[PATCH] RAS/AMD/ATL: Add MI300 row retirement support

[Yazen Ghannam]

DRAM row retirement depends on model-specific information that is best
done within the AMD Address Translation Library.

Export a generic wrapper function for other modules to use. Add any
model-specific helpers here.

Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
Signed-off-by: Borislav Petkov (AMD) <bp@xxxxxxxxx>
Link: https://lore.kernel.org/r/20240214033516.1344948-2-yazen.ghannam@xxxxxxx
---
 drivers/ras/amd/atl/Kconfig |  1 +
 drivers/ras/amd/atl/umc.c   | 51 +++++++++++++++++++++++++++++++++++++
 include/linux/ras.h         |  2 ++
 3 files changed, 54 insertions(+)

diff --git a/drivers/ras/amd/atl/Kconfig b/drivers/ras/amd/atl/Kconfig
index a43513a700f1..df49c23e7f62 100644
--- a/drivers/ras/amd/atl/Kconfig
+++ b/drivers/ras/amd/atl/Kconfig
@@ -10,6 +10,7 @@
 config AMD_ATL
 	tristate "AMD Address Translation Library"
 	depends on AMD_NB && X86_64 && RAS
+	depends on MEMORY_FAILURE
 	default N
 	help
 	  This library includes support for implementation-specific
diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
index 7e310d1dfcfc..08c6dbd44c62 100644
--- a/drivers/ras/amd/atl/umc.c
+++ b/drivers/ras/amd/atl/umc.c
@@ -239,6 +239,57 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr)
 	return addr;
 }
 
+/*
+ * When a DRAM ECC error occurs on MI300 systems, it is recommended to retire
+ * all memory within that DRAM row. This applies to the memory with a DRAM
+ * bank.
+ *
+ * To find the memory addresses, loop through permutations of the DRAM column
+ * bits and find the System Physical address of each. The column bits are used
+ * to calculate the intermediate Normalized address, so all permutations should
+ * be checked.
+ *
+ * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats.
+ */
+#define MI300_NUM_COL		BIT(HWEIGHT(MI300_UMC_MCA_COL))
+static void retire_row_mi300(struct atl_err *a_err)
+{
+	unsigned long addr;
+	struct page *p;
+	u8 col;
+
+	for (col = 0; col < MI300_NUM_COL; col++) {
+		a_err->addr &= ~MI300_UMC_MCA_COL;
+		a_err->addr |= FIELD_PREP(MI300_UMC_MCA_COL, col);
+
+		addr = amd_convert_umc_mca_addr_to_sys_addr(a_err);
+		if (IS_ERR_VALUE(addr))
+			continue;
+
+		addr = PHYS_PFN(addr);
+
+		/*
+		 * Skip invalid or already poisoned pages to avoid unnecessary
+		 * error messages from memory_failure().
+		 */
+		p = pfn_to_online_page(addr);
+		if (!p)
+			continue;
+
+		if (PageHWPoison(p))
+			continue;
+
+		memory_failure(addr, 0);
+	}
+}
+
+void amd_retire_dram_row(struct atl_err *a_err)
+{
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return retire_row_mi300(a_err);
+}
+EXPORT_SYMBOL_GPL(amd_retire_dram_row);
+
 static unsigned long get_addr(unsigned long addr)
 {
 	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
diff --git a/include/linux/ras.h b/include/linux/ras.h
index 09c632832bf1..a64182bc72ad 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -45,8 +45,10 @@ struct atl_err {
 #if IS_ENABLED(CONFIG_AMD_ATL)
 void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *));
 void amd_atl_unregister_decoder(void);
+void amd_retire_dram_row(struct atl_err *err);
 unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err);
 #else
+static inline void amd_retire_dram_row(struct atl_err *err) { }
 static inline unsigned long
 amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; }
 #endif /* CONFIG_AMD_ATL */
-- 
2.43.0

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette