KVM: x86: fix missed hardware breakpoints

[ Upstream commit 172b2386 ]

Sometimes when setting a breakpoint a process doesn't stop on it.
This is because the debug registers are not loaded correctly on
VCPU load.

The following simple reproducer from Oleg Nesterov tries using debug
registers in two threads.  To see the bug, run a 2-VCPU guest with
"taskset -c 0" and run "./bp 0 1" inside the guest.

    #include <unistd.h>
    #include <signal.h>
    #include <stdlib.h>
    #include <stdio.h>
    #include <sys/wait.h>
    #include <sys/ptrace.h>
    #include <sys/user.h>
    #include <asm/debugreg.h>
    #include <assert.h>

    #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)

    unsigned long encode_dr7(int drnum, int enable, unsigned int type, unsigned int len)
    {
        unsigned long dr7;

        dr7 = ((len | type) & 0xf)
            << (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE);
        if (enable)
            dr7 |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE));

        return dr7;
    }

    int write_dr(int pid, int dr, unsigned long val)
    {
        return ptrace(PTRACE_POKEUSER, pid,
                offsetof (struct user, u_debugreg[dr]),
                val);
    }

    void set_bp(pid_t pid, void *addr)
    {
        unsigned long dr7;
        assert(write_dr(pid, 0, (long)addr) == 0);
        dr7 = encode_dr7(0, 1, DR_RW_EXECUTE, DR_LEN_1);
        assert(write_dr(pid, 7, dr7) == 0);
    }

    void *get_rip(int pid)
    {
        return (void*)ptrace(PTRACE_PEEKUSER, pid,
                offsetof(struct user, regs.rip), 0);
    }

    void test(int nr)
    {
        void *bp_addr = &&label + nr, *bp_hit;
        int pid;

        printf("test bp %d\n", nr);
        assert(nr < 16); // see 16 asm nops below

        pid = fork();
        if (!pid) {
            assert(ptrace(PTRACE_TRACEME, 0,0,0) == 0);
            kill(getpid(), SIGSTOP);
            for (;;) {
                label: asm (
                    "nop; nop; nop; nop;"
                    "nop; nop; nop; nop;"
                    "nop; nop; nop; nop;"
                    "nop; nop; nop; nop;"
                );
            }
        }

        assert(pid == wait(NULL));
        set_bp(pid, bp_addr);

        for (;;) {
            assert(ptrace(PTRACE_CONT, pid, 0, 0) == 0);
            assert(pid == wait(NULL));

            bp_hit = get_rip(pid);
            if (bp_hit != bp_addr)
                fprintf(stderr, "ERR!! hit wrong bp %ld != %d\n",
                    bp_hit - &&label, nr);
        }
    }

    int main(int argc, const char *argv[])
    {
        while (--argc) {
            int nr = atoi(*++argv);
            if (!fork())
                test(nr);
        }

        while (wait(NULL) > 0)
            ;
        return 0;
    }

Cc: stable@vger.kernel.org
Suggested-by: Nadav Amit <namit@cs.technion.ac.il>
Reported-by: Andrey Wagin <avagin@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

arch/x86/kvm/x86.c

@@ -2968,6 +2968,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	accumulate_steal_time(vcpu);
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+	vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)