[RFC RESEND 5/6] system/hugetlb_ras: Handle madvise SIGBUS signal on listener

[“William Roche]

From: William Roche <william.roche@oracle.com>

madvise MADV_HWPOISON can generate a SIGBUS when called, so the listener
thread (the caller) needs to deal with this signal.
The signal handler recognizes a thread specific variable allowing it to
directly exit when generated from this thread.

Signed-off-by: William Roche <william.roche@oracle.com>
---
 system/cpus.c          |  9 +++++++++
 system/hugetlbfs_ras.c | 43 ++++++++++++++++++++++++++++++++++++++++--
 system/hugetlbfs_ras.h |  1 +
 3 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/system/cpus.c b/system/cpus.c
index 12e630f760..642055f729 100644
--- a/system/cpus.c
+++ b/system/cpus.c
@@ -47,6 +47,10 @@
 #include "hw/hw.h"
 #include "trace.h"
 
+#ifdef CONFIG_HUGETLBFS_RAS
+#include "system/hugetlbfs_ras.h"
+#endif
+
 #ifdef CONFIG_LINUX
 
 #include <sys/prctl.h>
@@ -374,6 +378,11 @@ static void sigbus_handler(int n, siginfo_t *siginfo, void 
*ctx)
         sigbus_reraise();
     }
 
+#ifdef CONFIG_HUGETLBFS_RAS
+    /* skip error on the listener thread - does not return in this case */
+    hugetlbfs_ras_signal_from_listener();
+#endif
+
     if (current_cpu) {
         /* Called asynchronously in VCPU thread.  */
         if (kvm_on_sigbus_vcpu(current_cpu, siginfo->si_code,
diff --git a/system/hugetlbfs_ras.c b/system/hugetlbfs_ras.c
index 2f7e550f56..90e399bbad 100644
--- a/system/hugetlbfs_ras.c
+++ b/system/hugetlbfs_ras.c
@@ -70,6 +70,8 @@ static QemuCond large_hwpoison_vm_running;
 static QemuMutex large_hwpoison_mtx;
 static QemuThread thread;
 static void *hugetlbfs_ras_listener(void *arg);
+static pthread_key_t id_key;
+static sigjmp_buf listener_jmp_buf;
 static int vm_running;
 static bool hugetlbfs_ras_initialized;
 static int _PAGE_SIZE = 4096;
@@ -105,6 +107,10 @@ hugetlbfs_ras_init(void)
     qemu_cond_init(&large_hwpoison_vm_running);
     qemu_mutex_init(&large_hwpoison_mtx);
 
+    if (pthread_key_create(&id_key, NULL) != 0) {
+        warn_report("No support for hugetlbfs largepage errors - no id_key");
+        return -EIO;
+    }
     qemu_thread_create(&thread, "hugetlbfs_error", hugetlbfs_ras_listener,
                        NULL, QEMU_THREAD_DETACHED);
 
@@ -288,6 +294,19 @@ hugetlbfs_ras_correct(void **paddr, size_t *psz, int code)
     return (*paddr == NULL ? false : true);
 }
 
+/* this madvise can generate a SIGBUS, use the jump buffer to deal with it */
+static bool poison_location(void *addr, int size)
+{
+    if (sigsetjmp(listener_jmp_buf, 1) == 0) {
+        if (madvise(addr, size, MADV_HWPOISON)) {
+            DPRINTF("poison injection failed: %s (addr:%p sz:%d)\n",
+                    strerror(errno), addr, size);
+            return false;
+        }
+    }
+    return true;
+}
+
 /*
  * Sequentially read the valid data from the failed large page (shared) backend
  * file and copy that into our set of standard sized pages.
@@ -321,7 +340,7 @@ static int take_valid_data_lpg(LargeHWPoisonPage *page, 
const char **err)
     slot_num = page->page_size / ps;
 
     if (!qemu_ram_is_shared(rb)) { /* we can't use the backend file */
-        if (madvise(page->page_addr, page->page_size, MADV_HWPOISON) == 0) {
+        if (poison_location(page->page_addr, page->page_size)) {
             page->first_poison = page->page_addr;
             warn_report("Large memory error, unrecoverable section "
                 "(unshared hugetlbfs): start:%p length: %ld",
@@ -350,7 +369,7 @@ static int take_valid_data_lpg(LargeHWPoisonPage *page, 
const char **err)
             retrieved += count;
         }
         if (retrieved < ps) { /* consider this page as poisoned */
-            if (madvise(page->page_addr + i * ps, ps, MADV_HWPOISON)) {
+            if (!poison_location(page->page_addr + i * ps, ps)) {
                 if (err) {
                     *err = "poison injection failed";
                 }
@@ -402,6 +421,19 @@ void hugetlbfs_ras_empty(void)
     qemu_mutex_unlock(&large_hwpoison_mtx);
 }
 
+/*
+ * Check if the signal is taken from the listener thread,
+ * in this thread we don't return as we jump after the madvise call.
+ */
+void
+hugetlbfs_ras_signal_from_listener(void)
+{
+    /* check if we take the SIGBUS in the listener */
+    if (pthread_getspecific(id_key) != NULL) {
+        siglongjmp(listener_jmp_buf, 1);
+    }
+}
+
 /*
  * Deal with the given page, initializing its data.
  */
@@ -498,6 +530,13 @@ hugetlbfs_ras_listener(void *arg)
     LargeHWPoisonPage *page;
     int new;
     const char *err;
+    sigset_t set;
+
+    pthread_setspecific(id_key, (void *)1);
+    /* unblock SIGBUS */
+    sigemptyset(&set);
+    sigaddset(&set, SIGBUS);
+    pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 
     /* monitor any newly submitted element in the list */
     qemu_mutex_lock(&large_hwpoison_mtx);
diff --git a/system/hugetlbfs_ras.h b/system/hugetlbfs_ras.h
index 324228bda3..9c2a6e49a1 100644
--- a/system/hugetlbfs_ras.h
+++ b/system/hugetlbfs_ras.h
@@ -1,3 +1,4 @@
 bool hugetlbfs_ras_use(void);
 bool hugetlbfs_ras_correct(void **paddr, size_t *psz, int code);
 void hugetlbfs_ras_empty(void);
+void hugetlbfs_ras_signal_from_listener(void);
-- 
2.43.5