181 lines
4.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
#include "mmu_internal.h"
#include "tdp_iter.h"
#include "spte.h"
/*
* Recalculates the pointer to the SPTE for the current GFN and level and
* reread the SPTE.
*/
static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
{
iter->sptep = iter->pt_path[iter->level - 1] +
SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
}
static gfn_t round_gfn_for_level(gfn_t gfn, int level)
{
return gfn & -KVM_PAGES_PER_HPAGE(level);
}
/*
* Return the TDP iterator to the root PT and allow it to continue its
* traversal over the paging structure from there.
*/
void tdp_iter_restart(struct tdp_iter *iter)
{
KVM: x86/mmu: Don't advance iterator after restart due to yielding After dropping mmu_lock in the TDP MMU, restart the iterator during tdp_iter_next() and do not advance the iterator. Advancing the iterator results in skipping the top-level SPTE and all its children, which is fatal if any of the skipped SPTEs were not visited before yielding. When zapping all SPTEs, i.e. when min_level == root_level, restarting the iter and then invoking tdp_iter_next() is always fatal if the current gfn has as a valid SPTE, as advancing the iterator results in try_step_side() skipping the current gfn, which wasn't visited before yielding. Sprinkle WARNs on iter->yielded being true in various helpers that are often used in conjunction with yielding, and tag the helper with __must_check to reduce the probabily of improper usage. Failing to zap a top-level SPTE manifests in one of two ways. If a valid SPTE is skipped by both kvm_tdp_mmu_zap_all() and kvm_tdp_mmu_put_root(), the shadow page will be leaked and KVM will WARN accordingly. WARNING: CPU: 1 PID: 3509 at arch/x86/kvm/mmu/tdp_mmu.c:46 [kvm] RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x3e/0x50 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2a0 [kvm] kvm_vcpu_release+0x34/0x60 [kvm] __fput+0x82/0x240 task_work_run+0x5c/0x90 do_exit+0x364/0xa10 ? futex_unqueue+0x38/0x60 do_group_exit+0x33/0xa0 get_signal+0x155/0x850 arch_do_signal_or_restart+0xed/0x750 exit_to_user_mode_prepare+0xc5/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae If kvm_tdp_mmu_zap_all() skips a gfn/SPTE but that SPTE is then zapped by kvm_tdp_mmu_put_root(), KVM triggers a use-after-free in the form of marking a struct page as dirty/accessed after it has been put back on the free list. This directly triggers a WARN due to encountering a page with page_count() == 0, but it can also lead to data corruption and additional errors in the kernel. WARNING: CPU: 7 PID: 1995658 at arch/x86/kvm/../../../virt/kvm/kvm_main.c:171 RIP: 0010:kvm_is_zone_device_pfn.part.0+0x9e/0xd0 [kvm] Call Trace: <TASK> kvm_set_pfn_dirty+0x120/0x1d0 [kvm] __handle_changed_spte+0x92e/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] zap_gfn_range+0x549/0x620 [kvm] kvm_tdp_mmu_put_root+0x1b6/0x270 [kvm] mmu_free_root_page+0x219/0x2c0 [kvm] kvm_mmu_free_roots+0x1b4/0x4e0 [kvm] kvm_mmu_unload+0x1c/0xa0 [kvm] kvm_arch_destroy_vm+0x1f2/0x5c0 [kvm] kvm_put_kvm+0x3b1/0x8b0 [kvm] kvm_vcpu_release+0x4e/0x70 [kvm] __fput+0x1f7/0x8c0 task_work_run+0xf8/0x1a0 do_exit+0x97b/0x2230 do_group_exit+0xda/0x2a0 get_signal+0x3be/0x1e50 arch_do_signal_or_restart+0x244/0x17f0 exit_to_user_mode_prepare+0xcb/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x4d/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Note, the underlying bug existed even before commit 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") moved calls to tdp_mmu_iter_cond_resched() to the beginning of loops, as KVM could still incorrectly advance past a top-level entry when yielding on a lower-level entry. But with respect to leaking shadow pages, the bug was introduced by yielding before processing the current gfn. Alternatively, tdp_mmu_iter_cond_resched() could simply fall through, or callers could jump to their "retry" label. The downside of that approach is that tdp_mmu_iter_cond_resched() _must_ be called before anything else in the loop, and there's no easy way to enfornce that requirement. Ideally, KVM would handling the cond_resched() fully within the iterator macro (the code is actually quite clean) and avoid this entire class of bugs, but that is extremely difficult do while also supporting yielding after tdp_mmu_set_spte_atomic() fails. Yielding after failing to set a SPTE is very desirable as the "owner" of the REMOVED_SPTE isn't strictly bounded, e.g. if it's zapping a high-level shadow page, the REMOVED_SPTE may block operations on the SPTE for a significant amount of time. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") Reported-by: Ignat Korchagin <ignat@cloudflare.com> Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <seanjc@google.com> Message-Id: <20211214033528.123268-1-seanjc@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-12-14 03:35:28 +00:00
iter->yielded = false;
iter->yielded_gfn = iter->next_last_level_gfn;
iter->level = iter->root_level;
iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
tdp_iter_refresh_sptep(iter);
iter->valid = true;
}
/*
* Sets a TDP iterator to walk a pre-order traversal of the paging structure
* rooted at root_pt, starting with the walk to translate next_last_level_gfn.
*/
void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
int min_level, gfn_t next_last_level_gfn)
{
int root_level = root->role.level;
WARN_ON(root_level < 1);
WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
iter->next_last_level_gfn = next_last_level_gfn;
iter->root_level = root_level;
iter->min_level = min_level;
iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt;
iter->as_id = kvm_mmu_page_as_id(root);
tdp_iter_restart(iter);
}
/*
* Given an SPTE and its level, returns a pointer containing the host virtual
* address of the child page table referenced by the SPTE. Returns null if
* there is no such entry.
*/
KVM: x86/mmu: Protect TDP MMU page table memory with RCU In order to enable concurrent modifications to the paging structures in the TDP MMU, threads must be able to safely remove pages of page table memory while other threads are traversing the same memory. To ensure threads do not access PT memory after it is freed, protect PT memory with RCU. Protecting concurrent accesses to page table memory from use-after-free bugs could also have been acomplished using walk_shadow_page_lockless_begin/end() and READING_SHADOW_PAGE_TABLES, coupling with the barriers in a TLB flush. The use of RCU for this case has several distinct advantages over that approach. 1. Disabling interrupts for long running operations is not desirable. Future commits will allow operations besides page faults to operate without the exclusive protection of the MMU lock and those operations are too long to disable iterrupts for their duration. 2. The use of RCU here avoids long blocking / spinning operations in perfromance critical paths. By freeing memory with an asynchronous RCU API we avoid the longer wait times TLB flushes experience when overlapping with a thread in walk_shadow_page_lockless_begin/end(). 3. RCU provides a separation of concerns when removing memory from the paging structure. Because the RCU callback to free memory can be scheduled immediately after a TLB flush, there's no need for the thread to manually free a queue of pages later, as commit_zap_pages does. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Reviewed-by: Peter Feiner <pfeiner@google.com> Suggested-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Ben Gardon <bgardon@google.com> Message-Id: <20210202185734.1680553-18-bgardon@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-02-02 10:57:23 -08:00
tdp_ptep_t spte_to_child_pt(u64 spte, int level)
{
/*
* There's no child entry if this entry isn't present or is a
* last-level entry.
*/
if (!is_shadow_present_pte(spte) || is_last_spte(spte, level))
return NULL;
KVM: x86/mmu: Protect TDP MMU page table memory with RCU In order to enable concurrent modifications to the paging structures in the TDP MMU, threads must be able to safely remove pages of page table memory while other threads are traversing the same memory. To ensure threads do not access PT memory after it is freed, protect PT memory with RCU. Protecting concurrent accesses to page table memory from use-after-free bugs could also have been acomplished using walk_shadow_page_lockless_begin/end() and READING_SHADOW_PAGE_TABLES, coupling with the barriers in a TLB flush. The use of RCU for this case has several distinct advantages over that approach. 1. Disabling interrupts for long running operations is not desirable. Future commits will allow operations besides page faults to operate without the exclusive protection of the MMU lock and those operations are too long to disable iterrupts for their duration. 2. The use of RCU here avoids long blocking / spinning operations in perfromance critical paths. By freeing memory with an asynchronous RCU API we avoid the longer wait times TLB flushes experience when overlapping with a thread in walk_shadow_page_lockless_begin/end(). 3. RCU provides a separation of concerns when removing memory from the paging structure. Because the RCU callback to free memory can be scheduled immediately after a TLB flush, there's no need for the thread to manually free a queue of pages later, as commit_zap_pages does. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Reviewed-by: Peter Feiner <pfeiner@google.com> Suggested-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Ben Gardon <bgardon@google.com> Message-Id: <20210202185734.1680553-18-bgardon@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-02-02 10:57:23 -08:00
return (tdp_ptep_t)__va(spte_to_pfn(spte) << PAGE_SHIFT);
}
/*
* Steps down one level in the paging structure towards the goal GFN. Returns
* true if the iterator was able to step down a level, false otherwise.
*/
static bool try_step_down(struct tdp_iter *iter)
{
KVM: x86/mmu: Protect TDP MMU page table memory with RCU In order to enable concurrent modifications to the paging structures in the TDP MMU, threads must be able to safely remove pages of page table memory while other threads are traversing the same memory. To ensure threads do not access PT memory after it is freed, protect PT memory with RCU. Protecting concurrent accesses to page table memory from use-after-free bugs could also have been acomplished using walk_shadow_page_lockless_begin/end() and READING_SHADOW_PAGE_TABLES, coupling with the barriers in a TLB flush. The use of RCU for this case has several distinct advantages over that approach. 1. Disabling interrupts for long running operations is not desirable. Future commits will allow operations besides page faults to operate without the exclusive protection of the MMU lock and those operations are too long to disable iterrupts for their duration. 2. The use of RCU here avoids long blocking / spinning operations in perfromance critical paths. By freeing memory with an asynchronous RCU API we avoid the longer wait times TLB flushes experience when overlapping with a thread in walk_shadow_page_lockless_begin/end(). 3. RCU provides a separation of concerns when removing memory from the paging structure. Because the RCU callback to free memory can be scheduled immediately after a TLB flush, there's no need for the thread to manually free a queue of pages later, as commit_zap_pages does. Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU") Reviewed-by: Peter Feiner <pfeiner@google.com> Suggested-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Ben Gardon <bgardon@google.com> Message-Id: <20210202185734.1680553-18-bgardon@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-02-02 10:57:23 -08:00
tdp_ptep_t child_pt;
if (iter->level == iter->min_level)
return false;
/*
* Reread the SPTE before stepping down to avoid traversing into page
* tables that are no longer linked from this entry.
*/
iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
child_pt = spte_to_child_pt(iter->old_spte, iter->level);
if (!child_pt)
return false;
iter->level--;
iter->pt_path[iter->level - 1] = child_pt;
iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
tdp_iter_refresh_sptep(iter);
return true;
}
/*
* Steps to the next entry in the current page table, at the current page table
* level. The next entry could point to a page backing guest memory or another
* page table, or it could be non-present. Returns true if the iterator was
* able to step to the next entry in the page table, false if the iterator was
* already at the end of the current page table.
*/
static bool try_step_side(struct tdp_iter *iter)
{
/*
* Check if the iterator is already at the end of the current page
* table.
*/
if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) ==
(SPTE_ENT_PER_PAGE - 1))
return false;
iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
iter->next_last_level_gfn = iter->gfn;
iter->sptep++;
iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
return true;
}
/*
* Tries to traverse back up a level in the paging structure so that the walk
* can continue from the next entry in the parent page table. Returns true on a
* successful step up, false if already in the root page.
*/
static bool try_step_up(struct tdp_iter *iter)
{
if (iter->level == iter->root_level)
return false;
iter->level++;
iter->gfn = round_gfn_for_level(iter->gfn, iter->level);
tdp_iter_refresh_sptep(iter);
return true;
}
/*
* Step to the next SPTE in a pre-order traversal of the paging structure.
* To get to the next SPTE, the iterator either steps down towards the goal
* GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a
* highter GFN.
*
* The basic algorithm is as follows:
* 1. If the current SPTE is a non-last-level SPTE, step down into the page
* table it points to.
* 2. If the iterator cannot step down, it will try to step to the next SPTE
* in the current page of the paging structure.
* 3. If the iterator cannot step to the next entry in the current page, it will
* try to step up to the parent paging structure page. In this case, that
* SPTE will have already been visited, and so the iterator must also step
* to the side again.
*/
void tdp_iter_next(struct tdp_iter *iter)
{
KVM: x86/mmu: Don't advance iterator after restart due to yielding After dropping mmu_lock in the TDP MMU, restart the iterator during tdp_iter_next() and do not advance the iterator. Advancing the iterator results in skipping the top-level SPTE and all its children, which is fatal if any of the skipped SPTEs were not visited before yielding. When zapping all SPTEs, i.e. when min_level == root_level, restarting the iter and then invoking tdp_iter_next() is always fatal if the current gfn has as a valid SPTE, as advancing the iterator results in try_step_side() skipping the current gfn, which wasn't visited before yielding. Sprinkle WARNs on iter->yielded being true in various helpers that are often used in conjunction with yielding, and tag the helper with __must_check to reduce the probabily of improper usage. Failing to zap a top-level SPTE manifests in one of two ways. If a valid SPTE is skipped by both kvm_tdp_mmu_zap_all() and kvm_tdp_mmu_put_root(), the shadow page will be leaked and KVM will WARN accordingly. WARNING: CPU: 1 PID: 3509 at arch/x86/kvm/mmu/tdp_mmu.c:46 [kvm] RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x3e/0x50 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2a0 [kvm] kvm_vcpu_release+0x34/0x60 [kvm] __fput+0x82/0x240 task_work_run+0x5c/0x90 do_exit+0x364/0xa10 ? futex_unqueue+0x38/0x60 do_group_exit+0x33/0xa0 get_signal+0x155/0x850 arch_do_signal_or_restart+0xed/0x750 exit_to_user_mode_prepare+0xc5/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae If kvm_tdp_mmu_zap_all() skips a gfn/SPTE but that SPTE is then zapped by kvm_tdp_mmu_put_root(), KVM triggers a use-after-free in the form of marking a struct page as dirty/accessed after it has been put back on the free list. This directly triggers a WARN due to encountering a page with page_count() == 0, but it can also lead to data corruption and additional errors in the kernel. WARNING: CPU: 7 PID: 1995658 at arch/x86/kvm/../../../virt/kvm/kvm_main.c:171 RIP: 0010:kvm_is_zone_device_pfn.part.0+0x9e/0xd0 [kvm] Call Trace: <TASK> kvm_set_pfn_dirty+0x120/0x1d0 [kvm] __handle_changed_spte+0x92e/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] zap_gfn_range+0x549/0x620 [kvm] kvm_tdp_mmu_put_root+0x1b6/0x270 [kvm] mmu_free_root_page+0x219/0x2c0 [kvm] kvm_mmu_free_roots+0x1b4/0x4e0 [kvm] kvm_mmu_unload+0x1c/0xa0 [kvm] kvm_arch_destroy_vm+0x1f2/0x5c0 [kvm] kvm_put_kvm+0x3b1/0x8b0 [kvm] kvm_vcpu_release+0x4e/0x70 [kvm] __fput+0x1f7/0x8c0 task_work_run+0xf8/0x1a0 do_exit+0x97b/0x2230 do_group_exit+0xda/0x2a0 get_signal+0x3be/0x1e50 arch_do_signal_or_restart+0x244/0x17f0 exit_to_user_mode_prepare+0xcb/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x4d/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Note, the underlying bug existed even before commit 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") moved calls to tdp_mmu_iter_cond_resched() to the beginning of loops, as KVM could still incorrectly advance past a top-level entry when yielding on a lower-level entry. But with respect to leaking shadow pages, the bug was introduced by yielding before processing the current gfn. Alternatively, tdp_mmu_iter_cond_resched() could simply fall through, or callers could jump to their "retry" label. The downside of that approach is that tdp_mmu_iter_cond_resched() _must_ be called before anything else in the loop, and there's no easy way to enfornce that requirement. Ideally, KVM would handling the cond_resched() fully within the iterator macro (the code is actually quite clean) and avoid this entire class of bugs, but that is extremely difficult do while also supporting yielding after tdp_mmu_set_spte_atomic() fails. Yielding after failing to set a SPTE is very desirable as the "owner" of the REMOVED_SPTE isn't strictly bounded, e.g. if it's zapping a high-level shadow page, the REMOVED_SPTE may block operations on the SPTE for a significant amount of time. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") Reported-by: Ignat Korchagin <ignat@cloudflare.com> Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <seanjc@google.com> Message-Id: <20211214033528.123268-1-seanjc@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-12-14 03:35:28 +00:00
if (iter->yielded) {
tdp_iter_restart(iter);
return;
}
if (try_step_down(iter))
return;
do {
if (try_step_side(iter))
return;
} while (try_step_up(iter));
iter->valid = false;
}