Merge tag 'vfio-ccw-20190603' of...

Merge tag 'vfio-ccw-20190603' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/vfio-ccw into features

various vfio-ccw fixes (ccw translation, state machine)

drivers/s390/cio/vfio_ccw_cp.c

@@ -50,31 +50,25 @@ struct ccwchain {
 };
 
 /*
- * pfn_array_alloc_pin() - alloc memory for PFNs, then pin user pages in memory
+ * pfn_array_alloc() - alloc memory for PFNs
  * @pa: pfn_array on which to perform the operation
- * @mdev: the mediated device to perform pin/unpin operations
  * @iova: target guest physical address
  * @len: number of bytes that should be pinned from @iova
  *
- * Attempt to allocate memory for PFNs, and pin user pages in memory.
+ * Attempt to allocate memory for PFNs.
  *
  * Usage of pfn_array:
  * We expect (pa_nr == 0) and (pa_iova_pfn == NULL), any field in
  * this structure will be filled in by this function.
  *
  * Returns:
- *   Number of pages pinned on success.
- *   If @pa->pa_nr is not 0, or @pa->pa_iova_pfn is not NULL initially,
- *   returns -EINVAL.
- *   If no pages were pinned, returns -errno.
+ *         0 if PFNs are allocated
+ *   -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova_pfn is not NULL
+ *   -ENOMEM if alloc failed
  */
-static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
-			       u64 iova, unsigned int len)
+static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
 {
-	int i, ret = 0;
-
-	if (!len)
-		return 0;
+	int i;
 
 	if (pa->pa_nr || pa->pa_iova_pfn)
 		return -EINVAL;
@@ -94,8 +88,27 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 	pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
 
 	pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
-	for (i = 1; i < pa->pa_nr; i++)
+	pa->pa_pfn[0] = -1ULL;
+	for (i = 1; i < pa->pa_nr; i++) {
 		pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
+		pa->pa_pfn[i] = -1ULL;
+	}
+
+	return 0;
+}
+
+/*
+ * pfn_array_pin() - Pin user pages in memory
+ * @pa: pfn_array on which to perform the operation
+ * @mdev: the mediated device to perform pin operations
+ *
+ * Returns number of pages pinned upon success.
+ * If the pin request partially succeeds, or fails completely,
+ * all pages are left unpinned and a negative error value is returned.
+ */
+static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+{
+	int ret = 0;
 
 	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
 			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
@@ -112,8 +125,6 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 
 err_out:
 	pa->pa_nr = 0;
-	kfree(pa->pa_iova_pfn);
-	pa->pa_iova_pfn = NULL;
 
 	return ret;
 }
@@ -121,7 +132,9 @@ static int pfn_array_alloc_pin(struct pfn_array *pa, struct device *mdev,
 /* Unpin the pages before releasing the memory. */
 static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
 {
-	vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+	/* Only unpin if any pages were pinned to begin with */
+	if (pa->pa_nr)
+		vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
 	pa->pa_nr = 0;
 	kfree(pa->pa_iova_pfn);
 }
@@ -209,10 +222,16 @@ static long copy_from_iova(struct device *mdev,
 	int i, ret;
 	unsigned long l, m;
 
-	ret = pfn_array_alloc_pin(&pa, mdev, iova, n);
-	if (ret <= 0)
+	ret = pfn_array_alloc(&pa, iova, n);
+	if (ret < 0)
 		return ret;
 
+	ret = pfn_array_pin(&pa, mdev);
+	if (ret < 0) {
+		pfn_array_unpin_free(&pa, mdev);
+		return ret;
+	}
+
 	l = n;
 	for (i = 0; i < pa.pa_nr; i++) {
 		from = pa.pa_pfn[i] << PAGE_SHIFT;
@@ -272,17 +291,56 @@ static long copy_ccw_from_iova(struct channel_program *cp,
 /*
  * Helpers to operate ccwchain.
  */
-#define ccw_is_test(_ccw) (((_ccw)->cmd_code & 0x0F) == 0)
+#define ccw_is_read(_ccw) (((_ccw)->cmd_code & 0x03) == 0x02)
+#define ccw_is_read_backward(_ccw) (((_ccw)->cmd_code & 0x0F) == 0x0C)
+#define ccw_is_sense(_ccw) (((_ccw)->cmd_code & 0x0F) == CCW_CMD_BASIC_SENSE)
 
 #define ccw_is_noop(_ccw) ((_ccw)->cmd_code == CCW_CMD_NOOP)
 
 #define ccw_is_tic(_ccw) ((_ccw)->cmd_code == CCW_CMD_TIC)
 
 #define ccw_is_idal(_ccw) ((_ccw)->flags & CCW_FLAG_IDA)
-
+#define ccw_is_skip(_ccw) ((_ccw)->flags & CCW_FLAG_SKIP)
 
 #define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC))
 
+/*
+ * ccw_does_data_transfer()
+ *
+ * Determine whether a CCW will move any data, such that the guest pages
+ * would need to be pinned before performing the I/O.
+ *
+ * Returns 1 if yes, 0 if no.
+ */
+static inline int ccw_does_data_transfer(struct ccw1 *ccw)
+{
+	/* If the count field is zero, then no data will be transferred */
+	if (ccw->count == 0)
+		return 0;
+
+	/* If the command is a NOP, then no data will be transferred */
+	if (ccw_is_noop(ccw))
+		return 0;
+
+	/* If the skip flag is off, then data will be transferred */
+	if (!ccw_is_skip(ccw))
+		return 1;
+
+	/*
+	 * If the skip flag is on, it is only meaningful if the command
+	 * code is a read, read backward, sense, or sense ID.  In those
+	 * cases, no data will be transferred.
+	 */
+	if (ccw_is_read(ccw) || ccw_is_read_backward(ccw))
+		return 0;
+
+	if (ccw_is_sense(ccw))
+		return 0;
+
+	/* The skip flag is on, but it is ignored for this command code. */
+	return 1;
+}
+
 /*
  * is_cpa_within_range()
  *
@@ -348,9 +406,7 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
 {
 	struct ccw1 *ccw = chain->ch_ccw + idx;
 
-	if (ccw_is_test(ccw) || ccw_is_noop(ccw) || ccw_is_tic(ccw))
-		return;
-	if (!ccw->count)
+	if (ccw_is_tic(ccw))
 		return;
 
 	kfree((void *)(u64)ccw->cda);
@@ -537,17 +593,14 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	struct pfn_array_table *pat;
 	unsigned long *idaws;
 	int ret;
+	int bytes = 1;
+	int idaw_nr = 1;
 
 	ccw = chain->ch_ccw + idx;
 
-	if (!ccw->count) {
-		/*
-		 * We just want the translation result of any direct ccw
-		 * to be an IDA ccw, so let's add the IDA flag for it.
-		 * Although the flag will be ignored by firmware.
-		 */
-		ccw->flags |= CCW_FLAG_IDA;
-		return 0;
+	if (ccw->count) {
+		bytes = ccw->count;
+		idaw_nr = idal_nr_words((void *)(u64)ccw->cda, ccw->count);
 	}
 
 	/*
@@ -560,12 +613,20 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	if (ret)
 		goto out_init;
 
-	ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count);
+	ret = pfn_array_alloc(pat->pat_pa, ccw->cda, bytes);
 	if (ret < 0)
 		goto out_unpin;
 
+	if (ccw_does_data_transfer(ccw)) {
+		ret = pfn_array_pin(pat->pat_pa, cp->mdev);
+		if (ret < 0)
+			goto out_unpin;
+	} else {
+		pat->pat_pa->pa_nr = 0;
+	}
+
 	/* Translate this direct ccw to a idal ccw. */
-	idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
+	idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
 	if (!idaws) {
 		ret = -ENOMEM;
 		goto out_unpin;
@@ -590,21 +651,23 @@ static int ccwchain_fetch_idal(struct ccwchain *chain,
 {
 	struct ccw1 *ccw;
 	struct pfn_array_table *pat;
+	struct pfn_array *pa;
 	unsigned long *idaws;
 	u64 idaw_iova;
 	unsigned int idaw_nr, idaw_len;
 	int i, ret;
+	int bytes = 1;
 
 	ccw = chain->ch_ccw + idx;
 
-	if (!ccw->count)
-		return 0;
+	if (ccw->count)
+		bytes = ccw->count;
 
 	/* Calculate size of idaws. */
 	ret = copy_from_iova(cp->mdev, &idaw_iova, ccw->cda, sizeof(idaw_iova));
 	if (ret)
 		return ret;
-	idaw_nr = idal_nr_words((void *)(idaw_iova), ccw->count);
+	idaw_nr = idal_nr_words((void *)(idaw_iova), bytes);
 	idaw_len = idaw_nr * sizeof(*idaws);
 
 	/* Pin data page(s) in memory. */
@@ -628,9 +691,18 @@ static int ccwchain_fetch_idal(struct ccwchain *chain,
 
 	for (i = 0; i < idaw_nr; i++) {
 		idaw_iova = *(idaws + i);
+		pa = pat->pat_pa + i;
 
-		ret = pfn_array_alloc_pin(pat->pat_pa + i, cp->mdev,
-					  idaw_iova, 1);
+		ret = pfn_array_alloc(pa, idaw_iova, 1);
+		if (ret < 0)
+			goto out_free_idaws;
+
+		if (!ccw_does_data_transfer(ccw)) {
+			pa->pa_nr = 0;
+			continue;
+		}
+
+		ret = pfn_array_pin(pa, cp->mdev);
 		if (ret < 0)
 			goto out_free_idaws;
 	}
@@ -660,9 +732,6 @@ static int ccwchain_fetch_one(struct ccwchain *chain,
 {
 	struct ccw1 *ccw = chain->ch_ccw + idx;
 
-	if (ccw_is_test(ccw) || ccw_is_noop(ccw))
-		return 0;
-
 	if (ccw_is_tic(ccw))
 		return ccwchain_fetch_tic(chain, idx, cp);
 
@@ -886,7 +955,11 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 	 */
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		ccw_head = (u32)(u64)chain->ch_ccw;
-		if (is_cpa_within_range(cpa, ccw_head, chain->ch_len)) {
+		/*
+		 * On successful execution, cpa points just beyond the end
+		 * of the chain.
+		 */
+		if (is_cpa_within_range(cpa, ccw_head, chain->ch_len + 1)) {
 			/*
 			 * (cpa - ccw_head) is the offset value of the host
 			 * physical ccw to its chain head.

drivers/s390/cio/vfio_ccw_drv.c

@@ -95,11 +95,11 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
 	mutex_unlock(&private->io_mutex);
 
-	if (private->io_trigger)
-		eventfd_signal(private->io_trigger, 1);
-
 	if (private->mdev && is_final)
 		private->state = VFIO_CCW_STATE_IDLE;
+
+	if (private->io_trigger)
+		eventfd_signal(private->io_trigger, 1);
 }
 
 /*