[PATCH iwl v2] ice: acquire NVM lock around each flash read

Robert Malz posted 1 patch 1 week ago
.../net/ethernet/intel/ice/devlink/devlink.c  | 32 ++------
drivers/net/ethernet/intel/ice/ice_ethtool.c  | 16 +---
drivers/net/ethernet/intel/ice/ice_nvm.c      | 76 +++++++++++--------
drivers/net/ethernet/intel/ice/ice_nvm.h      |  2 +-
4 files changed, 56 insertions(+), 70 deletions(-)
[PATCH iwl v2] ice: acquire NVM lock around each flash read
Posted by Robert Malz 1 week ago
FW caps the NVM read lock at a maximum of 3000ms regardless of the timeout
requested via ice_acquire_nvm(). ice_read_flat_nvm() splits a read into
multiple ice_aq_read_nvm() commands, one per 4KB sector, all issued under a
single lock taken by the caller. Reading a large region can exceed 3000ms,
so FW reclaims the lock mid-read and the remaining commands might fail.

Move the lock acquire/release into ice_read_flat_nvm() so it brackets each
individual ice_aq_read_nvm() command, ensuring the lock is never held
across more than one FW read.

ice_release_nvm() issues its own AQ command and overwrites
hw->adminq.sq_last_status, which some callers inspect after a failed read.
Add an optional read_aq_err output parameter to ice_read_flat_nvm() to
capture the failing read's AQ error before the release; callers that need
it (ice_discover_flash_size() and the ethtool/devlink log paths) use it
instead of sq_last_status, others pass NULL.

Callers that previously took the lock around ice_read_flat_nvm(),
ice_read_sr_word() or ice_read_flash_module() now call them without it.
The now-redundant per-block locking in ice_devlink_nvm_snapshot() is
dropped.

Fixes: e94509906d6b ("ice: create function to read a section of the NVM and Shadow RAM")
Signed-off-by: Robert Malz <robert.malz@canonical.com>
---
v2:
- Replace the save/restore of sq_last_status across ice_release_nvm(),
  which could race with a concurrent AdminQ command, with a new optional
  read_aq_err output parameter.
- Add missing "Return:" kdoc to ice_read_sr_word().
---
 .../net/ethernet/intel/ice/devlink/devlink.c  | 32 ++------
 drivers/net/ethernet/intel/ice/ice_ethtool.c  | 16 +---
 drivers/net/ethernet/intel/ice/ice_nvm.c      | 76 +++++++++++--------
 drivers/net/ethernet/intel/ice/ice_nvm.h      |  2 +-
 4 files changed, 56 insertions(+), 70 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 22b7d8e6bd9e..5a1ab9654fb8 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1856,6 +1856,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink,
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	struct device *dev = ice_pf_to_dev(pf);
+	enum libie_aq_err read_aq_err = LIBIE_AQ_RC_OK;
 	struct ice_hw *hw = &pf->hw;
 	bool read_shadow_ram;
 	u8 *nvm_data, *tmp, i;
@@ -1891,26 +1892,16 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink,
 	for (i = 0; i < num_blks; i++) {
 		u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE, left);
 
-		status = ice_acquire_nvm(hw, ICE_RES_READ);
-		if (status) {
-			dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
-				status, hw->adminq.sq_last_status);
-			NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
-			vfree(nvm_data);
-			return -EIO;
-		}
-
 		status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE,
-					   &read_sz, tmp, read_shadow_ram);
+					   &read_sz, tmp, read_shadow_ram,
+					   &read_aq_err);
 		if (status) {
 			dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n",
-				read_sz, status, hw->adminq.sq_last_status);
+				read_sz, status, read_aq_err);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
-			ice_release_nvm(hw);
 			vfree(nvm_data);
 			return -EIO;
 		}
-		ice_release_nvm(hw);
 
 		tmp += read_sz;
 		left -= read_sz;
@@ -1945,6 +1936,7 @@ static int ice_devlink_nvm_read(struct devlink *devlink,
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	struct device *dev = ice_pf_to_dev(pf);
+	enum libie_aq_err read_aq_err = LIBIE_AQ_RC_OK;
 	struct ice_hw *hw = &pf->hw;
 	bool read_shadow_ram;
 	u64 nvm_size;
@@ -1966,24 +1958,14 @@ static int ice_devlink_nvm_read(struct devlink *devlink,
 		return -ERANGE;
 	}
 
-	status = ice_acquire_nvm(hw, ICE_RES_READ);
-	if (status) {
-		dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
-			status, hw->adminq.sq_last_status);
-		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
-		return -EIO;
-	}
-
 	status = ice_read_flat_nvm(hw, (u32)offset, &size, data,
-				   read_shadow_ram);
+				   read_shadow_ram, &read_aq_err);
 	if (status) {
 		dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n",
-			size, status, hw->adminq.sq_last_status);
+			size, status, read_aq_err);
 		NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
-		ice_release_nvm(hw);
 		return -EIO;
 	}
-	ice_release_nvm(hw);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 49371b065845..ce5f5fbaea69 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -854,6 +854,7 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	       u8 *bytes)
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
+	enum libie_aq_err read_aq_err = LIBIE_AQ_RC_OK;
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	int ret;
@@ -869,24 +870,15 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	if (!buf)
 		return -ENOMEM;
 
-	ret = ice_acquire_nvm(hw, ICE_RES_READ);
-	if (ret) {
-		dev_err(dev, "ice_acquire_nvm failed, err %d aq_err %s\n",
-			ret, libie_aq_str(hw->adminq.sq_last_status));
-		goto out;
-	}
-
 	ret = ice_read_flat_nvm(hw, eeprom->offset, &eeprom->len, buf,
-				false);
+				false, &read_aq_err);
 	if (ret) {
 		dev_err(dev, "ice_read_flat_nvm failed, err %d aq_err %s\n",
-			ret, libie_aq_str(hw->adminq.sq_last_status));
-		goto release;
+			ret, libie_aq_str(read_aq_err));
+		goto out;
 	}
 
 	memcpy(bytes, buf, eeprom->len);
-release:
-	ice_release_nvm(hw);
 out:
 	kfree(buf);
 	return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 7e187a804dfa..5b7373a1c06d 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -53,17 +53,27 @@ int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
  * @length: (in) number of bytes to read; (out) number of bytes actually read
  * @data: buffer to return data in (sized to fit the specified length)
  * @read_shadow_ram: if true, read from shadow RAM instead of NVM
+ * @read_aq_err: if non-NULL, receives the AQ error status of the failing read
  *
  * Reads a portion of the NVM, as a flat memory space. This function correctly
  * breaks read requests across Shadow RAM sectors and ensures that no single
  * read request exceeds the maximum 4KB read for a single AdminQ command.
  *
+ * FW caps the read lock at a maximum of 3000ms, so a read spanning multiple
+ * 4KB sectors cannot be done under a single lock without FW reclaiming it
+ * mid-read. The NVM lock is therefore acquired and released around each AQ
+ * read, so this function must be called without the lock held.
+ *
+ * Since ice_release_nvm() issues an AQ command that overwrites
+ * hw->adminq.sq_last_status, callers that need the failing read's AQ error
+ * must use @read_aq_err rather than inspecting sq_last_status afterwards.
+ *
  * Returns a status code on failure. Note that the data pointer may be
  * partially updated if some reads succeed before a failure.
  */
 int
 ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
-		  bool read_shadow_ram)
+		  bool read_shadow_ram, enum libie_aq_err *read_aq_err)
 {
 	u32 inlen = *length;
 	u32 bytes_read = 0;
@@ -92,12 +102,27 @@ ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
 
 		last_cmd = !(bytes_read + read_size < inlen);
 
+		status = ice_acquire_nvm(hw, ICE_RES_READ);
+		if (status)
+			break;
+
 		status = ice_aq_read_nvm(hw, ICE_AQC_NVM_START_POINT,
 					 offset, read_size,
 					 data + bytes_read, last_cmd,
 					 read_shadow_ram, NULL);
-		if (status)
+		if (status) {
+			/* Capture the read's AQ error before ice_release_nvm()
+			 * issues its own AQ command and overwrites
+			 * sq_last_status.
+			 */
+			if (read_aq_err)
+				*read_aq_err = hw->adminq.sq_last_status;
+
+			ice_release_nvm(hw);
 			break;
+		}
+
+		ice_release_nvm(hw);
 
 		bytes_read += read_size;
 		offset += read_size;
@@ -194,7 +219,7 @@ static int ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data)
 	 * Shadow RAM sector restrictions necessary when reading from the NVM.
 	 */
 	status = ice_read_flat_nvm(hw, offset * sizeof(u16), &bytes,
-				   (__force u8 *)&data_local, true);
+				   (__force u8 *)&data_local, true, NULL);
 	if (status)
 		return status;
 
@@ -330,13 +355,8 @@ ice_read_flash_module(struct ice_hw *hw, enum ice_bank_select bank, u16 module,
 		return -EINVAL;
 	}
 
-	status = ice_acquire_nvm(hw, ICE_RES_READ);
-	if (status)
-		return status;
-
-	status = ice_read_flat_nvm(hw, start + offset, &length, data, false);
-
-	ice_release_nvm(hw);
+	status = ice_read_flat_nvm(hw, start + offset, &length, data, false,
+				   NULL);
 
 	return status;
 }
@@ -419,24 +439,21 @@ ice_read_netlist_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset
 }
 
 /**
- * ice_read_sr_word - Reads Shadow RAM word and acquire NVM if necessary
+ * ice_read_sr_word - Reads Shadow RAM word
  * @hw: pointer to the HW structure
  * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
  * @data: word read from the Shadow RAM
  *
- * Reads one 16 bit word from the Shadow RAM using the ice_read_sr_word_aq.
+ * Reads one 16 bit word from the Shadow RAM using ice_read_sr_word_aq.
+ *
+ * The NVM lock is acquired and released internally by ice_read_flat_nvm()
+ * around the FW read, so this function must be called without the lock held.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
 int ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
 {
-	int status;
-
-	status = ice_acquire_nvm(hw, ICE_RES_READ);
-	if (!status) {
-		status = ice_read_sr_word_aq(hw, offset, data);
-		ice_release_nvm(hw);
-	}
-
-	return status;
+	return ice_read_sr_word_aq(hw, offset, data);
 }
 
 /**
@@ -856,20 +873,18 @@ int ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netlist_info *net
 static int ice_discover_flash_size(struct ice_hw *hw)
 {
 	u32 min_size = 0, max_size = ICE_AQC_NVM_MAX_OFFSET + 1;
-	int status;
-
-	status = ice_acquire_nvm(hw, ICE_RES_READ);
-	if (status)
-		return status;
+	int status = 0;
 
 	while ((max_size - min_size) > 1) {
 		u32 offset = (max_size + min_size) / 2;
+		enum libie_aq_err read_aq_err = LIBIE_AQ_RC_OK;
 		u32 len = 1;
 		u8 data;
 
-		status = ice_read_flat_nvm(hw, offset, &len, &data, false);
+		status = ice_read_flat_nvm(hw, offset, &len, &data, false,
+					   &read_aq_err);
 		if (status == -EIO &&
-		    hw->adminq.sq_last_status == LIBIE_AQ_RC_EINVAL) {
+		    read_aq_err == LIBIE_AQ_RC_EINVAL) {
 			ice_debug(hw, ICE_DBG_NVM, "%s: New upper bound of %u bytes\n",
 				  __func__, offset);
 			status = 0;
@@ -880,7 +895,7 @@ static int ice_discover_flash_size(struct ice_hw *hw)
 			min_size = offset;
 		} else {
 			/* an unexpected error occurred */
-			goto err_read_flat_nvm;
+			return status;
 		}
 	}
 
@@ -888,9 +903,6 @@ static int ice_discover_flash_size(struct ice_hw *hw)
 
 	hw->flash.flash_size = max_size;
 
-err_read_flat_nvm:
-	ice_release_nvm(hw);
-
 	return status;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h
index 63cdc6bdac58..e1d1a11f5ca4 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.h
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.h
@@ -19,7 +19,7 @@ int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 		    bool read_shadow_ram, struct ice_sq_cd *cd);
 int
 ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
-		  bool read_shadow_ram);
+		  bool read_shadow_ram, enum libie_aq_err *read_aq_err);
 int
 ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		       u16 module_type);
-- 
2.34.1
RE: [Intel-wired-lan] [PATCH iwl v2] ice: acquire NVM lock around each flash read
Posted by Loktionov, Aleksandr 1 day, 19 hours ago

> -----Original Message-----
> From: Intel-wired-lan <intel-wired-lan-bounces@osuosl.org> On Behalf
> Of Robert Malz via Intel-wired-lan
> Sent: Friday, July 17, 2026 2:12 PM
> To: Nguyen, Anthony L <anthony.l.nguyen@intel.com>; Kitszel,
> Przemyslaw <przemyslaw.kitszel@intel.com>; Andrew Lunn
> <andrew+netdev@lunn.ch>; David S. Miller <davem@davemloft.net>; Eric
> Dumazet <edumazet@google.com>; Jakub Kicinski <kuba@kernel.org>; Paolo
> Abeni <pabeni@redhat.com>; Lobakin, Aleksander
> <aleksander.lobakin@intel.com>; Keller, Jacob E
> <jacob.e.keller@intel.com>; Jesse Brandeburg <jbrandeb@kernel.org>
> Cc: Robert Malz <robert.malz@canonical.com>; intel-wired-
> lan@lists.osuosl.org; netdev@vger.kernel.org; linux-
> kernel@vger.kernel.org
> Subject: [Intel-wired-lan] [PATCH iwl v2] ice: acquire NVM lock around
> each flash read
> 
> FW caps the NVM read lock at a maximum of 3000ms regardless of the
> timeout requested via ice_acquire_nvm(). ice_read_flat_nvm() splits a
> read into multiple ice_aq_read_nvm() commands, one per 4KB sector, all
> issued under a single lock taken by the caller. Reading a large region
> can exceed 3000ms, so FW reclaims the lock mid-read and the remaining
> commands might fail.
> 
> Move the lock acquire/release into ice_read_flat_nvm() so it brackets
> each individual ice_aq_read_nvm() command, ensuring the lock is never
> held across more than one FW read.
> 
> ice_release_nvm() issues its own AQ command and overwrites
> hw->adminq.sq_last_status, which some callers inspect after a failed
> read.
> Add an optional read_aq_err output parameter to ice_read_flat_nvm() to
> capture the failing read's AQ error before the release; callers that
> need it (ice_discover_flash_size() and the ethtool/devlink log paths)
> use it instead of sq_last_status, others pass NULL.
> 
> Callers that previously took the lock around ice_read_flat_nvm(),
> ice_read_sr_word() or ice_read_flash_module() now call them without
> it.
> The now-redundant per-block locking in ice_devlink_nvm_snapshot() is
> dropped.
> 
> Fixes: e94509906d6b ("ice: create function to read a section of the
> NVM and Shadow RAM")
> Signed-off-by: Robert Malz <robert.malz@canonical.com>
> ---
> v2:
> - Replace the save/restore of sq_last_status across ice_release_nvm(),
>   which could race with a concurrent AdminQ command, with a new
> optional
>   read_aq_err output parameter.
> - Add missing "Return:" kdoc to ice_read_sr_word().
> ---
>  .../net/ethernet/intel/ice/devlink/devlink.c  | 32 ++------
> drivers/net/ethernet/intel/ice/ice_ethtool.c  | 16 +---
>  drivers/net/ethernet/intel/ice/ice_nvm.c      | 76 +++++++++++-------
> -
>  drivers/net/ethernet/intel/ice/ice_nvm.h      |  2 +-
>  4 files changed, 56 insertions(+), 70 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c
> b/drivers/net/ethernet/intel/ice/devlink/devlink.c
> index 22b7d8e6bd9e..5a1ab9654fb8 100644
> --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
> +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
> @@ -1856,6 +1856,7 @@ static int ice_devlink_nvm_snapshot(struct
> devlink *devlink,  {
>  	struct ice_pf *pf = devlink_priv(devlink);
>  	struct device *dev = ice_pf_to_dev(pf);
> +	enum libie_aq_err read_aq_err = LIBIE_AQ_RC_OK;
>  	struct ice_hw *hw = &pf->hw;
>  	bool read_shadow_ram;
>  	u8 *nvm_data, *tmp, i;
> @@ -1891,26 +1892,16 @@ static int ice_devlink_nvm_snapshot(struct
> devlink *devlink,
>  	for (i = 0; i < num_blks; i++) {
>  		u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE,
> left);
> 

...

>  int
>  ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16
> *module_tlv_len,
>  		       u16 module_type);
> --
> 2.34.1

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>