[PATCH v2 00/18] powerpc/vas: Add support for FTW

[PATCH v2 00/18] powerpc/vas: Add support for FTW

[Sukadev Bhattiprolu]

The first 10 patches in this set were posted earlier[1] and don't have
any significant changes since then. This set sanitizes cpu/chip id to
VAS id mapping, improves vas_win_close() performance and adds a check
for return of credits and cleans up some code.

Patch 11 adds debugfs support for the VAS window contexts.

Patches 11-18 add support for user space aka Fast thread-wakeup windows
in VAS. These include a patch from Michael Neuling to support emulating
the paste instruction.

Michael Neuling (1):
  powerpc: Emulate paste instruction

Sukadev Bhattiprolu (17):
  powerpc/vas: init missing fields from [rt]xattr
  powerpc/vas: Validate window credits
  powerpc/vas: Cleanup some debug code
  powerpc/vas: Drop poll_window_cast_out().
  powerpc/vas: Use helper to unpin/close window
  powerpc/vas: Reduce polling interval for busy state
  powerpc/vas: Save configured window credits
  powerpc/vas: poll for return of window credits
  powerpc/vas: Create cpu to vas id mapping
  powerpc/vas, nx-842: Define and use chip_to_vas_id()
  powerpc/vas: Export HVWC to debugfs
  powerpc: have copy depend on CONFIG_BOOK3S_64
  powerpc: Add support for setting SPRN_TIDR
  powerpc: Define set_thread_used_vas()
  powerpc/vas: Define vas_win_paste_addr()
  powerpc/vas: Define vas_win_id()
  powerpc/vas: Add support for user receive window

 arch/powerpc/include/asm/emulated_ops.h     |   1 +
 arch/powerpc/include/asm/ppc-opcode.h       |   1 +
 arch/powerpc/include/asm/processor.h        |   3 +
 arch/powerpc/include/asm/reg.h              |   2 +
 arch/powerpc/include/asm/switch_to.h        |   5 +
 arch/powerpc/include/asm/vas.h              |  21 +++
 arch/powerpc/kernel/process.c               | 160 ++++++++++++++++--
 arch/powerpc/kernel/traps.c                 |  64 ++++++++
 arch/powerpc/platforms/powernv/Makefile     |   3 +-
 arch/powerpc/platforms/powernv/vas-debug.c  | 209 ++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/vas-window.c | 245 +++++++++++++++++++++++-----
 arch/powerpc/platforms/powernv/vas.c        |  31 +++-
 arch/powerpc/platforms/powernv/vas.h        |  95 ++++++-----
 drivers/crypto/nx/nx-842-powernv.c          |  18 +-
 14 files changed, 745 insertions(+), 113 deletions(-)
 create mode 100644 arch/powerpc/platforms/powernv/vas-debug.c

-- 
2.7.4

[PATCH v2 01/18] powerpc/vas: init missing fields from [rt]xattr

[Sukadev Bhattiprolu]

Initialize a few missing window context fields from the window attributes
specified by the caller. These fields are currently set to their default
values by the caller (NX-842), but would be good to apply them anyway.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 5aae845..cec7ab7 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -679,10 +679,13 @@ static void init_winctx_for_rxwin(struct vas_window *rxwin,
 
 	winctx->nx_win = rxattr->nx_win;
 	winctx->fault_win = rxattr->fault_win;
+	winctx->user_win = rxattr->user_win;
+	winctx->rej_no_credit = rxattr->rej_no_credit;
 	winctx->rx_word_mode = rxattr->rx_win_ord_mode;
 	winctx->tx_word_mode = rxattr->tx_win_ord_mode;
 	winctx->rx_wcred_mode = rxattr->rx_wcred_mode;
 	winctx->tx_wcred_mode = rxattr->tx_wcred_mode;
+	winctx->notify_early = rxattr->notify_early;
 
 	if (winctx->nx_win) {
 		winctx->data_stamp = true;
@@ -889,11 +892,14 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
 	winctx->user_win = txattr->user_win;
 	winctx->nx_win = txwin->rxwin->nx_win;
 	winctx->pin_win = txattr->pin_win;
+	winctx->rej_no_credit = txattr->rej_no_credit;
+	winctx->rsvd_txbuf_enable = txattr->rsvd_txbuf_enable;
 
 	winctx->rx_wcred_mode = txattr->rx_wcred_mode;
 	winctx->tx_wcred_mode = txattr->tx_wcred_mode;
 	winctx->rx_word_mode = txattr->rx_win_ord_mode;
 	winctx->tx_word_mode = txattr->tx_win_ord_mode;
+	winctx->rsvd_txbuf_count = txattr->rsvd_txbuf_count;
 
 	if (winctx->nx_win) {
 		winctx->data_stamp = true;
-- 
2.7.4

[PATCH v2 02/18] powerpc/vas: Validate window credits

[Sukadev Bhattiprolu]

NX-842, the only user of VAS, sets the window credits to default values
but VAS should check the credits against the possible max values.

The VAS_WCREDS_MIN is not needed and can be dropped.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 6 ++++++
 arch/powerpc/platforms/powernv/vas.h        | 4 ++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index cec7ab7..a2fe120 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -738,6 +738,9 @@ static bool rx_win_args_valid(enum vas_cop_type cop,
 	if (attr->rx_fifo_size > VAS_RX_FIFO_SIZE_MAX)
 		return false;
 
+	if (attr->wcreds_max > VAS_RX_WCREDS_MAX)
+		return false;
+
 	if (attr->nx_win) {
 		/* cannot be fault or user window if it is nx */
 		if (attr->fault_win || attr->user_win)
@@ -927,6 +930,9 @@ static bool tx_win_args_valid(enum vas_cop_type cop,
 	if (cop > VAS_COP_TYPE_MAX)
 		return false;
 
+	if (attr->wcreds_max > VAS_TX_WCREDS_MAX)
+		return false;
+
 	if (attr->user_win &&
 			(cop != VAS_COP_TYPE_FTW || attr->rsvd_txbuf_count))
 		return false;
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index 38dee5d..fea0de4 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -106,8 +106,8 @@
  *
  * TODO: Needs tuning for per-process credits
  */
-#define VAS_WCREDS_MIN			16
-#define VAS_WCREDS_MAX			((64 << 10) - 1)
+#define VAS_RX_WCREDS_MAX		((64 << 10) - 1)
+#define VAS_TX_WCREDS_MAX		((4 << 10) - 1)
 #define VAS_WCREDS_DEFAULT		(1 << 10)
 
 /*
-- 
2.7.4

[PATCH v2 03/18] powerpc/vas: Cleanup some debug code

[Sukadev Bhattiprolu]

Clean up vas.h and the debug code around ifdef vas_debug.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c |  8 +++--
 arch/powerpc/platforms/powernv/vas.h        | 56 +++++++----------------------
 2 files changed, 18 insertions(+), 46 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index a2fe120..67ffc5d 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -726,7 +726,10 @@ static void init_winctx_for_rxwin(struct vas_window *rxwin,
 static bool rx_win_args_valid(enum vas_cop_type cop,
 			struct vas_rx_win_attr *attr)
 {
-	dump_rx_win_attr(attr);
+	pr_debug("Rxattr: fault %d, notify %d, intr %d, early %d, fifo %d\n",
+			attr->fault_win, attr->notify_disable,
+			attr->intr_disable, attr->notify_early,
+			attr->rx_fifo_size);
 
 	if (cop >= VAS_COP_TYPE_MAX)
 		return false;
@@ -1050,7 +1053,8 @@ int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
 	else
 		rc = -EINVAL;
 
-	print_fifo_msg_count(txwin);
+	pr_debug("Txwin #%d: Msg count %llu\n", txwin->winid,
+			read_hvwc_reg(txwin, VREG(LRFIFO_PUSH)));
 
 	return rc;
 }
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index fea0de4..15d2dfa 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -259,6 +259,16 @@
 #define VAS_NX_UTIL_ADDER		PPC_BITMASK(32, 63)
 
 /*
+ * VREG(x):
+ * Expand a register's short name (eg: LPID) into two parameters:
+ *	- the register's short name in string form ("LPID"), and
+ *	- the name of the macro (eg: VAS_LPID_OFFSET), defining the
+ *	  register's offset in the window context
+ */
+#define VREG_SFX(n, s)	__stringify(n), VAS_##n##s
+#define VREG(r)		VREG_SFX(r, _OFFSET)
+
+/*
  * Local Notify Scope Control Register. (Receive windows only).
  */
 enum vas_notify_scope {
@@ -385,43 +395,15 @@ struct vas_winctx {
 
 extern struct vas_instance *find_vas_instance(int vasid);
 
-/*
- * VREG(x):
- * Expand a register's short name (eg: LPID) into two parameters:
- *	- the register's short name in string form ("LPID"), and
- *	- the name of the macro (eg: VAS_LPID_OFFSET), defining the
- *	  register's offset in the window context
- */
-#define VREG_SFX(n, s)	__stringify(n), VAS_##n##s
-#define VREG(r)		VREG_SFX(r, _OFFSET)
-
-#ifdef vas_debug
-static inline void dump_rx_win_attr(struct vas_rx_win_attr *attr)
-{
-	pr_err("fault %d, notify %d, intr %d early %d\n",
-			attr->fault_win, attr->notify_disable,
-			attr->intr_disable, attr->notify_early);
-
-	pr_err("rx_fifo_size %d, max value %d\n",
-				attr->rx_fifo_size, VAS_RX_FIFO_SIZE_MAX);
-}
-
 static inline void vas_log_write(struct vas_window *win, char *name,
 			void *regptr, u64 val)
 {
-	if (val)
-		pr_err("%swin #%d: %s reg %p, val 0x%016llx\n",
+	if (!val)
+		pr_debug("%swin #%d: %s reg %p, val 0x%016llx\n",
 				win->tx_win ? "Tx" : "Rx", win->winid, name,
 				regptr, val);
 }
 
-#else	/* vas_debug */
-
-#define vas_log_write(win, name, reg, val)
-#define dump_rx_win_attr(attr)
-
-#endif	/* vas_debug */
-
 static inline void write_uwc_reg(struct vas_window *win, char *name,
 			s32 reg, u64 val)
 {
@@ -450,18 +432,4 @@ static inline u64 read_hvwc_reg(struct vas_window *win,
 	return in_be64(win->hvwc_map+reg);
 }
 
-#ifdef vas_debug
-
-static void print_fifo_msg_count(struct vas_window *txwin)
-{
-	uint64_t read_hvwc_reg(struct vas_window *w, char *n, uint64_t o);
-	pr_devel("Winid %d, Msg count %llu\n", txwin->winid,
-			(uint64_t)read_hvwc_reg(txwin, VREG(LRFIFO_PUSH)));
-}
-#else	/* vas_debug */
-
-#define print_fifo_msg_count(window)
-
-#endif	/* vas_debug */
-
 #endif /* _VAS_H */
-- 
2.7.4

[PATCH v2 04/18] powerpc/vas: Drop poll_window_cast_out().

[Sukadev Bhattiprolu]

Polling for window cast out is listed in the spec, but turns out that
it is not strictly necessary and slows down window close. Making it a
stub for now.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 34 ++++++++++++++---------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 67ffc5d..8ab8a82 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1079,25 +1079,25 @@ static void poll_window_busy_state(struct vas_window *window)
 	}
 }
 
+/*
+ * Have the hardware cast a window out of cache and wait for it to
+ * be completed.
+ *
+ * NOTE: It can take a relatively long time to cast the window context
+ *	out of the cache. It is not strictly necessary to cast out if:
+ *
+ *	- we clear the "Pin Window" bit (so hardware is free to evict)
+ *
+ *	- we re-initialize the window context when it is reassigned.
+ *
+ *	We do the former in vas_win_close() and latter in vas_win_open().
+ *	So, ignoring the cast-out for now. We can add it as needed. If
+ *	casting out becomes necessary we should consider offloading the
+ *	job to a worker thread, so the window close can proceed quickly.
+ */
 static void poll_window_castout(struct vas_window *window)
 {
-	int cached;
-	u64 val;
-
-	/* Cast window context out of the cache */
-retry:
-	val = read_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL));
-	cached = GET_FIELD(VAS_WIN_CACHE_STATUS, val);
-	if (cached) {
-		val = 0ULL;
-		val = SET_FIELD(VAS_CASTOUT_REQ, val, 1);
-		val = SET_FIELD(VAS_PUSH_TO_MEM, val, 0);
-		write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), val);
-
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule_timeout(HZ);
-		goto retry;
-	}
+	/* stub for now */
 }
 
 /*
-- 
2.7.4

[PATCH v2 05/18] powerpc/vas: Use helper to unpin/close window

[Sukadev Bhattiprolu]

Use a helper to have the hardware unpin and mark a window closed.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 8ab8a82..95622a9 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1101,6 +1101,20 @@ static void poll_window_castout(struct vas_window *window)
 }
 
 /*
+ * Unpin and close a window so no new requests are accepted and the
+ * hardware can evict this window from cache if necessary.
+ */
+static void unpin_close_window(struct vas_window *window)
+{
+	u64 val;
+
+	val = read_hvwc_reg(window, VREG(WINCTL));
+	val = SET_FIELD(VAS_WINCTL_PIN, val, 0);
+	val = SET_FIELD(VAS_WINCTL_OPEN, val, 0);
+	write_hvwc_reg(window, VREG(WINCTL), val);
+}
+
+/*
  * Close a window.
  *
  * See Section 1.12.1 of VAS workbook v1.05 for details on closing window:
@@ -1114,8 +1128,6 @@ static void poll_window_castout(struct vas_window *window)
  */
 int vas_win_close(struct vas_window *window)
 {
-	u64 val;
-
 	if (!window)
 		return 0;
 
@@ -1131,11 +1143,7 @@ int vas_win_close(struct vas_window *window)
 
 	poll_window_busy_state(window);
 
-	/* Unpin window from cache and close it */
-	val = read_hvwc_reg(window, VREG(WINCTL));
-	val = SET_FIELD(VAS_WINCTL_PIN, val, 0);
-	val = SET_FIELD(VAS_WINCTL_OPEN, val, 0);
-	write_hvwc_reg(window, VREG(WINCTL), val);
+	unpin_close_window(window);
 
 	poll_window_castout(window);
 
-- 
2.7.4

[PATCH v2 06/18] powerpc/vas: Reduce polling interval for busy state

[Sukadev Bhattiprolu]

A VAS window is normally in "busy" state for only a short duration.
Reduce the time we wait for the window to go to "not-busy" state to
speed-up vas_win_close() a bit.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 95622a9..1422cdd 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1060,21 +1060,23 @@ int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
 }
 EXPORT_SYMBOL_GPL(vas_paste_crb);
 
+/*
+ * Wait for the window to go to "not-busy" state. It should only take a
+ * short time to queue a CRB, so window should not be busy for too long.
+ * Trying 5ms intervals.
+ */
 static void poll_window_busy_state(struct vas_window *window)
 {
 	int busy;
 	u64 val;
 
 retry:
-	/*
-	 * Poll Window Busy flag
-	 */
 	val = read_hvwc_reg(window, VREG(WIN_STATUS));
 	busy = GET_FIELD(VAS_WIN_BUSY, val);
 	if (busy) {
 		val = 0;
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule_timeout(HZ);
+		schedule_timeout(msecs_to_jiffies(5));
 		goto retry;
 	}
 }
-- 
2.7.4

[PATCH v2 07/18] powerpc/vas: Save configured window credits

[Sukadev Bhattiprolu]

Save the configured max window credits for a window in the vas_window
structure. We will need this when polling for return of window credits.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 6 ++++--
 arch/powerpc/platforms/powernv/vas.h        | 1 +
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 1422cdd..a59a187 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -674,7 +674,7 @@ static void init_winctx_for_rxwin(struct vas_window *rxwin,
 
 	winctx->rx_fifo = rxattr->rx_fifo;
 	winctx->rx_fifo_size = rxattr->rx_fifo_size;
-	winctx->wcreds_max = rxattr->wcreds_max ?: VAS_WCREDS_DEFAULT;
+	winctx->wcreds_max = rxwin->wcreds_max;
 	winctx->pin_win = rxattr->pin_win;
 
 	winctx->nx_win = rxattr->nx_win;
@@ -844,6 +844,7 @@ struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop,
 	rxwin->nx_win = rxattr->nx_win;
 	rxwin->user_win = rxattr->user_win;
 	rxwin->cop = cop;
+	rxwin->wcreds_max = rxattr->wcreds_max ?: VAS_WCREDS_DEFAULT;
 	if (rxattr->user_win)
 		rxwin->pid = task_pid_vnr(current);
 
@@ -893,7 +894,7 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
 	 */
 	memset(winctx, 0, sizeof(struct vas_winctx));
 
-	winctx->wcreds_max = txattr->wcreds_max ?: VAS_WCREDS_DEFAULT;
+	winctx->wcreds_max = txwin->wcreds_max;
 
 	winctx->user_win = txattr->user_win;
 	winctx->nx_win = txwin->rxwin->nx_win;
@@ -978,6 +979,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
 	txwin->nx_win = txwin->rxwin->nx_win;
 	txwin->pid = attr->pid;
 	txwin->user_win = attr->user_win;
+	txwin->wcreds_max = attr->wcreds_max ?: VAS_WCREDS_DEFAULT;
 
 	init_winctx_for_txwin(txwin, attr, &winctx);
 
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index 15d2dfa..ad906f6 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -332,6 +332,7 @@ struct vas_window {
 	void *hvwc_map;		/* HV window context */
 	void *uwc_map;		/* OS/User window context */
 	pid_t pid;		/* Linux process id of owner */
+	int wcreds_max;		/* Window credits */
 
 	/* Fields applicable only to send windows */
 	void *paste_kaddr;
-- 
2.7.4

[PATCH v2 08/18] powerpc/vas: poll for return of window credits

[Sukadev Bhattiprolu]

Normally, the NX driver waits for the CRBs to be processed before closing
the window. But it is better to ensure that the credits are returned before
the window gets reassigned later.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 45 +++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index a59a187..23c13a7 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1063,6 +1063,49 @@ int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
 EXPORT_SYMBOL_GPL(vas_paste_crb);
 
 /*
+ * If credit checking is enabled for this window, poll for the return
+ * of window credits (i.e for NX engines to process any outstanding CRBs).
+ * Since NX-842 waits for the CRBs to be processed before closing the
+ * window, we should not have to wait for too long.
+ *
+ * TODO: We retry in 10ms intervals now. We could/should probably peek at
+ *	the VAS_LRFIFO_PUSH_OFFSET register to get an estimate of pending
+ *	CRBs on the FIFO and compute the delay dynamically on each retry.
+ *	But that is not really needed until we support NX-GZIP access from
+ *	user space. (NX-842 driver waits for CSB and Fast thread-wakeup
+ *	doesn't use credit checking).
+ */
+static void poll_window_credits(struct vas_window *window)
+{
+	u64 val;
+	int creds, mode;
+
+	val = read_hvwc_reg(window, VREG(WINCTL));
+	if (window->tx_win)
+		mode = GET_FIELD(VAS_WINCTL_TX_WCRED_MODE, val);
+	else
+		mode = GET_FIELD(VAS_WINCTL_RX_WCRED_MODE, val);
+
+	if (!mode)
+		return;
+retry:
+	if (window->tx_win) {
+		val = read_hvwc_reg(window, VREG(TX_WCRED));
+		creds = GET_FIELD(VAS_TX_WCRED, val);
+	} else {
+		val = read_hvwc_reg(window, VREG(LRX_WCRED));
+		creds = GET_FIELD(VAS_LRX_WCRED, val);
+	}
+
+	if (creds < window->wcreds_max) {
+		val = 0;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(msecs_to_jiffies(10));
+		goto retry;
+	}
+}
+
+/*
  * Wait for the window to go to "not-busy" state. It should only take a
  * short time to queue a CRB, so window should not be busy for too long.
  * Trying 5ms intervals.
@@ -1149,6 +1192,8 @@ int vas_win_close(struct vas_window *window)
 
 	unpin_close_window(window);
 
+	poll_window_credits(window);
+
 	poll_window_castout(window);
 
 	/* if send window, drop reference to matching receive window */
-- 
2.7.4

[PATCH v2 09/18] powerpc/vas: Create cpu to vas id mapping

[Sukadev Bhattiprolu]

Create a cpu to vasid mapping so callers can specify -1 instead of
trying to find a VAS id.

Changelog[v2]
	[Michael Ellerman] Use per-cpu variables to simplify code.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index 565a487..abb7090 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -18,15 +18,18 @@
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/of.h>
+#include <asm/prom.h>
 
 #include "vas.h"
 
 static DEFINE_MUTEX(vas_mutex);
 static LIST_HEAD(vas_instances);
 
+static DEFINE_PER_CPU(int, cpu_vas_id);
+
 static int init_vas_instance(struct platform_device *pdev)
 {
-	int rc, vasid;
+	int rc, cpu, vasid;
 	struct resource *res;
 	struct vas_instance *vinst;
 	struct device_node *dn = pdev->dev.of_node;
@@ -74,6 +77,11 @@ static int init_vas_instance(struct platform_device *pdev)
 			"paste_win_id_shift 0x%llx\n", pdev->name, vasid,
 			vinst->paste_base_addr, vinst->paste_win_id_shift);
 
+	for_each_possible_cpu(cpu) {
+		if (cpu_to_chip_id(cpu) == of_get_ibm_chip_id(dn))
+			per_cpu(cpu_vas_id, cpu) = vasid;
+	}
+
 	mutex_lock(&vas_mutex);
 	list_add(&vinst->node, &vas_instances);
 	mutex_unlock(&vas_mutex);
@@ -98,6 +106,10 @@ struct vas_instance *find_vas_instance(int vasid)
 	struct vas_instance *vinst;
 
 	mutex_lock(&vas_mutex);
+
+	if (vasid == -1)
+		vasid = per_cpu(cpu_vas_id, smp_processor_id());
+
 	list_for_each(ent, &vas_instances) {
 		vinst = list_entry(ent, struct vas_instance, node);
 		if (vinst->vas_id == vasid) {
-- 
2.7.4

[PATCH v2 10/18] powerpc/vas, nx-842: Define and use chip_to_vas_id()

[Sukadev Bhattiprolu]

Define a helper, chip_to_vas_id() to map a given chip id to corresponding
vas id.

Normally, callers of vas_rx_win_open() and vas_tx_win_open() want the VAS
window to be on the same chip where the calling thread is executing. These
callers can pass in -1 for the VAS id.

This interface will be useful if a thread running on one chip wants to open
a window on another chip (like the NX-842 driver does during start up).

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/vas.h       |  9 +++++++++
 arch/powerpc/platforms/powernv/vas.c | 11 +++++++++++
 drivers/crypto/nx/nx-842-powernv.c   | 18 +++---------------
 3 files changed, 23 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index fd5963a..044748f 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -104,6 +104,15 @@ struct vas_tx_win_attr {
 };
 
 /*
+ * Helper to map a chip id to VAS id.
+ * For POWER9, this is a 1:1 mapping. In the future this maybe a 1:N
+ * mapping in which case, we will need to update this helper.
+ *
+ * Return the VAS id or -1 if no matching vasid is found.
+ */
+int chip_to_vas_id(int chipid);
+
+/*
  * Helper to initialize receive window attributes to defaults for an
  * NX window.
  */
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index abb7090..cd9a733 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -123,6 +123,17 @@ struct vas_instance *find_vas_instance(int vasid)
 	return NULL;
 }
 
+int chip_to_vas_id(int chipid)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu_to_chip_id(cpu) == chipid)
+			return per_cpu(cpu_vas_id, cpu);
+	}
+	return -1;
+}
+
 static int vas_probe(struct platform_device *pdev)
 {
 	return init_vas_instance(pdev);
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 874ddf5..eb221ed 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -847,24 +847,12 @@ static int __init nx842_powernv_probe_vas(struct device_node *pn)
 		return -EINVAL;
 	}
 
-	for_each_compatible_node(dn, NULL, "ibm,power9-vas-x") {
-		if (of_get_ibm_chip_id(dn) == chip_id)
-			break;
-	}
-
-	if (!dn) {
-		pr_err("Missing VAS device node\n");
+	vasid = chip_to_vas_id(chip_id);
+	if (vasid < 0) {
+		pr_err("Unable to map chip_id %d to vasid\n", chip_id);
 		return -EINVAL;
 	}
 
-	if (of_property_read_u32(dn, "ibm,vas-id", &vasid)) {
-		pr_err("Missing ibm,vas-id device property\n");
-		of_node_put(dn);
-		return -EINVAL;
-	}
-
-	of_node_put(dn);
-
 	for_each_child_of_node(pn, dn) {
 		if (of_device_is_compatible(dn, "ibm,p9-nx-842")) {
 			ret = vas_cfg_coproc_info(dn, chip_id, vasid);
-- 
2.7.4

[PATCH v2 11/18] powerpc/vas: Export HVWC to debugfs

[Sukadev Bhattiprolu]

Export the VAS Window context information to debugfs.

We need to hold a mutex when closing the window to prevent a race
with the debugfs read(). Rather than introduce a per-instance mutex,
we use the global vas_mutex for now, since it is not heavily contended.

The window->cop field is only relevant to a receive window so we were
not setting it for a send window (which is is paired to a receive window
anyway). But to simplify reporting in debugfs, set the 'cop' field for the
send window also.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/Makefile     |   3 +-
 arch/powerpc/platforms/powernv/vas-debug.c  | 209 ++++++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/vas-window.c |  34 ++++-
 arch/powerpc/platforms/powernv/vas.c        |   6 +-
 arch/powerpc/platforms/powernv/vas.h        |  14 ++
 5 files changed, 259 insertions(+), 7 deletions(-)
 create mode 100644 arch/powerpc/platforms/powernv/vas-debug.c

diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 37d60f7..17921c4 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -14,4 +14,5 @@ obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
 obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
-obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o
+obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o vas-debug.o
+obj-$(CONFIG_PPC_FTW)	+= nx-ftw.o
diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c
new file mode 100644
index 0000000..ca22f1e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/vas-debug.c
@@ -0,0 +1,209 @@
+/*
+ * Copyright 2016-17 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include "vas.h"
+
+static struct dentry *vas_debugfs;
+
+static char *cop_to_str(int cop)
+{
+	switch (cop) {
+	case VAS_COP_TYPE_FAULT:	return "Fault";
+	case VAS_COP_TYPE_842:		return "NX-842 Normal Priority";
+	case VAS_COP_TYPE_842_HIPRI:	return "NX-842 High Priority";
+	case VAS_COP_TYPE_GZIP:		return "NX-GZIP Normal Priority";
+	case VAS_COP_TYPE_GZIP_HIPRI:	return "NX-GZIP High Priority";
+	case VAS_COP_TYPE_FTW:		return "Fast Thread-wakeup";
+	default:			return "Unknown";
+	}
+}
+
+static int info_dbg_show(struct seq_file *s, void *private)
+{
+	struct vas_window *window = s->private;
+
+	mutex_lock(&vas_mutex);
+
+	/* ensure window is not unmapped */
+	if (!window->hvwc_map)
+		goto unlock;
+
+	seq_printf(s, "Type: %s, %s\n", cop_to_str(window->cop),
+					window->tx_win ? "Send" : "Receive");
+	seq_printf(s, "Pid : %d\n", window->pid);
+
+unlock:
+	mutex_unlock(&vas_mutex);
+	return 0;
+}
+
+static int info_dbg_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, info_dbg_show, inode->i_private);
+}
+
+static const struct file_operations info_fops = {
+	.open		= info_dbg_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static inline void print_reg(struct seq_file *s, struct vas_window *win,
+			char *name, u32 reg)
+{
+	seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name);
+}
+
+static int hvwc_dbg_show(struct seq_file *s, void *private)
+{
+	struct vas_window *window = s->private;
+
+	mutex_lock(&vas_mutex);
+
+	/* ensure window is not unmapped */
+	if (!window->hvwc_map)
+		goto unlock;
+
+	print_reg(s, window, VREG(LPID));
+	print_reg(s, window, VREG(PID));
+	print_reg(s, window, VREG(XLATE_MSR));
+	print_reg(s, window, VREG(XLATE_LPCR));
+	print_reg(s, window, VREG(XLATE_CTL));
+	print_reg(s, window, VREG(AMR));
+	print_reg(s, window, VREG(SEIDR));
+	print_reg(s, window, VREG(FAULT_TX_WIN));
+	print_reg(s, window, VREG(OSU_INTR_SRC_RA));
+	print_reg(s, window, VREG(HV_INTR_SRC_RA));
+	print_reg(s, window, VREG(PSWID));
+	print_reg(s, window, VREG(LFIFO_BAR));
+	print_reg(s, window, VREG(LDATA_STAMP_CTL));
+	print_reg(s, window, VREG(LDMA_CACHE_CTL));
+	print_reg(s, window, VREG(LRFIFO_PUSH));
+	print_reg(s, window, VREG(CURR_MSG_COUNT));
+	print_reg(s, window, VREG(LNOTIFY_AFTER_COUNT));
+	print_reg(s, window, VREG(LRX_WCRED));
+	print_reg(s, window, VREG(LRX_WCRED_ADDER));
+	print_reg(s, window, VREG(TX_WCRED));
+	print_reg(s, window, VREG(TX_WCRED_ADDER));
+	print_reg(s, window, VREG(LFIFO_SIZE));
+	print_reg(s, window, VREG(WINCTL));
+	print_reg(s, window, VREG(WIN_STATUS));
+	print_reg(s, window, VREG(WIN_CTX_CACHING_CTL));
+	print_reg(s, window, VREG(TX_RSVD_BUF_COUNT));
+	print_reg(s, window, VREG(LRFIFO_WIN_PTR));
+	print_reg(s, window, VREG(LNOTIFY_CTL));
+	print_reg(s, window, VREG(LNOTIFY_PID));
+	print_reg(s, window, VREG(LNOTIFY_LPID));
+	print_reg(s, window, VREG(LNOTIFY_TID));
+	print_reg(s, window, VREG(LNOTIFY_SCOPE));
+	print_reg(s, window, VREG(NX_UTIL_ADDER));
+unlock:
+	mutex_unlock(&vas_mutex);
+	return 0;
+}
+
+static int hvwc_dbg_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hvwc_dbg_show, inode->i_private);
+}
+
+static const struct file_operations hvwc_fops = {
+	.open		= hvwc_dbg_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void vas_window_free_dbgdir(struct vas_window *window)
+{
+	if (window->dbgdir) {
+		debugfs_remove_recursive(window->dbgdir);
+		kfree(window->dbgname);
+		window->dbgdir = NULL;
+		window->dbgname = NULL;
+	}
+}
+
+void vas_window_init_dbgdir(struct vas_window *window)
+{
+	struct dentry *f, *d;
+
+	if (!window->vinst->dbgdir)
+		return;
+
+	window->dbgname = kzalloc(16, GFP_KERNEL);
+	if (!window->dbgname)
+		return;
+
+	snprintf(window->dbgname, 16, "w%d", window->winid);
+
+	d = debugfs_create_dir(window->dbgname, window->vinst->dbgdir);
+	if (IS_ERR(d))
+		goto free_name;
+
+	window->dbgdir = d;
+
+	f = debugfs_create_file("info", 0444, d, window, &info_fops);
+	if (IS_ERR(f))
+		goto remove_dir;
+
+	f = debugfs_create_file("hvwc", 0444, d, window, &hvwc_fops);
+	if (IS_ERR(f))
+		goto remove_dir;
+
+	return;
+
+free_name:
+	kfree(window->dbgname);
+	window->dbgname = NULL;
+
+remove_dir:
+	debugfs_remove_recursive(window->dbgdir);
+	window->dbgdir = NULL;
+}
+
+void vas_instance_init_dbgdir(struct vas_instance *vinst)
+{
+	struct dentry *d;
+
+	if (!vas_debugfs)
+		return;
+
+	vinst->dbgname = kzalloc(16, GFP_KERNEL);
+	if (!vinst->dbgname)
+		return;
+
+	snprintf(vinst->dbgname, 16, "v%d", vinst->vas_id);
+
+	d = debugfs_create_dir(vinst->dbgname, vas_debugfs);
+	if (IS_ERR(d))
+		goto free_name;
+
+	vinst->dbgdir = d;
+	return;
+
+free_name:
+	kfree(vinst->dbgname);
+	vinst->dbgname = NULL;
+	vinst->dbgdir = NULL;
+}
+
+void vas_init_dbgdir(void)
+{
+	vas_debugfs = debugfs_create_dir("vas", NULL);
+	if (IS_ERR(vas_debugfs))
+		vas_debugfs = NULL;
+}
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 23c13a7..088ce56 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -145,24 +145,42 @@ static void unmap_paste_region(struct vas_window *window)
 }
 
 /*
- * Unmap the MMIO regions for a window.
+ * Unmap the MMIO regions for a window. Hold the vas_mutex so we don't
+ * unmap when the window's debugfs dir is in use. This serializes close
+ * of a window even on another VAS instance but since its not a critical
+ * path, just minimize the time we hold the mutex for now. We can add
+ * a per-instance mutex later if necessary.
  */
 static void unmap_winctx_mmio_bars(struct vas_window *window)
 {
 	int len;
+	void *uwc_map;
+	void *hvwc_map;
 	u64 busaddr_start;
 
+	mutex_lock(&vas_mutex);
+
 	if (window->hvwc_map) {
-		get_hvwc_mmio_bar(window, &busaddr_start, &len);
-		unmap_region(window->hvwc_map, busaddr_start, len);
+		hvwc_map = window->hvwc_map;
 		window->hvwc_map = NULL;
 	}
 
 	if (window->uwc_map) {
-		get_uwc_mmio_bar(window, &busaddr_start, &len);
-		unmap_region(window->uwc_map, busaddr_start, len);
+		uwc_map = window->uwc_map;
 		window->uwc_map = NULL;
 	}
+
+	mutex_unlock(&vas_mutex);
+
+	if (hvwc_map) {
+		get_hvwc_mmio_bar(window, &busaddr_start, &len);
+		unmap_region(hvwc_map, busaddr_start, len);
+	}
+
+	if (uwc_map) {
+		get_uwc_mmio_bar(window, &busaddr_start, &len);
+		unmap_region(uwc_map, busaddr_start, len);
+	}
 }
 
 /*
@@ -528,6 +546,9 @@ static void vas_window_free(struct vas_window *window)
 	struct vas_instance *vinst = window->vinst;
 
 	unmap_winctx_mmio_bars(window);
+
+	vas_window_free_dbgdir(window);
+
 	kfree(window);
 
 	vas_release_window_id(&vinst->ida, winid);
@@ -552,6 +573,8 @@ static struct vas_window *vas_window_alloc(struct vas_instance *vinst)
 	if (map_winctx_mmio_bars(window))
 		goto out_free;
 
+	vas_window_init_dbgdir(window);
+
 	return window;
 
 out_free:
@@ -974,6 +997,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
 		goto put_rxwin;
 	}
 
+	txwin->cop = cop;
 	txwin->tx_win = 1;
 	txwin->rxwin = rxwin;
 	txwin->nx_win = txwin->rxwin->nx_win;
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index cd9a733..c488621 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -22,7 +22,7 @@
 
 #include "vas.h"
 
-static DEFINE_MUTEX(vas_mutex);
+DEFINE_MUTEX(vas_mutex);
 static LIST_HEAD(vas_instances);
 
 static DEFINE_PER_CPU(int, cpu_vas_id);
@@ -86,6 +86,8 @@ static int init_vas_instance(struct platform_device *pdev)
 	list_add(&vinst->node, &vas_instances);
 	mutex_unlock(&vas_mutex);
 
+	vas_instance_init_dbgdir(vinst);
+
 	dev_set_drvdata(&pdev->dev, vinst);
 
 	return 0;
@@ -157,6 +159,8 @@ static int __init vas_init(void)
 	int found = 0;
 	struct device_node *dn;
 
+	vas_init_dbgdir();
+
 	platform_driver_register(&vas_driver);
 
 	for_each_compatible_node(dn, NULL, "ibm,vas") {
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index ad906f6..145749a 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -13,6 +13,8 @@
 #include <linux/idr.h>
 #include <asm/vas.h>
 #include <linux/io.h>
+#include <linux/dcache.h>
+#include <linux/mutex.h>
 
 /*
  * Overview of Virtual Accelerator Switchboard (VAS).
@@ -317,6 +319,9 @@ struct vas_instance {
 	struct mutex mutex;
 	struct vas_window *rxwin[VAS_COP_TYPE_MAX];
 	struct vas_window *windows[VAS_WINDOWS_PER_CHIP];
+
+	char *dbgname;
+	struct dentry *dbgdir;
 };
 
 /*
@@ -334,6 +339,9 @@ struct vas_window {
 	pid_t pid;		/* Linux process id of owner */
 	int wcreds_max;		/* Window credits */
 
+	char *dbgname;
+	struct dentry *dbgdir;
+
 	/* Fields applicable only to send windows */
 	void *paste_kaddr;
 	char *paste_addr_name;
@@ -394,7 +402,13 @@ struct vas_winctx {
 	enum vas_notify_after_count notify_after_count;
 };
 
+extern struct mutex vas_mutex;
+
 extern struct vas_instance *find_vas_instance(int vasid);
+extern void vas_init_dbgdir(void);
+extern void vas_instance_init_dbgdir(struct vas_instance *vinst);
+extern void vas_window_init_dbgdir(struct vas_window *win);
+extern void vas_window_free_dbgdir(struct vas_window *win);
 
 static inline void vas_log_write(struct vas_window *win, char *name,
 			void *regptr, u64 val)
-- 
2.7.4

Re: [PATCH v2 11/18] powerpc/vas: Export HVWC to debugfs

[Michael Ellerman]

Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> writes:

> diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
> index 23c13a7..088ce56 100644
> --- a/arch/powerpc/platforms/powernv/vas-window.c
> +++ b/arch/powerpc/platforms/powernv/vas-window.c
> @@ -145,24 +145,42 @@ static void unmap_paste_region(struct vas_window *window)
>  }
>  
>  /*
> - * Unmap the MMIO regions for a window.
> + * Unmap the MMIO regions for a window. Hold the vas_mutex so we don't
> + * unmap when the window's debugfs dir is in use. This serializes close
> + * of a window even on another VAS instance but since its not a critical
> + * path, just minimize the time we hold the mutex for now. We can add
> + * a per-instance mutex later if necessary.
>   */
>  static void unmap_winctx_mmio_bars(struct vas_window *window)
>  {
>  	int len;
> +	void *uwc_map;
> +	void *hvwc_map;
>  	u64 busaddr_start;
>  
> +	mutex_lock(&vas_mutex);
> +
>  	if (window->hvwc_map) {
> -		get_hvwc_mmio_bar(window, &busaddr_start, &len);
> -		unmap_region(window->hvwc_map, busaddr_start, len);
> +		hvwc_map = window->hvwc_map;
>  		window->hvwc_map = NULL;
>  	}
>  
>  	if (window->uwc_map) {
> -		get_uwc_mmio_bar(window, &busaddr_start, &len);
> -		unmap_region(window->uwc_map, busaddr_start, len);
> +		uwc_map = window->uwc_map;
>  		window->uwc_map = NULL;
>  	}
> +
> +	mutex_unlock(&vas_mutex);
> +
> +	if (hvwc_map) {
> +		get_hvwc_mmio_bar(window, &busaddr_start, &len);
> +		unmap_region(hvwc_map, busaddr_start, len);
> +	}
> +
> +	if (uwc_map) {
> +		get_uwc_mmio_bar(window, &busaddr_start, &len);
> +		unmap_region(uwc_map, busaddr_start, len);
> +	}

arch/powerpc/platforms/powernv/vas-window.c: In function 'unmap_winctx_mmio_bars':
arch/powerpc/platforms/powernv/vas-window.c:137:2: error: 'uwc_map' may be used uninitialized in this function [-Werror=maybe-uninitialized]
  iounmap(addr);
  ^
arch/powerpc/platforms/powernv/vas-window.c:168:8: note: 'uwc_map' was declared here
  void *uwc_map;
        ^
arch/powerpc/platforms/powernv/vas-window.c:137:2: error: 'hvwc_map' may be used uninitialized in this function [-Werror=maybe-uninitialized]
  iounmap(addr);
  ^
arch/powerpc/platforms/powernv/vas-window.c:169:8: note: 'hvwc_map' was declared here
  void *hvwc_map;
        ^
cc1: all warnings being treated as errors


cheers

[PATCH v2 12/18] powerpc: have copy depend on CONFIG_BOOK3S_64

[Sukadev Bhattiprolu]

Have the COPY/PASTE instructions depend on CONFIG_BOOK3S_64 rather than
CONFIG_PPC_STD_MMU_64.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/process.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a0c74bb..37ed60b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1215,10 +1215,14 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
+#endif /* CONFIG_PPC_STD_MMU_64 */
 
 	if (current_thread_info()->task->thread.regs) {
+#ifdef CONFIG_PPC_STD_MMU_64
 		restore_math(current_thread_info()->task->thread.regs);
+#endif /* CONFIG_PPC_STD_MMU_64 */
 
+#ifdef CONFIG_PPC_BOOK3S_64
 		/*
 		 * The copy-paste buffer can only store into foreign real
 		 * addresses, so unprivileged processes can not see the
@@ -1237,8 +1241,8 @@ struct task_struct *__switch_to(struct task_struct *prev,
 			asm volatile(PPC_COPY(%0, %1)
 					: : "r"(dummy_copy_buffer), "r"(0));
 		}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 	}
-#endif /* CONFIG_PPC_STD_MMU_64 */
 
 	return last;
 }
-- 
2.7.4

[PATCH v2 13/18] powerpc: Add support for setting SPRN_TIDR

[Sukadev Bhattiprolu]

We need the SPRN_TIDR to be set for use with fast thread-wakeup (core-
to-core wakeup) and also with CAPI.

Each thread in a process needs to have a unique id within the process.
But as explained below, for now, we assign globally unique thread ids
to all threads in the system.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
---
Changelog[v3]
	- Merge changes with and address comments to Christophe's patch.
	  (i.e drop CONFIG_PPC_VAS; use CONFIG_PPC64; check CPU_ARCH_300
	  before setting TIDR). Defer following to separate patches:
	  	- emulation parts of Christophe's patch,
		- setting TIDR for tasks other than 'current'
		- setting feature bit in AT_HWCAP2

Changelog[v2]
	- Michael Ellerman: Use an interface to assign TIDR so it is
	    assigned to only threads that need it; move assignment to
	    restore_sprs(). Drop lint from rebase;
---
 arch/powerpc/include/asm/processor.h |   1 +
 arch/powerpc/include/asm/switch_to.h |   3 +
 arch/powerpc/kernel/process.c        | 122 +++++++++++++++++++++++++++++++++++
 3 files changed, 126 insertions(+)

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index fab7ff8..58cc212 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -329,6 +329,7 @@ struct thread_struct {
 	 */
 	int		dscr_inherit;
 	unsigned long	ppr;	/* used to save/restore SMT priority */
+	unsigned long	tidr;
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	unsigned long	tar;
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 17c8380..f5da32f 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -91,4 +91,7 @@ static inline void clear_task_ebb(struct task_struct *t)
 #endif
 }
 
+extern int set_thread_tidr(struct task_struct *t);
+extern void clear_thread_tidr(struct task_struct *t);
+
 #endif /* _ASM_POWERPC_SWITCH_TO_H */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 37ed60b..d861fcd 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1120,6 +1120,13 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 			mtspr(SPRN_TAR, new_thread->tar);
 	}
 #endif
+#ifdef CONFIG_PPC64
+	if (old_thread->tidr != new_thread->tidr) {
+		/* TIDR should be non-zero only with ISA3.0. */
+		WARN_ON_ONCE(!cpu_has_feature(CPU_FTR_ARCH_300));
+		mtspr(SPRN_TIDR, new_thread->tidr);
+	}
+#endif
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1438,9 +1445,117 @@ void flush_thread(void)
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 }
 
+#ifdef CONFIG_PPC64
+static DEFINE_SPINLOCK(vas_thread_id_lock);
+static DEFINE_IDA(vas_thread_ida);
+
+/*
+ * We need to assign a unique thread id to each thread in a process.
+ *
+ * This thread id, referred to as TIDR, and separate from the Linux's tgid,
+ * is intended to be used to direct an ASB_Notify from the hardware to the
+ * thread, when a suitable event occurs in the system.
+ *
+ * One such event is a "paste" instruction in the context of Fast Thread
+ * Wakeup (aka Core-to-core wake up in the Virtual Accelerator Switchboard
+ * (VAS) in POWER9.
+ *
+ * To get a unique TIDR per process we could simply reuse task_pid_nr() but
+ * the problem is that task_pid_nr() is not yet available copy_thread() is
+ * called. Fixing that would require changing more intrusive arch-neutral
+ * code in code path in copy_process()?.
+ *
+ * Further, to assign unique TIDRs within each process, we need an atomic
+ * field (or an IDR) in task_struct, which again intrudes into the arch-
+ * neutral code. So try to assign globally unique TIDRs for now.
+ *
+ * NOTE: TIDR 0 indicates that the thread does not need a TIDR value.
+ *	 For now, only threads that expect to be notified by the VAS
+ *	 hardware need a TIDR value and we assign values > 0 for those.
+ */
+#define MAX_THREAD_CONTEXT	((1 << 16) - 1)
+static int assign_thread_tidr(void)
+{
+	int index;
+	int err;
+
+again:
+	if (!ida_pre_get(&vas_thread_ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	spin_lock(&vas_thread_id_lock);
+	err = ida_get_new_above(&vas_thread_ida, 1, &index);
+	spin_unlock(&vas_thread_id_lock);
+
+	if (err == -EAGAIN)
+		goto again;
+	else if (err)
+		return err;
+
+	if (index > MAX_THREAD_CONTEXT) {
+		spin_lock(&vas_thread_id_lock);
+		ida_remove(&vas_thread_ida, index);
+		spin_unlock(&vas_thread_id_lock);
+		return -ENOMEM;
+	}
+
+	return index;
+}
+
+static void free_thread_tidr(int id)
+{
+	spin_lock(&vas_thread_id_lock);
+	ida_remove(&vas_thread_ida, id);
+	spin_unlock(&vas_thread_id_lock);
+}
+
+/*
+ * Clear any TIDR value assigned to this thread.
+ */
+void clear_thread_tidr(struct task_struct *t)
+{
+	if (!t->thread.tidr)
+		return;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	mtspr(SPRN_TIDR, 0);
+	free_thread_tidr(t->thread.tidr);
+	t->thread.tidr = 0;
+}
+
+/*
+ * Assign a unique TIDR (thread id) for task @t and set it in the thread
+ * structure. For now, we only support setting TIDR for 'current' task.
+ */
+int set_thread_tidr(struct task_struct *t)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return -EINVAL;
+
+	if (t != current)
+		return -EINVAL;
+
+	t->thread.tidr = assign_thread_tidr();
+	if (t->thread.tidr < 0)
+		return t->thread.tidr;
+
+	mtspr(SPRN_TIDR, t->thread.tidr);
+
+	return 0;
+}
+
+#endif /* CONFIG_PPC64 */
+
 void
 release_thread(struct task_struct *t)
 {
+#ifdef CONFIG_PPC64
+	clear_thread_tidr(t);
+#endif
 }
 
 /*
@@ -1466,6 +1581,10 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	clear_task_ebb(dst);
 
+#ifdef CONFIG_PPC64
+	dst->thread.tidr = 0;
+#endif
+
 	return 0;
 }
 
@@ -1576,6 +1695,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif
 
 	setup_ksp_vsid(p, sp);
+#ifdef CONFIG_PPC64
+	p->thread.tidr = 0;
+#endif
 
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-- 
2.7.4

Re: [PATCH v2 13/18] powerpc: Add support for setting SPRN_TIDR

[Frederic Barrat]

Le 07/10/2017 à 04:28, Sukadev Bhattiprolu a écrit :
> We need the SPRN_TIDR to be set for use with fast thread-wakeup (core-
> to-core wakeup) and also with CAPI.
> 
> Each thread in a process needs to have a unique id within the process.
> But as explained below, for now, we assign globally unique thread ids
> to all threads in the system.
> 
> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
> Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
> Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
> ---

FWIW
Reviewed-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>


> Changelog[v3]
> 	- Merge changes with and address comments to Christophe's patch.
> 	  (i.e drop CONFIG_PPC_VAS; use CONFIG_PPC64; check CPU_ARCH_300
> 	  before setting TIDR). Defer following to separate patches:
> 	  	- emulation parts of Christophe's patch,
> 		- setting TIDR for tasks other than 'current'
> 		- setting feature bit in AT_HWCAP2
> 
> Changelog[v2]
> 	- Michael Ellerman: Use an interface to assign TIDR so it is
> 	    assigned to only threads that need it; move assignment to
> 	    restore_sprs(). Drop lint from rebase;
> ---
>   arch/powerpc/include/asm/processor.h |   1 +
>   arch/powerpc/include/asm/switch_to.h |   3 +
>   arch/powerpc/kernel/process.c        | 122 +++++++++++++++++++++++++++++++++++
>   3 files changed, 126 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
> index fab7ff8..58cc212 100644
> --- a/arch/powerpc/include/asm/processor.h
> +++ b/arch/powerpc/include/asm/processor.h
> @@ -329,6 +329,7 @@ struct thread_struct {
>   	 */
>   	int		dscr_inherit;
>   	unsigned long	ppr;	/* used to save/restore SMT priority */
> +	unsigned long	tidr;
>   #endif
>   #ifdef CONFIG_PPC_BOOK3S_64
>   	unsigned long	tar;
> diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
> index 17c8380..f5da32f 100644
> --- a/arch/powerpc/include/asm/switch_to.h
> +++ b/arch/powerpc/include/asm/switch_to.h
> @@ -91,4 +91,7 @@ static inline void clear_task_ebb(struct task_struct *t)
>   #endif
>   }
> 
> +extern int set_thread_tidr(struct task_struct *t);
> +extern void clear_thread_tidr(struct task_struct *t);
> +
>   #endif /* _ASM_POWERPC_SWITCH_TO_H */
> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index 37ed60b..d861fcd 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -1120,6 +1120,13 @@ static inline void restore_sprs(struct thread_struct *old_thread,
>   			mtspr(SPRN_TAR, new_thread->tar);
>   	}
>   #endif
> +#ifdef CONFIG_PPC64
> +	if (old_thread->tidr != new_thread->tidr) {
> +		/* TIDR should be non-zero only with ISA3.0. */
> +		WARN_ON_ONCE(!cpu_has_feature(CPU_FTR_ARCH_300));
> +		mtspr(SPRN_TIDR, new_thread->tidr);
> +	}
> +#endif
>   }
> 
>   #ifdef CONFIG_PPC_BOOK3S_64
> @@ -1438,9 +1445,117 @@ void flush_thread(void)
>   #endif /* CONFIG_HAVE_HW_BREAKPOINT */
>   }
> 
> +#ifdef CONFIG_PPC64
> +static DEFINE_SPINLOCK(vas_thread_id_lock);
> +static DEFINE_IDA(vas_thread_ida);
> +
> +/*
> + * We need to assign a unique thread id to each thread in a process.
> + *
> + * This thread id, referred to as TIDR, and separate from the Linux's tgid,
> + * is intended to be used to direct an ASB_Notify from the hardware to the
> + * thread, when a suitable event occurs in the system.
> + *
> + * One such event is a "paste" instruction in the context of Fast Thread
> + * Wakeup (aka Core-to-core wake up in the Virtual Accelerator Switchboard
> + * (VAS) in POWER9.
> + *
> + * To get a unique TIDR per process we could simply reuse task_pid_nr() but
> + * the problem is that task_pid_nr() is not yet available copy_thread() is
> + * called. Fixing that would require changing more intrusive arch-neutral
> + * code in code path in copy_process()?.
> + *
> + * Further, to assign unique TIDRs within each process, we need an atomic
> + * field (or an IDR) in task_struct, which again intrudes into the arch-
> + * neutral code. So try to assign globally unique TIDRs for now.
> + *
> + * NOTE: TIDR 0 indicates that the thread does not need a TIDR value.
> + *	 For now, only threads that expect to be notified by the VAS
> + *	 hardware need a TIDR value and we assign values > 0 for those.
> + */
> +#define MAX_THREAD_CONTEXT	((1 << 16) - 1)
> +static int assign_thread_tidr(void)
> +{
> +	int index;
> +	int err;
> +
> +again:
> +	if (!ida_pre_get(&vas_thread_ida, GFP_KERNEL))
> +		return -ENOMEM;
> +
> +	spin_lock(&vas_thread_id_lock);
> +	err = ida_get_new_above(&vas_thread_ida, 1, &index);
> +	spin_unlock(&vas_thread_id_lock);
> +
> +	if (err == -EAGAIN)
> +		goto again;
> +	else if (err)
> +		return err;
> +
> +	if (index > MAX_THREAD_CONTEXT) {
> +		spin_lock(&vas_thread_id_lock);
> +		ida_remove(&vas_thread_ida, index);
> +		spin_unlock(&vas_thread_id_lock);
> +		return -ENOMEM;
> +	}
> +
> +	return index;
> +}
> +
> +static void free_thread_tidr(int id)
> +{
> +	spin_lock(&vas_thread_id_lock);
> +	ida_remove(&vas_thread_ida, id);
> +	spin_unlock(&vas_thread_id_lock);
> +}
> +
> +/*
> + * Clear any TIDR value assigned to this thread.
> + */
> +void clear_thread_tidr(struct task_struct *t)
> +{
> +	if (!t->thread.tidr)
> +		return;
> +
> +	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
> +		WARN_ON_ONCE(1);
> +		return;
> +	}
> +
> +	mtspr(SPRN_TIDR, 0);
> +	free_thread_tidr(t->thread.tidr);
> +	t->thread.tidr = 0;
> +}
> +
> +/*
> + * Assign a unique TIDR (thread id) for task @t and set it in the thread
> + * structure. For now, we only support setting TIDR for 'current' task.
> + */
> +int set_thread_tidr(struct task_struct *t)
> +{
> +	if (!cpu_has_feature(CPU_FTR_ARCH_300))
> +		return -EINVAL;
> +
> +	if (t != current)
> +		return -EINVAL;
> +
> +	t->thread.tidr = assign_thread_tidr();
> +	if (t->thread.tidr < 0)
> +		return t->thread.tidr;
> +
> +	mtspr(SPRN_TIDR, t->thread.tidr);
> +
> +	return 0;
> +}
> +
> +#endif /* CONFIG_PPC64 */
> +
>   void
>   release_thread(struct task_struct *t)
>   {
> +#ifdef CONFIG_PPC64
> +	clear_thread_tidr(t);
> +#endif
>   }
> 
>   /*
> @@ -1466,6 +1581,10 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
> 
>   	clear_task_ebb(dst);
> 
> +#ifdef CONFIG_PPC64
> +	dst->thread.tidr = 0;
> +#endif
> +
>   	return 0;
>   }
> 
> @@ -1576,6 +1695,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
>   #endif
> 
>   	setup_ksp_vsid(p, sp);
> +#ifdef CONFIG_PPC64
> +	p->thread.tidr = 0;
> +#endif
> 
>   #ifdef CONFIG_PPC64
>   	if (cpu_has_feature(CPU_FTR_DSCR)) {
> 

[PATCH v2 14/18] powerpc: Define set_thread_used_vas()

[Sukadev Bhattiprolu]

A CP_ABORT instruction is required in processes that have mapped a VAS
"paste address" with the intention of using COPY/PASTE instructions.
But since CP_ABORT is expensive, we want to restrict it to only processes
that use/intend to use COPY/PASTE.

Define an interface, set_thread_used_vas(), that VAS can use to indicate
that the current process opened a send window. During context switch,
issue CP_ABORT only for processes that have the flag set.

Thanks for input from Nick Piggin, Michael Ellerman.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/processor.h |  2 ++
 arch/powerpc/include/asm/switch_to.h |  2 ++
 arch/powerpc/kernel/process.c        | 32 ++++++++++++++++++++++----------
 3 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 58cc212..bdab3b74 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -341,7 +341,9 @@ struct thread_struct {
 	unsigned long	sier;
 	unsigned long	mmcr2;
 	unsigned 	mmcr0;
+
 	unsigned 	used_ebb;
+	unsigned int	used_vas;
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index f5da32f..aeb305b 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -91,6 +91,8 @@ static inline void clear_task_ebb(struct task_struct *t)
 #endif
 }
 
+extern int set_thread_used_vas(void);
+
 extern int set_thread_tidr(struct task_struct *t);
 extern void clear_thread_tidr(struct task_struct *t);
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d861fcd..cb5f108 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1234,17 +1234,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		 * The copy-paste buffer can only store into foreign real
 		 * addresses, so unprivileged processes can not see the
 		 * data or use it in any way unless they have foreign real
-		 * mappings. We don't have a VAS driver that allocates those
-		 * yet, so no cpabort is required.
+		 * mappings. If the new process has the foreign real address
+		 * mappings, we must issue a cp_abort to clear any state and
+		 * prevent a covert channel being setup.
+		 *
+		 * DD1 allows paste into normal system memory so we do an
+		 * unpaired copy, rather than cp_abort, to clear the buffer,
+		 * since cp_abort is quite expensive.
 		 */
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-			/*
-			 * DD1 allows paste into normal system memory, so we
-			 * do an unpaired copy here to clear the buffer and
-			 * prevent a covert channel being set up.
-			 *
-			 * cpabort is not used because it is quite expensive.
-			 */
+		if (new_thread->used_vas) {
+			asm volatile(PPC_CP_ABORT);
+		} else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
 			asm volatile(PPC_COPY(%0, %1)
 					: : "r"(dummy_copy_buffer), "r"(0));
 		}
@@ -1445,6 +1445,18 @@ void flush_thread(void)
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 }
 
+int set_thread_used_vas(void)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return -EINVAL;
+
+	current->thread.used_vas = 1;
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+	return 0;
+}
+
 #ifdef CONFIG_PPC64
 static DEFINE_SPINLOCK(vas_thread_id_lock);
 static DEFINE_IDA(vas_thread_ida);
-- 
2.7.4

Re: [PATCH v2 14/18] powerpc: Define set_thread_used_vas()

[Nicholas Piggin]

On Fri,  6 Oct 2017 19:28:14 -0700
Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> wrote:

> A CP_ABORT instruction is required in processes that have mapped a VAS
> "paste address" with the intention of using COPY/PASTE instructions.
> But since CP_ABORT is expensive, we want to restrict it to only processes
> that use/intend to use COPY/PASTE.
> 
> Define an interface, set_thread_used_vas(), that VAS can use to indicate
> that the current process opened a send window. During context switch,
> issue CP_ABORT only for processes that have the flag set.
> 
> Thanks for input from Nick Piggin, Michael Ellerman.
> 
> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/processor.h |  2 ++
>  arch/powerpc/include/asm/switch_to.h |  2 ++
>  arch/powerpc/kernel/process.c        | 32 ++++++++++++++++++++++----------
>  3 files changed, 26 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
> index 58cc212..bdab3b74 100644
> --- a/arch/powerpc/include/asm/processor.h
> +++ b/arch/powerpc/include/asm/processor.h
> @@ -341,7 +341,9 @@ struct thread_struct {
>  	unsigned long	sier;
>  	unsigned long	mmcr2;
>  	unsigned 	mmcr0;
> +
>  	unsigned 	used_ebb;
> +	unsigned int	used_vas;
>  #endif
>  };
>  
> diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
> index f5da32f..aeb305b 100644
> --- a/arch/powerpc/include/asm/switch_to.h
> +++ b/arch/powerpc/include/asm/switch_to.h
> @@ -91,6 +91,8 @@ static inline void clear_task_ebb(struct task_struct *t)
>  #endif
>  }
>  
> +extern int set_thread_used_vas(void);
> +
>  extern int set_thread_tidr(struct task_struct *t);
>  extern void clear_thread_tidr(struct task_struct *t);
>  
> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index d861fcd..cb5f108 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -1234,17 +1234,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
>  		 * The copy-paste buffer can only store into foreign real
>  		 * addresses, so unprivileged processes can not see the
>  		 * data or use it in any way unless they have foreign real
> -		 * mappings. We don't have a VAS driver that allocates those
> -		 * yet, so no cpabort is required.
> +		 * mappings. If the new process has the foreign real address
> +		 * mappings, we must issue a cp_abort to clear any state and
> +		 * prevent a covert channel being setup.
> +		 *
> +		 * DD1 allows paste into normal system memory so we do an
> +		 * unpaired copy, rather than cp_abort, to clear the buffer,
> +		 * since cp_abort is quite expensive.
>  		 */
> -		if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
> -			/*
> -			 * DD1 allows paste into normal system memory, so we
> -			 * do an unpaired copy here to clear the buffer and
> -			 * prevent a covert channel being set up.
> -			 *
> -			 * cpabort is not used because it is quite expensive.
> -			 */
> +		if (new_thread->used_vas) {
> +			asm volatile(PPC_CP_ABORT);
> +		} else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
>  			asm volatile(PPC_COPY(%0, %1)
>  					: : "r"(dummy_copy_buffer), "r"(0));
>  		}

I *think* we're okay with this now, right? If we are switching to a thread
with a foreign address mapping (that could interact with something in the
copy buffer from a previous thread), then we cp_abort to ensure the copy
buffer is clear.

It's not just a covert channel, but also snooping, or accidental or
deliberate corruption .


> @@ -1445,6 +1445,18 @@ void flush_thread(void)
>  #endif /* CONFIG_HAVE_HW_BREAKPOINT */
>  }
>  
> +int set_thread_used_vas(void)
> +{

At the risk of nitpicking, I would like to change from used (past
tense) to something else that indicates future tense. We have to set
this before starting to use vas.

I think we should pull in the abort into this function rather than
the caller, and your caller in patch 18 does not check the return
code which it should.

Other than these small bits, it looks much better, thanks!

> +#ifdef CONFIG_PPC_BOOK3S_64
> +	if (!cpu_has_feature(CPU_FTR_ARCH_300))
> +		return -EINVAL;
> +
> +	current->thread.used_vas = 1;
> +
> +#endif /* CONFIG_PPC_BOOK3S_64 */
> +	return 0;
> +}
> +
>  #ifdef CONFIG_PPC64
>  static DEFINE_SPINLOCK(vas_thread_id_lock);
>  static DEFINE_IDA(vas_thread_ida);

Re: [PATCH v2 14/18] powerpc: Define set_thread_used_vas()

[Michael Ellerman]

Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> writes:

> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index d861fcd..cb5f108 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -1234,17 +1234,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
>  		 * The copy-paste buffer can only store into foreign real
>  		 * addresses, so unprivileged processes can not see the
>  		 * data or use it in any way unless they have foreign real
> -		 * mappings. We don't have a VAS driver that allocates those
> -		 * yet, so no cpabort is required.
> +		 * mappings. If the new process has the foreign real address
> +		 * mappings, we must issue a cp_abort to clear any state and
> +		 * prevent a covert channel being setup.
> +		 *
> +		 * DD1 allows paste into normal system memory so we do an
> +		 * unpaired copy, rather than cp_abort, to clear the buffer,
> +		 * since cp_abort is quite expensive.
>  		 */
> -		if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
> -			/*
> -			 * DD1 allows paste into normal system memory, so we
> -			 * do an unpaired copy here to clear the buffer and
> -			 * prevent a covert channel being set up.
> -			 *
> -			 * cpabort is not used because it is quite expensive.
> -			 */
> +		if (new_thread->used_vas) {

So this has a bug in that it's not safe to use new_thread here.

Because this is on the way out of __switch_to(), this code can run both
when switching to a new task and also when switching back to an older
task. In the latter case the task pointed to by new_thread may have
already been freed.

I've fixed it up here to use current_thread_info()->task->thread.used_vas,
so that it's always checking current.

cheers

[PATCH v2 15/18] powerpc: Emulate paste instruction

[Sukadev Bhattiprolu]

From: Michael Neuling <mikey@neuling.org>

On POWER9 DD2.1 and below there are issues when the paste instruction
generates an error. If an error occurs when thread reconfiguration
happens (ie another thread in the core goes into/out of powersave) the
core may hang.

To avoid this a special sequence is required which stops thread
configuration so that the paste can be safely executed.

This patch assumes paste executed in userspace are trapped into the
illegal instruction exception at 0xe40.

Here we re-execute the paste instruction but with the required
sequence to ensure thread reconfiguration doesn't occur.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---

Edit by Sukadev: Use PPC_PASTE() rather than the paste instruction since
	in older versions the instruction required a third parameter.
---
 arch/powerpc/include/asm/emulated_ops.h |  1 +
 arch/powerpc/include/asm/ppc-opcode.h   |  1 +
 arch/powerpc/include/asm/reg.h          |  2 ++
 arch/powerpc/kernel/traps.c             | 64 +++++++++++++++++++++++++++++++++
 4 files changed, 68 insertions(+)

diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index f00e10e..9247af9 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -55,6 +55,7 @@ extern struct ppc_emulated {
 	struct ppc_emulated_entry mfdscr;
 	struct ppc_emulated_entry mtdscr;
 	struct ppc_emulated_entry lq_stq;
+	struct ppc_emulated_entry paste;
 #endif
 } ppc_emulated;
 
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index ce0930d..a55d2ef 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -229,6 +229,7 @@
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
 #define PPC_INST_PASTE			0x7c20070d
+#define PPC_INST_PASTE_MASK		0xfc2007ff
 #define PPC_INST_POPCNTB		0x7c0000f4
 #define PPC_INST_POPCNTB_MASK		0xfc0007fe
 #define PPC_INST_POPCNTD		0x7c0003f4
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f92eaf7..5cde1c4 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -468,6 +468,8 @@
 #define SPRN_DBAT7U	0x23E	/* Data BAT 7 Upper Register */
 #define SPRN_PPR	0x380	/* SMT Thread status Register */
 #define SPRN_TSCR	0x399	/* Thread Switch Control Register */
+#define SPRN_TRIG1	0x371	/* WAT Trigger 1 */
+#define SPRN_TRIG2	0x372	/* WAT Trigger 2 */
 
 #define SPRN_DEC	0x016		/* Decrement Register */
 #define SPRN_DER	0x095		/* Debug Enable Register */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 13c9dcd..7e6b1fe 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -956,6 +956,65 @@ static inline bool tm_abort_check(struct pt_regs *regs, int reason)
 }
 #endif
 
+static DEFINE_SPINLOCK(paste_emulation_lock);
+
+static inline int paste(void *i)
+{
+	int cr;
+	long retval = 0;
+
+	/* Need per core lock to ensure trig1/2 writes don't race */
+	spin_lock(&paste_emulation_lock);
+	mtspr(SPRN_TRIG1, 0); /* data doesn't matter */
+	mtspr(SPRN_TRIG1, 0); /* HW says do this twice */
+	asm volatile(
+		"1: " PPC_PASTE(0, %2) "\n"
+		"2: mfcr %1\n"
+		".section .fixup,\"ax\"\n"
+		"3:	li %0,%3\n"
+		"	li %2,0\n"
+		"	b 2b\n"
+		".previous\n"
+		EX_TABLE(1b, 3b)
+		: "=r" (retval), "=r" (cr)
+		: "b" (i), "i" (-EFAULT), "0" (retval));
+	mtspr(SPRN_TRIG2, 0);
+	spin_unlock(&paste_emulation_lock);
+	return cr;
+}
+
+static int emulate_paste(struct pt_regs *regs, u32 instword)
+{
+	const void __user *addr;
+	unsigned long ea;
+	u8 ra, rb;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return -EINVAL;
+
+	ra = (instword >> 16) & 0x1f;
+	rb = (instword >> 11) & 0x1f;
+
+	ea = regs->gpr[rb] + (ra ? regs->gpr[ra] : 0ul);
+	if (is_32bit_task())
+		ea &= 0xfffffffful;
+	addr = (__force const void __user *)ea;
+
+	if (!access_ok(VERIFY_WRITE, addr, 128)) // cacheline size == 128
+		return -EFAULT;
+
+	hard_irq_disable(); /* FIXME: could we just soft disable ?? */
+	pagefault_disable();
+
+	PPC_WARN_EMULATED(paste, regs);
+	regs->ccr = paste((void *)addr);
+
+	pagefault_enable();
+	may_hard_irq_enable();
+
+	return 0;
+}
+
 static int emulate_instruction(struct pt_regs *regs)
 {
 	u32 instword;
@@ -968,6 +1027,10 @@ static int emulate_instruction(struct pt_regs *regs)
 	if (get_user(instword, (u32 __user *)(regs->nip)))
 		return -EFAULT;
 
+	/* Emulate the paste RA, RB. */
+	if ((instword & PPC_INST_PASTE_MASK) == PPC_INST_PASTE)
+		return emulate_paste(regs, instword);
+
 	/* Emulate the mfspr rD, PVR. */
 	if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
 		PPC_WARN_EMULATED(mfpvr, regs);
@@ -1924,6 +1987,7 @@ struct ppc_emulated ppc_emulated = {
 	WARN_EMULATED_SETUP(mfdscr),
 	WARN_EMULATED_SETUP(mtdscr),
 	WARN_EMULATED_SETUP(lq_stq),
+	WARN_EMULATED_SETUP(paste),
 #endif
 };
 
-- 
2.7.4

Re: [PATCH v2 15/18] powerpc: Emulate paste instruction

[Michael Neuling]

@ -1924,6 +1987,7 @@ struct ppc_emulated ppc_emulated = {
>  	WARN_EMULATED_SETUP(mfdscr),
>  	WARN_EMULATED_SETUP(mtdscr),
>  	WARN_EMULATED_SETUP(lq_stq),
> +	WARN_EMULATED_SETUP(paste),

You'll need to rebase this on powerpc/next as this has changed upstream.

Mikey

Re: [PATCH v2 15/18] powerpc: Emulate paste instruction

[Michael Neuling]

@ -1924,6 +1987,7 @@ struct ppc_emulated ppc_emulated =3D {
> =C2=A0	WARN_EMULATED_SETUP(mfdscr),
> =C2=A0	WARN_EMULATED_SETUP(mtdscr),
> =C2=A0	WARN_EMULATED_SETUP(lq_stq),
> +	WARN_EMULATED_SETUP(paste),

You'll need to rebase this on powerpc/next as this has changed upstream.

Mikey

Re: [PATCH v2 15/18] powerpc: Emulate paste instruction

[Michael Ellerman]

Michael Neuling <mikey@neuling.org> writes:

> @ -1924,6 +1987,7 @@ struct ppc_emulated ppc_emulated = {
>>  	WARN_EMULATED_SETUP(mfdscr),
>>  	WARN_EMULATED_SETUP(mtdscr),
>>  	WARN_EMULATED_SETUP(lq_stq),
>> +	WARN_EMULATED_SETUP(paste),
>
> You'll need to rebase this on powerpc/next as this has changed upstream.

I can handle that, it should be a trivial conflict.

cheers

Re: [PATCH v2 15/18] powerpc: Emulate paste instruction

[Michael Ellerman]

Michael Neuling <mikey@neuling.org> writes:

> @ -1924,6 +1987,7 @@ struct ppc_emulated ppc_emulated =3D {
>> =C2=A0	WARN_EMULATED_SETUP(mfdscr),
>> =C2=A0	WARN_EMULATED_SETUP(mtdscr),
>> =C2=A0	WARN_EMULATED_SETUP(lq_stq),
>> +	WARN_EMULATED_SETUP(paste),
>
> You'll need to rebase this on powerpc/next as this has changed upstream.

I can handle that, it should be a trivial conflict.

cheers

[PATCH v2 16/18] powerpc/vas: Define vas_win_paste_addr()

[Sukadev Bhattiprolu]

Define an interface that the NX drivers can use to find the physical
paste address of a send window. This interface is expected to be used
with the mmap() operation of the NX driver's device. i.e the user space
process can use driver's mmap() operation to map the send window's paste
address into their address space and then use copy and paste instructions
to submit the CRBs to the NX engine.

Note that kernel drivers will use vas_paste_crb() directly and don't need
this interface.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/vas.h              |  7 +++++++
 arch/powerpc/platforms/powernv/vas-window.c | 10 ++++++++++
 2 files changed, 17 insertions(+)

diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index 044748f..f98ade8 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_POWERPC_VAS_H
 #define _ASM_POWERPC_VAS_H
 
+struct vas_window;
+
 /*
  * Min and max FIFO sizes are based on Version 1.05 Section 3.1.4.25
  * (Local FIFO Size Register) of the VAS workbook.
@@ -165,4 +167,9 @@ int vas_copy_crb(void *crb, int offset);
  */
 int vas_paste_crb(struct vas_window *win, int offset, bool re);
 
+/*
+ * Return the power bus paste address associated with @win so the caller
+ * can map that address into their address space.
+ */
+extern u64 vas_win_paste_addr(struct vas_window *win);
 #endif /* __ASM_POWERPC_VAS_H */
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 088ce56..e4a9c7b 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -40,6 +40,16 @@ static void compute_paste_address(struct vas_window *window, u64 *addr, int *len
 	pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
 }
 
+u64 vas_win_paste_addr(struct vas_window *win)
+{
+	u64 addr;
+
+	compute_paste_address(win, &addr, NULL);
+
+	return addr;
+}
+EXPORT_SYMBOL(vas_win_paste_addr);
+
 static inline void get_hvwc_mmio_bar(struct vas_window *window,
 			u64 *start, int *len)
 {
-- 
2.7.4

[PATCH v2 17/18] powerpc/vas: Define vas_win_id()

[Sukadev Bhattiprolu]

Define an interface to return a system-wide unique id for a given VAS
window.

The vas_win_id() will be used in a follow-on patch to generate an unique
handle for a user space receive window. Applications can use this handle
to pair send and receive windows for fast thread-wakeup.

The hardware refers to this system-wide unique id as a Partition Send
Window ID which is expected to be used during fault handling. Hence the
"pswid" in the function names.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/vas.h              |  5 +++++
 arch/powerpc/platforms/powernv/vas-window.c |  9 +++++++++
 arch/powerpc/platforms/powernv/vas.h        | 28 ++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index f98ade8..7714562 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -168,6 +168,11 @@ int vas_copy_crb(void *crb, int offset);
 int vas_paste_crb(struct vas_window *win, int offset, bool re);
 
 /*
+ * Return a system-wide unique id for the VAS window @win.
+ */
+extern u32 vas_win_id(struct vas_window *win);
+
+/*
  * Return the power bus paste address associated with @win so the caller
  * can map that address into their address space.
  */
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index e4a9c7b..1d08b64 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1239,3 +1239,12 @@ int vas_win_close(struct vas_window *window)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vas_win_close);
+
+/*
+ * Return a system-wide unique window id for the window @win.
+ */
+u32 vas_win_id(struct vas_window *win)
+{
+	return encode_pswid(win->vinst->vas_id, win->winid);
+}
+EXPORT_SYMBOL_GPL(vas_win_id);
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index 145749a..78a8926 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -447,4 +447,32 @@ static inline u64 read_hvwc_reg(struct vas_window *win,
 	return in_be64(win->hvwc_map+reg);
 }
 
+/*
+ * Encode/decode the Partition Send Window ID (PSWID) for a window in
+ * a way that we can uniquely identify any window in the system. i.e.
+ * we should be able to locate the 'struct vas_window' given the PSWID.
+ *
+ *	Bits	Usage
+ *	0:7	VAS id (8 bits)
+ *	8:15	Unused, 0 (3 bits)
+ *	16:31	Window id (16 bits)
+ */
+static inline u32 encode_pswid(int vasid, int winid)
+{
+	u32 pswid = 0;
+
+	pswid |= vasid << (31 - 7);
+	pswid |= winid;
+
+	return pswid;
+}
+
+static inline void decode_pswid(u32 pswid, int *vasid, int *winid)
+{
+	if (vasid)
+		*vasid = pswid >> (31 - 7) & 0xFF;
+
+	if (winid)
+		*winid = pswid & 0xFFFF;
+}
 #endif /* _VAS_H */
-- 
2.7.4

[PATCH v2 18/18] powerpc/vas: Add support for user receive window

[Sukadev Bhattiprolu]

Add support for user space receive window (for the Fast thread-wakeup
coprocessor type)

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/vas-window.c | 59 +++++++++++++++++++++++++----
 1 file changed, 52 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 1d08b64..99642ec 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -16,7 +16,8 @@
 #include <linux/log2.h>
 #include <linux/rcupdate.h>
 #include <linux/cred.h>
-
+#include <asm/switch_to.h>
+#include <asm/ppc-opcode.h>
 #include "vas.h"
 #include "copy-paste.h"
 
@@ -602,6 +603,32 @@ static void put_rx_win(struct vas_window *rxwin)
 }
 
 /*
+ * Find the user space receive window given the @pswid.
+ *      - We must have a valid vasid and it must belong to this instance.
+ *        (so both send and receive windows are on the same VAS instance)
+ *      - The window must refer to an OPEN, FTW, RECEIVE window.
+ *
+ * NOTE: We access ->windows[] table and assume that vinst->mutex is held.
+ */
+static struct vas_window *get_user_rxwin(struct vas_instance *vinst, u32 pswid)
+{
+	int vasid, winid;
+	struct vas_window *rxwin;
+
+	decode_pswid(pswid, &vasid, &winid);
+
+	if (vinst->vas_id != vasid)
+		return ERR_PTR(-EINVAL);
+
+	rxwin = vinst->windows[winid];
+
+	if (!rxwin || rxwin->tx_win || rxwin->cop != VAS_COP_TYPE_FTW)
+		return ERR_PTR(-EINVAL);
+
+	return rxwin;
+}
+
+/*
  * Get the VAS receive window associated with NX engine identified
  * by @cop and if applicable, @pswid.
  *
@@ -614,10 +641,10 @@ static struct vas_window *get_vinst_rxwin(struct vas_instance *vinst,
 
 	mutex_lock(&vinst->mutex);
 
-	if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI)
-		rxwin = vinst->rxwin[cop] ?: ERR_PTR(-EINVAL);
+	if (cop == VAS_COP_TYPE_FTW)
+		rxwin = get_user_rxwin(vinst, pswid);
 	else
-		rxwin = ERR_PTR(-EINVAL);
+		rxwin = vinst->rxwin[cop] ?: ERR_PTR(-EINVAL);
 
 	if (!IS_ERR(rxwin))
 		atomic_inc(&rxwin->num_txwins);
@@ -941,10 +968,9 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
 	winctx->tx_word_mode = txattr->tx_win_ord_mode;
 	winctx->rsvd_txbuf_count = txattr->rsvd_txbuf_count;
 
-	if (winctx->nx_win) {
+	winctx->intr_disable = true;
+	if (winctx->nx_win)
 		winctx->data_stamp = true;
-		winctx->intr_disable = true;
-	}
 
 	winctx->lpid = txattr->lpid;
 	winctx->pidr = txattr->pidr;
@@ -989,6 +1015,14 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
 	if (!tx_win_args_valid(cop, attr))
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * If caller did not specify a vasid but specified the PSWID of a
+	 * receive window (applicable only to FTW windows), use the vasid
+	 * from that receive window.
+	 */
+	if (vasid == -1 && attr->pswid)
+		decode_pswid(attr->pswid, &vasid, NULL);
+
 	vinst = find_vas_instance(vasid);
 	if (!vinst) {
 		pr_devel("vasid %d not found!\n", vasid);
@@ -1037,6 +1071,17 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
 
 	set_vinst_win(vinst, txwin);
 
+	set_thread_used_vas();
+
+	/*
+	 * Even a process that has no foreign real address mapping can use
+	 * an unpaired COPY instruction (to no real effect). Issue CP_ABORT
+	 * to clear any pending COPY and prevent a covert channel.
+	 *
+	 * __switch_to() will issue CP_ABORT on future context switches.
+	 */
+	asm volatile(PPC_CP_ABORT);
+
 	return txwin;
 
 free_window:
-- 
2.7.4