Received-SPF: pass (google.com: domain of linux-kernel+bounces-77057-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Serge Semin <fancer.lancer@gmail.com>
To: Michal Simek <michal.simek@amd.com>,
	Alexander Stein <alexander.stein@ew.tq-group.com>,
	Borislav Petkov <bp@alien8.de>,
	Tony Luck <tony.luck@intel.com>,
	James Morse <james.morse@arm.com>,
	Mauro Carvalho Chehab <mchehab@kernel.org>,
	Robert Richter <rric@kernel.org>,
	Dinh Nguyen <dinguyen@kernel.org>
Cc: Serge Semin <fancer.lancer@gmail.com>,
	Punnaiah Choudary Kalluri <punnaiah.choudary.kalluri@xilinx.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-edac@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Sherry Sun <sherry.sun@nxp.com>,
	Borislav Petkov <bp@suse.de>
Subject: [PATCH v5 01/20] EDAC/synopsys: Fix ECC status data and IRQ disable race condition
Date: Thu, 22 Feb 2024 21:12:46 +0300
Message-ID: <20240222181324.28242-2-fancer.lancer@gmail.com>
In-Reply-To: <20240222181324.28242-1-fancer.lancer@gmail.com>
References: <20240222181324.28242-1-fancer.lancer@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

The race condition around the ECCCLR register access happens in the IRQ
disable method called in the device remove() procedure and in the ECC IRQ
handler:
1. Enable IRQ:
   a. ECCCLR = EN_CE | EN_UE
2. Disable IRQ:
   a. ECCCLR = 0
3. IRQ handler:
   a. ECCCLR = CLR_CE | CLR_CE_CNT | CLR_CE | CLR_CE_CNT
   b. ECCCLR = 0
   c. ECCCLR = EN_CE | EN_UE
So if the IRQ disabling procedure is called concurrently with the IRQ
handler method the IRQ might be actually left enabled due to the
statement 3c.

The root cause of the problem is that ECCCLR register (which since v3.10a
has been called as ECCCTL) has intermixed ECC status data clear flags and
the IRQ enable/disable flags. Thus the IRQ disabling (clear EN flags) and
handling (write 1 to clear ECC status data) procedures must be serialised
around the ECCCTL register modification to prevent the race.

So fix the problem described above by adding the spin-lock around the
ECCCLR modifications and preventing the IRQ-handler from modifying the
IRQs enable flags (there is no point in disabling the IRQ and then
re-enabling it again within a single IRQ handler call, see the statements
3a/3b and 3c above).

Fixes: f7824ded4149 ("EDAC/synopsys: Add support for version 3 of the Synopsys EDAC DDR")
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>

---

Cc: Sherry Sun <sherry.sun@nxp.com>

Changelog v4:
- This is a new patch detached from
  [PATCH v3 01/17] EDAC/synopsys: Fix native uMCTL2 IRQs handling procedure
- Rename lock to reglock (Borislav)
---
 drivers/edac/synopsys_edac.c | 50 ++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 13 deletions(-)

diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index 709babce43ba..0168b05e3ca1 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -9,6 +9,7 @@
 #include <linux/edac.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 
@@ -299,6 +300,7 @@ struct synps_ecc_status {
 /**
  * struct synps_edac_priv - DDR memory controller private instance data.
  * @baseaddr:		Base address of the DDR controller.
+ * @reglock:		Concurrent CSRs access lock.
  * @message:		Buffer for framing the event specific info.
  * @stat:		ECC status information.
  * @p_data:		Platform data.
@@ -313,6 +315,7 @@ struct synps_ecc_status {
  */
 struct synps_edac_priv {
 	void __iomem *baseaddr;
+	spinlock_t reglock;
 	char message[SYNPS_EDAC_MSG_SIZE];
 	struct synps_ecc_status stat;
 	const struct synps_platform_data *p_data;
@@ -408,7 +411,8 @@ static int zynq_get_error_info(struct synps_edac_priv *priv)
 static int zynqmp_get_error_info(struct synps_edac_priv *priv)
 {
 	struct synps_ecc_status *p;
-	u32 regval, clearval = 0;
+	u32 regval, clearval;
+	unsigned long flags;
 	void __iomem *base;
 
 	base = priv->baseaddr;
@@ -452,10 +456,14 @@ static int zynqmp_get_error_info(struct synps_edac_priv *priv)
 	p->ueinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK);
 	p->ueinfo.data = readl(base + ECC_UESYND0_OFST);
 out:
-	clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT;
-	clearval |= ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT;
+	spin_lock_irqsave(&priv->reglock, flags);
+
+	clearval = readl(base + ECC_CLR_OFST) |
+		   ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT |
+		   ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT;
 	writel(clearval, base + ECC_CLR_OFST);
-	writel(0x0, base + ECC_CLR_OFST);
+
+	spin_unlock_irqrestore(&priv->reglock, flags);
 
 	return 0;
 }
@@ -515,24 +523,41 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p)
 
 static void enable_intr(struct synps_edac_priv *priv)
 {
+	unsigned long flags;
+
 	/* Enable UE/CE Interrupts */
-	if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)
-		writel(DDR_UE_MASK | DDR_CE_MASK,
-		       priv->baseaddr + ECC_CLR_OFST);
-	else
+	if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) {
 		writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
 		       priv->baseaddr + DDR_QOS_IRQ_EN_OFST);
 
+		return;
+	}
+
+	spin_lock_irqsave(&priv->reglock, flags);
+
+	writel(DDR_UE_MASK | DDR_CE_MASK,
+	       priv->baseaddr + ECC_CLR_OFST);
+
+	spin_unlock_irqrestore(&priv->reglock, flags);
 }
 
 static void disable_intr(struct synps_edac_priv *priv)
 {
+	unsigned long flags;
+
 	/* Disable UE/CE Interrupts */
-	if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)
-		writel(0x0, priv->baseaddr + ECC_CLR_OFST);
-	else
+	if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) {
 		writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
 		       priv->baseaddr + DDR_QOS_IRQ_DB_OFST);
+
+		return;
+	}
+
+	spin_lock_irqsave(&priv->reglock, flags);
+
+	writel(0, priv->baseaddr + ECC_CLR_OFST);
+
+	spin_unlock_irqrestore(&priv->reglock, flags);
 }
 
 /**
@@ -576,8 +601,6 @@ static irqreturn_t intr_handler(int irq, void *dev_id)
 	/* v3.0 of the controller does not have this register */
 	if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR))
 		writel(regval, priv->baseaddr + DDR_QOS_IRQ_STAT_OFST);
-	else
-		enable_intr(priv);
 
 	return IRQ_HANDLED;
 }
@@ -1359,6 +1382,7 @@ static int mc_probe(struct platform_device *pdev)
 	priv = mci->pvt_info;
 	priv->baseaddr = baseaddr;
 	priv->p_data = p_data;
+	spin_lock_init(&priv->reglock);
 
 	mc_init(mci, pdev);
 
-- 
2.43.0