EDAC/amd64: Fix size calculation for Non-Power-of-Two DIMMs

JIRA: https://issues.redhat.com/browse/RHEL-101167

commit a3f3040
Author: Avadhut Naik <avadhut.naik@amd.com>
Date:   Thu May 29 20:50:04 2025 +0000

    EDAC/amd64: Fix size calculation for Non-Power-of-Two DIMMs

    Each Chip-Select (CS) of a Unified Memory Controller (UMC) on AMD Zen-based
    SOCs has an Address Mask and a Secondary Address Mask register associated with
    it. The amd64_edac module logs DIMM sizes on a per-UMC per-CS granularity
    during init using these two registers.

    Currently, the module primarily considers only the Address Mask register for
    computing DIMM sizes. The Secondary Address Mask register is only considered
    for odd CS. Additionally, if it has been considered, the Address Mask register
    is ignored altogether for that CS. For power-of-two DIMMs i.e. DIMMs whose
    total capacity is a power of two (32GB, 64GB, etc), this is not an issue
    since only the Address Mask register is used.

    For non-power-of-two DIMMs i.e., DIMMs whose total capacity is not a power of
    two (48GB, 96GB, etc), however, the Secondary Address Mask register is used
    in conjunction with the Address Mask register. However, since the module only
    considers either of the two registers for a CS, the size computed by the
    module is incorrect. The Secondary Address Mask register is not considered for
    even CS, and the Address Mask register is not considered for odd CS.

    Introduce a new helper function so that both Address Mask and Secondary
    Address Mask registers are considered, when valid, for computing DIMM sizes.
    Furthermore, also rename some variables for greater clarity.

    Fixes: 81f5090 ("EDAC/amd64: Support asymmetric dual-rank DIMMs")
    Closes: https://lore.kernel.org/dbec22b6-00f2-498b-b70d-ab6f8a5ec87e@natrix.lt
    Reported-by: Žilvinas Žaltiena <zilvinas@natrix.lt>
    Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
    Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
    Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
    Tested-by: Žilvinas Žaltiena <zilvinas@natrix.lt>
    Cc: stable@vger.kernel.org
    Link: https://lore.kernel.org/20250529205013.403450-1-avadhut.naik@amd.com"

Signed-off-by: Joel Savitz <jsavitz@redhat.com>

Author: theyoyojo

drivers/edac/amd64_edac.c

@@ -1212,7 +1212,9 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	if (csrow_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_PRIMARY;
 
-	/* Asymmetric dual-rank DIMM support. */
+	if (csrow_sec_enabled(2 * dimm, ctrl, pvt))
+		cs_mode |= CS_EVEN_SECONDARY;
+
 	if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_SECONDARY;
 
@@ -1233,12 +1235,13 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	return cs_mode;
 }
 
-static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
-				  int csrow_nr, int dimm)
+static int calculate_cs_size(u32 mask, unsigned int cs_mode)
 {
-	u32 msb, weight, num_zero_bits;
-	u32 addr_mask_deinterleaved;
-	int size = 0;
+	int msb, weight, num_zero_bits;
+	u32 deinterleaved_mask;
+
+	if (!mask)
+		return 0;
 
 	/*
 	 * The number of zero bits in the mask is equal to the number of bits
@@ -1251,19 +1254,30 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 	 * without swapping with the most significant bit. This can be handled
 	 * by keeping the MSB where it is and ignoring the single zero bit.
 	 */
-	msb = fls(addr_mask_orig) - 1;
-	weight = hweight_long(addr_mask_orig);
+	msb = fls(mask) - 1;
+	weight = hweight_long(mask);
 	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
 
 	/* Take the number of zero bits off from the top of the mask. */
-	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
+	deinterleaved_mask = GENMASK(msb - num_zero_bits, 1);
+	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask);
+
+	return (deinterleaved_mask >> 2) + 1;
+}
+
+static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec,
+				  unsigned int cs_mode, int csrow_nr, int dimm)
+{
+	int size;
 
 	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
-	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
-	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
+	edac_dbg(1, "  Primary AddrMask: 0x%x\n", addr_mask);
 
 	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
-	size = (addr_mask_deinterleaved >> 2) + 1;
+	size = calculate_cs_size(addr_mask, cs_mode);
+
+	edac_dbg(1, "  Secondary AddrMask: 0x%x\n", addr_mask_sec);
+	size += calculate_cs_size(addr_mask_sec, cs_mode);
 
 	/* Return size in MBs. */
 	return size >> 10;
@@ -1272,8 +1286,8 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
+	u32 addr_mask = 0, addr_mask_sec = 0;
 	int cs_mask_nr = csrow_nr;
-	u32 addr_mask_orig;
 	int dimm, size = 0;
 
 	/* No Chip Selects are enabled. */
@@ -1311,13 +1325,13 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 	if (!pvt->flags.zn_regs_v2)
 		cs_mask_nr >>= 1;
 
-	/* Asymmetric dual-rank DIMM support. */
-	if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY))
-		addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr];
-	else
-		addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr];
+	if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY))
+		addr_mask = pvt->csels[umc].csmasks[cs_mask_nr];
+
+	if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY))
+		addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm);
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm);
 }
 
 static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -3516,9 +3530,10 @@ static void gpu_get_err_info(struct mce *m, struct err_info *err)
 static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
-	u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask		= pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask_sec	= pvt->csels[umc].csmasks_sec[csrow_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1);
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1);
 }
 
 static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)