drm/i915: avoid big kmallocs on reading error state
Sometimes when user is trying to get error state out from
debugfs after gpu hang, the memory is low and/or fragmented
enough that kmalloc in seq_file will fail.
Prevent big kmalloc by avoiding seq_file and instead convert
error state to string in smaller chunks.
v2: better alloc flags, better truncate, correct
locking, and error handling improvements (Chris Wilson)
v3: printf annotations (Daniel Vetter)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a55630a..3a8409a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -604,15 +604,80 @@
return purgeable ? " purgeable" : "";
}
-static void print_error_buffers(struct seq_file *m,
+static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
+ const char *f, va_list args)
+{
+ unsigned len;
+
+ if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) {
+ e->err = -ENOSPC;
+ return;
+ }
+
+ if (e->bytes == e->size - 1 || e->err)
+ return;
+
+ /* Seek the first printf which is hits start position */
+ if (e->pos < e->start) {
+ len = vsnprintf(NULL, 0, f, args);
+ if (e->pos + len <= e->start) {
+ e->pos += len;
+ return;
+ }
+
+ /* First vsnprintf needs to fit in full for memmove*/
+ if (len >= e->size) {
+ e->err = -EIO;
+ return;
+ }
+ }
+
+ len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args);
+ if (len >= e->size - e->bytes)
+ len = e->size - e->bytes - 1;
+
+ /* If this is first printf in this window, adjust it so that
+ * start position matches start of the buffer
+ */
+ if (e->pos < e->start) {
+ const size_t off = e->start - e->pos;
+
+ /* Should not happen but be paranoid */
+ if (off > len || e->bytes) {
+ e->err = -EIO;
+ return;
+ }
+
+ memmove(e->buf, e->buf + off, len - off);
+ e->bytes = len - off;
+ e->pos = e->start;
+ return;
+ }
+
+ e->bytes += len;
+ e->pos += len;
+}
+
+void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
+{
+ va_list args;
+
+ va_start(args, f);
+ i915_error_vprintf(e, f, args);
+ va_end(args);
+}
+
+#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
+
+static void print_error_buffers(struct drm_i915_error_state_buf *m,
const char *name,
struct drm_i915_error_buffer *err,
int count)
{
- seq_printf(m, "%s [%d]:\n", name, count);
+ err_printf(m, "%s [%d]:\n", name, count);
while (count--) {
- seq_printf(m, " %08x %8u %02x %02x %x %x%s%s%s%s%s%s%s",
+ err_printf(m, " %08x %8u %02x %02x %x %x%s%s%s%s%s%s%s",
err->gtt_offset,
err->size,
err->read_domains,
@@ -627,50 +692,50 @@
cache_level_str(err->cache_level));
if (err->name)
- seq_printf(m, " (name: %d)", err->name);
+ err_printf(m, " (name: %d)", err->name);
if (err->fence_reg != I915_FENCE_REG_NONE)
- seq_printf(m, " (fence: %d)", err->fence_reg);
+ err_printf(m, " (fence: %d)", err->fence_reg);
- seq_printf(m, "\n");
+ err_printf(m, "\n");
err++;
}
}
-static void i915_ring_error_state(struct seq_file *m,
+static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
struct drm_device *dev,
struct drm_i915_error_state *error,
unsigned ring)
{
BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
- seq_printf(m, "%s command stream:\n", ring_str(ring));
- seq_printf(m, " HEAD: 0x%08x\n", error->head[ring]);
- seq_printf(m, " TAIL: 0x%08x\n", error->tail[ring]);
- seq_printf(m, " CTL: 0x%08x\n", error->ctl[ring]);
- seq_printf(m, " ACTHD: 0x%08x\n", error->acthd[ring]);
- seq_printf(m, " IPEIR: 0x%08x\n", error->ipeir[ring]);
- seq_printf(m, " IPEHR: 0x%08x\n", error->ipehr[ring]);
- seq_printf(m, " INSTDONE: 0x%08x\n", error->instdone[ring]);
+ err_printf(m, "%s command stream:\n", ring_str(ring));
+ err_printf(m, " HEAD: 0x%08x\n", error->head[ring]);
+ err_printf(m, " TAIL: 0x%08x\n", error->tail[ring]);
+ err_printf(m, " CTL: 0x%08x\n", error->ctl[ring]);
+ err_printf(m, " ACTHD: 0x%08x\n", error->acthd[ring]);
+ err_printf(m, " IPEIR: 0x%08x\n", error->ipeir[ring]);
+ err_printf(m, " IPEHR: 0x%08x\n", error->ipehr[ring]);
+ err_printf(m, " INSTDONE: 0x%08x\n", error->instdone[ring]);
if (ring == RCS && INTEL_INFO(dev)->gen >= 4)
- seq_printf(m, " BBADDR: 0x%08llx\n", error->bbaddr);
+ err_printf(m, " BBADDR: 0x%08llx\n", error->bbaddr);
if (INTEL_INFO(dev)->gen >= 4)
- seq_printf(m, " INSTPS: 0x%08x\n", error->instps[ring]);
- seq_printf(m, " INSTPM: 0x%08x\n", error->instpm[ring]);
- seq_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]);
+ err_printf(m, " INSTPS: 0x%08x\n", error->instps[ring]);
+ err_printf(m, " INSTPM: 0x%08x\n", error->instpm[ring]);
+ err_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]);
if (INTEL_INFO(dev)->gen >= 6) {
- seq_printf(m, " RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
- seq_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
- seq_printf(m, " SYNC_0: 0x%08x [last synced 0x%08x]\n",
+ err_printf(m, " RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
+ err_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
+ err_printf(m, " SYNC_0: 0x%08x [last synced 0x%08x]\n",
error->semaphore_mboxes[ring][0],
error->semaphore_seqno[ring][0]);
- seq_printf(m, " SYNC_1: 0x%08x [last synced 0x%08x]\n",
+ err_printf(m, " SYNC_1: 0x%08x [last synced 0x%08x]\n",
error->semaphore_mboxes[ring][1],
error->semaphore_seqno[ring][1]);
}
- seq_printf(m, " seqno: 0x%08x\n", error->seqno[ring]);
- seq_printf(m, " waiting: %s\n", yesno(error->waiting[ring]));
- seq_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
- seq_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
+ err_printf(m, " seqno: 0x%08x\n", error->seqno[ring]);
+ err_printf(m, " waiting: %s\n", yesno(error->waiting[ring]));
+ err_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
+ err_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
}
struct i915_error_state_file_priv {
@@ -678,9 +743,11 @@
struct drm_i915_error_state *error;
};
-static int i915_error_state(struct seq_file *m, void *unused)
+
+static int i915_error_state(struct i915_error_state_file_priv *error_priv,
+ struct drm_i915_error_state_buf *m)
+
{
- struct i915_error_state_file_priv *error_priv = m->private;
struct drm_device *dev = error_priv->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_error_state *error = error_priv->error;
@@ -688,34 +755,35 @@
int i, j, page, offset, elt;
if (!error) {
- seq_printf(m, "no error state collected\n");
+ err_printf(m, "no error state collected\n");
return 0;
}
- seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
+ err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
error->time.tv_usec);
- seq_printf(m, "Kernel: " UTS_RELEASE "\n");
- seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
- seq_printf(m, "EIR: 0x%08x\n", error->eir);
- seq_printf(m, "IER: 0x%08x\n", error->ier);
- seq_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
- seq_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
- seq_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
- seq_printf(m, "CCID: 0x%08x\n", error->ccid);
+ err_printf(m, "Kernel: " UTS_RELEASE "\n");
+ err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
+ err_printf(m, "EIR: 0x%08x\n", error->eir);
+ err_printf(m, "IER: 0x%08x\n", error->ier);
+ err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
+ err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
+ err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
+ err_printf(m, "CCID: 0x%08x\n", error->ccid);
for (i = 0; i < dev_priv->num_fence_regs; i++)
- seq_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]);
+ err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]);
for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++)
- seq_printf(m, " INSTDONE_%d: 0x%08x\n", i, error->extra_instdone[i]);
+ err_printf(m, " INSTDONE_%d: 0x%08x\n", i,
+ error->extra_instdone[i]);
if (INTEL_INFO(dev)->gen >= 6) {
- seq_printf(m, "ERROR: 0x%08x\n", error->error);
- seq_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
+ err_printf(m, "ERROR: 0x%08x\n", error->error);
+ err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
}
if (INTEL_INFO(dev)->gen == 7)
- seq_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
+ err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
for_each_ring(ring, dev_priv, i)
i915_ring_error_state(m, dev, error, i);
@@ -734,24 +802,25 @@
struct drm_i915_error_object *obj;
if ((obj = error->ring[i].batchbuffer)) {
- seq_printf(m, "%s --- gtt_offset = 0x%08x\n",
+ err_printf(m, "%s --- gtt_offset = 0x%08x\n",
dev_priv->ring[i].name,
obj->gtt_offset);
offset = 0;
for (page = 0; page < obj->page_count; page++) {
for (elt = 0; elt < PAGE_SIZE/4; elt++) {
- seq_printf(m, "%08x : %08x\n", offset, obj->pages[page][elt]);
+ err_printf(m, "%08x : %08x\n", offset,
+ obj->pages[page][elt]);
offset += 4;
}
}
}
if (error->ring[i].num_requests) {
- seq_printf(m, "%s --- %d requests\n",
+ err_printf(m, "%s --- %d requests\n",
dev_priv->ring[i].name,
error->ring[i].num_requests);
for (j = 0; j < error->ring[i].num_requests; j++) {
- seq_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n",
+ err_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n",
error->ring[i].requests[j].seqno,
error->ring[i].requests[j].jiffies,
error->ring[i].requests[j].tail);
@@ -759,13 +828,13 @@
}
if ((obj = error->ring[i].ringbuffer)) {
- seq_printf(m, "%s --- ringbuffer = 0x%08x\n",
+ err_printf(m, "%s --- ringbuffer = 0x%08x\n",
dev_priv->ring[i].name,
obj->gtt_offset);
offset = 0;
for (page = 0; page < obj->page_count; page++) {
for (elt = 0; elt < PAGE_SIZE/4; elt++) {
- seq_printf(m, "%08x : %08x\n",
+ err_printf(m, "%08x : %08x\n",
offset,
obj->pages[page][elt]);
offset += 4;
@@ -775,12 +844,12 @@
obj = error->ring[i].ctx;
if (obj) {
- seq_printf(m, "%s --- HW Context = 0x%08x\n",
+ err_printf(m, "%s --- HW Context = 0x%08x\n",
dev_priv->ring[i].name,
obj->gtt_offset);
offset = 0;
for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
- seq_printf(m, "[%04x] %08x %08x %08x %08x\n",
+ err_printf(m, "[%04x] %08x %08x %08x %08x\n",
offset,
obj->pages[0][elt],
obj->pages[0][elt+1],
@@ -806,8 +875,7 @@
size_t cnt,
loff_t *ppos)
{
- struct seq_file *m = filp->private_data;
- struct i915_error_state_file_priv *error_priv = m->private;
+ struct i915_error_state_file_priv *error_priv = filp->private_data;
struct drm_device *dev = error_priv->dev;
int ret;
@@ -842,25 +910,81 @@
kref_get(&error_priv->error->ref);
spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
- return single_open(file, i915_error_state, error_priv);
+ file->private_data = error_priv;
+
+ return 0;
}
static int i915_error_state_release(struct inode *inode, struct file *file)
{
- struct seq_file *m = file->private_data;
- struct i915_error_state_file_priv *error_priv = m->private;
+ struct i915_error_state_file_priv *error_priv = file->private_data;
if (error_priv->error)
kref_put(&error_priv->error->ref, i915_error_state_free);
kfree(error_priv);
- return single_release(inode, file);
+ return 0;
+}
+
+static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
+ size_t count, loff_t *pos)
+{
+ struct i915_error_state_file_priv *error_priv = file->private_data;
+ struct drm_i915_error_state_buf error_str;
+ loff_t tmp_pos = 0;
+ ssize_t ret_count = 0;
+ int ret = 0;
+
+ memset(&error_str, 0, sizeof(error_str));
+
+ /* We need to have enough room to store any i915_error_state printf
+ * so that we can move it to start position.
+ */
+ error_str.size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
+ error_str.buf = kmalloc(error_str.size,
+ GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
+
+ if (error_str.buf == NULL) {
+ error_str.size = PAGE_SIZE;
+ error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
+ }
+
+ if (error_str.buf == NULL) {
+ error_str.size = 128;
+ error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
+ }
+
+ if (error_str.buf == NULL)
+ return -ENOMEM;
+
+ error_str.start = *pos;
+
+ ret = i915_error_state(error_priv, &error_str);
+ if (ret)
+ goto out;
+
+ if (error_str.bytes == 0 && error_str.err) {
+ ret = error_str.err;
+ goto out;
+ }
+
+ ret_count = simple_read_from_buffer(userbuf, count, &tmp_pos,
+ error_str.buf,
+ error_str.bytes);
+
+ if (ret_count < 0)
+ ret = ret_count;
+ else
+ *pos = error_str.start + ret_count;
+out:
+ kfree(error_str.buf);
+ return ret ?: ret_count;
}
static const struct file_operations i915_error_state_fops = {
.owner = THIS_MODULE,
.open = i915_error_state_open,
- .read = seq_read,
+ .read = i915_error_state_read,
.write = i915_error_state_write,
.llseek = default_llseek,
.release = i915_error_state_release,