diff mbox

[V3] powerpc/85xx: Add machine check handler to fix PCIe erratum on mpc85xx

Message ID 1342406750-32694-1-git-send-email-B38951@freescale.com (mailing list archive)
State Superseded
Headers show

Commit Message

Hongtao Jia July 16, 2012, 2:45 a.m. UTC 
A PCIe erratum of mpc85xx may causes a core hang when a link of PCIe
goes down. when the link goes down, Non-posted transactions issued
via the ATMU requiring completion result in an instruction stall.
At the same time a machine-check exception is generated to the core
to allow further processing by the handler. We implements the handler
which skips the instruction caused the stall.

Signed-off-by: Zhao Chenhui <b35336@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Liu Shuo <soniccat.liu@gmail.com>
Signed-off-by: Jia Hongtao <B38951@freescale.com>
---
V3 changed: Just rebase the patch.

 arch/powerpc/kernel/cpu_setup_fsl_booke.S |    2 +-
 arch/powerpc/kernel/traps.c               |    3 ++
 arch/powerpc/sysdev/fsl_pci.c             |   39 +++++++++++++++++++++++++++++
 arch/powerpc/sysdev/fsl_pci.h             |    6 ++++
 4 files changed, 49 insertions(+), 1 deletions(-)

Comments

David Laight July 16, 2012, 8:45 a.m. UTC | #1 
> A PCIe erratum of mpc85xx may causes a core hang when a link of PCIe
> goes down. when the link goes down, Non-posted transactions issued
> via the ATMU requiring completion result in an instruction stall.
> At the same time a machine-check exception is generated to the core
> to allow further processing by the handler. We implements the handler
> which skips the instruction caused the stall.

Does skipping the faulting instruction really help?

We use the mpc83xx and have seen PCIe issues that may be
related to a documented errata in the CSB-PEX bridge (which
I can't find my copy of).
Do the 85xx and 83xx have the same PCIe block?
Recovery from it seems almost impossible - my interpretation
was that you have to hard reset the PCIe block and rewrite
the entire configuration.

The problem we see happens during some PEX DMA transfers
(possibly due to issues with the target), the DMA doesn't
complete and any further PIO transfers fault (and panic).
Unfortunately the PEX has no documented status registers,
so it is difficult to determine what is (or rather isn't)
Happening.

	David
diff mbox

Patch

diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 69fdd23..9c4b768 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -64,7 +64,7 @@  _GLOBAL(__setup_cpu_e500v2)
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
 	bl	__setup_e500_ivors
-#ifdef CONFIG_FSL_RIO
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
 	/* Ensure that RFXE is set */
 	mfspr	r3,SPRN_HID1
 	oris	r3,r3,HID1_RFXE@h
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1589723..096a1a1 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -59,6 +59,7 @@ 
 #include <asm/fadump.h>
 #include <asm/switch_to.h>
 #include <asm/debug.h>
+#include <sysdev/fsl_pci.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -555,6 +556,8 @@  int machine_check_e500(struct pt_regs *regs)
 	if (reason & MCSR_BUS_RBERR) {
 		if (fsl_rio_mcheck_exception(regs))
 			return 1;
+		if (fsl_pci_mcheck_exception(regs))
+			return 1;
 	}
 
 	printk("Machine check in kernel mode.\n");
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index a7b2a60..52f3b5d 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -30,6 +30,7 @@ 
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
 #include <asm/machdep.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
@@ -808,6 +809,44 @@  u64 fsl_pci_immrbar_base(struct pci_controller *hose)
 	return 0;
 }
 
+static int is_in_pci_mem_space(phys_addr_t addr)
+{
+	struct pci_controller *hose;
+	struct resource *res;
+	int i;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		if (!early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP))
+			continue;
+
+		for (i = 0; i < 3; i++) {
+			res = &hose->mem_resources[i];
+			if ((res->flags & IORESOURCE_MEM) &&
+				addr >= res->start && addr <= res->end)
+				return 1;
+		}
+	}
+	return 0;
+}
+
+int fsl_pci_mcheck_exception(struct pt_regs *regs)
+{
+	phys_addr_t addr = 0;
+
+#ifdef CONFIG_PHYS_64BIT
+	addr = mfspr(SPRN_MCARU);
+	addr <<= 32;
+#endif
+	addr += mfspr(SPRN_MCAR);
+
+	if (is_in_pci_mem_space(addr)) {
+		regs->nip += 4;
+		return 1;
+	}
+
+	return 0;
+}
+
 #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static const struct of_device_id pci_ids[] = {
 	{ .compatible = "fsl,mpc8540-pci", },
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index baa0fd1..efd1907 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -101,5 +101,11 @@  void fsl_pci_init(void);
 static inline void fsl_pci_init(void) {}
 #endif
 
+#ifdef CONFIG_FSL_PCI
+extern int fsl_pci_mcheck_exception(struct pt_regs *);
+#else
+static inline int fsl_pci_mcheck_exception(struct pt_regs *regs) {return 0; }
+#endif
+
 #endif /* __POWERPC_FSL_PCI_H */
 #endif /* __KERNEL__ */