FAILED: patch "[PATCH] firmware: samsung: acpm: Fix missing LKMM barriers in" failed to apply to 7.0-stable tree

index 620880d8820a..3fa9fe283be4 100644
@@ -7,7 +7,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitmap.h>
-#include <linux/bits.h>
+#include <linux/bitops.h>
 #include <linux/cleanup.h>
 #include <linux/container_of.h>
 #include <linux/delay.h>

@@ -340,7 +340,7 @@ static int acpm_dequeue_by_polling(struct acpm_chan *achan,
 				acpm_get_saved_rx(achan, xfer, seqnum);
 
 			/* Relinquish ownership of the sequence slot */
-			clear_bit(seqnum - 1, achan->bitmap_seqnum);
+			clear_bit_unlock(seqnum - 1, achan->bitmap_seqnum);
 			return 0;
 		}
 

@@ -397,11 +397,18 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 	struct acpm_rx_data *rx_data;
 	u32 *txd = (u32 *)xfer->txd;
 
-	/* Prevent chan->seqnum from being re-used */
+	/*
+	 * Prevent chan->seqnum from being re-used.
+	 * test_and_set_bit_lock() provides formal LKMM Acquire semantics.
+	 * It pairs with the RX thread's clear_bit_unlock() to ensure the CPU
+	 * does not speculatively execute the rx_data buffer wipe (memset)
+	 * before the sequence number is safely claimed.
+	 */
 	do {
 		if (++achan->seqnum == ACPM_SEQNUM_MAX)
 			achan->seqnum = 1;
-	} while (test_bit(achan->seqnum - 1, achan->bitmap_seqnum));
+		/* Flag the index based on seqnum. (seqnum: 1~63, bitmap: 0~62) */
+	} while (test_and_set_bit_lock(achan->seqnum - 1, achan->bitmap_seqnum));
 
 	txd[0] |= FIELD_PREP(ACPM_PROTOCOL_SEQNUM, achan->seqnum);
 

@@ -411,9 +418,6 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 	memset(rx_data->cmd, 0, sizeof(*rx_data->cmd) * rx_data->n_cmd);
 	/* zero means no response expected */
 	rx_data->rxcnt = xfer->rxcnt;
-
-	/* Flag the index based on seqnum. (seqnum: 1~63, bitmap: 0~62) */
-	set_bit(achan->seqnum - 1, achan->bitmap_seqnum);
 }
 
 /**

index 66448c8037aca6..352a6e64d79ddc 100644
@@ -5,6 +5,7 @@
  * Copyright 2025 Linaro Ltd.
  */
 
+#include <linux/array_size.h>
 #include <linux/bitfield.h>
 #include <linux/firmware/samsung/exynos-acpm-protocol.h>
 #include <linux/ktime.h>

@@ -25,11 +26,11 @@ static void acpm_dvfs_set_xfer(struct acpm_xfer *xfer, u32 *cmd, size_t cmdlen,
 {
 	xfer->acpm_chan_id = acpm_chan_id;
 	xfer->txd = cmd;
-	xfer->txlen = cmdlen;
+	xfer->txcnt = cmdlen;
 
 	if (response) {
 		xfer->rxd = cmd;
-		xfer->rxlen = cmdlen;
+		xfer->rxcnt = cmdlen;
 	}
 }
 

@@ -50,7 +51,7 @@ int acpm_dvfs_set_rate(struct acpm_handle *handle,
 	u32 cmd[4];
 
 	acpm_dvfs_init_set_rate_cmd(cmd, clk_id, rate);
-	acpm_dvfs_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id, false);
+	acpm_dvfs_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id, false);
 
 	return acpm_do_xfer(handle, &xfer);
 }

@@ -70,7 +71,7 @@ unsigned long acpm_dvfs_get_rate(struct acpm_handle *handle,
 	int ret;
 
 	acpm_dvfs_init_get_rate_cmd(cmd, clk_id);
-	acpm_dvfs_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id, true);
+	acpm_dvfs_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id, true);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

index 52e89d1b790f01..58edb3115d5fa3 100644
@@ -63,8 +63,8 @@ static void acpm_pmic_set_xfer(struct acpm_xfer *xfer, u32 *cmd, size_t cmdlen,
 {
 	xfer->txd = cmd;
 	xfer->rxd = cmd;
-	xfer->txlen = cmdlen;
-	xfer->rxlen = cmdlen;
+	xfer->txcnt = cmdlen;
+	xfer->rxcnt = cmdlen;
 	xfer->acpm_chan_id = acpm_chan_id;
 }
 

@@ -86,7 +86,7 @@ int acpm_pmic_read_reg(struct acpm_handle *handle,
 	int ret;
 
 	acpm_pmic_init_read_cmd(cmd, type, reg, chan);
-	acpm_pmic_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id);
+	acpm_pmic_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

@@ -119,7 +119,7 @@ int acpm_pmic_bulk_read(struct acpm_handle *handle,
 		return -EINVAL;
 
 	acpm_pmic_init_bulk_read_cmd(cmd, type, reg, chan, count);
-	acpm_pmic_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id);
+	acpm_pmic_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

@@ -159,7 +159,7 @@ int acpm_pmic_write_reg(struct acpm_handle *handle,
 	int ret;
 
 	acpm_pmic_init_write_cmd(cmd, type, reg, chan, value);
-	acpm_pmic_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id);
+	acpm_pmic_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

@@ -199,7 +199,7 @@ int acpm_pmic_bulk_write(struct acpm_handle *handle,
 		return -EINVAL;
 
 	acpm_pmic_init_bulk_write_cmd(cmd, type, reg, chan, count, buf);
-	acpm_pmic_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id);
+	acpm_pmic_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

@@ -229,7 +229,7 @@ int acpm_pmic_update_reg(struct acpm_handle *handle,
 	int ret;
 
 	acpm_pmic_init_update_cmd(cmd, type, reg, chan, value, mask);
-	acpm_pmic_set_xfer(&xfer, cmd, sizeof(cmd), acpm_chan_id);
+	acpm_pmic_set_xfer(&xfer, cmd, ARRAY_SIZE(cmd), acpm_chan_id);
 
 	ret = acpm_do_xfer(handle, &xfer);
 	if (ret)

index 987b59778ffc4a..16c46ed6083716 100644
@@ -205,7 +205,7 @@ static void acpm_get_saved_rx(struct acpm_chan *achan,
 	rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, rx_data->cmd[0]);
 
 	if (rx_seqnum == tx_seqnum) {
-		memcpy(xfer->rxd, rx_data->cmd, xfer->rxlen);
+		memcpy(xfer->rxd, rx_data->cmd, xfer->rxcnt * sizeof(*xfer->rxd));
 		clear_bit(rx_seqnum - 1, achan->bitmap_seqnum);
 	}
 }

@@ -258,8 +258,7 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 
 		if (rx_data->response) {
 			if (rx_seqnum == tx_seqnum) {
-				__ioread32_copy(xfer->rxd, addr,
-						xfer->rxlen / 4);
+				__ioread32_copy(xfer->rxd, addr, xfer->rxcnt);
 				rx_set = true;
 				clear_bit(seqnum, achan->bitmap_seqnum);
 			} else {

@@ -269,8 +268,7 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 				 * clear yet the bitmap. It will be cleared
 				 * after the response is copied to the request.
 				 */
-				__ioread32_copy(rx_data->cmd, addr,
-						xfer->rxlen / 4);
+				__ioread32_copy(rx_data->cmd, addr, xfer->rxcnt);
 			}
 		} else {
 			clear_bit(seqnum, achan->bitmap_seqnum);

@@ -425,7 +423,9 @@ int acpm_do_xfer(struct acpm_handle *handle, const struct acpm_xfer *xfer)
 
 	achan = &acpm->chans[xfer->acpm_chan_id];
 
-	if (!xfer->txd || xfer->txlen > achan->mlen || xfer->rxlen > achan->mlen)
+	if (!xfer->txd ||
+	    (xfer->txcnt * sizeof(*xfer->txd) > achan->mlen) ||
+	    (xfer->rxcnt * sizeof(*xfer->rxd) > achan->mlen))
 		return -EINVAL;
 
 	if (!achan->poll_completion) {

@@ -448,7 +448,7 @@ int acpm_do_xfer(struct acpm_handle *handle, const struct acpm_xfer *xfer)
 
 		/* Write TX command. */
 		__iowrite32_copy(achan->tx.base + achan->mlen * tx_front,
-				 xfer->txd, xfer->txlen / 4);
+				 xfer->txd, xfer->txcnt);
 
 		/* Advance TX front. */
 		writel(idx, achan->tx.front);

index 6417550f89aa97..ac634ef9c6780e 100644
@@ -10,8 +10,8 @@
 struct acpm_xfer {
 	const u32 *txd;
 	u32 *rxd;
-	size_t txlen;
-	size_t rxlen;
+	size_t txcnt;
+	size_t rxcnt;
 	unsigned int acpm_chan_id;
 };
 

index 352a6e64d79ddc..06bdf62dea1f30 100644
@@ -25,12 +25,12 @@ static void acpm_dvfs_set_xfer(struct acpm_xfer *xfer, u32 *cmd, size_t cmdlen,
 			       unsigned int acpm_chan_id, bool response)
 {
 	xfer->acpm_chan_id = acpm_chan_id;
-	xfer->txd = cmd;
 	xfer->txcnt = cmdlen;
+	xfer->txd = cmd;
 
 	if (response) {
-		xfer->rxd = cmd;
 		xfer->rxcnt = cmdlen;
+		xfer->rxd = cmd;
 	}
 }
 

index ac634ef9c6780e..5df8354dc96ce6 100644
@@ -8,8 +8,8 @@
 #define __EXYNOS_ACPM_H__
 
 struct acpm_xfer {
-	const u32 *txd;
-	u32 *rxd;
+	const u32 *txd __counted_by_ptr(txcnt);
+	u32 *rxd __counted_by_ptr(rxcnt);
 	size_t txcnt;
 	size_t rxcnt;
 	unsigned int acpm_chan_id;

index 06bdf62dea1f30..fdea7aa24ca02e 100644
@@ -31,6 +31,9 @@ static void acpm_dvfs_set_xfer(struct acpm_xfer *xfer, u32 *cmd, size_t cmdlen,
 	if (response) {
 		xfer->rxcnt = cmdlen;
 		xfer->rxd = cmd;
+	} else {
+		xfer->rxcnt = 0;
+		xfer->rxd = NULL;
 	}
 }
 

index 16c46ed6083716..e95edc350efa6c 100644
@@ -104,12 +104,12 @@ struct acpm_queue {
  *
  * @cmd:	pointer to where the data shall be saved.
  * @n_cmd:	number of 32-bit commands.
- * @response:	true if the client expects the RX data.
+ * @rxcnt:	expected length of the response in 32-bit words.
  */
 struct acpm_rx_data {
 	u32 *cmd;
 	size_t n_cmd;
-	bool response;
+	size_t rxcnt;
 };
 
 #define ACPM_SEQNUM_MAX    64

@@ -199,7 +199,7 @@ static void acpm_get_saved_rx(struct acpm_chan *achan,
 	const struct acpm_rx_data *rx_data = &achan->rx_data[tx_seqnum - 1];
 	u32 rx_seqnum;
 
-	if (!rx_data->response)
+	if (!rx_data->rxcnt)
 		return;
 
 	rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, rx_data->cmd[0]);

@@ -256,7 +256,7 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 		seqnum = rx_seqnum - 1;
 		rx_data = &achan->rx_data[seqnum];
 
-		if (rx_data->response) {
+		if (rx_data->rxcnt) {
 			if (rx_seqnum == tx_seqnum) {
 				__ioread32_copy(xfer->rxd, addr, xfer->rxcnt);
 				rx_set = true;

@@ -268,7 +268,8 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 				 * clear yet the bitmap. It will be cleared
 				 * after the response is copied to the request.
 				 */
-				__ioread32_copy(rx_data->cmd, addr, xfer->rxcnt);
+				__ioread32_copy(rx_data->cmd, addr,
+						rx_data->rxcnt);
 			}
 		} else {
 			clear_bit(seqnum, achan->bitmap_seqnum);

@@ -380,8 +381,8 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 	/* Clear data for upcoming responses */
 	rx_data = &achan->rx_data[achan->seqnum - 1];
 	memset(rx_data->cmd, 0, sizeof(*rx_data->cmd) * rx_data->n_cmd);
-	if (xfer->rxd)
-		rx_data->response = true;
+	/* zero means no response expected */
+	rx_data->rxcnt = xfer->rxcnt;
 
 	/* Flag the index based on seqnum. (seqnum: 1~63, bitmap: 0~62) */
 	set_bit(achan->seqnum - 1, achan->bitmap_seqnum);

index e95edc350efa6c..7eda1aff4c197b 100644
@@ -105,11 +105,14 @@ struct acpm_queue {
  * @cmd:	pointer to where the data shall be saved.
  * @n_cmd:	number of 32-bit commands.
  * @rxcnt:	expected length of the response in 32-bit words.
+ * @completed:	flag indicating if the firmware response has been fully
+ *		processed.
  */
 struct acpm_rx_data {
 	u32 *cmd;
 	size_t n_cmd;
 	size_t rxcnt;
+	bool completed;
 };
 
 #define ACPM_SEQNUM_MAX    64

@@ -204,26 +207,28 @@ static void acpm_get_saved_rx(struct acpm_chan *achan,
 
 	rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, rx_data->cmd[0]);
 
-	if (rx_seqnum == tx_seqnum) {
+	if (rx_seqnum == tx_seqnum)
 		memcpy(xfer->rxd, rx_data->cmd, xfer->rxcnt * sizeof(*xfer->rxd));
-		clear_bit(rx_seqnum - 1, achan->bitmap_seqnum);
-	}
 }
 
 /**
  * acpm_get_rx() - get response from RX queue.
  * @achan:	ACPM channel info.
  * @xfer:	reference to the transfer to get response for.
+ * @native_match: pointer to a boolean set to true if the thread natively
+ *                processed its own sequence number during this call.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
+static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer,
+		       bool *native_match)
 {
 	u32 rx_front, rx_seqnum, tx_seqnum, seqnum;
 	const void __iomem *base, *addr;
 	struct acpm_rx_data *rx_data;
 	u32 i, val, mlen;
-	bool rx_set = false;
+
+	*native_match = false;
 
 	guard(mutex)(&achan->rx_lock);
 

@@ -232,10 +237,8 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 
 	tx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, xfer->txd[0]);
 
-	if (i == rx_front) {
-		acpm_get_saved_rx(achan, xfer, tx_seqnum);
+	if (i == rx_front)
 		return 0;
-	}
 
 	base = achan->rx.base;
 	mlen = achan->mlen;

@@ -259,8 +262,13 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 		if (rx_data->rxcnt) {
 			if (rx_seqnum == tx_seqnum) {
 				__ioread32_copy(xfer->rxd, addr, xfer->rxcnt);
-				rx_set = true;
-				clear_bit(seqnum, achan->bitmap_seqnum);
+				/*
+				 * Signal completion to the polling thread.
+				 * Pairs with smp_load_acquire() in polling
+				 * loop.
+				 */
+				smp_store_release(&rx_data->completed, true);
+				*native_match = true;
 			} else {
 				/*
 				 * The RX data corresponds to another request.

@@ -270,9 +278,21 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 				 */
 				__ioread32_copy(rx_data->cmd, addr,
 						rx_data->rxcnt);
+				/*
+				 * Signal completion to the polling thread.
+				 * Pairs with smp_load_acquire() in polling
+				 * loop.
+				 */
+				smp_store_release(&rx_data->completed, true);
 			}
 		} else {
-			clear_bit(seqnum, achan->bitmap_seqnum);
+			/*
+			 * Signal completion to the polling thread.
+			 * Pairs with smp_load_acquire() in polling loop.
+			 */
+			smp_store_release(&rx_data->completed, true);
+			if (rx_seqnum == tx_seqnum)
+				*native_match = true;
 		}
 
 		i = (i + 1) % achan->qlen;

@@ -281,13 +301,6 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer)
 	/* We saved all responses, mark RX empty. */
 	writel(rx_front, achan->rx.rear);
 
-	/*
-	 * If the response was not in this iteration of the queue, check if the
-	 * RX data was previously saved.
-	 */
-	if (!rx_set)
-		acpm_get_saved_rx(achan, xfer, tx_seqnum);
-
 	return 0;
 }
 

@@ -302,6 +315,7 @@ static int acpm_dequeue_by_polling(struct acpm_chan *achan,
 				   const struct acpm_xfer *xfer)
 {
 	struct device *dev = achan->acpm->dev;
+	bool native_match;
 	ktime_t timeout;
 	u32 seqnum;
 	int ret;

@@ -310,12 +324,25 @@ static int acpm_dequeue_by_polling(struct acpm_chan *achan,
 
 	timeout = ktime_add_us(ktime_get(), ACPM_POLL_TIMEOUT_US);
 	do {
-		ret = acpm_get_rx(achan, xfer);
+		ret = acpm_get_rx(achan, xfer, &native_match);
 		if (ret)
 			return ret;
 
-		if (!test_bit(seqnum - 1, achan->bitmap_seqnum))
+		/*
+		 * Safely check if our specific transaction has been processed.
+		 * smp_load_acquire prevents the CPU from speculatively
+		 * executing subsequent instructions before the transaction is
+		 * synchronized.
+		 */
+		if (smp_load_acquire(&achan->rx_data[seqnum - 1].completed)) {
+			/* Retrieve payload if another thread cached it for us */
+			if (!native_match)
+				acpm_get_saved_rx(achan, xfer, seqnum);
+
+			/* Relinquish ownership of the sequence slot */
+			clear_bit(seqnum - 1, achan->bitmap_seqnum);
 			return 0;
+		}
 
 		/* Determined experimentally. */
 		udelay(20);

@@ -380,6 +407,7 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 
 	/* Clear data for upcoming responses */
 	rx_data = &achan->rx_data[achan->seqnum - 1];
+	rx_data->completed = false;
 	memset(rx_data->cmd, 0, sizeof(*rx_data->cmd) * rx_data->n_cmd);
 	/* zero means no response expected */
 	rx_data->rxcnt = xfer->rxcnt;

index 7eda1aff4c197b..c472569441949c 100644
@@ -7,7 +7,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitmap.h>
-#include <linux/bits.h>
+#include <linux/bitops.h>
 #include <linux/cleanup.h>
 #include <linux/container_of.h>
 #include <linux/delay.h>

@@ -340,7 +340,7 @@ static int acpm_dequeue_by_polling(struct acpm_chan *achan,
 				acpm_get_saved_rx(achan, xfer, seqnum);
 
 			/* Relinquish ownership of the sequence slot */
-			clear_bit(seqnum - 1, achan->bitmap_seqnum);
+			clear_bit_unlock(seqnum - 1, achan->bitmap_seqnum);
 			return 0;
 		}
 

@@ -397,11 +397,18 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 	struct acpm_rx_data *rx_data;
 	u32 *txd = (u32 *)xfer->txd;
 
-	/* Prevent chan->seqnum from being re-used */
+	/*
+	 * Prevent chan->seqnum from being re-used.
+	 * test_and_set_bit_lock() provides formal LKMM Acquire semantics.
+	 * It pairs with the RX thread's clear_bit_unlock() to ensure the CPU
+	 * does not speculatively execute the rx_data buffer wipe (memset)
+	 * before the sequence number is safely claimed.
+	 */
 	do {
 		if (++achan->seqnum == ACPM_SEQNUM_MAX)
 			achan->seqnum = 1;
-	} while (test_bit(achan->seqnum - 1, achan->bitmap_seqnum));
+		/* Flag the index based on seqnum. (seqnum: 1~63, bitmap: 0~62) */
+	} while (test_and_set_bit_lock(achan->seqnum - 1, achan->bitmap_seqnum));
 
 	txd[0] |= FIELD_PREP(ACPM_PROTOCOL_SEQNUM, achan->seqnum);
 

@@ -411,9 +418,6 @@ static void acpm_prepare_xfer(struct acpm_chan *achan,
 	memset(rx_data->cmd, 0, sizeof(*rx_data->cmd) * rx_data->n_cmd);
 	/* zero means no response expected */
 	rx_data->rxcnt = xfer->rxcnt;
-
-	/* Flag the index based on seqnum. (seqnum: 1~63, bitmap: 0~62) */
-	set_bit(achan->seqnum - 1, achan->bitmap_seqnum);
 }
 
 /**