PCI/ERR: Handle TLP Log in Flit mode

Flit mode introduced in PCIe r6.0 alters how the TLP Header Log is
presented through AER and DPC Capability registers. The TLP Prefix Log
Register is not present with Flit mode, and the register becomes an
extension of the TLP Header Log (PCIe r6.1 secs 7.8.4.12 & 7.9.14.13).

Adapt pcie_read_tlp_log() and struct pcie_tlp_log to read and store the
extended TLP Header Log when the Link is in Flit mode. As the Prefix Log
and Extended TLP Header are not present at the same time, a C union can be
used.

Determining whether the error occurred while the Link was in Flit mode is a
bit complicated. In case of AER, the Advanced Error Capabilities and
Control Register directly tells whether the error was logged in Flit mode
or not (PCIe r6.1 sec 7.8.4.7). The DPC Capability (PCIe r6.1 sec 7.9.14),
unfortunately, does not contain the same information.

Unlike AER, the DPC Capability does not provide a way to discern whether
the error was logged in Flit mode (this is confirmed by PCI WG to be an
oversight in the spec). DPC will bring the Link down immediately following
an error, which makes it impossible to acquire the Flit Mode Status
directly from the Link Status 2 register because Flit Mode Status is only
set in certain Link states (PCIe r6.1 sec 7.5.3.20). As a workaround, use
the flit_mode value stored into the struct pci_bus.

Link: https://lore.kernel.org/r/20250207161836.2755-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

3 files changed, 21 insertions, 9 deletions

diff --git a/include/linux/aer.h b/include/linux/aer.h
index 947b63091902..02940be66324 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -22,12 +22,20 @@
  */
 #define PCIE_STD_NUM_TLP_HEADERLOG     4
 #define PCIE_STD_MAX_TLP_PREFIXLOG     4
+#define PCIE_STD_MAX_TLP_HEADERLOG	(PCIE_STD_NUM_TLP_HEADERLOG + 10)
 
 struct pci_dev;
 
 struct pcie_tlp_log {
-	u32 dw[PCIE_STD_NUM_TLP_HEADERLOG];
-	u32 prefix[PCIE_STD_MAX_TLP_PREFIXLOG];
+	union {
+		u32 dw[PCIE_STD_MAX_TLP_HEADERLOG];
+		struct {
+			u32 _do_not_use[PCIE_STD_NUM_TLP_HEADERLOG];
+			u32 prefix[PCIE_STD_MAX_TLP_PREFIXLOG];
+		};
+	};
+	u8 header_len;		/* Length of the Logged TLP Header in DWORDs */
+	bool flit;		/* TLP was logged when in Flit mode */
 };
 
 struct aer_capability_regs {
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index e5f7ee0864e7..14c9f943d53f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -309,7 +309,7 @@ TRACE_EVENT(aer_event,
 		__field(	u32,		status		)
 		__field(	u8,		severity	)
 		__field(	u8, 		tlp_header_valid)
-		__array(	u32, 		tlp_header, 4	)
+		__array(	u32, 		tlp_header, PCIE_STD_MAX_TLP_HEADERLOG)
 	),
 
 	TP_fast_assign(
@@ -318,10 +318,10 @@ TRACE_EVENT(aer_event,
 		__entry->severity	= severity;
 		__entry->tlp_header_valid = tlp_header_valid;
 		if (tlp_header_valid) {
-			__entry->tlp_header[0] = tlp->dw[0];
-			__entry->tlp_header[1] = tlp->dw[1];
-			__entry->tlp_header[2] = tlp->dw[2];
-			__entry->tlp_header[3] = tlp->dw[3];
+			int i;
+
+			for (i = 0; i < PCIE_STD_MAX_TLP_HEADERLOG; i++)
+				__entry->tlp_header[i] = tlp->dw[i];
 		}
 	),
 
@@ -334,7 +334,7 @@ TRACE_EVENT(aer_event,
 		__print_flags(__entry->status, "|", aer_correctable_errors) :
 		__print_flags(__entry->status, "|", aer_uncorrectable_errors),
 		__entry->tlp_header_valid ?
-			__print_array(__entry->tlp_header, 4, 4) :
+			__print_array(__entry->tlp_header, PCIE_STD_MAX_TLP_HEADERLOG, 4) :
 			"Not available")
 );
 
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 3445c4970e4d..2c801c0c968a 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -486,6 +486,7 @@
 #define   PCI_EXP_TYPE_RC_EC	   0xa	/* Root Complex Event Collector */
 #define  PCI_EXP_FLAGS_SLOT	0x0100	/* Slot implemented */
 #define  PCI_EXP_FLAGS_IRQ	0x3e00	/* Interrupt message number */
+#define  PCI_EXP_FLAGS_FLIT	0x8000	/* Flit Mode Supported */
 #define PCI_EXP_DEVCAP		0x04	/* Device capabilities */
 #define  PCI_EXP_DEVCAP_PAYLOAD	0x00000007 /* Max_Payload_Size */
 #define  PCI_EXP_DEVCAP_PHANTOM	0x00000018 /* Phantom functions */
@@ -795,6 +796,8 @@
 #define  PCI_ERR_CAP_ECRC_CHKC		0x00000080 /* ECRC Check Capable */
 #define  PCI_ERR_CAP_ECRC_CHKE		0x00000100 /* ECRC Check Enable */
 #define  PCI_ERR_CAP_PREFIX_LOG_PRESENT	0x00000800 /* TLP Prefix Log Present */
+#define  PCI_ERR_CAP_TLP_LOG_FLIT	0x00040000 /* TLP was logged in Flit Mode */
+#define  PCI_ERR_CAP_TLP_LOG_SIZE	0x00f80000 /* Logged TLP Size (only in Flit mode) */
 #define PCI_ERR_HEADER_LOG	0x1c	/* Header Log Register (16 bytes) */
 #define PCI_ERR_ROOT_COMMAND	0x2c	/* Root Error Command */
 #define  PCI_ERR_ROOT_CMD_COR_EN	0x00000001 /* Correctable Err Reporting Enable */
@@ -1061,8 +1064,9 @@
 #define  PCI_EXP_DPC_CAP_RP_EXT		0x0020	/* Root Port Extensions */
 #define  PCI_EXP_DPC_CAP_POISONED_TLP	0x0040	/* Poisoned TLP Egress Blocking Supported */
 #define  PCI_EXP_DPC_CAP_SW_TRIGGER	0x0080	/* Software Triggering Supported */
-#define  PCI_EXP_DPC_RP_PIO_LOG_SIZE	0x0F00	/* RP PIO Log Size */
+#define  PCI_EXP_DPC_RP_PIO_LOG_SIZE	0x0F00	/* RP PIO Log Size [3:0] */
 #define  PCI_EXP_DPC_CAP_DL_ACTIVE	0x1000	/* ERR_COR signal on DL_Active supported */
+#define  PCI_EXP_DPC_RP_PIO_LOG_SIZE4	0x2000	/* RP PIO Log Size [4] */
 
 #define PCI_EXP_DPC_CTL			0x06	/* DPC control */
 #define  PCI_EXP_DPC_CTL_EN_FATAL	0x0001	/* Enable trigger on ERR_FATAL message */