diff options
author | Alexey Kardashevskiy <aik@ozlabs.ru> | 2020-06-09 12:12:29 +1000 |
---|---|---|
committer | Paul Mackerras <paulus@ozlabs.org> | 2020-07-21 15:38:03 +1000 |
commit | 1508c22f112ce11944cea84efb128a623e8ff03b (patch) | |
tree | 2b3e7322721cb21e2d43b9bb1af5e4c1f00d5a3e /arch/powerpc/kvm/book3s_hv_nested.c | |
parent | e55f4d5898a9855350834535037f62732bbd320a (diff) |
KVM: PPC: Protect kvm_vcpu_read_guest with srcu locks
The kvm_vcpu_read_guest/kvm_vcpu_write_guest used for nested guests
eventually call srcu_dereference_check to dereference a memslot and
lockdep produces a warning as neither kvm->slots_lock nor
kvm->srcu lock is held and kvm->users_count is above zero (>100 in fact).
This wraps mentioned VCPU read/write helpers in srcu read lock/unlock as
it is done in other places. This uses vcpu->srcu_idx when possible.
These helpers are only used for nested KVM so this may explain why
we did not see these before.
Here is an example of a warning:
=============================
WARNING: suspicious RCU usage
5.7.0-rc3-le_dma-bypass.3.2_a+fstn1 #897 Not tainted
-----------------------------
include/linux/kvm_host.h:633 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by qemu-system-ppc/2752:
#0: c000200359016be0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x144/0xd80 [kvm]
stack backtrace:
CPU: 80 PID: 2752 Comm: qemu-system-ppc Not tainted 5.7.0-rc3-le_dma-bypass.3.2_a+fstn1 #897
Call Trace:
[c0002003591ab240] [c000000000b23ab4] dump_stack+0x190/0x25c (unreliable)
[c0002003591ab2b0] [c00000000023f954] lockdep_rcu_suspicious+0x140/0x164
[c0002003591ab330] [c008000004a445f8] kvm_vcpu_gfn_to_memslot+0x4c0/0x510 [kvm]
[c0002003591ab3a0] [c008000004a44c18] kvm_vcpu_read_guest+0xa0/0x180 [kvm]
[c0002003591ab410] [c008000004ff9bd8] kvmhv_enter_nested_guest+0x90/0xb80 [kvm_hv]
[c0002003591ab980] [c008000004fe07bc] kvmppc_pseries_do_hcall+0x7b4/0x1c30 [kvm_hv]
[c0002003591aba10] [c008000004fe5d30] kvmppc_vcpu_run_hv+0x10a8/0x1a30 [kvm_hv]
[c0002003591abae0] [c008000004a5d954] kvmppc_vcpu_run+0x4c/0x70 [kvm]
[c0002003591abb10] [c008000004a56e54] kvm_arch_vcpu_ioctl_run+0x56c/0x7c0 [kvm]
[c0002003591abba0] [c008000004a3ddc4] kvm_vcpu_ioctl+0x4ac/0xd80 [kvm]
[c0002003591abd20] [c0000000006ebb58] ksys_ioctl+0x188/0x210
[c0002003591abd70] [c0000000006ebc28] sys_ioctl+0x48/0xb0
[c0002003591abdb0] [c000000000042764] system_call_exception+0x1d4/0x2e0
[c0002003591abe20] [c00000000000cce8] system_call_common+0xe8/0x214
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_nested.c')
-rw-r--r-- | arch/powerpc/kvm/book3s_hv_nested.c | 30 |
1 files changed, 19 insertions, 11 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 2c849a65db77..6822d23a2da4 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -233,20 +233,21 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); + regs_ptr = kvmppc_get_gpr(vcpu, 5); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); + sizeof(struct hv_guest_state)) || + kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_PARAMETER; + if (kvmppc_need_byteswap(vcpu)) byteswap_hv_regs(&l2_hv); if (l2_hv.version != HV_GUEST_STATE_VERSION) return H_P2; - regs_ptr = kvmppc_get_gpr(vcpu, 5); - err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, - sizeof(struct pt_regs)); - if (err) - return H_PARAMETER; if (kvmppc_need_byteswap(vcpu)) byteswap_pt_regs(&l2_regs); if (l2_hv.vcpu_token >= NR_CPUS) @@ -323,12 +324,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); - if (err) - return H_AUTHORITY; - err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct hv_guest_state)) || + kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_AUTHORITY; @@ -508,12 +509,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; @@ -548,9 +553,12 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp) ret = -EFAULT; ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4); - if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) + if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) { + int srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, ptbl_addr, &ptbl_entry, sizeof(ptbl_entry)); + srcu_read_unlock(&kvm->srcu, srcu_idx); + } if (ret) { gp->l1_gr_to_hr = 0; gp->process_table = 0; |