);
if (ret == -1) {
/* If we couldn't map a primary PTE, try a secondary */
hash = ~hash;
vflags ^= HPTE_V_SECONDARY;
attempt++;
goto map_again;
} else if (ret < 0) {
r = -EIO;
goto out_unlock;
} else {
trace_kvm_book3s_64_mmu_map(rflags, hpteg,
vpn, hpaddr, orig_pte);
/*
* The mmu_hash_ops code may give us a secondary entry even
* though we asked for a primary. Fix up.
*/
if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) {
hash = ~hash;
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
}
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
cpte->slot = hpteg + (ret & 7);
cpte->host_vpn = vpn;
cpte->pte = *orig_pte;
cpte->pfn = pfn;
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
cpte->pagesize = hpsize;
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
kvmppc_mmu_hpte_cache_map(vcpu, cpte);
cpte = NULL;
}
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
out_unlock:
spin_unlock(&kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
KVM: PPC: Book3S PR: Use mmu_notifier_retry() in kvmppc_mmu_map_page() When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the existing host HPTEs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been getting a page and instantiating a host HPTE for the page. This therefore adds a call to mmu_notifier_retry inside kvmppc_mmu_map_page(). This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Inside this region we also create the host HPTE and link the corresponding hpte_cache structure into the lists used to find it later. We cannot allocate the hpte_cache structure inside this locked region because that can lead to deadlock, so we allocate it outside the region and free it if we end up not using it. This also moves the updates of vcpu3s->hpte_cache_count inside the regions locked with vcpu3s->mmu_lock, and does the increment in kvmppc_mmu_hpte_cache_map() when the pte is added to the cache rather than when it is allocated, in order that the hpte_cache_count is accurate. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:52 +08:00
if (cpte)
kvmppc_mmu_hpte_cache_free(cpte);
out:
return r;
}
KVM: PPC: Book3S PR: Better handling of host-side read-only pages Currently we request write access to all pages that get mapped into the guest, even if the guest is only loading from the page. This reduces the effectiveness of KSM because it means that we unshare every page we access. Also, we always set the changed (C) bit in the guest HPTE if it allows writing, even for a guest load. This fixes both these problems. We pass an 'iswrite' flag to the mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether the access is a load or a store. The mmu.xlate() functions now only set C for stores. kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot() instead of gfn_to_pfn() so that it can indicate whether we need write access to the page, and get back a 'writable' flag to indicate whether the page is writable or not. If that 'writable' flag is clear, we then make the host HPTE read-only even if the guest HPTE allowed writing. This means that we can get a protection fault when the guest writes to a page that it has mapped read-write but which is read-only on the host side (perhaps due to KSM having merged the page). Thus we now call kvmppc_handle_pagefault() for protection faults as well as HPTE not found faults. In kvmppc_handle_pagefault(), if the access was allowed by the guest HPTE and we thus need to install a new host HPTE, we then need to remove the old host HPTE if there is one. This is done with a new function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to find and remove the old host HPTE. Since the memslot-related functions require the KVM SRCU read lock to be held, this adds srcu_read_lock/unlock pairs around the calls to kvmppc_handle_pagefault(). Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore guest HPTEs that don't permit access, and to return -EPERM for accesses that are not permitted by the page protections. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2013-09-20 12:52:51 +08:00
void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
{
u64 mask = 0xfffffffffULL;
u64 vsid;
vcpu->arch.mmu.esid_to_vsid(vcpu, pte->eaddr >> SID_SHIFT, &vsid);
if (vsid & VSID_64K)
mask = 0xffffffff0ULL;
kvmppc_mmu_pte_vflush(vcpu, pte->vpage, mask);
}
static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
{
unsigned long vsid_bits = VSID_BITS_65_256M;
struct kvmppc_sid_map *map;
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
u16 sid_map_mask;
static int backwards_map = 0;
if (kvmppc_get_msr(vcpu) & MSR_PR)
gvsid |= VSID_PR;
/* We might get collisions that trap in preceding order, so let's
map them differently */
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
if (backwards_map)
sid_map_mask = SID_MAP_MASK - sid_map_mask;
map = &to_book3s(vcpu)->sid_map[sid_map_mask];
/* Make sure we're taking the other map next time */
backwards_map = !backwards_map;
/* Uh-oh ... out of mappings. Let's flush! */
if (vcpu_book3s->proto_vsid_next == vcpu_book3s->proto_vsid_max) {
vcpu_book3s->proto_vsid_next = vcpu_book3s->proto_vsid_first;
memset(vcpu_book3s->sid_map, 0,
sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
kvmppc_mmu_pte_flush(vcpu, 0, 0);
kvmppc_mmu_flush_segments(vcpu);
}
if (mmu_has_feature(MMU_FTR_68_BIT_VA))
vsid_bits = VSID_BITS_256M;
map->host_vsid = vsid_scramble(vcpu_book3s->proto_vsid_next++,
VSID_MULTIPLIER_256M, vsid_bits);
map->guest_vsid = gvsid;
map->valid = true;
trace_kvm_book3s_slb_map(sid_map_mask, gvsid, map->host_vsid);
return map;
}
static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
int i;
int max_slb_size = 64;
int found_inval = -1;
int r;
/* Are we overwriting? */
for (i = 0; i < svcpu->slb_max; i++) {
if (!(svcpu->slb[i].esid & SLB_ESID_V))
found_inval = i;
else if ((svcpu->slb[i].esid & ESID_MASK) == esid) {
r = i;
goto out;
}
}
/* Found a spare entry that was invalidated before */
if (found_inval >= 0) {
r = found_inval;
goto out;
}
/* No spare invalid entry, so create one */
if (mmu_slb_size < 64)
max_slb_size = mmu_slb_size;
/* Overflowing -> purge */
if ((svcpu->slb_max) == max_slb_size)
kvmppc_mmu_flush_segments(vcpu);
r = svcpu->slb_max;
svcpu->slb_max++;
out:
svcpu_put(svcpu);
return r;
}
int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
u64 esid = eaddr >> SID_SHIFT;
u64 slb_esid = (eaddr & ESID_MASK) | SLB_ESID_V;
u64 slb_vsid = SLB_VSID_USER;
u64 gvsid;
int slb_index;
struct kvmppc_sid_map *map;
int r = 0;
slb_index = kvmppc_mmu_next_segment(vcpu, eaddr & ESID_MASK);
if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
/* Invalidate an entry */
svcpu->slb[slb_index].esid = 0;
r = -ENOENT;
goto out;
}
map = find_sid_vsid(vcpu, gvsid);
if (!map)
map = create_sid_map(vcpu, gvsid);
map->guest_esid = esid;
slb_vsid |= (map->host_vsid << 12);
slb_vsid &= ~SLB_VSID_KP;
slb_esid |= slb_index;
#ifdef CONFIG_PPC_64K_PAGES
/* Set host segment base page size to 64K if possible */
if (gvsid & VSID_64K)
slb_vsid |= mmu_psize_defs[MMU_PAGE_64K].sllp;
#endif
svcpu->slb[slb_index].esid = slb_esid;
svcpu->slb[slb_index].vsid = slb_vsid;
trace_kvm_book3s_slbmte(slb_vsid, slb_esid);
out:
svcpu_put(svcpu);
return r;
}
void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong ea, ulong seg_size)
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
ulong seg_mask = -seg_size;
int i;
for (i = 0; i < svcpu->slb_max; i++) {
if ((svcpu->slb[i].esid & SLB_ESID_V) &&
(svcpu->slb[i].esid & seg_mask) == ea) {
/* Invalidate this entry */
svcpu->slb[i].esid = 0;
}
}
svcpu_put(svcpu);
}
void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
{
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
svcpu->slb_max = 0;
svcpu->slb[0].esid = 0;
svcpu_put(svcpu);
}
void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
{
kvmppc_mmu_hpte_destroy(vcpu);
__destroy_context(to_book3s(vcpu)->context_id[0]);
}
int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
int err;
err = hash__alloc_context_id();
if (err < 0)
return -1;
vcpu3s->context_id[0] = err;
vcpu3s->proto_vsid_max = ((u64)(vcpu3s->context_id[0] + 1)
<< ESID_BITS) - 1;
vcpu3s->proto_vsid_first = (u64)vcpu3s->context_id[0] << ESID_BITS;
vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first;
kvmppc_mmu_hpte_init(vcpu);
return 0;
}