*
*/
-#include <linux/utsname.h>
+#include <linux/ascii85.h>
+#include <linux/nmi.h>
+#include <linux/scatterlist.h>
#include <linux/stop_machine.h>
+#include <linux/utsname.h>
#include <linux/zlib.h>
+
#include <drm/drm_print.h>
-#include <linux/ascii85.h>
#include "i915_gpu_error.h"
#include "i915_drv.h"
return purgeable ? " purgeable" : "";
}
-static bool __i915_error_ok(struct drm_i915_error_state_buf *e)
+static void __sg_set_buf(struct scatterlist *sg,
+ void *addr, unsigned int len, loff_t it)
{
-
- if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) {
- e->err = -ENOSPC;
- return false;
- }
-
- if (e->bytes == e->size - 1 || e->err)
- return false;
-
- return true;
+ sg->page_link = (unsigned long)virt_to_page(addr);
+ sg->offset = offset_in_page(addr);
+ sg->length = len;
+ sg->dma_address = it;
}
-static bool __i915_error_seek(struct drm_i915_error_state_buf *e,
- unsigned len)
+static bool __i915_error_grow(struct drm_i915_error_state_buf *e, size_t len)
{
- if (e->pos + len <= e->start) {
- e->pos += len;
+ if (!len)
return false;
- }
- /* First vsnprintf needs to fit in its entirety for memmove */
- if (len >= e->size) {
- e->err = -EIO;
- return false;
- }
+ if (e->bytes + len + 1 <= e->size)
+ return true;
- return true;
-}
+ if (e->bytes) {
+ __sg_set_buf(e->cur++, e->buf, e->bytes, e->iter);
+ e->iter += e->bytes;
+ e->buf = NULL;
+ e->bytes = 0;
+ }
-static void __i915_error_advance(struct drm_i915_error_state_buf *e,
- unsigned len)
-{
- /* If this is first printf in this window, adjust it so that
- * start position matches start of the buffer
- */
+ if (e->cur == e->end) {
+ struct scatterlist *sgl;
- if (e->pos < e->start) {
- const size_t off = e->start - e->pos;
+ sgl = (typeof(sgl))__get_free_page(GFP_KERNEL);
+ if (!sgl) {
+ e->err = -ENOMEM;
+ return false;
+ }
- /* Should not happen but be paranoid */
- if (off > len || e->bytes) {
- e->err = -EIO;
- return;
+ if (e->cur) {
+ e->cur->offset = 0;
+ e->cur->length = 0;
+ e->cur->page_link =
+ (unsigned long)sgl | SG_CHAIN;
+ } else {
+ e->sgl = sgl;
}
- memmove(e->buf, e->buf + off, len - off);
- e->bytes = len - off;
- e->pos = e->start;
- return;
+ e->cur = sgl;
+ e->end = sgl + SG_MAX_SINGLE_ALLOC - 1;
}
- e->bytes += len;
- e->pos += len;
+ e->size = ALIGN(len + 1, SZ_64K);
+ e->buf = kmalloc(e->size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+ if (!e->buf) {
+ e->size = PAGE_ALIGN(len + 1);
+ e->buf = kmalloc(e->size, GFP_KERNEL);
+ }
+ if (!e->buf) {
+ e->err = -ENOMEM;
+ return false;
+ }
+
+ return true;
}
__printf(2, 0)
static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
- const char *f, va_list args)
+ const char *fmt, va_list args)
{
- unsigned len;
+ va_list ap;
+ int len;
- if (!__i915_error_ok(e))
+ if (e->err)
return;
- /* Seek the first printf which is hits start position */
- if (e->pos < e->start) {
- va_list tmp;
-
- va_copy(tmp, args);
- len = vsnprintf(NULL, 0, f, tmp);
- va_end(tmp);
-
- if (!__i915_error_seek(e, len))
- return;
+ va_copy(ap, args);
+ len = vsnprintf(NULL, 0, fmt, ap);
+ va_end(ap);
+ if (len <= 0) {
+ e->err = len;
+ 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 (!__i915_error_grow(e, len))
+ return;
- __i915_error_advance(e, len);
+ GEM_BUG_ON(e->bytes >= e->size);
+ len = vscnprintf(e->buf + e->bytes, e->size - e->bytes, fmt, args);
+ if (len < 0) {
+ e->err = len;
+ return;
+ }
+ e->bytes += len;
}
-static void i915_error_puts(struct drm_i915_error_state_buf *e,
- const char *str)
+static void i915_error_puts(struct drm_i915_error_state_buf *e, const char *str)
{
unsigned len;
- if (!__i915_error_ok(e))
+ if (e->err || !str)
return;
len = strlen(str);
+ if (!__i915_error_grow(e, len))
+ return;
- /* Seek the first printf which is hits start position */
- if (e->pos < e->start) {
- if (!__i915_error_seek(e, len))
- return;
- }
-
- if (len >= e->size - e->bytes)
- len = e->size - e->bytes - 1;
+ GEM_BUG_ON(e->bytes + len > e->size);
memcpy(e->buf + e->bytes, str, len);
-
- __i915_error_advance(e, len);
+ e->bytes += len;
}
#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK)
return -EIO;
+
+ touch_nmi_watchdog();
} while (zstream->avail_in);
/* Fallback to uncompressed if we increase size? */
print_error_obj(m, NULL, "GuC log buffer", error_uc->guc_log);
}
-int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
- const struct i915_gpu_state *error)
+static void err_free_sgl(struct scatterlist *sgl)
{
- struct drm_i915_private *dev_priv = m->i915;
- struct drm_i915_error_object *obj;
- struct timespec64 ts;
- int i, j;
+ while (sgl) {
+ struct scatterlist *sg;
- if (!error) {
- err_printf(m, "No error state collected\n");
- return 0;
+ for (sg = sgl; !sg_is_chain(sg); sg++) {
+ kfree(sg_virt(sg));
+ if (sg_is_last(sg))
+ break;
+ }
+
+ sg = sg_is_last(sg) ? NULL : sg_chain_ptr(sg);
+ free_page((unsigned long)sgl);
+ sgl = sg;
}
+}
- if (IS_ERR(error))
- return PTR_ERR(error);
+static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
+ struct i915_gpu_state *error)
+{
+ struct drm_i915_error_object *obj;
+ struct timespec64 ts;
+ int i, j;
if (*error->error_msg)
err_printf(m, "%s\n", error->error_msg);
err_printf(m, "Reset count: %u\n", error->reset_count);
err_printf(m, "Suspend count: %u\n", error->suspend_count);
err_printf(m, "Platform: %s\n", intel_platform_name(error->device_info.platform));
- err_print_pciid(m, error->i915);
+ err_print_pciid(m, m->i915);
err_printf(m, "IOMMU enabled?: %d\n", error->iommu);
- if (HAS_CSR(dev_priv)) {
- struct intel_csr *csr = &dev_priv->csr;
+ if (HAS_CSR(m->i915)) {
+ struct intel_csr *csr = &m->i915->csr;
err_printf(m, "DMC loaded: %s\n",
yesno(csr->dmc_payload != NULL));
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);
- err_printf(m, "Missed interrupts: 0x%08lx\n", dev_priv->gpu_error.missed_irq_rings);
+ err_printf(m, "Missed interrupts: 0x%08lx\n",
+ m->i915->gpu_error.missed_irq_rings);
for (i = 0; i < error->nfence; i++)
err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]);
- if (INTEL_GEN(dev_priv) >= 6) {
+ if (INTEL_GEN(m->i915) >= 6) {
err_printf(m, "ERROR: 0x%08x\n", error->error);
- if (INTEL_GEN(dev_priv) >= 8)
+ if (INTEL_GEN(m->i915) >= 8)
err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
error->fault_data1, error->fault_data0);
err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
}
- if (IS_GEN7(dev_priv))
+ if (IS_GEN7(m->i915))
err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
len += scnprintf(buf + len, sizeof(buf), "%s%s",
first ? "" : ", ",
- dev_priv->engine[j]->name);
+ m->i915->engine[j]->name);
first = 0;
}
scnprintf(buf + len, sizeof(buf), ")");
obj = ee->batchbuffer;
if (obj) {
- err_puts(m, dev_priv->engine[i]->name);
+ err_puts(m, m->i915->engine[i]->name);
if (ee->context.pid)
err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d%s)",
ee->context.comm,
err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
upper_32_bits(obj->gtt_offset),
lower_32_bits(obj->gtt_offset));
- print_error_obj(m, dev_priv->engine[i], NULL, obj);
+ print_error_obj(m, m->i915->engine[i], NULL, obj);
}
for (j = 0; j < ee->user_bo_count; j++)
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"user", ee->user_bo[j]);
if (ee->num_requests) {
err_printf(m, "%s --- %d requests\n",
- dev_priv->engine[i]->name,
+ m->i915->engine[i]->name,
ee->num_requests);
for (j = 0; j < ee->num_requests; j++)
error_print_request(m, " ",
if (IS_ERR(ee->waiters)) {
err_printf(m, "%s --- ? waiters [unable to acquire spinlock]\n",
- dev_priv->engine[i]->name);
+ m->i915->engine[i]->name);
} else if (ee->num_waiters) {
err_printf(m, "%s --- %d waiters\n",
- dev_priv->engine[i]->name,
+ m->i915->engine[i]->name,
ee->num_waiters);
for (j = 0; j < ee->num_waiters; j++) {
err_printf(m, " seqno 0x%08x for %s [%d]\n",
}
}
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"ringbuffer", ee->ringbuffer);
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"HW Status", ee->hws_page);
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"HW context", ee->ctx);
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"WA context", ee->wa_ctx);
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"WA batchbuffer", ee->wa_batchbuffer);
- print_error_obj(m, dev_priv->engine[i],
+ print_error_obj(m, m->i915->engine[i],
"NULL context", ee->default_state);
}
err_print_capabilities(m, &error->device_info, &error->driver_caps);
err_print_params(m, &error->params);
err_print_uc(m, &error->uc);
+}
+
+static int err_print_to_sgl(struct i915_gpu_state *error)
+{
+ struct drm_i915_error_state_buf m;
+
+ if (IS_ERR(error))
+ return PTR_ERR(error);
+
+ if (READ_ONCE(error->sgl))
+ return 0;
+
+ memset(&m, 0, sizeof(m));
+ m.i915 = error->i915;
+
+ __err_print_to_sgl(&m, error);
+
+ if (m.buf) {
+ __sg_set_buf(m.cur++, m.buf, m.bytes, m.iter);
+ m.bytes = 0;
+ m.buf = NULL;
+ }
+ if (m.cur) {
+ GEM_BUG_ON(m.end < m.cur);
+ sg_mark_end(m.cur - 1);
+ }
+ GEM_BUG_ON(m.sgl && !m.cur);
+
+ if (m.err) {
+ err_free_sgl(m.sgl);
+ return m.err;
+ }
- if (m->bytes == 0 && m->err)
- return m->err;
+ if (cmpxchg(&error->sgl, NULL, m.sgl))
+ err_free_sgl(m.sgl);
return 0;
}
-int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf,
- struct drm_i915_private *i915,
- size_t count, loff_t pos)
+ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
+ char *buf, loff_t off, size_t rem)
{
- memset(ebuf, 0, sizeof(*ebuf));
- ebuf->i915 = i915;
+ struct scatterlist *sg;
+ size_t count;
+ loff_t pos;
+ int err;
- /* We need to have enough room to store any i915_error_state printf
- * so that we can move it to start position.
- */
- ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
- ebuf->buf = kmalloc(ebuf->size,
- GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+ if (!error || !rem)
+ return 0;
- if (ebuf->buf == NULL) {
- ebuf->size = PAGE_SIZE;
- ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
- }
+ err = err_print_to_sgl(error);
+ if (err)
+ return err;
- if (ebuf->buf == NULL) {
- ebuf->size = 128;
- ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
- }
+ sg = READ_ONCE(error->fit);
+ if (!sg || off < sg->dma_address)
+ sg = error->sgl;
+ if (!sg)
+ return 0;
- if (ebuf->buf == NULL)
- return -ENOMEM;
+ pos = sg->dma_address;
+ count = 0;
+ do {
+ size_t len, start;
+
+ if (sg_is_chain(sg)) {
+ sg = sg_chain_ptr(sg);
+ GEM_BUG_ON(sg_is_chain(sg));
+ }
+
+ len = sg->length;
+ if (pos + len <= off) {
+ pos += len;
+ continue;
+ }
- ebuf->start = pos;
+ start = sg->offset;
+ if (pos < off) {
+ GEM_BUG_ON(off - pos > len);
+ len -= off - pos;
+ start += off - pos;
+ pos = off;
+ }
- return 0;
+ len = min(len, rem);
+ GEM_BUG_ON(!len || len > sg->length);
+
+ memcpy(buf, page_address(sg_page(sg)) + start, len);
+
+ count += len;
+ pos += len;
+
+ buf += len;
+ rem -= len;
+ if (!rem) {
+ WRITE_ONCE(error->fit, sg);
+ break;
+ }
+ } while (!sg_is_last(sg++));
+
+ return count;
}
static void i915_error_object_free(struct drm_i915_error_object *obj)
cleanup_params(error);
cleanup_uc_state(error);
+ err_free_sgl(error->sgl);
kfree(error);
}