Patchwork [V5] powerpc/85xx: Add machine check handler to fix PCIe erratum on mpc85xx

login
register
mail settings
Submitter Hongtao Jia
Date April 8, 2013, 8:26 a.m.
Message ID <1365409614-2634-1-git-send-email-hongtao.jia@freescale.com>
Download mbox | patch
Permalink /patch/234609/
State Superseded
Delegated to: Kumar Gala
Headers show

Comments

Hongtao Jia - April 8, 2013, 8:26 a.m.
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.

This patch depends on patch:
powerpc/85xx: Add platform_device declaration to fsl_pci.h

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 <hongtao.jia@freescale.com>
---
Changes for V4:
* Fill rd with all-Fs if the skipped instruction is load and emulate the
  instruction.
* Let KVM/QEMU deal with the exception if the machine check comes from KVM.

 arch/powerpc/kernel/cpu_setup_fsl_booke.S |   2 +-
 arch/powerpc/kernel/traps.c               |   3 +
 arch/powerpc/sysdev/fsl_pci.c             | 121 ++++++++++++++++++++++++++++++
 arch/powerpc/sysdev/fsl_pci.h             |   6 ++
 4 files changed, 131 insertions(+), 1 deletion(-)
Hongtao Jia - April 10, 2013, 2:27 a.m.
Hi Scott,

I added load instruction handler for the skipped instruction.
For now most common load instructions are handled in this patch.

Any advice for this?

Thanks.
-Hongtao.

> -----Original Message-----
> From: Jia Hongtao-B38951
> Sent: Monday, April 08, 2013 4:27 PM
> To: linuxppc-dev@lists.ozlabs.org; galak@kernel.crashing.org
> Cc: Wood Scott-B07421; Li Yang-R58472; Jia Hongtao-B38951
> Subject: [PATCH V5] powerpc/85xx: Add machine check handler to fix PCIe
> erratum on mpc85xx
> 
> 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.
> 
> This patch depends on patch:
> powerpc/85xx: Add platform_device declaration to fsl_pci.h
> 
> 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 <hongtao.jia@freescale.com>
> ---
> Changes for V4:
> * Fill rd with all-Fs if the skipped instruction is load and emulate the
>   instruction.
> * Let KVM/QEMU deal with the exception if the machine check comes from
> KVM.
> 
>  arch/powerpc/kernel/cpu_setup_fsl_booke.S |   2 +-
>  arch/powerpc/kernel/traps.c               |   3 +
>  arch/powerpc/sysdev/fsl_pci.c             | 121
> ++++++++++++++++++++++++++++++
>  arch/powerpc/sysdev/fsl_pci.h             |   6 ++
>  4 files changed, 131 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
> b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
> index dcd8819..f1bde90 100644
> --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
> +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
> @@ -66,7 +66,7 @@ _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 a008cf5..dd275a4 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; @@ -556,6 +557,8 @@
> 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
> 682084d..48326cd 100644
> --- a/arch/powerpc/sysdev/fsl_pci.c
> +++ b/arch/powerpc/sysdev/fsl_pci.c
> @@ -26,11 +26,14 @@
>  #include <linux/memblock.h>
>  #include <linux/log2.h>
>  #include <linux/slab.h>
> +#include <linux/uaccess.h>
> 
>  #include <asm/io.h>
>  #include <asm/prom.h>
>  #include <asm/pci-bridge.h>
> +#include <asm/ppc-pci.h>
>  #include <asm/machdep.h>
> +#include <asm/disassemble.h>
>  #include <sysdev/fsl_soc.h>
>  #include <sysdev/fsl_pci.h>
> 
> @@ -826,6 +829,124 @@ u64 fsl_pci_immrbar_base(struct pci_controller
> *hose)
>  	return 0;
>  }
> 
> +#ifdef CONFIG_E500
> +
> +#define OP_LWZ  32
> +#define OP_LWZU 33
> +#define OP_LBZ  34
> +#define OP_LBZU 35
> +#define OP_LHZ  40
> +#define OP_LHZU 41
> +#define OP_LHA  42
> +#define OP_LHAU 43
> +
> +static int mcheck_handle_load(struct pt_regs *regs, u32 inst) {
> +	unsigned int rd, ra, d;
> +
> +	rd = get_rt(inst);
> +	ra = get_ra(inst);
> +	d = get_d(inst);
> +
> +	switch (get_op(inst)) {
> +	case OP_LWZ:
> +		regs->gpr[rd] = 0xffffffff;
> +		break;
> +
> +	case OP_LWZU:
> +		regs->gpr[rd] = 0xffffffff;
> +		regs->gpr[ra] += (s16)d;
> +		break;
> +
> +	case OP_LBZ:
> +		regs->gpr[rd] = 0xff;
> +		break;
> +
> +	case OP_LBZU:
> +		regs->gpr[rd] = 0xff;
> +		regs->gpr[ra] += (s16)d;
> +		break;
> +
> +	case OP_LHZ:
> +		regs->gpr[rd] = 0xffff;
> +		break;
> +
> +	case OP_LHZU:
> +		regs->gpr[rd] = 0xffff;
> +		regs->gpr[ra] += (s16)d;
> +		break;
> +
> +	case OP_LHA:
> +		regs->gpr[rd] = 0xffff;
> +		break;
> +
> +	case OP_LHAU:
> +		regs->gpr[rd] = 0xffff;
> +		regs->gpr[ra] += (s16)d;
> +		break;
> +
> +	default:
> +		return 0;
> +	}
> +
> +	return 1;
> +}
> +
> +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) {
> +	u32 inst;
> +	int ret;
> +	phys_addr_t addr = 0;
> +
> +	/* Let KVM/QEMU deal with the exception */
> +	if (regs->msr & MSR_GS)
> +		return 0;
> +
> +#ifdef CONFIG_PHYS_64BIT
> +	addr = mfspr(SPRN_MCARU);
> +	addr <<= 32;
> +#endif
> +	addr += mfspr(SPRN_MCAR);
> +
> +	if (is_in_pci_mem_space(addr)) {
> +		if (user_mode(regs)) {
> +			pagefault_disable();
> +			ret = get_user(regs->nip, &inst);
> +			pagefault_enable();
> +		} else {
> +			ret = probe_kernel_address(regs->nip, inst);
> +		}
> +
> +		if (mcheck_handle_load(regs, inst)) {
> +			regs->nip += 4;
> +			return 1;
> +		}
> +	}
> +
> +	return 0;
> +}
> +#endif
> +
>  #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 851dd56..b0d01ea 100644
> --- a/arch/powerpc/sysdev/fsl_pci.h
> +++ b/arch/powerpc/sysdev/fsl_pci.h
> @@ -115,5 +115,11 @@ static inline int mpc85xx_pci_err_probe(struct
> platform_device *op)  }  #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__ */
> --
> 1.8.0
Hongtao Jia - April 11, 2013, 9:14 a.m.
> -----Original Message-----
> From: Wood Scott-B07421
> Sent: Thursday, April 11, 2013 5:52 AM
> To: Jia Hongtao-B38951
> Cc: linuxppc-dev@lists.ozlabs.org; galak@kernel.crashing.org; Wood Scott-
> B07421; Li Yang-R58472; Jia Hongtao-B38951
> Subject: Re: [PATCH V5] powerpc/85xx: Add machine check handler to fix
> PCIe erratum on mpc85xx
> 
> On 04/08/2013 03:26:54 AM, Jia Hongtao wrote:
> > @@ -826,6 +829,124 @@ u64 fsl_pci_immrbar_base(struct pci_controller
> > *hose)
> >  	return 0;
> >  }
> >
> > +#ifdef CONFIG_E500
> > +
> > +#define OP_LWZ  32
> > +#define OP_LWZU 33
> > +#define OP_LBZ  34
> > +#define OP_LBZU 35
> > +#define OP_LHZ  40
> > +#define OP_LHZU 41
> > +#define OP_LHA  42
> > +#define OP_LHAU 43
> 
> Can you move these to asm/ppc-opcode.h (or possibly
> asm/ppc-disassemble.h if we don't want to mix the two methods of
> describing instructions)?

Yes, mix the two methods is not appropriate.
asm/ppc-disassemble.h is a nice choice.

> 
> > +static int mcheck_handle_load(struct pt_regs *regs, u32 inst)
> > +{
> > +	unsigned int rd, ra, d;
> > +
> > +	rd = get_rt(inst);
> > +	ra = get_ra(inst);
> > +	d = get_d(inst);
> > +
> > +	switch (get_op(inst)) {
> > +	case OP_LWZ:
> > +		regs->gpr[rd] = 0xffffffff;
> > +		break;
> > +
> > +	case OP_LWZU:
> > +		regs->gpr[rd] = 0xffffffff;
> > +		regs->gpr[ra] += (s16)d;
> > +		break;
> > +
> > +	case OP_LBZ:
> > +		regs->gpr[rd] = 0xff;
> > +		break;
> > +
> > +	case OP_LBZU:
> > +		regs->gpr[rd] = 0xff;
> > +		regs->gpr[ra] += (s16)d;
> > +		break;
> > +
> > +	case OP_LHZ:
> > +		regs->gpr[rd] = 0xffff;
> > +		break;
> > +
> > +	case OP_LHZU:
> > +		regs->gpr[rd] = 0xffff;
> > +		regs->gpr[ra] += (s16)d;
> > +		break;
> > +
> > +	case OP_LHA:
> > +		regs->gpr[rd] = 0xffff;
> > +		break;
> > +
> > +	case OP_LHAU:
> > +		regs->gpr[rd] = 0xffff;
> > +		regs->gpr[ra] += (s16)d;
> > +		break;
> 
> The X and (especially for PCI) BRX versions are important -- probably
> more so than the U versions.  I doubt we need the A variant.

Then I will add X and BRX variant and remove A variant.

> 
> If you do support the A variant, why are you not sign-extending the
> value?

Just curious, sign-extending the value means fill rd with 0xffffffff?

> 
> Is this erratum present on any 64-bit chips?

No. This erratum only happened in e500 core chips.

> 
> -Scott

Thanks.
-Hongtao
Scott Wood - April 11, 2013, 2:47 p.m.
On 04/11/2013 04:14:51 AM, Jia Hongtao-B38951 wrote:
> 
> 
> > -----Original Message-----
> > From: Wood Scott-B07421
> > Sent: Thursday, April 11, 2013 5:52 AM
> > To: Jia Hongtao-B38951
> > Cc: linuxppc-dev@lists.ozlabs.org; galak@kernel.crashing.org; Wood  
> Scott-
> > B07421; Li Yang-R58472; Jia Hongtao-B38951
> > Subject: Re: [PATCH V5] powerpc/85xx: Add machine check handler to  
> fix
> > PCIe erratum on mpc85xx
> >
> > The X and (especially for PCI) BRX versions are important --  
> probably
> > more so than the U versions.  I doubt we need the A variant.
> 
> Then I will add X and BRX variant and remove A variant.
> 
> >
> > If you do support the A variant, why are you not sign-extending the
> > value?
> 
> Just curious, sign-extending the value means fill rd with 0xffffffff?

Or 0xffffffffffffffff on 64-bit (even if you're not going to implement  
64-bit instructions, the ones you do implement shouldn't misbehave  
there).  You could write it as "regs->gpr[rd] = ~0UL".

-Scott

Patch

diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index dcd8819..f1bde90 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -66,7 +66,7 @@  _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 a008cf5..dd275a4 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;
@@ -556,6 +557,8 @@  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 682084d..48326cd 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -26,11 +26,14 @@ 
 #include <linux/memblock.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
 #include <asm/machdep.h>
+#include <asm/disassemble.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
@@ -826,6 +829,124 @@  u64 fsl_pci_immrbar_base(struct pci_controller *hose)
 	return 0;
 }
 
+#ifdef CONFIG_E500
+
+#define OP_LWZ  32
+#define OP_LWZU 33
+#define OP_LBZ  34
+#define OP_LBZU 35
+#define OP_LHZ  40
+#define OP_LHZU 41
+#define OP_LHA  42
+#define OP_LHAU 43
+
+static int mcheck_handle_load(struct pt_regs *regs, u32 inst)
+{
+	unsigned int rd, ra, d;
+
+	rd = get_rt(inst);
+	ra = get_ra(inst);
+	d = get_d(inst);
+
+	switch (get_op(inst)) {
+	case OP_LWZ:
+		regs->gpr[rd] = 0xffffffff;
+		break;
+
+	case OP_LWZU:
+		regs->gpr[rd] = 0xffffffff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LBZ:
+		regs->gpr[rd] = 0xff;
+		break;
+
+	case OP_LBZU:
+		regs->gpr[rd] = 0xff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LHZ:
+		regs->gpr[rd] = 0xffff;
+		break;
+
+	case OP_LHZU:
+		regs->gpr[rd] = 0xffff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LHA:
+		regs->gpr[rd] = 0xffff;
+		break;
+
+	case OP_LHAU:
+		regs->gpr[rd] = 0xffff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+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)
+{
+	u32 inst;
+	int ret;
+	phys_addr_t addr = 0;
+
+	/* Let KVM/QEMU deal with the exception */
+	if (regs->msr & MSR_GS)
+		return 0;
+
+#ifdef CONFIG_PHYS_64BIT
+	addr = mfspr(SPRN_MCARU);
+	addr <<= 32;
+#endif
+	addr += mfspr(SPRN_MCAR);
+
+	if (is_in_pci_mem_space(addr)) {
+		if (user_mode(regs)) {
+			pagefault_disable();
+			ret = get_user(regs->nip, &inst);
+			pagefault_enable();
+		} else {
+			ret = probe_kernel_address(regs->nip, inst);
+		}
+
+		if (mcheck_handle_load(regs, inst)) {
+			regs->nip += 4;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+#endif
+
 #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 851dd56..b0d01ea 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -115,5 +115,11 @@  static inline int mpc85xx_pci_err_probe(struct platform_device *op)
 }
 #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__ */