* [PATCH v5 16/27] irq_domain: Remove irq_domain_add_simple()
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Russell King
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
irq_domain_add_simple() was a stop-gap measure until complete irq_domain
support was complete. This patch removes the irq_domain_add_simple()
interface.
This patch also drops the explicit irq_domain initialization performed
by the mach-versatile code because the versatile interrupt controller
already has irq_domain support built into it. This was a bug that was
hanging around quietly for a while, but with the full irq_domain which
actually verifies that irq_domain ranges are available it would cause
the registration to fail and the system wouldn't boot.
v4: Fixed number of irqs in mx5 gpio code
v2: Updated to pass in host_data pointer on irq_domain allocation.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Tested-by: Olof Johansson <olof@lixom.net>
---
arch/arm/mach-imx/imx51-dt.c | 4 ++--
arch/arm/mach-imx/imx53-dt.c | 4 ++--
arch/arm/mach-imx/mach-imx6q.c | 3 ++-
arch/arm/mach-msm/board-msm8x60.c | 8 ++------
arch/arm/mach-omap2/board-generic.c | 2 +-
arch/arm/mach-prima2/irq.c | 2 +-
include/linux/irqdomain.h | 1 -
kernel/irq/irqdomain.c | 10 ++--------
8 files changed, 12 insertions(+), 22 deletions(-)
diff --git a/arch/arm/mach-imx/imx51-dt.c b/arch/arm/mach-imx/imx51-dt.c
index e6bad17..1e03ef4 100644
--- a/arch/arm/mach-imx/imx51-dt.c
+++ b/arch/arm/mach-imx/imx51-dt.c
@@ -47,7 +47,7 @@ static const struct of_dev_auxdata imx51_auxdata_lookup[] __initconst = {
static int __init imx51_tzic_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
- irq_domain_add_simple(np, 0);
+ irq_domain_add_legacy(np, 128, 0, 0, &irq_domain_simple_ops, NULL);
return 0;
}
@@ -57,7 +57,7 @@ static int __init imx51_gpio_add_irq_domain(struct device_node *np,
static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
gpio_irq_base -= 32;
- irq_domain_add_simple(np, gpio_irq_base);
+ irq_domain_add_legacy(np, 32, gpio_irq_base, 0, &irq_domain_simple_ops, NULL);
return 0;
}
diff --git a/arch/arm/mach-imx/imx53-dt.c b/arch/arm/mach-imx/imx53-dt.c
index 05ebb3e..fd5be0f 100644
--- a/arch/arm/mach-imx/imx53-dt.c
+++ b/arch/arm/mach-imx/imx53-dt.c
@@ -51,7 +51,7 @@ static const struct of_dev_auxdata imx53_auxdata_lookup[] __initconst = {
static int __init imx53_tzic_add_irq_domain(struct device_node *np,
struct device_node *interrupt_parent)
{
- irq_domain_add_simple(np, 0);
+ irq_domain_add_legacy(np, 128, 0, 0, &irq_domain_simple_ops, NULL);
return 0;
}
@@ -61,7 +61,7 @@ static int __init imx53_gpio_add_irq_domain(struct device_node *np,
static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
gpio_irq_base -= 32;
- irq_domain_add_simple(np, gpio_irq_base);
+ irq_domain_add_legacy(np, 32, gpio_irq_base, 0, &irq_domain_simple_ops, NULL);
return 0;
}
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index c257281..6075d4d 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -97,7 +97,8 @@ static int __init imx6q_gpio_add_irq_domain(struct device_node *np,
static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
gpio_irq_base -= 32;
- irq_domain_add_simple(np, gpio_irq_base);
+ irq_domain_add_legacy(np, 32, gpio_irq_base, 0, &irq_domain_simple_ops,
+ NULL);
return 0;
}
diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c
index 0a11342..962e711 100644
--- a/arch/arm/mach-msm/board-msm8x60.c
+++ b/arch/arm/mach-msm/board-msm8x60.c
@@ -80,12 +80,8 @@ static struct of_device_id msm_dt_gic_match[] __initdata = {
static void __init msm8x60_dt_init(void)
{
- struct device_node *node;
-
- node = of_find_matching_node_by_address(NULL, msm_dt_gic_match,
- MSM8X60_QGIC_DIST_PHYS);
- if (node)
- irq_domain_add_simple(node, GIC_SPI_START);
+ irq_domain_generate_simple(msm_dt_gic_match, MSM8X60_QGIC_DIST_PHYS,
+ GIC_SPI_START);
if (of_machine_is_compatible("qcom,msm8660-surf")) {
printk(KERN_INFO "Init surf UART registers\n");
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index d587560..00b1d02 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -67,7 +67,7 @@ static void __init omap_generic_init(void)
{
struct device_node *node = of_find_matching_node(NULL, intc_match);
if (node)
- irq_domain_add_simple(node, 0);
+ irq_domain_add_legacy(node, 32, 0, 0, &irq_domain_simple_ops, NULL);
omap_sdrc_init(NULL, NULL);
diff --git a/arch/arm/mach-prima2/irq.c b/arch/arm/mach-prima2/irq.c
index d93ceef..37c2de9 100644
--- a/arch/arm/mach-prima2/irq.c
+++ b/arch/arm/mach-prima2/irq.c
@@ -68,7 +68,7 @@ void __init sirfsoc_of_irq_init(void)
if (!sirfsoc_intc_base)
panic("unable to map intc cpu registers\n");
- irq_domain_add_simple(np, 0);
+ irq_domain_add_legacy(np, 32, 0, 0, &irq_domain_simple_ops, NULL);
of_node_put(np);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 624e9ac..e7379a3 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -164,7 +164,6 @@ extern unsigned int irq_linear_revmap(struct irq_domain *host,
extern struct irq_domain_ops irq_domain_simple_ops;
#if defined(CONFIG_OF_IRQ)
-extern void irq_domain_add_simple(struct device_node *controller, int irq_base);
extern void irq_domain_generate_simple(const struct of_device_id *match,
u64 phys_base, unsigned int irq_start);
#else /* CONFIG_OF_IRQ */
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index dad793f..03f571a 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -722,13 +722,6 @@ struct irq_domain_ops irq_domain_simple_ops = {
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
#ifdef CONFIG_OF_IRQ
-void irq_domain_add_simple(struct device_node *controller, int irq_base)
-{
- irq_domain_add_legacy(controller, 32, irq_base, 0,
- &irq_domain_simple_ops, NULL);
-}
-EXPORT_SYMBOL_GPL(irq_domain_add_simple);
-
void irq_domain_generate_simple(const struct of_device_id *match,
u64 phys_base, unsigned int irq_start)
{
@@ -737,7 +730,8 @@ void irq_domain_generate_simple(const struct of_device_id *match,
(unsigned long long) phys_base, (int) irq_start);
node = of_find_matching_node_by_address(NULL, match, phys_base);
if (node)
- irq_domain_add_simple(node, irq_start);
+ irq_domain_add_legacy(node, 32, irq_start, 0,
+ &irq_domain_simple_ops, NULL);
}
EXPORT_SYMBOL_GPL(irq_domain_generate_simple);
#endif
--
1.7.9
^ permalink raw reply related
* [PATCH v5 17/27] irq_domain: Create common xlate functions that device drivers can use
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Mark Salter
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
Rather than having each interrupt controller driver creating its own barely
unique .xlate function for irq_domain, create a library of translators which
any driver can use directly.
v5: - Remove irq_domain_xlate_pci(). It was incorrect.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
Tested-by: Olof Johansson <olof@lixom.net>
---
include/linux/irqdomain.h | 12 ++++++++
kernel/irq/irqdomain.c | 65 ++++++++++++++++++++++++++++++++++++++-------
2 files changed, 67 insertions(+), 10 deletions(-)
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index e7379a3..ea58f36 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -163,6 +163,18 @@ extern unsigned int irq_linear_revmap(struct irq_domain *host,
irq_hw_number_t hwirq);
extern struct irq_domain_ops irq_domain_simple_ops;
+
+/* stock xlate functions */
+int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_type);
+int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_type);
+int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_type);
+
#if defined(CONFIG_OF_IRQ)
extern void irq_domain_generate_simple(const struct of_device_id *match,
u64 phys_base, unsigned int irq_start);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 03f571a..9a8f95e 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -699,25 +699,70 @@ int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
return 0;
}
-int irq_domain_simple_xlate(struct irq_domain *d,
- struct device_node *controller,
- const u32 *intspec, unsigned int intsize,
- unsigned long *out_hwirq, unsigned int *out_type)
+/**
+ * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with one cell
+ * bindings where the cell value maps directly to the hwirq number.
+ */
+int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ unsigned long *out_hwirq, unsigned int *out_type)
{
- if (d->of_node != controller)
- return -EINVAL;
- if (intsize < 1)
+ if (WARN_ON(intsize < 1))
return -EINVAL;
*out_hwirq = intspec[0];
*out_type = IRQ_TYPE_NONE;
- if (intsize > 1)
- *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
return 0;
}
+EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell);
+
+/**
+ * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with two cell
+ * bindings where the cell values map directly to the hwirq number
+ * and linux irq flags.
+ */
+int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ irq_hw_number_t *out_hwirq, unsigned int *out_type)
+{
+ if (WARN_ON(intsize < 2))
+ return -EINVAL;
+ *out_hwirq = intspec[0];
+ *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell);
+
+/**
+ * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with either one
+ * or two cell bindings where the cell values map directly to the hwirq number
+ * and linux irq flags.
+ *
+ * Note: don't use this function unless your interrupt controller explicitly
+ * supports both one and two cell bindings. For the majority of controllers
+ * the _onecell() or _twocell() variants above should be used.
+ */
+int irq_domain_xlate_onetwocell(struct irq_domain *d,
+ struct device_node *ctrlr,
+ const u32 *intspec, unsigned int intsize,
+ unsigned long *out_hwirq, unsigned int *out_type)
+{
+ if (WARN_ON(intsize < 1))
+ return -EINVAL;
+ *out_hwirq = intspec[0];
+ *out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell);
struct irq_domain_ops irq_domain_simple_ops = {
.map = irq_domain_simple_map,
- .xlate = irq_domain_simple_xlate,
+ .xlate = irq_domain_xlate_onetwocell,
};
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
--
1.7.9
^ permalink raw reply related
* [PATCH v5 18/27] irq_domain: constify irq_domain_ops
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
Make irq_domain_ops pointer a constant to make it safer for multiple
instances to share the same ops pointer and change the irq_domain code
so that it does not modify the ops.
v4: Fix mismatched type reference in powerpc code
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Milton Miller <miltonm@bga.com>
Tested-by: Olof Johansson <olof@lixom.net>
---
arch/powerpc/sysdev/mpic_msi.c | 2 +-
include/linux/irqdomain.h | 14 +++++++-------
kernel/irq/irqdomain.c | 31 +++++++++++++++----------------
3 files changed, 23 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c
index 00395f4..0622aa9 100644
--- a/arch/powerpc/sysdev/mpic_msi.c
+++ b/arch/powerpc/sysdev/mpic_msi.c
@@ -32,7 +32,7 @@ void mpic_msi_reserve_hwirq(struct mpic *mpic, irq_hw_number_t hwirq)
static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
{
irq_hw_number_t hwirq;
- struct irq_domain_ops *ops = mpic->irqhost->ops;
+ const struct irq_domain_ops *ops = mpic->irqhost->ops;
struct device_node *np;
int flags, index, i;
struct of_irq oirq;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index ea58f36..5245488 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -106,7 +106,7 @@ struct irq_domain {
} linear;
struct radix_tree_root tree;
} revmap_data;
- struct irq_domain_ops *ops;
+ const struct irq_domain_ops *ops;
void *host_data;
irq_hw_number_t inval_irq;
@@ -119,17 +119,17 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
unsigned int size,
unsigned int first_irq,
irq_hw_number_t first_hwirq,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data);
struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
unsigned int size,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data);
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data);
struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data);
extern struct irq_domain *irq_find_host(struct device_node *node);
@@ -138,7 +138,7 @@ extern void irq_set_virq_count(unsigned int count);
static inline struct irq_domain *irq_domain_add_legacy_isa(
struct device_node *of_node,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
return irq_domain_add_legacy(of_node, NUM_ISA_INTERRUPTS, 0, 0, ops,
@@ -162,7 +162,7 @@ extern unsigned int irq_radix_revmap_lookup(struct irq_domain *host,
extern unsigned int irq_linear_revmap(struct irq_domain *host,
irq_hw_number_t hwirq);
-extern struct irq_domain_ops irq_domain_simple_ops;
+extern const struct irq_domain_ops irq_domain_simple_ops;
/* stock xlate functions */
int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr,
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 9a8f95e..2d3dfff 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -26,11 +26,6 @@ static DEFINE_MUTEX(revmap_trees_mutex);
static unsigned int irq_virq_count = NR_IRQS;
static struct irq_domain *irq_default_domain;
-static int default_irq_domain_match(struct irq_domain *d, struct device_node *np)
-{
- return d->of_node != NULL && d->of_node == np;
-}
-
/**
* irq_domain_alloc() - Allocate a new irq_domain data structure
* @of_node: optional device-tree node of the interrupt controller
@@ -44,7 +39,7 @@ static int default_irq_domain_match(struct irq_domain *d, struct device_node *np
*/
static struct irq_domain *irq_domain_alloc(struct device_node *of_node,
unsigned int revmap_type,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain;
@@ -59,9 +54,6 @@ static struct irq_domain *irq_domain_alloc(struct device_node *of_node,
domain->host_data = host_data;
domain->of_node = of_node_get(of_node);
- if (domain->ops->match == NULL)
- domain->ops->match = default_irq_domain_match;
-
return domain;
}
@@ -104,7 +96,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
unsigned int size,
unsigned int first_irq,
irq_hw_number_t first_hwirq,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain;
@@ -170,7 +162,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
*/
struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
unsigned int size,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain;
@@ -192,7 +184,7 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
}
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain = irq_domain_alloc(of_node,
@@ -211,7 +203,7 @@ struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
* (the reverse mapping will use the slow path until that happens).
*/
struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
- struct irq_domain_ops *ops,
+ const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain = irq_domain_alloc(of_node,
@@ -230,6 +222,7 @@ struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
struct irq_domain *irq_find_host(struct device_node *node)
{
struct irq_domain *h, *found = NULL;
+ int rc;
/* We might want to match the legacy controller last since
* it might potentially be set to match all interrupts in
@@ -237,11 +230,17 @@ struct irq_domain *irq_find_host(struct device_node *node)
* yet though...
*/
mutex_lock(&irq_domain_mutex);
- list_for_each_entry(h, &irq_domain_list, link)
- if (h->ops->match(h, node)) {
+ list_for_each_entry(h, &irq_domain_list, link) {
+ if (h->ops->match)
+ rc = h->ops->match(h, node);
+ else
+ rc = (h->of_node != NULL) && (h->of_node == node);
+
+ if (rc) {
found = h;
break;
}
+ }
mutex_unlock(&irq_domain_mutex);
return found;
}
@@ -760,7 +759,7 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d,
}
EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell);
-struct irq_domain_ops irq_domain_simple_ops = {
+const struct irq_domain_ops irq_domain_simple_ops = {
.map = irq_domain_simple_map,
.xlate = irq_domain_xlate_onetwocell,
};
--
1.7.9
^ permalink raw reply related
* [PATCH v5 19/27] irq_domain/c6x: Convert c6x to use generic irq_domain support.
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Aurelien Jacquiot, Mark Salter
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
From: Mark Salter <msalter@redhat.com>
The C6X IRQ support was copied almost verbatim from the PowerPC virtual IRQ
code. The PowerPC code was used as the basis for generic irq_domain support,
so this patch mostly copies what what done to arch/powerpc by Grant Likely
in his irq_domain patch series.
Signed-off-by: Mark Salter <msalter@redhat.com>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Aurelien Jacquiot <a-jacquiot@ti.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
arch/c6x/Kconfig | 1 +
arch/c6x/include/asm/irq.h | 245 +---------------
arch/c6x/kernel/irq.c | 611 +-------------------------------------
arch/c6x/platforms/megamod-pic.c | 13 +-
4 files changed, 21 insertions(+), 849 deletions(-)
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 26e67f0..3c64b28 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -12,6 +12,7 @@ config TMS320C6X
select HAVE_GENERIC_HARDIRQS
select HAVE_MEMBLOCK
select HAVE_SPARSE_IRQ
+ select IRQ_DOMAIN
select OF
select OF_EARLY_FLATTREE
diff --git a/arch/c6x/include/asm/irq.h b/arch/c6x/include/asm/irq.h
index a6ae3c9..f13b78d 100644
--- a/arch/c6x/include/asm/irq.h
+++ b/arch/c6x/include/asm/irq.h
@@ -13,6 +13,7 @@
#ifndef _ASM_C6X_IRQ_H
#define _ASM_C6X_IRQ_H
+#include <linux/irqdomain.h>
#include <linux/threads.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
@@ -41,253 +42,9 @@
/* This number is used when no interrupt has been assigned */
#define NO_IRQ 0
-/* This type is the placeholder for a hardware interrupt number. It has to
- * be big enough to enclose whatever representation is used by a given
- * platform.
- */
-typedef unsigned long irq_hw_number_t;
-
-/* Interrupt controller "host" data structure. This could be defined as a
- * irq domain controller. That is, it handles the mapping between hardware
- * and virtual interrupt numbers for a given interrupt domain. The host
- * structure is generally created by the PIC code for a given PIC instance
- * (though a host can cover more than one PIC if they have a flat number
- * model). It's the host callbacks that are responsible for setting the
- * irq_chip on a given irq_desc after it's been mapped.
- *
- * The host code and data structures are fairly agnostic to the fact that
- * we use an open firmware device-tree. We do have references to struct
- * device_node in two places: in irq_find_host() to find the host matching
- * a given interrupt controller node, and of course as an argument to its
- * counterpart host->ops->match() callback. However, those are treated as
- * generic pointers by the core and the fact that it's actually a device-node
- * pointer is purely a convention between callers and implementation. This
- * code could thus be used on other architectures by replacing those two
- * by some sort of arch-specific void * "token" used to identify interrupt
- * controllers.
- */
-struct irq_host;
-struct radix_tree_root;
-struct device_node;
-
-/* Functions below are provided by the host and called whenever a new mapping
- * is created or an old mapping is disposed. The host can then proceed to
- * whatever internal data structures management is required. It also needs
- * to setup the irq_desc when returning from map().
- */
-struct irq_host_ops {
- /* Match an interrupt controller device node to a host, returns
- * 1 on a match
- */
- int (*match)(struct irq_host *h, struct device_node *node);
-
- /* Create or update a mapping between a virtual irq number and a hw
- * irq number. This is called only once for a given mapping.
- */
- int (*map)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw);
-
- /* Dispose of such a mapping */
- void (*unmap)(struct irq_host *h, unsigned int virq);
-
- /* Translate device-tree interrupt specifier from raw format coming
- * from the firmware to a irq_hw_number_t (interrupt line number) and
- * type (sense) that can be passed to set_irq_type(). In the absence
- * of this callback, irq_create_of_mapping() and irq_of_parse_and_map()
- * will return the hw number in the first cell and IRQ_TYPE_NONE for
- * the type (which amount to keeping whatever default value the
- * interrupt controller has for that line)
- */
- int (*xlate)(struct irq_host *h, struct device_node *ctrler,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_type);
-};
-
-struct irq_host {
- struct list_head link;
-
- /* type of reverse mapping technique */
- unsigned int revmap_type;
-#define IRQ_HOST_MAP_PRIORITY 0 /* core priority irqs, get irqs 1..15 */
-#define IRQ_HOST_MAP_NOMAP 1 /* no fast reverse mapping */
-#define IRQ_HOST_MAP_LINEAR 2 /* linear map of interrupts */
-#define IRQ_HOST_MAP_TREE 3 /* radix tree */
- union {
- struct {
- unsigned int size;
- unsigned int *revmap;
- } linear;
- struct radix_tree_root tree;
- } revmap_data;
- struct irq_host_ops *ops;
- void *host_data;
- irq_hw_number_t inval_irq;
-
- /* Optional device node pointer */
- struct device_node *of_node;
-};
-
struct irq_data;
extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
extern irq_hw_number_t virq_to_hw(unsigned int virq);
-extern bool virq_is_host(unsigned int virq, struct irq_host *host);
-
-/**
- * irq_alloc_host - Allocate a new irq_host data structure
- * @of_node: optional device-tree node of the interrupt controller
- * @revmap_type: type of reverse mapping to use
- * @revmap_arg: for IRQ_HOST_MAP_LINEAR linear only: size of the map
- * @ops: map/unmap host callbacks
- * @inval_irq: provide a hw number in that host space that is always invalid
- *
- * Allocates and initialize and irq_host structure. Note that in the case of
- * IRQ_HOST_MAP_LEGACY, the map() callback will be called before this returns
- * for all legacy interrupts except 0 (which is always the invalid irq for
- * a legacy controller). For a IRQ_HOST_MAP_LINEAR, the map is allocated by
- * this call as well. For a IRQ_HOST_MAP_TREE, the radix tree will be allocated
- * later during boot automatically (the reverse mapping will use the slow path
- * until that happens).
- */
-extern struct irq_host *irq_alloc_host(struct device_node *of_node,
- unsigned int revmap_type,
- unsigned int revmap_arg,
- struct irq_host_ops *ops,
- irq_hw_number_t inval_irq);
-
-
-/**
- * irq_find_host - Locates a host for a given device node
- * @node: device-tree node of the interrupt controller
- */
-extern struct irq_host *irq_find_host(struct device_node *node);
-
-
-/**
- * irq_set_default_host - Set a "default" host
- * @host: default host pointer
- *
- * For convenience, it's possible to set a "default" host that will be used
- * whenever NULL is passed to irq_create_mapping(). It makes life easier for
- * platforms that want to manipulate a few hard coded interrupt numbers that
- * aren't properly represented in the device-tree.
- */
-extern void irq_set_default_host(struct irq_host *host);
-
-
-/**
- * irq_set_virq_count - Set the maximum number of virt irqs
- * @count: number of linux virtual irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-extern void irq_set_virq_count(unsigned int count);
-
-
-/**
- * irq_create_mapping - Map a hardware interrupt into linux virq space
- * @host: host owning this hardware interrupt or NULL for default host
- * @hwirq: hardware irq number in that host space
- *
- * Only one mapping per hardware interrupt is permitted. Returns a linux
- * virq number.
- * If the sense/trigger is to be specified, set_irq_type() should be called
- * on the number returned from that call.
- */
-extern unsigned int irq_create_mapping(struct irq_host *host,
- irq_hw_number_t hwirq);
-
-
-/**
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- */
-extern void irq_dispose_mapping(unsigned int virq);
-
-/**
- * irq_find_mapping - Find a linux virq from an hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a slow path, for use by generic code. It's expected that an
- * irq controller implementation directly calls the appropriate low level
- * mapping function.
- */
-extern unsigned int irq_find_mapping(struct irq_host *host,
- irq_hw_number_t hwirq);
-
-/**
- * irq_create_direct_mapping - Allocate a virq for direct mapping
- * @host: host to allocate the virq for or NULL for default host
- *
- * This routine is used for irq controllers which can choose the hardware
- * interrupt numbers they generate. In such a case it's simplest to use
- * the linux virq as the hardware interrupt number.
- */
-extern unsigned int irq_create_direct_mapping(struct irq_host *host);
-
-/**
- * irq_radix_revmap_insert - Insert a hw irq to linux virq number mapping.
- * @host: host owning this hardware interrupt
- * @virq: linux irq number
- * @hwirq: hardware irq number in that host space
- *
- * This is for use by irq controllers that use a radix tree reverse
- * mapping for fast lookup.
- */
-extern void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
- irq_hw_number_t hwirq);
-
-/**
- * irq_radix_revmap_lookup - Find a linux virq from a hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a fast path, for use by irq controller code that uses radix tree
- * revmaps
- */
-extern unsigned int irq_radix_revmap_lookup(struct irq_host *host,
- irq_hw_number_t hwirq);
-
-/**
- * irq_linear_revmap - Find a linux virq from a hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a fast path, for use by irq controller code that uses linear
- * revmaps. It does fallback to the slow path if the revmap doesn't exist
- * yet and will create the revmap entry with appropriate locking
- */
-
-extern unsigned int irq_linear_revmap(struct irq_host *host,
- irq_hw_number_t hwirq);
-
-
-
-/**
- * irq_alloc_virt - Allocate virtual irq numbers
- * @host: host owning these new virtual irqs
- * @count: number of consecutive numbers to allocate
- * @hint: pass a hint number, the allocator will try to use a 1:1 mapping
- *
- * This is a low level function that is used internally by irq_create_mapping()
- * and that can be used by some irq controllers implementations for things
- * like allocating ranges of numbers for MSIs. The revmaps are left untouched.
- */
-extern unsigned int irq_alloc_virt(struct irq_host *host,
- unsigned int count,
- unsigned int hint);
-
-/**
- * irq_free_virt - Free virtual irq numbers
- * @virq: virtual irq number of the first interrupt to free
- * @count: number of interrupts to free
- *
- * This function is the opposite of irq_alloc_virt. It will not clear reverse
- * maps, this should be done previously by unmap'ing the interrupt. In fact,
- * all interrupts covered by the range being freed should have been unmapped
- * prior to calling this.
- */
-extern void irq_free_virt(unsigned int virq, unsigned int count);
extern void __init init_pic_c64xplus(void);
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index 0929e4b..3d5ac60 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -73,10 +73,10 @@ asmlinkage void c6x_do_IRQ(unsigned int prio, struct pt_regs *regs)
set_irq_regs(old_regs);
}
-static struct irq_host *core_host;
+static struct irq_domain *core_domain;
-static int core_host_map(struct irq_host *h, unsigned int virq,
- irq_hw_number_t hw)
+static int core_domain_map(struct irq_domain *h, unsigned int virq,
+ irq_hw_number_t hw)
{
if (hw < 4 || hw >= NR_PRIORITY_IRQS)
return -EINVAL;
@@ -86,8 +86,8 @@ static int core_host_map(struct irq_host *h, unsigned int virq,
return 0;
}
-static struct irq_host_ops core_host_ops = {
- .map = core_host_map,
+static struct irq_domain_ops core_domain_ops = {
+ .map = core_domain_map,
};
void __init init_IRQ(void)
@@ -100,10 +100,11 @@ void __init init_IRQ(void)
np = of_find_compatible_node(NULL, NULL, "ti,c64x+core-pic");
if (np != NULL) {
/* create the core host */
- core_host = irq_alloc_host(np, IRQ_HOST_MAP_PRIORITY, 0,
- &core_host_ops, 0);
- if (core_host)
- irq_set_default_host(core_host);
+ core_domain = irq_domain_add_legacy(np, NR_PRIORITY_IRQS,
+ 0, 0, &core_domain_ops,
+ NULL);
+ if (core_domain)
+ irq_set_default_host(core_domain);
of_node_put(np);
}
@@ -128,601 +129,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
return 0;
}
-/*
- * IRQ controller and virtual interrupts
- */
-
-/* The main irq map itself is an array of NR_IRQ entries containing the
- * associate host and irq number. An entry with a host of NULL is free.
- * An entry can be allocated if it's free, the allocator always then sets
- * hwirq first to the host's invalid irq number and then fills ops.
- */
-struct irq_map_entry {
- irq_hw_number_t hwirq;
- struct irq_host *host;
-};
-
-static LIST_HEAD(irq_hosts);
-static DEFINE_RAW_SPINLOCK(irq_big_lock);
-static DEFINE_MUTEX(revmap_trees_mutex);
-static struct irq_map_entry irq_map[NR_IRQS];
-static unsigned int irq_virq_count = NR_IRQS;
-static struct irq_host *irq_default_host;
-
irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
{
- return irq_map[d->irq].hwirq;
+ return d->hwirq;
}
EXPORT_SYMBOL_GPL(irqd_to_hwirq);
irq_hw_number_t virq_to_hw(unsigned int virq)
{
- return irq_map[virq].hwirq;
+ struct irq_data *irq_data = irq_get_irq_data(virq);
+ return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
}
EXPORT_SYMBOL_GPL(virq_to_hw);
-
-bool virq_is_host(unsigned int virq, struct irq_host *host)
-{
- return irq_map[virq].host == host;
-}
-EXPORT_SYMBOL_GPL(virq_is_host);
-
-static int default_irq_host_match(struct irq_host *h, struct device_node *np)
-{
- return h->of_node != NULL && h->of_node == np;
-}
-
-struct irq_host *irq_alloc_host(struct device_node *of_node,
- unsigned int revmap_type,
- unsigned int revmap_arg,
- struct irq_host_ops *ops,
- irq_hw_number_t inval_irq)
-{
- struct irq_host *host;
- unsigned int size = sizeof(struct irq_host);
- unsigned int i;
- unsigned int *rmap;
- unsigned long flags;
-
- /* Allocate structure and revmap table if using linear mapping */
- if (revmap_type == IRQ_HOST_MAP_LINEAR)
- size += revmap_arg * sizeof(unsigned int);
- host = kzalloc(size, GFP_KERNEL);
- if (host == NULL)
- return NULL;
-
- /* Fill structure */
- host->revmap_type = revmap_type;
- host->inval_irq = inval_irq;
- host->ops = ops;
- host->of_node = of_node_get(of_node);
-
- if (host->ops->match == NULL)
- host->ops->match = default_irq_host_match;
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
-
- /* Check for the priority controller. */
- if (revmap_type == IRQ_HOST_MAP_PRIORITY) {
- if (irq_map[0].host != NULL) {
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- of_node_put(host->of_node);
- kfree(host);
- return NULL;
- }
- irq_map[0].host = host;
- }
-
- list_add(&host->link, &irq_hosts);
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-
- /* Additional setups per revmap type */
- switch (revmap_type) {
- case IRQ_HOST_MAP_PRIORITY:
- /* 0 is always the invalid number for priority */
- host->inval_irq = 0;
- /* setup us as the host for all priority interrupts */
- for (i = 1; i < NR_PRIORITY_IRQS; i++) {
- irq_map[i].hwirq = i;
- smp_wmb();
- irq_map[i].host = host;
- smp_wmb();
-
- ops->map(host, i, i);
- }
- break;
- case IRQ_HOST_MAP_LINEAR:
- rmap = (unsigned int *)(host + 1);
- for (i = 0; i < revmap_arg; i++)
- rmap[i] = NO_IRQ;
- host->revmap_data.linear.size = revmap_arg;
- smp_wmb();
- host->revmap_data.linear.revmap = rmap;
- break;
- case IRQ_HOST_MAP_TREE:
- INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL);
- break;
- default:
- break;
- }
-
- pr_debug("irq: Allocated host of type %d @0x%p\n", revmap_type, host);
-
- return host;
-}
-
-struct irq_host *irq_find_host(struct device_node *node)
-{
- struct irq_host *h, *found = NULL;
- unsigned long flags;
-
- /* We might want to match the legacy controller last since
- * it might potentially be set to match all interrupts in
- * the absence of a device node. This isn't a problem so far
- * yet though...
- */
- raw_spin_lock_irqsave(&irq_big_lock, flags);
- list_for_each_entry(h, &irq_hosts, link)
- if (h->ops->match(h, node)) {
- found = h;
- break;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return found;
-}
-EXPORT_SYMBOL_GPL(irq_find_host);
-
-void irq_set_default_host(struct irq_host *host)
-{
- pr_debug("irq: Default host set to @0x%p\n", host);
-
- irq_default_host = host;
-}
-
-void irq_set_virq_count(unsigned int count)
-{
- pr_debug("irq: Trying to set virq count to %d\n", count);
-
- BUG_ON(count < NR_PRIORITY_IRQS);
- if (count < NR_IRQS)
- irq_virq_count = count;
-}
-
-static int irq_setup_virq(struct irq_host *host, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- int res;
-
- res = irq_alloc_desc_at(virq, 0);
- if (res != virq) {
- pr_debug("irq: -> allocating desc failed\n");
- goto error;
- }
-
- /* map it */
- smp_wmb();
- irq_map[virq].hwirq = hwirq;
- smp_mb();
-
- if (host->ops->map(host, virq, hwirq)) {
- pr_debug("irq: -> mapping failed, freeing\n");
- goto errdesc;
- }
-
- irq_clear_status_flags(virq, IRQ_NOREQUEST);
-
- return 0;
-
-errdesc:
- irq_free_descs(virq, 1);
-error:
- irq_free_virt(virq, 1);
- return -1;
-}
-
-unsigned int irq_create_direct_mapping(struct irq_host *host)
-{
- unsigned int virq;
-
- if (host == NULL)
- host = irq_default_host;
-
- BUG_ON(host == NULL);
- WARN_ON(host->revmap_type != IRQ_HOST_MAP_NOMAP);
-
- virq = irq_alloc_virt(host, 1, 0);
- if (virq == NO_IRQ) {
- pr_debug("irq: create_direct virq allocation failed\n");
- return NO_IRQ;
- }
-
- pr_debug("irq: create_direct obtained virq %d\n", virq);
-
- if (irq_setup_virq(host, virq, virq))
- return NO_IRQ;
-
- return virq;
-}
-
-unsigned int irq_create_mapping(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int virq, hint;
-
- pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", host, hwirq);
-
- /* Look for default host if nececssary */
- if (host == NULL)
- host = irq_default_host;
- if (host == NULL) {
- printk(KERN_WARNING "irq_create_mapping called for"
- " NULL host, hwirq=%lx\n", hwirq);
- WARN_ON(1);
- return NO_IRQ;
- }
- pr_debug("irq: -> using host @%p\n", host);
-
- /* Check if mapping already exists */
- virq = irq_find_mapping(host, hwirq);
- if (virq != NO_IRQ) {
- pr_debug("irq: -> existing mapping on virq %d\n", virq);
- return virq;
- }
-
- /* Allocate a virtual interrupt number */
- hint = hwirq % irq_virq_count;
- virq = irq_alloc_virt(host, 1, hint);
- if (virq == NO_IRQ) {
- pr_debug("irq: -> virq allocation failed\n");
- return NO_IRQ;
- }
-
- if (irq_setup_virq(host, virq, hwirq))
- return NO_IRQ;
-
- pr_debug("irq: irq %lu on host %s mapped to virtual irq %u\n",
- hwirq, host->of_node ? host->of_node->full_name : "null", virq);
-
- return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_mapping);
-
-unsigned int irq_create_of_mapping(struct device_node *controller,
- const u32 *intspec, unsigned int intsize)
-{
- struct irq_host *host;
- irq_hw_number_t hwirq;
- unsigned int type = IRQ_TYPE_NONE;
- unsigned int virq;
-
- if (controller == NULL)
- host = irq_default_host;
- else
- host = irq_find_host(controller);
- if (host == NULL) {
- printk(KERN_WARNING "irq: no irq host found for %s !\n",
- controller->full_name);
- return NO_IRQ;
- }
-
- /* If host has no translation, then we assume interrupt line */
- if (host->ops->xlate == NULL)
- hwirq = intspec[0];
- else {
- if (host->ops->xlate(host, controller, intspec, intsize,
- &hwirq, &type))
- return NO_IRQ;
- }
-
- /* Create mapping */
- virq = irq_create_mapping(host, hwirq);
- if (virq == NO_IRQ)
- return virq;
-
- /* Set type if specified and different than the current one */
- if (type != IRQ_TYPE_NONE &&
- type != (irqd_get_trigger_type(irq_get_irq_data(virq))))
- irq_set_irq_type(virq, type);
- return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
-
-void irq_dispose_mapping(unsigned int virq)
-{
- struct irq_host *host;
- irq_hw_number_t hwirq;
-
- if (virq == NO_IRQ)
- return;
-
- /* Never unmap priority interrupts */
- if (virq < NR_PRIORITY_IRQS)
- return;
-
- host = irq_map[virq].host;
- if (WARN_ON(host == NULL))
- return;
-
- irq_set_status_flags(virq, IRQ_NOREQUEST);
-
- /* remove chip and handler */
- irq_set_chip_and_handler(virq, NULL, NULL);
-
- /* Make sure it's completed */
- synchronize_irq(virq);
-
- /* Tell the PIC about it */
- if (host->ops->unmap)
- host->ops->unmap(host, virq);
- smp_mb();
-
- /* Clear reverse map */
- hwirq = irq_map[virq].hwirq;
- switch (host->revmap_type) {
- case IRQ_HOST_MAP_LINEAR:
- if (hwirq < host->revmap_data.linear.size)
- host->revmap_data.linear.revmap[hwirq] = NO_IRQ;
- break;
- case IRQ_HOST_MAP_TREE:
- mutex_lock(&revmap_trees_mutex);
- radix_tree_delete(&host->revmap_data.tree, hwirq);
- mutex_unlock(&revmap_trees_mutex);
- break;
- }
-
- /* Destroy map */
- smp_mb();
- irq_map[virq].hwirq = host->inval_irq;
-
- irq_free_descs(virq, 1);
- /* Free it */
- irq_free_virt(virq, 1);
-}
-EXPORT_SYMBOL_GPL(irq_dispose_mapping);
-
-unsigned int irq_find_mapping(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int i;
- unsigned int hint = hwirq % irq_virq_count;
-
- /* Look for default host if nececssary */
- if (host == NULL)
- host = irq_default_host;
- if (host == NULL)
- return NO_IRQ;
-
- /* Slow path does a linear search of the map */
- i = hint;
- do {
- if (irq_map[i].host == host &&
- irq_map[i].hwirq == hwirq)
- return i;
- i++;
- if (i >= irq_virq_count)
- i = 4;
- } while (i != hint);
- return NO_IRQ;
-}
-EXPORT_SYMBOL_GPL(irq_find_mapping);
-
-unsigned int irq_radix_revmap_lookup(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- struct irq_map_entry *ptr;
- unsigned int virq;
-
- if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE))
- return irq_find_mapping(host, hwirq);
-
- /*
- * The ptr returned references the static global irq_map.
- * but freeing an irq can delete nodes along the path to
- * do the lookup via call_rcu.
- */
- rcu_read_lock();
- ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq);
- rcu_read_unlock();
-
- /*
- * If found in radix tree, then fine.
- * Else fallback to linear lookup - this should not happen in practice
- * as it means that we failed to insert the node in the radix tree.
- */
- if (ptr)
- virq = ptr - irq_map;
- else
- virq = irq_find_mapping(host, hwirq);
-
- return virq;
-}
-
-void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE))
- return;
-
- if (virq != NO_IRQ) {
- mutex_lock(&revmap_trees_mutex);
- radix_tree_insert(&host->revmap_data.tree, hwirq,
- &irq_map[virq]);
- mutex_unlock(&revmap_trees_mutex);
- }
-}
-
-unsigned int irq_linear_revmap(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int *revmap;
-
- if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR))
- return irq_find_mapping(host, hwirq);
-
- /* Check revmap bounds */
- if (unlikely(hwirq >= host->revmap_data.linear.size))
- return irq_find_mapping(host, hwirq);
-
- /* Check if revmap was allocated */
- revmap = host->revmap_data.linear.revmap;
- if (unlikely(revmap == NULL))
- return irq_find_mapping(host, hwirq);
-
- /* Fill up revmap with slow path if no mapping found */
- if (unlikely(revmap[hwirq] == NO_IRQ))
- revmap[hwirq] = irq_find_mapping(host, hwirq);
-
- return revmap[hwirq];
-}
-
-unsigned int irq_alloc_virt(struct irq_host *host,
- unsigned int count,
- unsigned int hint)
-{
- unsigned long flags;
- unsigned int i, j, found = NO_IRQ;
-
- if (count == 0 || count > (irq_virq_count - NR_PRIORITY_IRQS))
- return NO_IRQ;
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
-
- /* Use hint for 1 interrupt if any */
- if (count == 1 && hint >= NR_PRIORITY_IRQS &&
- hint < irq_virq_count && irq_map[hint].host == NULL) {
- found = hint;
- goto hint_found;
- }
-
- /* Look for count consecutive numbers in the allocatable
- * (non-legacy) space
- */
- for (i = NR_PRIORITY_IRQS, j = 0; i < irq_virq_count; i++) {
- if (irq_map[i].host != NULL)
- j = 0;
- else
- j++;
-
- if (j == count) {
- found = i - count + 1;
- break;
- }
- }
- if (found == NO_IRQ) {
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return NO_IRQ;
- }
- hint_found:
- for (i = found; i < (found + count); i++) {
- irq_map[i].hwirq = host->inval_irq;
- smp_wmb();
- irq_map[i].host = host;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return found;
-}
-
-void irq_free_virt(unsigned int virq, unsigned int count)
-{
- unsigned long flags;
- unsigned int i;
-
- WARN_ON(virq < NR_PRIORITY_IRQS);
- WARN_ON(count == 0 || (virq + count) > irq_virq_count);
-
- if (virq < NR_PRIORITY_IRQS) {
- if (virq + count < NR_PRIORITY_IRQS)
- return;
- count -= NR_PRIORITY_IRQS - virq;
- virq = NR_PRIORITY_IRQS;
- }
-
- if (count > irq_virq_count || virq > irq_virq_count - count) {
- if (virq > irq_virq_count)
- return;
- count = irq_virq_count - virq;
- }
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
- for (i = virq; i < (virq + count); i++) {
- struct irq_host *host;
-
- host = irq_map[i].host;
- irq_map[i].hwirq = host->inval_irq;
- smp_wmb();
- irq_map[i].host = NULL;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-}
-
-#ifdef CONFIG_VIRQ_DEBUG
-static int virq_debug_show(struct seq_file *m, void *private)
-{
- unsigned long flags;
- struct irq_desc *desc;
- const char *p;
- static const char none[] = "none";
- void *data;
- int i;
-
- seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq",
- "chip name", "chip data", "host name");
-
- for (i = 1; i < nr_irqs; i++) {
- desc = irq_to_desc(i);
- if (!desc)
- continue;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
-
- if (desc->action && desc->action->handler) {
- struct irq_chip *chip;
-
- seq_printf(m, "%5d ", i);
- seq_printf(m, "0x%05lx ", irq_map[i].hwirq);
-
- chip = irq_desc_get_chip(desc);
- if (chip && chip->name)
- p = chip->name;
- else
- p = none;
- seq_printf(m, "%-15s ", p);
-
- data = irq_desc_get_chip_data(desc);
- seq_printf(m, "0x%16p ", data);
-
- if (irq_map[i].host && irq_map[i].host->of_node)
- p = irq_map[i].host->of_node->full_name;
- else
- p = none;
- seq_printf(m, "%s\n", p);
- }
-
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- }
-
- return 0;
-}
-
-static int virq_debug_open(struct inode *inode, struct file *file)
-{
- return single_open(file, virq_debug_show, inode->i_private);
-}
-
-static const struct file_operations virq_debug_fops = {
- .open = virq_debug_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int __init irq_debugfs_init(void)
-{
- if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
- NULL, &virq_debug_fops) == NULL)
- return -ENOMEM;
-
- return 0;
-}
-device_initcall(irq_debugfs_init);
-#endif /* CONFIG_VIRQ_DEBUG */
diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c
index 7c37a94..61f5863 100644
--- a/arch/c6x/platforms/megamod-pic.c
+++ b/arch/c6x/platforms/megamod-pic.c
@@ -48,7 +48,7 @@ struct megamod_regs {
};
struct megamod_pic {
- struct irq_host *irqhost;
+ struct irq_domain *irqhost;
struct megamod_regs __iomem *regs;
raw_spinlock_t lock;
@@ -116,7 +116,7 @@ static void megamod_irq_cascade(unsigned int irq, struct irq_desc *desc)
}
}
-static int megamod_map(struct irq_host *h, unsigned int virq,
+static int megamod_map(struct irq_domain *h, unsigned int virq,
irq_hw_number_t hw)
{
struct megamod_pic *pic = h->host_data;
@@ -136,7 +136,7 @@ static int megamod_map(struct irq_host *h, unsigned int virq,
return 0;
}
-static int megamod_xlate(struct irq_host *h, struct device_node *ct,
+static int megamod_xlate(struct irq_domain *h, struct device_node *ct,
const u32 *intspec, unsigned int intsize,
irq_hw_number_t *out_hwirq, unsigned int *out_type)
@@ -148,7 +148,7 @@ static int megamod_xlate(struct irq_host *h, struct device_node *ct,
return 0;
}
-static struct irq_host_ops megamod_host_ops = {
+static struct irq_domain_ops megamod_domain_ops = {
.map = megamod_map,
.xlate = megamod_xlate,
};
@@ -223,9 +223,8 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np)
return NULL;
}
- pic->irqhost = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
- NR_COMBINERS * 32, &megamod_host_ops,
- IRQ_UNMAPPED);
+ pic->irqhost = irq_domain_add_linear(np, NR_COMBINERS * 32,
+ &megamod_domain_ops, pic);
if (!pic->irqhost) {
pr_err("%s: Could not alloc host.\n", np->full_name);
goto error_free;
--
1.7.9
^ permalink raw reply related
* [PATCH v5 20/27] irq_domain/c6x: constify irq_domain structures
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Mark Salter
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Mark Salter <msalter@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
arch/arm/common/gic.c | 2 +-
arch/c6x/kernel/irq.c | 2 +-
arch/c6x/platforms/megamod-pic.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 7275d80..f0783be 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -635,7 +635,7 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
return 0;
}
-struct irq_domain_ops gic_irq_domain_ops = {
+const struct irq_domain_ops gic_irq_domain_ops = {
.map = gic_irq_domain_map,
.xlate = gic_irq_domain_xlate,
};
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index 3d5ac60..c6b36e8 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -86,7 +86,7 @@ static int core_domain_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops core_domain_ops = {
+static const struct irq_domain_ops core_domain_ops = {
.map = core_domain_map,
};
diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c
index 61f5863..9f35fbf 100644
--- a/arch/c6x/platforms/megamod-pic.c
+++ b/arch/c6x/platforms/megamod-pic.c
@@ -148,7 +148,7 @@ static int megamod_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops megamod_domain_ops = {
+static const struct irq_domain_ops megamod_domain_ops = {
.map = megamod_map,
.xlate = megamod_xlate,
};
--
1.7.9
^ permalink raw reply related
* [PATCH v5 21/27] irq_domain/c6x: Use library of xlate functions
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Mark Salter
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
The c6x irq controllers don't need to define custom .xlate hooks
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
arch/c6x/kernel/irq.c | 1 +
arch/c6x/platforms/megamod-pic.c | 14 +-------------
2 files changed, 2 insertions(+), 13 deletions(-)
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index c6b36e8..d77bcfd 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -88,6 +88,7 @@ static int core_domain_map(struct irq_domain *h, unsigned int virq,
static const struct irq_domain_ops core_domain_ops = {
.map = core_domain_map,
+ .xlate = irq_domain_xlate_onecell,
};
void __init init_IRQ(void)
diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c
index 9f35fbf..c1c4e2a 100644
--- a/arch/c6x/platforms/megamod-pic.c
+++ b/arch/c6x/platforms/megamod-pic.c
@@ -136,21 +136,9 @@ static int megamod_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int megamod_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_type)
-
-{
- /* megamod intspecs must have 1 cell */
- BUG_ON(intsize != 1);
- *out_hwirq = intspec[0];
- *out_type = IRQ_TYPE_NONE;
- return 0;
-}
-
static const struct irq_domain_ops megamod_domain_ops = {
.map = megamod_map,
- .xlate = megamod_xlate,
+ .xlate = irq_domain_xlate_onecell,
};
static void __init set_megamod_mux(struct megamod_pic *pic, int src, int output)
--
1.7.9
^ permalink raw reply related
* [PATCH v5 22/27] irq_domain/powerpc: constify irq_domain_ops
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
Make all the irq_domain_ops structures in powerpc 'static const'
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
Tested-by: Olof Johansson <olof@lixom.net>
---
arch/powerpc/platforms/512x/mpc5121_ads_cpld.c | 2 +-
arch/powerpc/platforms/52xx/media5200.c | 2 +-
arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 2 +-
arch/powerpc/platforms/52xx/mpc52xx_pic.c | 2 +-
arch/powerpc/platforms/82xx/pq2ads-pci-pic.c | 2 +-
arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 +-
arch/powerpc/platforms/86xx/gef_pic.c | 2 +-
arch/powerpc/platforms/cell/axon_msi.c | 2 +-
arch/powerpc/platforms/cell/beat_interrupt.c | 2 +-
arch/powerpc/platforms/cell/interrupt.c | 2 +-
arch/powerpc/platforms/cell/spider-pic.c | 2 +-
arch/powerpc/platforms/embedded6xx/flipper-pic.c | 2 +-
arch/powerpc/platforms/embedded6xx/hlwd-pic.c | 2 +-
arch/powerpc/platforms/iseries/irq.c | 2 +-
arch/powerpc/platforms/powermac/pic.c | 2 +-
arch/powerpc/platforms/powermac/smp.c | 2 +-
arch/powerpc/platforms/ps3/interrupt.c | 2 +-
arch/powerpc/platforms/wsp/opb_pic.c | 2 +-
arch/powerpc/sysdev/cpm1.c | 2 +-
arch/powerpc/sysdev/cpm2_pic.c | 2 +-
arch/powerpc/sysdev/ehv_pic.c | 2 +-
arch/powerpc/sysdev/fsl_msi.c | 2 +-
22 files changed, 22 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 291d61c..ca3a062 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -137,7 +137,7 @@ cpld_pic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops cpld_pic_host_ops = {
+static const struct irq_domain_ops cpld_pic_host_ops = {
.match = cpld_pic_host_match,
.map = cpld_pic_host_map,
};
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 5db5cfb..17d91b7 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -136,7 +136,7 @@ static int media5200_irq_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops media5200_irq_ops = {
+static const struct irq_domain_ops media5200_irq_ops = {
.map = media5200_irq_map,
.xlate = media5200_irq_xlate,
};
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index b53275d..028470b 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -236,7 +236,7 @@ static int mpc52xx_gpt_irq_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops mpc52xx_gpt_irq_ops = {
+static const struct irq_domain_ops mpc52xx_gpt_irq_ops = {
.map = mpc52xx_gpt_irq_map,
.xlate = mpc52xx_gpt_irq_xlate,
};
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 41fa671..8520b58 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -384,7 +384,7 @@ static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops mpc52xx_irqhost_ops = {
+static const struct irq_domain_ops mpc52xx_irqhost_ops = {
.xlate = mpc52xx_irqhost_xlate,
.map = mpc52xx_irqhost_map,
};
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 4ef9d69..328d221 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -112,7 +112,7 @@ static int pci_pic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops pci_pic_host_ops = {
+static const struct irq_domain_ops pci_pic_host_ops = {
.map = pci_pic_host_map,
};
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 1092c12..3bbbf74 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -269,7 +269,7 @@ static int socrates_fpga_pic_host_xlate(struct irq_domain *h,
return 0;
}
-static struct irq_domain_ops socrates_fpga_pic_host_ops = {
+static const struct irq_domain_ops socrates_fpga_pic_host_ops = {
.map = socrates_fpga_pic_host_map,
.xlate = socrates_fpga_pic_host_xlate,
};
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index 126a94b..af3fd69 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -177,7 +177,7 @@ static int gef_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops gef_pic_host_ops = {
+static const struct irq_domain_ops gef_pic_host_ops = {
.map = gef_pic_host_map,
.xlate = gef_pic_host_xlate,
};
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index cf9fd3c..db360fc 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -327,7 +327,7 @@ static int msic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops msic_host_ops = {
+static const struct irq_domain_ops msic_host_ops = {
.map = msic_host_map,
};
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index bbdf574..e5c3a2c 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -172,7 +172,7 @@ static int beatic_pic_host_match(struct irq_domain *h, struct device_node *np)
return 1;
}
-static struct irq_domain_ops beatic_pic_host_ops = {
+static const struct irq_domain_ops beatic_pic_host_ops = {
.map = beatic_pic_host_map,
.unmap = beatic_pic_host_unmap,
.xlate = beatic_pic_host_xlate,
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index c844797..2d42f3b 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -285,7 +285,7 @@ static int iic_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops iic_host_ops = {
+static const struct irq_domain_ops iic_host_ops = {
.match = iic_host_match,
.map = iic_host_map,
.xlate = iic_host_xlate,
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 6521d20..d8b7cc8 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -194,7 +194,7 @@ static int spider_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops spider_host_ops = {
+static const struct irq_domain_ops spider_host_ops = {
.map = spider_host_map,
.xlate = spider_host_xlate,
};
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 4345971..675335a 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -113,7 +113,7 @@ static int flipper_pic_match(struct irq_domain *h, struct device_node *np)
}
-static struct irq_domain_ops flipper_irq_domain_ops = {
+static const struct irq_domain_ops flipper_irq_domain_ops = {
.map = flipper_pic_map,
.match = flipper_pic_match,
};
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 499d410..da6ca02 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -100,7 +100,7 @@ static int hlwd_pic_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops hlwd_irq_domain_ops = {
+static const struct irq_domain_ops hlwd_irq_domain_ops = {
.map = hlwd_pic_map,
};
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 5538b59..05ce516 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -356,7 +356,7 @@ static int iseries_irq_host_match(struct irq_domain *h, struct device_node *np)
return 1;
}
-static struct irq_domain_ops iseries_irq_domain_ops = {
+static const struct irq_domain_ops iseries_irq_domain_ops = {
.map = iseries_irq_host_map,
.match = iseries_irq_host_match,
};
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 646fdf3..46a5f32 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -299,7 +299,7 @@ static int pmac_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops pmac_pic_host_ops = {
+static const struct irq_domain_ops pmac_pic_host_ops = {
.match = pmac_pic_host_match,
.map = pmac_pic_host_map,
.xlate = pmac_pic_host_xlate,
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 09afd70..a81e5a8 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -184,7 +184,7 @@ static int psurge_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-struct irq_domain_ops psurge_host_ops = {
+static const struct irq_domain_ops psurge_host_ops = {
.map = psurge_host_map,
};
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index c05808f..2a4ff86 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -684,7 +684,7 @@ static int ps3_host_match(struct irq_domain *h, struct device_node *np)
return 1;
}
-static struct irq_domain_ops ps3_host_ops = {
+static const struct irq_domain_ops ps3_host_ops = {
.map = ps3_host_map,
.match = ps3_host_match,
};
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
index 4837515..0c6fe0b 100644
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -207,7 +207,7 @@ static int opb_host_xlate(struct irq_domain *host, struct device_node *dn,
return 0;
}
-static struct irq_domain_ops opb_host_ops = {
+static const struct irq_domain_ops opb_host_ops = {
.map = opb_host_map,
.xlate = opb_host_xlate,
};
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 53f39db..d4fa03f 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -123,7 +123,7 @@ static struct irqaction cpm_error_irqaction = {
.name = "error",
};
-static struct irq_domain_ops cpm_pic_host_ops = {
+static const struct irq_domain_ops cpm_pic_host_ops = {
.map = cpm_pic_host_map,
};
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index b364332..8c9fc9c 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -236,7 +236,7 @@ static int cpm2_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops cpm2_pic_host_ops = {
+static const struct irq_domain_ops cpm2_pic_host_ops = {
.map = cpm2_pic_host_map,
.xlate = cpm2_pic_host_xlate,
};
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index adea322..6e0e100 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -248,7 +248,7 @@ static int ehv_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
return 0;
}
-static struct irq_domain_ops ehv_pic_host_ops = {
+static const struct irq_domain_ops ehv_pic_host_ops = {
.match = ehv_pic_host_match,
.map = ehv_pic_host_map,
.xlate = ehv_pic_host_xlate,
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index f4fd95b..0c01deb 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -74,7 +74,7 @@ static int fsl_msi_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static struct irq_domain_ops fsl_msi_host_ops = {
+static const struct irq_domain_ops fsl_msi_host_ops = {
.map = fsl_msi_host_map,
};
--
1.7.9
^ permalink raw reply related
* [PATCH v5 23/27] irq_domain/powerpc: Replace custom xlate functions with library functions
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
This patch converts a number of the powerpc drivers to use the common library
of irq_domain xlate functions, dropping a bunch of lines in the process.
v5: - Remove tsi108 changes from patch
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
Tested-by: Olof Johansson <olof@lixom.net>
---
arch/powerpc/platforms/powermac/pic.c | 13 +------------
arch/powerpc/platforms/wsp/opb_pic.c | 13 +------------
arch/powerpc/sysdev/cpm2_pic.c | 14 +-------------
arch/powerpc/sysdev/ipic.c | 18 +-----------------
arch/powerpc/sysdev/qe_lib/qe_ic.c | 15 +--------------
arch/powerpc/sysdev/uic.c | 14 +-------------
drivers/gpio/gpio-mpc8xxx.c | 17 +----------------
7 files changed, 7 insertions(+), 97 deletions(-)
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 46a5f32..92afc38 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -288,21 +288,10 @@ static int pmac_pic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int pmac_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq,
- unsigned int *out_flags)
-
-{
- *out_flags = IRQ_TYPE_NONE;
- *out_hwirq = *intspec;
- return 0;
-}
-
static const struct irq_domain_ops pmac_pic_host_ops = {
.match = pmac_pic_host_match,
.map = pmac_pic_host_map,
- .xlate = pmac_pic_host_xlate,
+ .xlate = irq_domain_xlate_onecell,
};
static void __init pmac_pic_probe_oldstyle(void)
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
index 0c6fe0b..cb565bf 100644
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -196,20 +196,9 @@ static int opb_host_map(struct irq_domain *host, unsigned int virq,
return 0;
}
-static int opb_host_xlate(struct irq_domain *host, struct device_node *dn,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_type)
-{
- /* Interrupt size must == 2 */
- BUG_ON(intsize != 2);
- *out_hwirq = intspec[0];
- *out_type = intspec[1];
- return 0;
-}
-
static const struct irq_domain_ops opb_host_ops = {
.map = opb_host_map,
- .xlate = opb_host_xlate,
+ .xlate = irq_domain_xlate_twocell,
};
irqreturn_t opb_irq_handler(int irq, void *private)
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 8c9fc9c..d3be961 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -224,21 +224,9 @@ static int cpm2_pic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int cpm2_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-{
- *out_hwirq = intspec[0];
- if (intsize > 1)
- *out_flags = intspec[1];
- else
- *out_flags = IRQ_TYPE_NONE;
- return 0;
-}
-
static const struct irq_domain_ops cpm2_pic_host_ops = {
.map = cpm2_pic_host_map,
- .xlate = cpm2_pic_host_xlate,
+ .xlate = irq_domain_xlate_onetwocell,
};
void cpm2_pic_init(struct device_node *node)
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 0eaaa01..b50f978 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -692,26 +692,10 @@ static int ipic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int ipic_host_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-
-{
- /* interrupt sense values coming from the device tree equal either
- * LEVEL_LOW (low assertion) or EDGE_FALLING (high-to-low change)
- */
- *out_hwirq = intspec[0];
- if (intsize > 1)
- *out_flags = intspec[1];
- else
- *out_flags = IRQ_TYPE_NONE;
- return 0;
-}
-
static struct irq_domain_ops ipic_host_ops = {
.match = ipic_host_match,
.map = ipic_host_map,
- .xlate = ipic_host_xlate,
+ .xlate = irq_domain_xlate_onetwocell,
};
struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index e9b3d5c..2fba6ef 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -272,23 +272,10 @@ static int qe_ic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int qe_ic_host_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 * intspec, unsigned int intsize,
- irq_hw_number_t * out_hwirq,
- unsigned int *out_flags)
-{
- *out_hwirq = intspec[0];
- if (intsize > 1)
- *out_flags = intspec[1];
- else
- *out_flags = IRQ_TYPE_NONE;
- return 0;
-}
-
static struct irq_domain_ops qe_ic_host_ops = {
.match = qe_ic_host_match,
.map = qe_ic_host_map,
- .xlate = qe_ic_host_xlate,
+ .xlate = irq_domain_xlate_onetwocell,
};
/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 84e59c9..9203393 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -190,21 +190,9 @@ static int uic_host_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int uic_host_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq, unsigned int *out_type)
-
-{
- /* UIC intspecs must have 2 cells */
- BUG_ON(intsize != 2);
- *out_hwirq = intspec[0];
- *out_type = intspec[1];
- return 0;
-}
-
static struct irq_domain_ops uic_host_ops = {
.map = uic_host_map,
- .xlate = uic_host_xlate,
+ .xlate = irq_domain_xlate_twocell,
};
void uic_irq_cascade(unsigned int virq, struct irq_desc *desc)
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 149d987..e6568c1 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -296,24 +296,9 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int virq,
return 0;
}
-static int mpc8xxx_gpio_irq_xlate(struct irq_domain *h, struct device_node *ct,
- const u32 *intspec, unsigned int intsize,
- irq_hw_number_t *out_hwirq,
- unsigned int *out_flags)
-
-{
- /* interrupt sense values coming from the device tree equal either
- * EDGE_FALLING or EDGE_BOTH
- */
- *out_hwirq = intspec[0];
- *out_flags = intspec[1];
-
- return 0;
-}
-
static struct irq_domain_ops mpc8xxx_gpio_irq_ops = {
.map = mpc8xxx_gpio_irq_map,
- .xlate = mpc8xxx_gpio_irq_xlate,
+ .xlate = irq_domain_xlate_twocell,
};
static struct of_device_id mpc8xxx_gpio_ids[] __initdata = {
--
1.7.9
^ permalink raw reply related
* [PATCH v5 24/27] irq_domain/microblaze: Convert microblaze to use irq_domains
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
Cc: Michal Simek, John Linn, John Williams
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
This patch converts Microblaze to use the irq_domain remapper and get
away from hard coding the offset between hwirq number and the linux irq
number space. This also paves the way for multiple interrupt controllers.
v2: Don't enable SPARSE_IRQ and keep NR_IRQS set to 33
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Michal Simek <monstr@monstr.eu>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: John Williams <john.williams@petalogix.com>
Cc: John Linn <john.linn@xilinx.com>
---
arch/microblaze/Kconfig | 1 +
arch/microblaze/include/asm/hardirq.h | 16 ---------
arch/microblaze/include/asm/irq.h | 42 ++---------------------
arch/microblaze/kernel/intc.c | 61 ++++++++++++++++++++-------------
arch/microblaze/kernel/irq.c | 24 ++-----------
5 files changed, 45 insertions(+), 99 deletions(-)
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index c8d6efb..11060fa 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -14,6 +14,7 @@ config MICROBLAZE
select TRACING_SUPPORT
select OF
select OF_EARLY_FLATTREE
+ select IRQ_DOMAIN
select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
diff --git a/arch/microblaze/include/asm/hardirq.h b/arch/microblaze/include/asm/hardirq.h
index cd1ac9a..fb3c05a 100644
--- a/arch/microblaze/include/asm/hardirq.h
+++ b/arch/microblaze/include/asm/hardirq.h
@@ -1,17 +1 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_HARDIRQ_H
-#define _ASM_MICROBLAZE_HARDIRQ_H
-
-/* should be defined in each interrupt controller driver */
-extern unsigned int get_irq(struct pt_regs *regs);
-
#include <asm-generic/hardirq.h>
-
-#endif /* _ASM_MICROBLAZE_HARDIRQ_H */
diff --git a/arch/microblaze/include/asm/irq.h b/arch/microblaze/include/asm/irq.h
index 7798ad1..bab3b13 100644
--- a/arch/microblaze/include/asm/irq.h
+++ b/arch/microblaze/include/asm/irq.h
@@ -9,49 +9,13 @@
#ifndef _ASM_MICROBLAZE_IRQ_H
#define _ASM_MICROBLAZE_IRQ_H
-
-/*
- * Linux IRQ# is currently offset by one to map to the hardware
- * irq number. So hardware IRQ0 maps to Linux irq 1.
- */
-#define NO_IRQ_OFFSET 1
-#define IRQ_OFFSET NO_IRQ_OFFSET
-#define NR_IRQS (32 + IRQ_OFFSET)
+#define NR_IRQS (32 + 1)
#include <asm-generic/irq.h>
-/* This type is the placeholder for a hardware interrupt number. It has to
- * be big enough to enclose whatever representation is used by a given
- * platform.
- */
-typedef unsigned long irq_hw_number_t;
-
-extern unsigned int nr_irq;
-
struct pt_regs;
extern void do_IRQ(struct pt_regs *regs);
-/** FIXME - not implement
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- */
-static inline void irq_dispose_mapping(unsigned int virq)
-{
- return;
-}
-
-struct irq_domain;
-
-/**
- * irq_create_mapping - Map a hardware interrupt into linux virq space
- * @host: host owning this hardware interrupt or NULL for default host
- * @hwirq: hardware irq number in that host space
- *
- * Only one mapping per hardware interrupt is permitted. Returns a linux
- * virq number.
- * If the sense/trigger is to be specified, set_irq_type() should be called
- * on the number returned from that call.
- */
-extern unsigned int irq_create_mapping(struct irq_domain *host,
- irq_hw_number_t hwirq);
+/* should be defined in each interrupt controller driver */
+extern unsigned int get_irq(void);
#endif /* _ASM_MICROBLAZE_IRQ_H */
diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c
index 44b177e..ad12067 100644
--- a/arch/microblaze/kernel/intc.c
+++ b/arch/microblaze/kernel/intc.c
@@ -9,6 +9,7 @@
*/
#include <linux/init.h>
+#include <linux/irqdomain.h>
#include <linux/irq.h>
#include <asm/page.h>
#include <linux/io.h>
@@ -25,8 +26,6 @@ static unsigned int intc_baseaddr;
#define INTC_BASE intc_baseaddr
#endif
-unsigned int nr_irq;
-
/* No one else should require these constants, so define them locally here. */
#define ISR 0x00 /* Interrupt Status Register */
#define IPR 0x04 /* Interrupt Pending Register */
@@ -84,24 +83,45 @@ static struct irq_chip intc_dev = {
.irq_mask_ack = intc_mask_ack,
};
-unsigned int get_irq(struct pt_regs *regs)
+static struct irq_domain *root_domain;
+
+unsigned int get_irq(void)
{
- int irq;
+ unsigned int hwirq, irq = -1;
- /*
- * NOTE: This function is the one that needs to be improved in
- * order to handle multiple interrupt controllers. It currently
- * is hardcoded to check for interrupts only on the first INTC.
- */
- irq = in_be32(INTC_BASE + IVR) + NO_IRQ_OFFSET;
- pr_debug("get_irq: %d\n", irq);
+ hwirq = in_be32(INTC_BASE + IVR);
+ if (hwirq != -1U)
+ irq = irq_find_mapping(root_domain, hwirq);
+
+ pr_debug("get_irq: hwirq=%d, irq=%d\n", hwirq, irq);
return irq;
}
+int xintc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
+{
+ u32 intr_mask = (u32)d->host_data;
+
+ if (intr_mask & (1 << hw)) {
+ irq_set_chip_and_handler_name(irq, &intc_dev,
+ handle_edge_irq, "edge");
+ irq_clear_status_flags(irq, IRQ_LEVEL);
+ } else {
+ irq_set_chip_and_handler_name(irq, &intc_dev,
+ handle_level_irq, "level");
+ irq_set_status_flags(irq, IRQ_LEVEL);
+ }
+ return 0;
+}
+
+static const struct irq_domain_ops xintc_irq_domain_ops = {
+ .xlate = irq_domain_xlate_onetwocell,
+ .map = xintc_map,
+};
+
void __init init_IRQ(void)
{
- u32 i, intr_mask;
+ u32 nr_irq, intr_mask;
struct device_node *intc = NULL;
#ifdef CONFIG_SELFMOD_INTC
unsigned int intc_baseaddr = 0;
@@ -146,16 +166,9 @@ void __init init_IRQ(void)
/* Turn on the Master Enable. */
out_be32(intc_baseaddr + MER, MER_HIE | MER_ME);
- for (i = IRQ_OFFSET; i < (nr_irq + IRQ_OFFSET); ++i) {
- if (intr_mask & (0x00000001 << (i - IRQ_OFFSET))) {
- irq_set_chip_and_handler_name(i, &intc_dev,
- handle_edge_irq, "edge");
- irq_clear_status_flags(i, IRQ_LEVEL);
- } else {
- irq_set_chip_and_handler_name(i, &intc_dev,
- handle_level_irq, "level");
- irq_set_status_flags(i, IRQ_LEVEL);
- }
- irq_get_irq_data(i)->hwirq = i - IRQ_OFFSET;
- }
+ /* Yeah, okay, casting the intr_mask to a void* is butt-ugly, but I'm
+ * lazy and Michal can clean it up to something nicer when he tests
+ * and commits this patch. ~~gcl */
+ root_domain = irq_domain_add_linear(intc, nr_irq, &xintc_irq_domain_ops,
+ (void *)intr_mask);
}
diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c
index 3f613df..ace700a 100644
--- a/arch/microblaze/kernel/irq.c
+++ b/arch/microblaze/kernel/irq.c
@@ -31,14 +31,13 @@ void __irq_entry do_IRQ(struct pt_regs *regs)
trace_hardirqs_off();
irq_enter();
- irq = get_irq(regs);
+ irq = get_irq();
next_irq:
BUG_ON(!irq);
- /* Substract 1 because of get_irq */
- generic_handle_irq(irq + IRQ_OFFSET - NO_IRQ_OFFSET);
+ generic_handle_irq(irq);
- irq = get_irq(regs);
- if (irq) {
+ irq = get_irq();
+ if (irq != -1U) {
pr_debug("next irq: %d\n", irq);
++concurrent_irq;
goto next_irq;
@@ -48,18 +47,3 @@ next_irq:
set_irq_regs(old_regs);
trace_hardirqs_on();
}
-
-/* MS: There is no any advance mapping mechanism. We are using simple 32bit
- intc without any cascades or any connection that's why mapping is 1:1 */
-unsigned int irq_create_mapping(struct irq_domain *host, irq_hw_number_t hwirq)
-{
- return hwirq + IRQ_OFFSET;
-}
-EXPORT_SYMBOL_GPL(irq_create_mapping);
-
-unsigned int irq_create_of_mapping(struct device_node *controller,
- const u32 *intspec, unsigned int intsize)
-{
- return intspec[0] + IRQ_OFFSET;
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
--
1.7.9
^ permalink raw reply related
* [PATCH v5 25/27] irq_domain: remove "hint" when allocating irq numbers
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
The 'hint' used to try and line up irq numbers with hw irq numbers is
rather a hack and not very useful. Now that /proc/interrupts also outputs
the hwirq number, it is even less useful to keep around the 'hint' heuristic.
This patch removes it.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
Tested-by: Olof Johansson <olof@lixom.net>
---
kernel/irq/irqdomain.c | 20 ++++----------------
1 files changed, 4 insertions(+), 16 deletions(-)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 2d3dfff..db7adb2 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -350,7 +350,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
unsigned int irq_create_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int virq, hint;
+ unsigned int virq;
pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
@@ -377,12 +377,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
return irq_domain_legacy_revmap(domain, hwirq);
/* Allocate a virtual interrupt number */
- hint = hwirq % irq_virq_count;
- if (hint == 0)
- hint++;
- virq = irq_alloc_desc_from(hint, 0);
- if (!virq)
- virq = irq_alloc_desc_from(1, 0);
+ virq = irq_alloc_desc_from(1, 0);
if (!virq) {
pr_debug("irq: -> virq allocation failed\n");
return 0;
@@ -503,7 +498,6 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
unsigned int i;
- unsigned int hint = hwirq % irq_virq_count;
/* Look for default domain if nececssary */
if (domain == NULL)
@@ -516,17 +510,11 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
return irq_domain_legacy_revmap(domain, hwirq);
/* Slow path does a linear search of the map */
- if (hint == 0)
- hint = 1;
- i = hint;
- do {
+ for (i = 0; i < irq_virq_count; i++) {
struct irq_data *data = irq_get_irq_data(i);
if (data && (data->domain == domain) && (data->hwirq == hwirq))
return i;
- i++;
- if (i >= irq_virq_count)
- i = 1
- } while(i != hint);
+ }
return 0;
}
EXPORT_SYMBOL_GPL(irq_find_mapping);
--
1.7.9
^ permalink raw reply related
* [PATCH v5 26/27] irq_domain: mostly eliminate slow-path revmap lookups
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
With the current state of irq_domain, the reverse map is always updated
when new IRQs get mapped. This means that the irq_find_mapping() function
can be simplified to always execute the revmap-specific lookup function.
This patch adds lookup functions for the revmaps that don't yet have one
and removes the slow path lookup from most of the code paths. The only
place where the slow path legitimately remains is where the linear map
is used with a hwirq number larger than the revmap size.
v5: rewrite to not use a ->revmap() callback. It is simpler, smaller,
safer and faster to open code each of the revmap lookups directly into
irq_find_mapping() via a switch statement.
v4: Fix build failure on incorrect variable reference.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
---
arch/powerpc/sysdev/xics/icp-hv.c | 2 +-
arch/powerpc/sysdev/xics/icp-native.c | 2 +-
arch/powerpc/sysdev/xics/xics-common.c | 3 -
include/linux/irqdomain.h | 4 -
kernel/irq/irqdomain.c | 121 ++++++++++++--------------------
5 files changed, 48 insertions(+), 84 deletions(-)
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 253dce9..14469cf 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -111,7 +111,7 @@ static unsigned int icp_hv_get_irq(void)
if (vec == XICS_IRQ_SPURIOUS)
return NO_IRQ;
- irq = irq_radix_revmap_lookup(xics_host, vec);
+ irq = irq_find_mapping(xics_host, vec);
if (likely(irq != NO_IRQ)) {
xics_push_cppr(vec);
return irq;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 4c79b6f..48861d3 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -119,7 +119,7 @@ static unsigned int icp_native_get_irq(void)
if (vec == XICS_IRQ_SPURIOUS)
return NO_IRQ;
- irq = irq_radix_revmap_lookup(xics_host, vec);
+ irq = irq_find_mapping(xics_host, vec);
if (likely(irq != NO_IRQ)) {
xics_push_cppr(vec);
return irq;
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index ea5e204..1d7067d 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -330,9 +330,6 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq,
pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
- /* Insert the interrupt mapping into the radix tree for fast lookup */
- irq_radix_revmap_insert(xics_host, virq, hw);
-
/* They aren't all level sensitive but we just don't really know */
irq_set_status_flags(virq, IRQ_LEVEL);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 5245488..47af458 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -155,10 +155,6 @@ extern void irq_dispose_mapping(unsigned int virq);
extern unsigned int irq_find_mapping(struct irq_domain *host,
irq_hw_number_t hwirq);
extern unsigned int irq_create_direct_mapping(struct irq_domain *host);
-extern void irq_radix_revmap_insert(struct irq_domain *host, unsigned int virq,
- irq_hw_number_t hwirq);
-extern unsigned int irq_radix_revmap_lookup(struct irq_domain *host,
- irq_hw_number_t hwirq);
extern unsigned int irq_linear_revmap(struct irq_domain *host,
irq_hw_number_t hwirq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index db7adb2..e7d8e96 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -313,7 +313,8 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
domain = irq_default_domain;
BUG_ON(domain == NULL);
- WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP);
+ if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP))
+ return 0;
virq = irq_alloc_desc_from(1, 0);
if (!virq) {
@@ -389,6 +390,18 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
return 0;
}
+ switch(domain->revmap_type) {
+ case IRQ_DOMAIN_MAP_LINEAR:
+ if (hwirq < domain->revmap_data.linear.size)
+ domain->revmap_data.linear.revmap[hwirq] = virq;
+ break;
+ case IRQ_DOMAIN_MAP_TREE:
+ mutex_lock(&revmap_trees_mutex);
+ radix_tree_insert(&domain->revmap_data.tree, hwirq,
+ irq_get_irq_data(virq));
+ mutex_unlock(&revmap_trees_mutex);
+ break;
+ }
pr_debug("irq: irq %lu on domain %s mapped to virtual irq %u\n",
hwirq, domain->of_node ? domain->of_node->full_name : "null", virq);
@@ -497,7 +510,7 @@ EXPORT_SYMBOL_GPL(irq_dispose_mapping);
unsigned int irq_find_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int i;
+ struct irq_data *data;
/* Look for default domain if nececssary */
if (domain == NULL)
@@ -505,74 +518,43 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
if (domain == NULL)
return 0;
- /* legacy -> bail early */
- if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY)
+ switch (domain->revmap_type) {
+ case IRQ_DOMAIN_MAP_LEGACY:
return irq_domain_legacy_revmap(domain, hwirq);
-
- /* Slow path does a linear search of the map */
- for (i = 0; i < irq_virq_count; i++) {
- struct irq_data *data = irq_get_irq_data(i);
+ case IRQ_DOMAIN_MAP_LINEAR:
+ return irq_linear_revmap(domain, hwirq);
+ case IRQ_DOMAIN_MAP_TREE:
+ rcu_read_lock();
+ data = radix_tree_lookup(&domain->revmap_data.tree, hwirq);
+ rcu_read_unlock();
+ if (data)
+ return data->irq;
+ break;
+ case IRQ_DOMAIN_MAP_NOMAP:
+ data = irq_get_irq_data(hwirq);
if (data && (data->domain == domain) && (data->hwirq == hwirq))
- return i;
+ return hwirq;
+ break;
}
+
+ WARN(1, "ERROR: irq revmap went horribly wrong. revmap_type=%i\n",
+ domain->revmap_type);
return 0;
}
EXPORT_SYMBOL_GPL(irq_find_mapping);
-/**
- * irq_radix_revmap_lookup() - Find a linux irq from a hw irq number.
- * @domain: domain owning this hardware interrupt
- * @hwirq: hardware irq number in that domain space
- *
- * This is a fast path, for use by irq controller code that uses radix tree
- * revmaps
- */
-unsigned int irq_radix_revmap_lookup(struct irq_domain *domain,
- irq_hw_number_t hwirq)
+static unsigned int irq_find_mapping_slow(struct irq_domain *domain,
+ irq_hw_number_t hwirq)
{
- struct irq_data *irq_data;
-
- if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
- return irq_find_mapping(domain, hwirq);
-
- /*
- * Freeing an irq can delete nodes along the path to
- * do the lookup via call_rcu.
- */
- rcu_read_lock();
- irq_data = radix_tree_lookup(&domain->revmap_data.tree, hwirq);
- rcu_read_unlock();
-
- /*
- * If found in radix tree, then fine.
- * Else fallback to linear lookup - this should not happen in practice
- * as it means that we failed to insert the node in the radix tree.
- */
- return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq);
-}
-
-/**
- * irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping.
- * @domain: domain owning this hardware interrupt
- * @virq: linux irq number
- * @hwirq: hardware irq number in that domain space
- *
- * This is for use by irq controllers that use a radix tree reverse
- * mapping for fast lookup.
- */
-void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- struct irq_data *irq_data = irq_get_irq_data(virq);
-
- if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
- return;
+ unsigned int i;
- if (virq) {
- mutex_lock(&revmap_trees_mutex);
- radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data);
- mutex_unlock(&revmap_trees_mutex);
+ /* Slow path does a linear search of the map */
+ for (i = 0; i < irq_virq_count; i++) {
+ struct irq_data *data = irq_get_irq_data(i);
+ if (data && (data->domain == domain) && (data->hwirq == hwirq))
+ return i;
}
+ return 0;
}
/**
@@ -581,31 +563,20 @@ void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
* @hwirq: hardware irq number in that domain space
*
* This is a fast path, for use by irq controller code that uses linear
- * revmaps. It does fallback to the slow path if the revmap doesn't exist
- * yet and will create the revmap entry with appropriate locking
+ * revmaps. It does fallback to the slow path if the hwirq number is outside
+ * the range of the hwirq numbers.
*/
unsigned int irq_linear_revmap(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int *revmap;
-
if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR))
return irq_find_mapping(domain, hwirq);
/* Check revmap bounds */
if (unlikely(hwirq >= domain->revmap_data.linear.size))
- return irq_find_mapping(domain, hwirq);
-
- /* Check if revmap was allocated */
- revmap = domain->revmap_data.linear.revmap;
- if (unlikely(revmap == NULL))
- return irq_find_mapping(domain, hwirq);
-
- /* Fill up revmap with slow path if no mapping found */
- if (unlikely(!revmap[hwirq]))
- revmap[hwirq] = irq_find_mapping(domain, hwirq);
+ return irq_find_mapping_slow(domain, hwirq);
- return revmap[hwirq];
+ return domain->revmap_data.linear.revmap[hwirq];
}
#ifdef CONFIG_VIRQ_DEBUG
--
1.7.9
^ permalink raw reply related
* [PATCH v5 27/27] irq_domain: For NOMAP revmap, allow users to specify the largest usable virq
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
This patch replaces the old global setting of irq_virq_count that is only
used by the NOMAP mapping and instead uses a revmap_data property so that
the maximum NOMAP allocation can be set per NOMAP irq_domain.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
---
arch/powerpc/platforms/cell/axon_msi.c | 2 +-
arch/powerpc/platforms/cell/beat_interrupt.c | 2 +-
arch/powerpc/platforms/iseries/irq.c | 8 +------
arch/powerpc/platforms/powermac/smp.c | 2 +-
arch/powerpc/platforms/ps3/interrupt.c | 3 +-
include/linux/irqdomain.h | 7 ++---
kernel/irq/irqdomain.c | 29 ++++++-------------------
7 files changed, 15 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index db360fc..369df06 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -392,7 +392,7 @@ static int axon_msi_probe(struct platform_device *device)
}
memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
- msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic);
+ msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic, ~0);
if (!msic->irq_domain) {
printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
dn->full_name);
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index e5c3a2c..4315349 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void)
ppc_md.get_irq = beatic_get_irq;
/* Allocate an irq host */
- beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL);
+ beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL, ~0);
BUG_ON(beatic_host == NULL);
irq_set_default_host(beatic_host);
}
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 05ce516..db48abe 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -371,16 +371,10 @@ void __init iSeries_init_IRQ(void)
struct irq_domain *host;
int ret;
- /*
- * The Hypervisor only allows us up to 256 interrupt
- * sources (the irq number is passed in a u8).
- */
- irq_set_virq_count(256);
-
/* Create irq host. No need for a revmap since HV will give us
* back our virtual irq number
*/
- host = irq_domain_add_nomap(NULL, &iseries_irq_domain_ops, NULL);
+ host = irq_domain_add_nomap(NULL, &iseries_irq_domain_ops, NULL, 256);
BUG_ON(host == NULL);
irq_set_default_host(host);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a81e5a8..40f12af 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void)
{
int rc = -ENOMEM;
- psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL);
+ psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL, ~0);
if (psurge_host)
psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 2a4ff86..0700a98 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -753,9 +753,8 @@ void __init ps3_init_IRQ(void)
unsigned cpu;
struct irq_domain *host;
- host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL);
+ host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL, PS3_PLUG_MAX + 1);
irq_set_default_host(host);
- irq_set_virq_count(PS3_PLUG_MAX + 1);
for_each_possible_cpu(cpu) {
struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 47af458..80bb917 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -105,6 +105,7 @@ struct irq_domain {
unsigned int *revmap;
} linear;
struct radix_tree_root tree;
+ unsigned int nomap_max_virq;
} revmap_data;
const struct irq_domain_ops *ops;
void *host_data;
@@ -126,15 +127,14 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
const struct irq_domain_ops *ops,
void *host_data);
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
- const struct irq_domain_ops *ops,
- void *host_data);
+ const struct irq_domain_ops *ops,
+ void *host_data, unsigned int max_virq);
struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
const struct irq_domain_ops *ops,
void *host_data);
extern struct irq_domain *irq_find_host(struct device_node *node);
extern void irq_set_default_host(struct irq_domain *host);
-extern void irq_set_virq_count(unsigned int count);
static inline struct irq_domain *irq_domain_add_legacy_isa(
struct device_node *of_node,
@@ -146,7 +146,6 @@ static inline struct irq_domain *irq_domain_add_legacy_isa(
}
extern struct irq_domain *irq_find_host(struct device_node *node);
extern void irq_set_default_host(struct irq_domain *host);
-extern void irq_set_virq_count(unsigned int count);
extern unsigned int irq_create_mapping(struct irq_domain *host,
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index e7d8e96..e820b53 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,7 +23,6 @@ static LIST_HEAD(irq_domain_list);
static DEFINE_MUTEX(irq_domain_mutex);
static DEFINE_MUTEX(revmap_trees_mutex);
-static unsigned int irq_virq_count = NR_IRQS;
static struct irq_domain *irq_default_domain;
/**
@@ -185,12 +184,14 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
const struct irq_domain_ops *ops,
- void *host_data)
+ void *host_data, unsigned int max_virq)
{
struct irq_domain *domain = irq_domain_alloc(of_node,
IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
- if (domain)
+ if (domain) {
+ domain->revmap_data.nomap_max_virq = max_virq;
irq_domain_add(domain);
+ }
return domain;
}
@@ -262,22 +263,6 @@ void irq_set_default_host(struct irq_domain *domain)
irq_default_domain = domain;
}
-/**
- * irq_set_virq_count() - Set the maximum number of linux irqs
- * @count: number of linux irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-void irq_set_virq_count(unsigned int count)
-{
- pr_debug("irq: Trying to set virq count to %d\n", count);
-
- BUG_ON(count < NUM_ISA_INTERRUPTS);
- if (count < NR_IRQS)
- irq_virq_count = count;
-}
-
static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
irq_hw_number_t hwirq)
{
@@ -321,9 +306,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
pr_debug("irq: create_direct virq allocation failed\n");
return 0;
}
- if (virq >= irq_virq_count) {
+ if (virq > domain->revmap_data.nomap_max_virq) {
pr_err("ERROR: no free irqs available below %i maximum\n",
- irq_virq_count);
+ domain->revmap_data.nomap_max_virq);
irq_free_desc(virq);
return 0;
}
@@ -549,7 +534,7 @@ static unsigned int irq_find_mapping_slow(struct irq_domain *domain,
unsigned int i;
/* Slow path does a linear search of the map */
- for (i = 0; i < irq_virq_count; i++) {
+ for (i = 0; i < nr_irqs; i++) {
struct irq_data *data = irq_get_irq_data(i);
if (data && (data->domain == domain) && (data->hwirq == hwirq))
return i;
--
1.7.9
^ permalink raw reply related
* [PATCH v4 3/3] KVM: PPC: epapr: install ev_idle hcall for e500 guest
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
In-Reply-To: <1329384365-4028-2-git-send-email-yu.liu@freescale.com>
If the guest hypervisor node contains "has-idle" property.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
1. discard the CONFIG_E500 to make code for all powerpc platform
2. code cleanup
arch/powerpc/kernel/epapr.S | 29 +++++++++++++++++++++++++++++
arch/powerpc/kernel/epapr_para.c | 13 ++++++++++++-
2 files changed, 41 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
index 697b390..f06d636 100644
--- a/arch/powerpc/kernel/epapr.S
+++ b/arch/powerpc/kernel/epapr.S
@@ -15,6 +15,35 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
+#define HC_VENDOR_EPAPR (1 << 16)
+#define HC_EV_IDLE 16
+
+_GLOBAL(epapr_ev_idle)
+epapr_ev_idle:
+ rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
+ ori r4,r4,_TLF_NAPPING /* so when we take an exception */
+ stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+
+ wrteei 1
+
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, HC_VENDOR_EPAPR | HC_EV_IDLE)
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+
+ /*
+ * Guard against spurious wakeups (e.g. from a hypervisor) --
+ * any real interrupt will cause us to return to LR due to
+ * _TLF_NAPPING.
+ */
+ b idle_loop
+
/* Hypercall entry point. Will be patched with device tree instructions. */
.global epapr_hypercall_start
epapr_hypercall_start:
diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_para.c
index ea13cac..adee4f1 100644
--- a/arch/powerpc/kernel/epapr_para.c
+++ b/arch/powerpc/kernel/epapr_para.c
@@ -20,6 +20,10 @@
#include <linux/of.h>
#include <asm/epapr_hcalls.h>
#include <asm/cacheflush.h>
+#include <asm/machdep.h>
+
+extern void epapr_ev_idle(void);
+extern u32 epapr_ev_idle_start[];
bool epapr_para_enabled = false;
@@ -35,10 +39,17 @@ static int __init epapr_para_init(void)
insts = of_get_property(hyper_node, "hcall-instructions", &len);
if (!(len % 4) && (len >= (4 * 4))) {
- for (i = 0; i < (len / 4); i++)
+ for (i = 0; i < (len / 4); i++) {
epapr_hypercall_start[i] = insts[i];
+ epapr_ev_idle_start[i] = insts[i];
+ }
flush_icache_range((ulong)epapr_hypercall_start,
(ulong)epapr_hypercall_start + len);
+ flush_icache_range((ulong)epapr_ev_idle_start,
+ (ulong)epapr_ev_idle_start + len);
+
+ if (of_get_property(hyper_node, "has-idle", NULL))
+ ppc_md.power_save = epapr_ev_idle;
epapr_para_enabled = true;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH v4 1/3] KVM: PPC: epapr: Factor out the epapr init
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
from the kvm guest paravirt init code.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
1. code cleanup
2. move kvm_hypercall_start() to epapr_hypercall_start()
arch/powerpc/Kconfig | 4 ++
arch/powerpc/include/asm/epapr_hcalls.h | 2 +
arch/powerpc/kernel/Makefile | 1 +
arch/powerpc/kernel/epapr.S | 25 ++++++++++++++++
arch/powerpc/kernel/epapr_para.c | 49 +++++++++++++++++++++++++++++++
arch/powerpc/kernel/kvm.c | 28 ++----------------
arch/powerpc/kernel/kvm_emul.S | 10 ------
arch/powerpc/kvm/Kconfig | 1 +
8 files changed, 85 insertions(+), 35 deletions(-)
create mode 100644 arch/powerpc/kernel/epapr.S
create mode 100644 arch/powerpc/kernel/epapr_para.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1919634..1262b43 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -202,6 +202,10 @@ config EPAPR_BOOT
Used to allow a board to specify it wants an ePAPR compliant wrapper.
default n
+config EPAPR_PARAVIRT
+ bool
+ default n
+
config DEFAULT_UIMAGE
bool
help
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index f3b0c2c..0ff3f24 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -148,6 +148,8 @@
#define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
#define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
+extern bool epapr_para_enabled;
+extern u32 epapr_hypercall_start[];
/*
* We use "uintptr_t" to define a register because it's guaranteed to be a
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e4..9e807f3 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -136,6 +136,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
obj-y += ppc_save_regs.o
endif
+obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_para.o epapr.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
# Disable GCOV in odd or sensitive code
diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
new file mode 100644
index 0000000..697b390
--- /dev/null
+++ b/arch/powerpc/kernel/epapr.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ blr
diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_para.c
new file mode 100644
index 0000000..ea13cac
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_para.c
@@ -0,0 +1,49 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+
+bool epapr_para_enabled = false;
+
+static int __init epapr_para_init(void)
+{
+ struct device_node *hyper_node;
+ const u32 *insts;
+ int len, i;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return -ENODEV;
+
+ insts = of_get_property(hyper_node, "hcall-instructions", &len);
+ if (!(len % 4) && (len >= (4 * 4))) {
+ for (i = 0; i < (len / 4); i++)
+ epapr_hypercall_start[i] = insts[i];
+ flush_icache_range((ulong)epapr_hypercall_start,
+ (ulong)epapr_hypercall_start + len);
+
+ epapr_para_enabled = true;
+ }
+
+ return 0;
+}
+
+early_initcall(epapr_para_init);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 62bdf23..9dfc24a 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -31,6 +31,7 @@
#include <asm/cacheflush.h>
#include <asm/disassemble.h>
#include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
unsigned long register r11 asm("r11") = nr;
unsigned long register r12 asm("r12");
- asm volatile("bl kvm_hypercall_start"
+ asm volatile("bl epapr_hypercall_start"
: "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
"=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
"=r"(r12)
@@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
}
EXPORT_SYMBOL_GPL(kvm_hypercall);
-static int kvm_para_setup(void)
-{
- extern u32 kvm_hypercall_start;
- struct device_node *hyper_node;
- u32 *insts;
- int len, i;
-
- hyper_node = of_find_node_by_path("/hypervisor");
- if (!hyper_node)
- return -1;
-
- insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
- if (len % 4)
- return -1;
- if (len > (4 * 4))
- return -1;
-
- for (i = 0; i < (len / 4); i++)
- kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
- return 0;
-}
-
static __init void kvm_free_tmp(void)
{
unsigned long start, end;
@@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
if (!kvm_para_available())
goto free_tmp;
- if (kvm_para_setup())
+ if (!epapr_para_enabled)
goto free_tmp;
if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index e291cf3..62ceb2a 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -24,16 +24,6 @@
#include <asm/page.h>
#include <asm/asm-offsets.h>
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
- li r3, -1
- nop
- nop
- nop
- blr
-
#define KVM_MAGIC_PAGE (-4096)
#ifdef CONFIG_64BIT
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 8f64709..9bb9d18 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,6 +20,7 @@ config KVM
bool
select PREEMPT_NOTIFIERS
select ANON_INODES
+ select EPAPR_PARAVIRT
config KVM_BOOK3S_HANDLER
bool
--
1.7.0.4
^ permalink raw reply related
* [PATCH v4 2/3] KVM: PPC: epapr: Add idle hcall support for host
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
In-Reply-To: <1329384365-4028-1-git-send-email-yu.liu@freescale.com>
And add a new flag definition in kvm_ppc_pvinfo to indicate
whether host support EV_IDLE hcall.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
no change
arch/powerpc/include/asm/kvm_para.h | 14 ++++++++++++--
arch/powerpc/kvm/powerpc.c | 8 ++++++++
include/linux/kvm.h | 2 ++
3 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 7b754e7..81a34c9 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -75,9 +75,19 @@ struct kvm_vcpu_arch_shared {
};
#define KVM_SC_MAGIC_R0 0x4b564d21 /* "KVM!" */
-#define HC_VENDOR_KVM (42 << 16)
+
+#include <asm/epapr_hcalls.h>
+
+/* ePAPR Hypercall Vendor ID */
+#define HC_VENDOR_EPAPR (EV_EPAPR_VENDOR_ID << 16)
+#define HC_VENDOR_KVM (EV_KVM_VENDOR_ID << 16)
+
+/* ePAPR Hypercall Token */
+#define HC_EV_IDLE EV_IDLE
+
+/* ePAPR Hypercall Return Codes */
#define HC_EV_SUCCESS 0
-#define HC_EV_UNIMPLEMENTED 12
+#define HC_EV_UNIMPLEMENTED EV_UNIMPLEMENTED
#define KVM_FEATURE_MAGIC_PAGE 1
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0e21d15..03ebd5d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -81,6 +81,10 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
/* Second return value is in r4 */
break;
+ case HC_VENDOR_EPAPR | HC_EV_IDLE:
+ r = HC_EV_SUCCESS;
+ kvm_vcpu_block(vcpu);
+ break;
default:
r = HC_EV_UNIMPLEMENTED;
break;
@@ -746,6 +750,10 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
pvinfo->hcall[2] = inst_sc;
pvinfo->hcall[3] = inst_nop;
+#ifdef CONFIG_BOOKE
+ pvinfo->flags |= KVM_PPC_PVINFO_FLAGS_EV_IDLE;
+#endif
+
return 0;
}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index acbe429..6b2c70e 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -449,6 +449,8 @@ struct kvm_ppc_pvinfo {
__u8 pad[108];
};
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
--
1.7.0.4
^ permalink raw reply related
* [PATCH] powerpc/usb: fix bug of kernel hang when initializing usb
From: Shengzhou Liu @ 2012-02-16 10:02 UTC (permalink / raw)
To: linux-usb; +Cc: linuxppc-dev, Shengzhou Liu
If USB UTMI PHY is not enable, writing to portsc register will lead to
kernel hang during boot up.
Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
---
Apply for master branch of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
Tested on P5020DS, the issue was reported by Benjamin Herrenschmidt.
drivers/usb/host/ehci-fsl.c | 4 ++++
drivers/usb/host/ehci-fsl.h | 1 +
2 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index c26a82e..0090ed2 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -216,6 +216,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
unsigned int port_offset)
{
u32 portsc;
+ struct usb_hcd *hcd = ehci_to_hcd(ehci);
+ void __iomem *non_ehci = hcd->regs;
portsc = ehci_readl(ehci, &ehci->regs->port_status[port_offset]);
portsc &= ~(PORT_PTS_MSK | PORT_PTS_PTW);
@@ -231,6 +233,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
portsc |= PORT_PTS_PTW;
/* fall through */
case FSL_USB2_PHY_UTMI:
+ /* enable UTMI PHY */
+ setbits32(non_ehci + FSL_SOC_USB_CTRL, CTRL_UTMI_PHY_EN);
portsc |= PORT_PTS_UTMI;
break;
case FSL_USB2_PHY_NONE:
diff --git a/drivers/usb/host/ehci-fsl.h b/drivers/usb/host/ehci-fsl.h
index bdf43e2..0e400c2 100644
--- a/drivers/usb/host/ehci-fsl.h
+++ b/drivers/usb/host/ehci-fsl.h
@@ -45,6 +45,7 @@
#define FSL_SOC_USB_PRICTRL 0x40c /* NOTE: big-endian */
#define FSL_SOC_USB_SICTRL 0x410 /* NOTE: big-endian */
#define FSL_SOC_USB_CTRL 0x500 /* NOTE: big-endian */
+#define CTRL_UTMI_PHY_EN (1<<9)
#define CTRL_PHY_CLK_VALID (1 << 17)
#define SNOOP_SIZE_2GB 0x1e
#endif /* _EHCI_FSL_H */
--
1.6.4
^ permalink raw reply related
* Re: [PATCH v4 1/3] KVM: PPC: epapr: Factor out the epapr init
From: Alexander Graf @ 2012-02-16 10:17 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-1-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> from the kvm guest paravirt init code.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> 1. code cleanup
> 2. move kvm_hypercall_start() to epapr_hypercall_start()
>=20
> arch/powerpc/Kconfig | 4 ++
> arch/powerpc/include/asm/epapr_hcalls.h | 2 +
> arch/powerpc/kernel/Makefile | 1 +
> arch/powerpc/kernel/epapr.S | 25 ++++++++++++++++
> arch/powerpc/kernel/epapr_para.c | 49 +++++++++++++++++++++++++++=
++++
> arch/powerpc/kernel/kvm.c | 28 ++----------------
> arch/powerpc/kernel/kvm_emul.S | 10 ------
> arch/powerpc/kvm/Kconfig | 1 +
> 8 files changed, 85 insertions(+), 35 deletions(-)
> create mode 100644 arch/powerpc/kernel/epapr.S
> create mode 100644 arch/powerpc/kernel/epapr_para.c
>=20
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 1919634..1262b43 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -202,6 +202,10 @@ config EPAPR_BOOT
> Used to allow a board to specify it wants an ePAPR compliant wrapper.=
> default n
>=20
> +config EPAPR_PARAVIRT
> + bool
> + default n
> +
> config DEFAULT_UIMAGE
> bool
> help
> diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/includ=
e/asm/epapr_hcalls.h
> index f3b0c2c..0ff3f24 100644
> --- a/arch/powerpc/include/asm/epapr_hcalls.h
> +++ b/arch/powerpc/include/asm/epapr_hcalls.h
> @@ -148,6 +148,8 @@
> #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
> #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
>=20
> +extern bool epapr_para_enabled;
> +extern u32 epapr_hypercall_start[];
>=20
> /*
> * We use "uintptr_t" to define a register because it's guaranteed to be a=
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index ee728e4..9e807f3 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -136,6 +136,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
> obj-y +=3D ppc_save_regs.o
> endif
>=20
> +obj-$(CONFIG_EPAPR_PARAVIRT) +=3D epapr_para.o epapr.o
> obj-$(CONFIG_KVM_GUEST) +=3D kvm.o kvm_emul.o
>=20
> # Disable GCOV in odd or sensitive code
> diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
> new file mode 100644
> index 0000000..697b390
> --- /dev/null
> +++ b/arch/powerpc/kernel/epapr.S
> @@ -0,0 +1,25 @@
> +/*
> + * Copyright (C) 2012 Freescale Semiconductor, Inc.
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public License
> + * as published by the Free Software Foundation; either version
> + * 2 of the License, or (at your option) any later version.
> + */
> +
> +#include <linux/threads.h>
> +#include <asm/reg.h>
> +#include <asm/page.h>
> +#include <asm/cputable.h>
> +#include <asm/thread_info.h>
> +#include <asm/ppc_asm.h>
> +#include <asm/asm-offsets.h>
> +
> +/* Hypercall entry point. Will be patched with device tree instructions. *=
/
> +.global epapr_hypercall_start
> +epapr_hypercall_start:
> + li r3, -1
> + nop
> + nop
> + nop
> + blr
> diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_=
para.c
> new file mode 100644
> index 0000000..ea13cac
> --- /dev/null
> +++ b/arch/powerpc/kernel/epapr_para.c
> @@ -0,0 +1,49 @@
> +/*
> + * ePAPR para-virtualization support.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License, version 2, as
> + * published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program; if not, write to the Free Software
> + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, U=
SA.
> + *
> + * Copyright (C) 2012 Freescale Semiconductor, Inc.
> + */
> +
> +#include <linux/of.h>
> +#include <asm/epapr_hcalls.h>
> +#include <asm/cacheflush.h>
> +
> +bool epapr_para_enabled =3D false;
> +
> +static int __init epapr_para_init(void)
> +{
> + struct device_node *hyper_node;
> + const u32 *insts;
> + int len, i;
> +
> + hyper_node =3D of_find_node_by_path("/hypervisor");
> + if (!hyper_node)
> + return -ENODEV;
> +
> + insts =3D of_get_property(hyper_node, "hcall-instructions", &len);
> + if (!(len % 4) && (len >=3D (4 * 4))) {
> + for (i =3D 0; i < (len / 4); i++)
So if the dt passes in less than 4 ops, you bail out, and for more you overw=
rite the buffer? Not good :)
> + epapr_hypercall_start[i] =3D insts[i];
> + flush_icache_range((ulong)epapr_hypercall_start,
> + (ulong)epapr_hypercall_start + len);
> +
> + epapr_para_enabled =3D true;
> + }
> +
> + return 0;
> +}
> +
> +early_initcall(epapr_para_init);
> diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
> index 62bdf23..9dfc24a 100644
> --- a/arch/powerpc/kernel/kvm.c
> +++ b/arch/powerpc/kernel/kvm.c
> @@ -31,6 +31,7 @@
> #include <asm/cacheflush.h>
> #include <asm/disassemble.h>
> #include <asm/ppc-opcode.h>
> +#include <asm/epapr_hcalls.h>
>=20
> #define KVM_MAGIC_PAGE (-4096L)
> #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared=
, x)
> @@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
> unsigned long register r11 asm("r11") =3D nr;
> unsigned long register r12 asm("r12");
>=20
> - asm volatile("bl kvm_hypercall_start"
> + asm volatile("bl epapr_hypercall_start"
> : "=3Dr"(r0), "=3Dr"(r3), "=3Dr"(r4), "=3Dr"(r5), "=3Dr"(r6),
> "=3Dr"(r7), "=3Dr"(r8), "=3Dr"(r9), "=3Dr"(r10), "=3Dr"(r11)=
,
> "=3Dr"(r12)
> @@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
> }
> EXPORT_SYMBOL_GPL(kvm_hypercall);
>=20
> -static int kvm_para_setup(void)
> -{
> - extern u32 kvm_hypercall_start;
> - struct device_node *hyper_node;
> - u32 *insts;
> - int len, i;
> -
> - hyper_node =3D of_find_node_by_path("/hypervisor");
> - if (!hyper_node)
> - return -1;
> -
> - insts =3D (u32*)of_get_property(hyper_node, "hcall-instructions", &le=
n);
> - if (len % 4)
> - return -1;
> - if (len > (4 * 4))
As you can see, the previous code allowed for less than 4 instructions, but n=
ot more.
Alex
> - return -1;
> -
> - for (i =3D 0; i < (len / 4); i++)
> - kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
> -
> - return 0;
> -}
> -
> static __init void kvm_free_tmp(void)
> {
> unsigned long start, end;
> @@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
> if (!kvm_para_available())
> goto free_tmp;
>=20
> - if (kvm_para_setup())
> + if (!epapr_para_enabled)
> goto free_tmp;
>=20
> if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
> diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul=
.S
> index e291cf3..62ceb2a 100644
> --- a/arch/powerpc/kernel/kvm_emul.S
> +++ b/arch/powerpc/kernel/kvm_emul.S
> @@ -24,16 +24,6 @@
> #include <asm/page.h>
> #include <asm/asm-offsets.h>
>=20
> -/* Hypercall entry point. Will be patched with device tree instructions. *=
/
> -
> -.global kvm_hypercall_start
> -kvm_hypercall_start:
> - li r3, -1
> - nop
> - nop
> - nop
> - blr
> -
> #define KVM_MAGIC_PAGE (-4096)
>=20
> #ifdef CONFIG_64BIT
> diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
> index 8f64709..9bb9d18 100644
> --- a/arch/powerpc/kvm/Kconfig
> +++ b/arch/powerpc/kvm/Kconfig
> @@ -20,6 +20,7 @@ config KVM
> bool
> select PREEMPT_NOTIFIERS
> select ANON_INODES
> + select EPAPR_PARAVIRT
>=20
> config KVM_BOOK3S_HANDLER
> bool
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [PATCH] powerpc/usb: fix issue of CPU halt when missing USB PHY clock
From: Liu Shengzhou-B36685 @ 2012-02-16 10:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: linuxppc-dev@lists.ozlabs.org, linux-usb@vger.kernel.org,
Pavan Kondeti
In-Reply-To: <1329273064.3772.18.camel@pasglop>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^ permalink raw reply
* Re: [PATCH v4 2/3] KVM: PPC: epapr: Add idle hcall support for host
From: Alexander Graf @ 2012-02-16 10:20 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-2-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> And add a new flag definition in kvm_ppc_pvinfo to indicate
> whether host support EV_IDLE hcall.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> no change
>=20
> arch/powerpc/include/asm/kvm_para.h | 14 ++++++++++++--
> arch/powerpc/kvm/powerpc.c | 8 ++++++++
> include/linux/kvm.h | 2 ++
> 3 files changed, 22 insertions(+), 2 deletions(-)
>=20
> diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/as=
m/kvm_para.h
> index 7b754e7..81a34c9 100644
> --- a/arch/powerpc/include/asm/kvm_para.h
> +++ b/arch/powerpc/include/asm/kvm_para.h
> @@ -75,9 +75,19 @@ struct kvm_vcpu_arch_shared {
> };
>=20
> #define KVM_SC_MAGIC_R0 0x4b564d21 /* "KVM!" */
> -#define HC_VENDOR_KVM (42 << 16)
> +
> +#include <asm/epapr_hcalls.h>
> +
> +/* ePAPR Hypercall Vendor ID */
> +#define HC_VENDOR_EPAPR (EV_EPAPR_VENDOR_ID << 16)
> +#define HC_VENDOR_KVM (EV_KVM_VENDOR_ID << 16)
> +
> +/* ePAPR Hypercall Token */
> +#define HC_EV_IDLE EV_IDLE
> +
> +/* ePAPR Hypercall Return Codes */
> #define HC_EV_SUCCESS 0
> -#define HC_EV_UNIMPLEMENTED 12
> +#define HC_EV_UNIMPLEMENTED EV_UNIMPLEMENTED
>=20
> #define KVM_FEATURE_MAGIC_PAGE 1
>=20
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 0e21d15..03ebd5d 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -81,6 +81,10 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
>=20
> /* Second return value is in r4 */
> break;
> + case HC_VENDOR_EPAPR | HC_EV_IDLE:
> + r =3D HC_EV_SUCCESS;
> + kvm_vcpu_block(vcpu);
> + break;
> default:
> r =3D HC_EV_UNIMPLEMENTED;
> break;
> @@ -746,6 +750,10 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvi=
nfo *pvinfo)
> pvinfo->hcall[2] =3D inst_sc;
> pvinfo->hcall[3] =3D inst_nop;
>=20
> +#ifdef CONFIG_BOOKE
Why limit it to booke? The less ifdefs our code has, the better :)
Alex
> + pvinfo->flags |=3D KVM_PPC_PVINFO_FLAGS_EV_IDLE;
> +#endif
> +
> return 0;
> }
>=20
> diff --git a/include/linux/kvm.h b/include/linux/kvm.h
> index acbe429..6b2c70e 100644
> --- a/include/linux/kvm.h
> +++ b/include/linux/kvm.h
> @@ -449,6 +449,8 @@ struct kvm_ppc_pvinfo {
> __u8 pad[108];
> };
>=20
> +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
> +
> #define KVMIO 0xAE
>=20
> /* machine type bits, to be used as argument to KVM_CREATE_VM */
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 3/3] KVM: PPC: epapr: install ev_idle hcall for e500 guest
From: Alexander Graf @ 2012-02-16 10:24 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-3-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> If the guest hypervisor node contains "has-idle" property.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> 1. discard the CONFIG_E500 to make code for all powerpc platform
> 2. code cleanup
>=20
> arch/powerpc/kernel/epapr.S | 29 +++++++++++++++++++++++++++++
> arch/powerpc/kernel/epapr_para.c | 13 ++++++++++++-
> 2 files changed, 41 insertions(+), 1 deletions(-)
>=20
> diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
> index 697b390..f06d636 100644
> --- a/arch/powerpc/kernel/epapr.S
> +++ b/arch/powerpc/kernel/epapr.S
> @@ -15,6 +15,35 @@
> #include <asm/ppc_asm.h>
> #include <asm/asm-offsets.h>
>=20
> +#define HC_VENDOR_EPAPR (1 << 16)
> +#define HC_EV_IDLE 16
> +
> +_GLOBAL(epapr_ev_idle)
> +epapr_ev_idle:
> + rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */
> + lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
> + ori r4,r4,_TLF_NAPPING /* so when we take an exception */
> + stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
> +
> + wrteei 1
> +
> +idle_loop:
> + LOAD_REG_IMMEDIATE(r11, HC_VENDOR_EPAPR | HC_EV_IDLE)
> +
> +.global epapr_ev_idle_start
> +epapr_ev_idle_start:
> + li r3, -1
> + nop
> + nop
> + nop
Can't you just bl into epapr_hypercall_start? You don't even have to save th=
e old lr. because we never return anyways :)
Alex
> +
> + /*
> + * Guard against spurious wakeups (e.g. from a hypervisor) --
> + * any real interrupt will cause us to return to LR due to
> + * _TLF_NAPPING.
> + */
> + b idle_loop
> +
> /* Hypercall entry point. Will be patched with device tree instructions. *=
/
> .global epapr_hypercall_start
> epapr_hypercall_start:
> diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_=
para.c
> index ea13cac..adee4f1 100644
> --- a/arch/powerpc/kernel/epapr_para.c
> +++ b/arch/powerpc/kernel/epapr_para.c
> @@ -20,6 +20,10 @@
> #include <linux/of.h>
> #include <asm/epapr_hcalls.h>
> #include <asm/cacheflush.h>
> +#include <asm/machdep.h>
> +
> +extern void epapr_ev_idle(void);
> +extern u32 epapr_ev_idle_start[];
>=20
> bool epapr_para_enabled =3D false;
>=20
> @@ -35,10 +39,17 @@ static int __init epapr_para_init(void)
>=20
> insts =3D of_get_property(hyper_node, "hcall-instructions", &len);
> if (!(len % 4) && (len >=3D (4 * 4))) {
> - for (i =3D 0; i < (len / 4); i++)
> + for (i =3D 0; i < (len / 4); i++) {
> epapr_hypercall_start[i] =3D insts[i];
> + epapr_ev_idle_start[i] =3D insts[i];
> + }
> flush_icache_range((ulong)epapr_hypercall_start,
> (ulong)epapr_hypercall_start + len);
> + flush_icache_range((ulong)epapr_ev_idle_start,
> + (ulong)epapr_ev_idle_start + len);
> +
> + if (of_get_property(hyper_node, "has-idle", NULL))
> + ppc_md.power_save =3D epapr_ev_idle;
>=20
> epapr_para_enabled =3D true;
> }
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] powerpc/usb: fix bug of kernel hang when initializing usb
From: Benjamin Herrenschmidt @ 2012-02-16 10:39 UTC (permalink / raw)
To: Shengzhou Liu; +Cc: linux-usb, linuxppc-dev
In-Reply-To: <1329386540-12341-1-git-send-email-Shengzhou.Liu@freescale.com>
On Thu, 2012-02-16 at 18:02 +0800, Shengzhou Liu wrote:
> If USB UTMI PHY is not enable, writing to portsc register will lead to
> kernel hang during boot up.
Thanks, I'll try that tomorrow.
Greg, you're picking that up or should I ?
Cheers,
Ben.
> Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
> ---
> Apply for master branch of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
> Tested on P5020DS, the issue was reported by Benjamin Herrenschmidt.
>
> drivers/usb/host/ehci-fsl.c | 4 ++++
> drivers/usb/host/ehci-fsl.h | 1 +
> 2 files changed, 5 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
> index c26a82e..0090ed2 100644
> --- a/drivers/usb/host/ehci-fsl.c
> +++ b/drivers/usb/host/ehci-fsl.c
> @@ -216,6 +216,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
> unsigned int port_offset)
> {
> u32 portsc;
> + struct usb_hcd *hcd = ehci_to_hcd(ehci);
> + void __iomem *non_ehci = hcd->regs;
>
> portsc = ehci_readl(ehci, &ehci->regs->port_status[port_offset]);
> portsc &= ~(PORT_PTS_MSK | PORT_PTS_PTW);
> @@ -231,6 +233,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
> portsc |= PORT_PTS_PTW;
> /* fall through */
> case FSL_USB2_PHY_UTMI:
> + /* enable UTMI PHY */
> + setbits32(non_ehci + FSL_SOC_USB_CTRL, CTRL_UTMI_PHY_EN);
> portsc |= PORT_PTS_UTMI;
> break;
> case FSL_USB2_PHY_NONE:
> diff --git a/drivers/usb/host/ehci-fsl.h b/drivers/usb/host/ehci-fsl.h
> index bdf43e2..0e400c2 100644
> --- a/drivers/usb/host/ehci-fsl.h
> +++ b/drivers/usb/host/ehci-fsl.h
> @@ -45,6 +45,7 @@
> #define FSL_SOC_USB_PRICTRL 0x40c /* NOTE: big-endian */
> #define FSL_SOC_USB_SICTRL 0x410 /* NOTE: big-endian */
> #define FSL_SOC_USB_CTRL 0x500 /* NOTE: big-endian */
> +#define CTRL_UTMI_PHY_EN (1<<9)
> #define CTRL_PHY_CLK_VALID (1 << 17)
> #define SNOOP_SIZE_2GB 0x1e
> #endif /* _EHCI_FSL_H */
^ permalink raw reply
* [RFC PATCH v7 00/10] fadump: Firmware-assisted dump support for Powerpc.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
Hi All,
Please find the version 7 of the patchset that implements firmware-assisted
dump mechanism to capture kernel crash dump for Powerpc architecture.
Firmware-assisted dump is a robust mechanism to get reliable kernel crash
dump with the assistance of firmware. This approach does not use kexec,
instead firmware assists in booting the kdump kernel while preserving memory
contents.
- Firmware assisted dump (fadump) infrastructure is intended to replace
the existing phyp assisted dump.
- Fadump uses the same firmware interfaces and memory reservation model
as phyp assisted dump.
- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
in the ELF format in the same way as kdump. This helps us reuse the
kdump infrastructure for dump capture and filtering.
- Unlike phyp dump, userspace tool does not need to refer any sysfs
interface while reading /proc/vmcore.
- Unlike phyp dump, fadump allows user to release all the memory reserved
for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
- Once enabled through kernel boot parameter, fadump can be
started/stopped through /sys/kernel/fadump_registered interface and
can be easily integrated with kdump service start/stop init scripts.
- Once the dump is copied out, the memory that held the dump is
immediately available to the running kernel. And therefore, unlike
kdump, fadump doesn't need a 2nd reboot to get back the system to
the production configuration.
Fadump reuses much of the code written by Manish Ahuja and Linas Vepstas
for the phyp assisted dump.
I have tested the patches on following system configuration:
1. LPAR on Power6 with 4GB RAM and 8 CPUs
2. LPAR on Power7 with 2GB RAM and 20 CPUs
3. LPAR on Power7 with 1TB RAM and 896 CPUs
Please review the patchset and let me know your comments.
ChangeLog:
Change in v7:
-------------
- Updated the documentation explaining the enhancement in fadump over old
phyp dump.
- Re-based patches to commit d65b4e98d7 (v3.3-rc3)
Change in v6:
-------------
- Use of_read_number and of_read_ulong while reading the dump sizes
from rtas node ibm,configure-kernel-kdump-sizes and few minor changes.
- Kernel command line option 'fadump' now uses on/off values to
enable/disable fadump.
- Added the last patch in this series 10/10 to remove phyp dump code.
Change in v5:
-------------
- Added 'fadump_' prefix to all static functions defined.
patch 02/10:
- Merged patch 10/10 which introduces a config option CONFIG_FA_DUMP
for firmware assisted dump feature on Powerpc (ppc64) architecture.
- Increased MIN_BOOT_MEM by 64M to avoid OOM issue during network
dump capture. When kdump infrastructure is configured to save vmcore
over network, we run into OOM issue while loading modules related to
network setup.
Changes in v4:
--------------
patch 04/10:
- Move the init_elfcore_header() function and 'memblock_num_regions' macro
from generic code to power specific code as these are used only by
firmware assisted dump implementation which is power specific feature.
patch 05/10:
- Fixes a issue where memblock_free() is invoked from build_cpu_notes()
function during error_out path. Invoke cpu_notes_buf_free() in error_out
path instead of memblock_free().
Changes in v3:
-------------
- Re-factored the implementation to work with kdump service start/stop.
Introduce fadump_registered sysfs control file which will be used by
kdump init scripts to start/stop firmware assisted dump. echo 1 to
/sys/kernel/fadump_registered file for fadump registration and
echo 0 to /sys/kernel/fadump_registered file for fadump un-registration.
- Introduced the locking mechanism to handle simultaneous writes to
sysfs control files fadump_registered and fadump_release_mem
Affected patches are: 01/10, 03/10, 08/10.
Changes in v2:
-------------
patch 01/10:
- Modified the documentation to reflect the change of fadump_region
file under debugfs filesystem.
patch 02/10:
- Modified to use standard pr_debug() macro.
- Modified early_init_dt_scan_fw_dump() to get the size of
"ibm,configure-kernel-dump-sizes" property and use it to iterate through
an array of dump sections.
- Introduced boot option 'fadump_reserve_mem=' to let user specify the
fadump boot memory to be reserved.
patch 03/10:
- Removed few debug print statements.
- Moved the setup_fadump() call from setup_system() and now calling it
subsys_initcall.
- Moved fadump_region attribute under debugfs.
- Clear the TCE entries if firmware assisted dump is active.
patch 05/10:
- Moved the crash_fadump() invocation from generic code to panic notifier.
- Introduced cpu_notes_buf_alloc() function to allocate cpu notes buffer
using get_free_pages().
patch 08/10:
- Introduced cpu_notes_buf_free() function to free memory allocated for
cpu notes buffer.
Thanks,
-Mahesh.
---
Mahesh Salgaonkar (10):
fadump: Add documentation for firmware-assisted dump.
fadump: Reserve the memory for firmware assisted dump.
fadump: Register for firmware assisted dump.
fadump: Initialize elfcore header and add PT_LOAD program headers.
fadump: Convert firmware-assisted cpu state dump data into elf notes.
fadump: Add PT_NOTE program header for vmcoreinfo
fadump: Introduce cleanup routine to invalidate /proc/vmcore.
fadump: Invalidate registration and release reserved memory for general use.
fadump: Invalidate the fadump registration during machine shutdown.
fadump: Remove the phyp assisted dump code.
Documentation/powerpc/firmware-assisted-dump.txt | 270 +++++
Documentation/powerpc/phyp-assisted-dump.txt | 127 --
arch/powerpc/Kconfig | 17
arch/powerpc/include/asm/fadump.h | 218 ++++
arch/powerpc/include/asm/phyp_dump.h | 47 -
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/fadump.c | 1312 ++++++++++++++++++++++
arch/powerpc/kernel/iommu.c | 8
arch/powerpc/kernel/prom.c | 98 --
arch/powerpc/kernel/setup-common.c | 14
arch/powerpc/kernel/traps.c | 3
arch/powerpc/mm/hash_utils_64.c | 11
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/phyp_dump.c | 513 ---------
fs/proc/vmcore.c | 23
15 files changed, 1881 insertions(+), 782 deletions(-)
create mode 100644 Documentation/powerpc/firmware-assisted-dump.txt
delete mode 100644 Documentation/powerpc/phyp-assisted-dump.txt
create mode 100644 arch/powerpc/include/asm/fadump.h
delete mode 100644 arch/powerpc/include/asm/phyp_dump.h
create mode 100644 arch/powerpc/kernel/fadump.c
delete mode 100644 arch/powerpc/platforms/pseries/phyp_dump.c
--
-Mahesh
^ permalink raw reply
* [RFC PATCH v7 02/10] fadump: Reserve the memory for firmware assisted dump.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reserve the memory during early boot to preserve CPU state data, HPTE region
and RMA (real mode area) region data in case of kernel crash. At the time of
crash, powerpc firmware will store CPU state data, HPTE region data and move
RMA region data to the reserved memory area.
If the firmware-assisted dump fails to reserve the memory, then fallback
to existing kexec-based kdump.
Most of the code implementation to reserve memory has been
adapted from phyp assisted dump implementation written by Linas Vepstas
and Manish Ahuja
This patch also introduces a config option CONFIG_FA_DUMP for firmware
assisted dump feature on Powerpc (ppc64) architecture.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 13 ++
arch/powerpc/include/asm/fadump.h | 71 +++++++++++
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/fadump.c | 246 +++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/prom.c | 15 ++
5 files changed, 345 insertions(+), 1 deletions(-)
create mode 100644 arch/powerpc/include/asm/fadump.h
create mode 100644 arch/powerpc/kernel/fadump.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1919634..afa4dab 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -386,6 +386,19 @@ config PHYP_DUMP
If unsure, say "N"
+config FA_DUMP
+ bool "Firmware-assisted dump"
+ depends on PPC64 && PPC_RTAS && CRASH_DUMP
+ help
+ A robust mechanism to get reliable kernel crash dump with
+ assistance from firmware. This approach does not use kexec,
+ instead firmware assists in booting the kdump kernel
+ while preserving memory contents. Firmware-assisted dump
+ is meant to be a kdump replacement offering robustness and
+ speed not possible without system firmware assistance.
+
+ If unsure, say "N"
+
config IRQ_ALL_CPUS
bool "Distribute interrupts on all CPUs by default"
depends on SMP && !MV64360
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
new file mode 100644
index 0000000..7be25d3
--- /dev/null
+++ b/arch/powerpc/include/asm/fadump.h
@@ -0,0 +1,71 @@
+/*
+ * Firmware Assisted dump header file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef __PPC64_FA_DUMP_H__
+#define __PPC64_FA_DUMP_H__
+
+#ifdef CONFIG_FA_DUMP
+
+/*
+ * The RMA region will be saved for later dumping when kernel crashes.
+ * RMA is Real Mode Area, the first block of logical memory address owned
+ * by logical partition, containing the storage that may be accessed with
+ * translate off.
+ */
+#define RMA_START 0x0
+#define RMA_END (ppc64_rma_size)
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need aditional 64M
+ * of memory to avoid OOM issue.
+ */
+#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+ + (0x1UL << 26))
+
+/* Firmware provided dump sections */
+#define FADUMP_CPU_STATE_DATA 0x0001
+#define FADUMP_HPTE_REGION 0x0002
+#define FADUMP_REAL_MODE_REGION 0x0011
+
+struct fw_dump {
+ unsigned long cpu_state_data_size;
+ unsigned long hpte_region_size;
+ unsigned long boot_memory_size;
+ unsigned long reserve_dump_area_start;
+ unsigned long reserve_dump_area_size;
+ /* cmd line option during boot */
+ unsigned long reserve_bootvar;
+
+ int ibm_configure_kernel_dump;
+
+ unsigned long fadump_enabled:1;
+ unsigned long fadump_supported:1;
+ unsigned long dump_active:1;
+};
+
+extern int early_init_dt_scan_fw_dump(unsigned long node,
+ const char *uname, int depth, void *data);
+extern int fadump_reserve_mem(void);
+#endif
+#endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e4..391bf7e 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -60,6 +60,7 @@ obj-$(CONFIG_IBMVIO) += vio.o
obj-$(CONFIG_IBMEBUS) += ibmebus.o
obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_FA_DUMP) += fadump.o
ifeq ($(CONFIG_PPC32),y)
obj-$(CONFIG_E500) += idle_e500.o
endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
new file mode 100644
index 0000000..deb276a
--- /dev/null
+++ b/arch/powerpc/kernel/fadump.c
@@ -0,0 +1,246 @@
+/*
+ * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
+ * dump with assistance from firmware. This approach does not use kexec,
+ * instead firmware assists in booting the kdump kernel while preserving
+ * memory contents. The most of the code implementation has been adapted
+ * from phyp assisted dump implementation written by Linas Vepstas and
+ * Manish Ahuja
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+
+static struct fw_dump fw_dump;
+
+/* Scan the Firmware Assisted dump configuration details. */
+int __init early_init_dt_scan_fw_dump(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ __be32 *sections;
+ int i, num_sections;
+ unsigned long size;
+ const int *token;
+
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ /*
+ * Check if Firmware Assisted dump is supported. if yes, check
+ * if dump has been initiated on last reboot.
+ */
+ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+ if (!token)
+ return 0;
+
+ fw_dump.fadump_supported = 1;
+ fw_dump.ibm_configure_kernel_dump = *token;
+
+ /*
+ * The 'ibm,kernel-dump' rtas node is present only if there is
+ * dump data waiting for us.
+ */
+ if (of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL))
+ fw_dump.dump_active = 1;
+
+ /* Get the sizes required to store dump data for the firmware provided
+ * dump sections.
+ * For each dump section type supported, a 32bit cell which defines
+ * the ID of a supported section followed by two 32 bit cells which
+ * gives teh size of the section in bytes.
+ */
+ sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+ &size);
+
+ if (!sections)
+ return 0;
+
+ num_sections = size / (3 * sizeof(u32));
+
+ for (i = 0; i < num_sections; i++, sections += 3) {
+ u32 type = (u32)of_read_number(sections, 1);
+
+ switch (type) {
+ case FADUMP_CPU_STATE_DATA:
+ fw_dump.cpu_state_data_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ case FADUMP_HPTE_REGION:
+ fw_dump.hpte_region_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ }
+ }
+ return 1;
+}
+
+/**
+ * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
+ *
+ * Function to find the largest memory size we need to reserve during early
+ * boot process. This will be the size of the memory that is required for a
+ * kernel to boot successfully.
+ *
+ * This function has been taken from phyp-assisted dump feature implementation.
+ *
+ * returns larger of 256MB or 5% rounded down to multiples of 256MB.
+ *
+ * TODO: Come up with better approach to find out more accurate memory size
+ * that is required for a kernel to boot successfully.
+ *
+ */
+static inline unsigned long fadump_calculate_reserve_size(void)
+{
+ unsigned long size;
+
+ /*
+ * Check if the size is specified through fadump_reserve_mem= cmdline
+ * option. If yes, then use that.
+ */
+ if (fw_dump.reserve_bootvar)
+ return fw_dump.reserve_bootvar;
+
+ /* divide by 20 to get 5% of value */
+ size = memblock_end_of_DRAM() / 20;
+
+ /* round it down in multiples of 256 */
+ size = size & ~0x0FFFFFFFUL;
+
+ /* Truncate to memory_limit. We don't want to over reserve the memory.*/
+ if (memory_limit && size > memory_limit)
+ size = memory_limit;
+
+ return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+}
+
+/*
+ * Calculate the total memory size required to be reserved for
+ * firmware-assisted dump registration.
+ */
+static unsigned long get_fadump_area_size(void)
+{
+ unsigned long size = 0;
+
+ size += fw_dump.cpu_state_data_size;
+ size += fw_dump.hpte_region_size;
+ size += fw_dump.boot_memory_size;
+
+ size = PAGE_ALIGN(size);
+ return size;
+}
+
+int __init fadump_reserve_mem(void)
+{
+ unsigned long base, size, memory_boundary;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_INFO "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ fw_dump.fadump_enabled = 0;
+ return 0;
+ }
+ /* Initialize boot memory size */
+ fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+
+ /*
+ * Calculate the memory boundary.
+ * If memory_limit is less than actual memory boundary then reserve
+ * the memory for fadump beyond the memory_limit and adjust the
+ * memory_limit accordingly, so that the running kernel can run with
+ * specified memory_limit.
+ */
+ if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
+ size = get_fadump_area_size();
+ if ((memory_limit + size) < memblock_end_of_DRAM())
+ memory_limit += size;
+ else
+ memory_limit = memblock_end_of_DRAM();
+ printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
+ " dump, now %#016llx\n",
+ (unsigned long long)memory_limit);
+ }
+ if (memory_limit)
+ memory_boundary = memory_limit;
+ else
+ memory_boundary = memblock_end_of_DRAM();
+
+ if (fw_dump.dump_active) {
+ printk(KERN_INFO "Firmware-assisted dump is active.\n");
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot_memory_size so that we don't touch it until
+ * dump is written to disk by userspace tool. This memory
+ * will be released for general use once the dump is saved.
+ */
+ base = fw_dump.boot_memory_size;
+ size = memory_boundary - base;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for saving crash dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+ } else {
+ /* Reserve the memory at the top of memory. */
+ size = get_fadump_area_size();
+ base = memory_boundary - size;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for firmware-assisted dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+ }
+ fw_dump.reserve_dump_area_start = base;
+ fw_dump.reserve_dump_area_size = size;
+ return 1;
+}
+
+/* Look for fadump= cmdline option. */
+static int __init early_fadump_param(char *p)
+{
+ if (!p)
+ return 1;
+
+ if (strncmp(p, "on", 2) == 0)
+ fw_dump.fadump_enabled = 1;
+ else if (strncmp(p, "off", 3) == 0)
+ fw_dump.fadump_enabled = 0;
+
+ return 0;
+}
+early_param("fadump", early_fadump_param);
+
+/* Look for fadump_reserve_mem= cmdline option */
+static int __init early_fadump_reserve_mem(char *p)
+{
+ if (p)
+ fw_dump.reserve_bootvar = memparse(p, &p);
+ return 0;
+}
+early_param("fadump_reserve_mem", early_fadump_reserve_mem);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index abe405d..70222b3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -55,6 +55,7 @@
#include <asm/phyp_dump.h>
#include <asm/kexec.h>
#include <asm/opal.h>
+#include <asm/fadump.h>
#include <mm/mmu_decl.h>
@@ -719,6 +720,11 @@ void __init early_init_devtree(void *params)
of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
#endif
+#ifdef CONFIG_FA_DUMP
+ /* scan tree to see if dump is active during last boot */
+ of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
+#endif
+
/* Pre-initialize the cmd_line with the content of boot_commmand_line,
* which will be empty except when the content of the variable has
* been overriden by a bootloading mechanism. This happens typically
@@ -750,7 +756,14 @@ void __init early_init_devtree(void *params)
if (PHYSICAL_START > MEMORY_START)
memblock_reserve(MEMORY_START, 0x8000);
reserve_kdump_trampoline();
- reserve_crashkernel();
+#ifdef CONFIG_FA_DUMP
+ /*
+ * If we fail to reserve memory for firmware-assisted dump then
+ * fallback to kexec based kdump.
+ */
+ if (fadump_reserve_mem() == 0)
+#endif
+ reserve_crashkernel();
early_reserve_mem();
phyp_dump_reserve_mem();
^ permalink raw reply related
* [RFC PATCH v7 04/10] fadump: Initialize elfcore header and add PT_LOAD program headers.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Build the crash memory range list by traversing through system memory during
the first kernel before we register for firmware-assisted dump. After the
successful dump registration, initialize the elfcore header and populate
PT_LOAD program headers with crash memory ranges. The elfcore header is
saved in the scratch area within the reserved memory. The scratch area starts
at the end of the memory reserved for saving RMR region contents. The
scratch area contains fadump crash info structure that contains magic number
for fadump validation and physical address where the eflcore header can be
found. This structure will also be used to pass some important crash info
data to the second kernel which will help second kernel to populate ELF core
header with correct data before it gets exported through /proc/vmcore. Since
the firmware preserves the entire partition memory at the time of crash the
contents of the scratch area will be preserved till second kernel boot.
Since the memory dump exported through /proc/vmcore is in ELF format similar
to kdump, it will help us to reuse the kdump infrastructure for dump capture
and filtering. Unlike phyp dump, userspace tool does not need to refer any
sysfs interface while reading /proc/vmcore.
NOTE: The current design implementation does not address a possibility of
introducing additional fields (in future) to this structure without affecting
compatibility. It's on TODO list to come up with better approach to
address this.
Reserved dump area start => +-------------------------------------+
| CPU state dump data |
+-------------------------------------+
| HPTE region data |
+-------------------------------------+
| RMR region data |
Scratch area start => +-------------------------------------+
| fadump crash info structure { |
| magic nummber |
+------|---- elfcorehdr_addr |
| | } |
+----> +-------------------------------------+
| ELF core header |
Reserved dump area end => +-------------------------------------+
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 43 +++++++
arch/powerpc/kernel/fadump.c | 233 +++++++++++++++++++++++++++++++++++++
2 files changed, 275 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index bbaf278..9e172a5 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -43,6 +43,12 @@
#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+ (0x1UL << 26))
+#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt)
+
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS 0
+#endif
+
/* Firmware provided dump sections */
#define FADUMP_CPU_STATE_DATA 0x0001
#define FADUMP_HPTE_REGION 0x0002
@@ -56,6 +62,9 @@
#define FADUMP_UNREGISTER 2
#define FADUMP_INVALIDATE 3
+/* Dump status flag */
+#define FADUMP_ERROR_FLAG 0x2000
+
/* Kernel Dump section info */
struct fadump_section {
u32 request_flag;
@@ -109,6 +118,7 @@ struct fw_dump {
/* cmd line option during boot */
unsigned long reserve_bootvar;
+ unsigned long fadumphdr_addr;
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -117,6 +127,39 @@ struct fw_dump {
unsigned long dump_registered:1;
};
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ * The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 str_to_u64(const char *str)
+{
+ u64 val = 0;
+ int i;
+
+ for (i = 0; i < sizeof(val); i++)
+ val = (*str) ? (val << 8) | *str++ : val << 8;
+ return val;
+}
+#define STR_TO_HEX(x) str_to_u64(x)
+
+#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF")
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+ u64 magic_number;
+ u64 elfcorehdr_addr;
+};
+
+/* Crash memory ranges */
+#define INIT_CRASHMEM_RANGES (INIT_MEMBLOCK_REGIONS + 2)
+
+struct fad_crash_memory_ranges {
+ unsigned long long base;
+ unsigned long long size;
+};
+
extern int early_init_dt_scan_fw_dump(unsigned long node,
const char *uname, int depth, void *data);
extern int fadump_reserve_mem(void);
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 13c22cd..f85a63f 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -32,6 +32,7 @@
#include <linux/delay.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -43,6 +44,8 @@ static struct fadump_mem_struct fdm;
static const struct fadump_mem_struct *fdm_active;
static DEFINE_MUTEX(fadump_mutex);
+struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
+int crash_mem_ranges;
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node,
@@ -235,6 +238,10 @@ static unsigned long get_fadump_area_size(void)
size += fw_dump.cpu_state_data_size;
size += fw_dump.hpte_region_size;
size += fw_dump.boot_memory_size;
+ size += sizeof(struct fadump_crash_info_header);
+ size += sizeof(struct elfhdr); /* ELF core header.*/
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
size = PAGE_ALIGN(size);
return size;
@@ -300,6 +307,12 @@ int __init fadump_reserve_mem(void)
"for saving crash dump\n",
(unsigned long)(size >> 20),
(unsigned long)(base >> 20));
+
+ fw_dump.fadumphdr_addr =
+ fdm_active->rmr_region.destination_address +
+ fdm_active->rmr_region.source_len;
+ pr_debug("fadumphdr_addr = %p\n",
+ (void *) fw_dump.fadumphdr_addr);
} else {
/* Reserve the memory at the top of memory. */
size = get_fadump_area_size();
@@ -380,8 +393,210 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
}
}
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!fdm_active || !fw_dump.fadumphdr_addr)
+ return -EINVAL;
+
+ /* Check if the dump data is valid. */
+ if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+ (fdm_active->rmr_region.error_flags != 0)) {
+ printk(KERN_ERR "Dump taken by platform is not valid\n");
+ return -EINVAL;
+ }
+ if (fdm_active->rmr_region.bytes_dumped !=
+ fdm_active->rmr_region.source_len) {
+ printk(KERN_ERR "Dump taken by platform is incomplete\n");
+ return -EINVAL;
+ }
+
+ /* Validate the fadump crash info header */
+ fdh = __va(fw_dump.fadumphdr_addr);
+ if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+ printk(KERN_ERR "Crash info header is not valid.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * We are done validating dump info and elfcore header is now ready
+ * to be exported. set elfcorehdr_addr so that vmcore module will
+ * export the elfcore header through '/proc/vmcore'.
+ */
+ elfcorehdr_addr = fdh->elfcorehdr_addr;
+
+ return 0;
+}
+
+static inline void fadump_add_crash_memory(unsigned long long base,
+ unsigned long long end)
+{
+ if (base == end)
+ return;
+
+ pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+ crash_mem_ranges, base, end - 1, (end - base));
+ crash_memory_ranges[crash_mem_ranges].base = base;
+ crash_memory_ranges[crash_mem_ranges].size = end - base;
+ crash_mem_ranges++;
+}
+
+static void fadump_exclude_reserved_area(unsigned long long start,
+ unsigned long long end)
+{
+ unsigned long long ra_start, ra_end;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ if ((ra_start < end) && (ra_end > start)) {
+ if ((start < ra_start) && (end > ra_end)) {
+ fadump_add_crash_memory(start, ra_start);
+ fadump_add_crash_memory(ra_end, end);
+ } else if (start < ra_start) {
+ fadump_add_crash_memory(start, ra_start);
+ } else if (ra_end < end) {
+ fadump_add_crash_memory(ra_end, end);
+ }
+ } else
+ fadump_add_crash_memory(start, end);
+}
+
+static int fadump_init_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+
+ elf = (struct elfhdr *) bufp;
+ bufp += sizeof(struct elfhdr);
+ memcpy(elf->e_ident, ELFMAG, SELFMAG);
+ elf->e_ident[EI_CLASS] = ELF_CLASS;
+ elf->e_ident[EI_DATA] = ELF_DATA;
+ elf->e_ident[EI_VERSION] = EV_CURRENT;
+ elf->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+ elf->e_type = ET_CORE;
+ elf->e_machine = ELF_ARCH;
+ elf->e_version = EV_CURRENT;
+ elf->e_entry = 0;
+ elf->e_phoff = sizeof(struct elfhdr);
+ elf->e_shoff = 0;
+ elf->e_flags = ELF_CORE_EFLAGS;
+ elf->e_ehsize = sizeof(struct elfhdr);
+ elf->e_phentsize = sizeof(struct elf_phdr);
+ elf->e_phnum = 0;
+ elf->e_shentsize = 0;
+ elf->e_shnum = 0;
+ elf->e_shstrndx = 0;
+
+ return 0;
+}
+
+/*
+ * Traverse through memblock structure and setup crash memory ranges. These
+ * ranges will be used create PT_LOAD program headers in elfcore header.
+ */
+static void fadump_setup_crash_memory_ranges(void)
+{
+ struct memblock_region *reg;
+ unsigned long long start, end;
+
+ pr_debug("Setup crash memory ranges.\n");
+ crash_mem_ranges = 0;
+ /*
+ * add the first memory chunk (RMA_START through boot_memory_size) as
+ * a separate memory chunk. The reason is, at the time crash firmware
+ * will move the content of this memory chunk to different location
+ * specified during fadump registration. We need to create a separate
+ * program header for this chunk with the correct offset.
+ */
+ fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+
+ for_each_memblock(memory, reg) {
+ start = (unsigned long long)reg->base;
+ end = start + (unsigned long long)reg->size;
+ if (start == RMA_START && end >= fw_dump.boot_memory_size)
+ start = fw_dump.boot_memory_size;
+
+ /* add this range excluding the reserved dump area. */
+ fadump_exclude_reserved_area(start, end);
+ }
+}
+
+static int fadump_create_elfcore_headers(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+ int i;
+
+ fadump_init_elfcore_header(bufp);
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /* setup PT_LOAD sections. */
+
+ for (i = 0; i < crash_mem_ranges; i++) {
+ unsigned long long mbase, msize;
+ mbase = crash_memory_ranges[i].base;
+ msize = crash_memory_ranges[i].size;
+
+ if (!msize)
+ continue;
+
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_offset = mbase;
+
+ if (mbase == RMA_START) {
+ /*
+ * The entire RMA region will be moved by firmware
+ * to the specified destination_address. Hence set
+ * the correct offset.
+ */
+ phdr->p_offset = fdm.rmr_region.destination_address;
+ }
+
+ phdr->p_paddr = mbase;
+ phdr->p_vaddr = (unsigned long)__va(mbase);
+ phdr->p_filesz = msize;
+ phdr->p_memsz = msize;
+ phdr->p_align = 0;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ }
+ return 0;
+}
+
+static unsigned long init_fadump_header(unsigned long addr)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!addr)
+ return 0;
+
+ fw_dump.fadumphdr_addr = addr;
+ fdh = __va(addr);
+ addr += sizeof(struct fadump_crash_info_header);
+
+ memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+ fdh->elfcorehdr_addr = addr;
+
+ return addr;
+}
+
static void register_fadump(void)
{
+ unsigned long addr;
+ void *vaddr;
+
/*
* If no memory is reserved then we can not register for firmware-
* assisted dump.
@@ -389,6 +604,16 @@ static void register_fadump(void)
if (!fw_dump.reserve_dump_area_size)
return;
+ fadump_setup_crash_memory_ranges();
+
+ addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len;
+ /* Initialize fadump crash info header. */
+ addr = init_fadump_header(addr);
+ vaddr = __va(addr);
+
+ pr_debug("Creating ELF core headers at %#016lx\n", addr);
+ fadump_create_elfcore_headers(vaddr);
+
/* register the future kernel dump with firmware. */
register_fw_dump(&fdm);
}
@@ -582,8 +807,14 @@ int __init setup_fadump(void)
}
fadump_show_config();
+ /*
+ * If dump data is available then see if it is valid and prepare for
+ * saving it to the disk.
+ */
+ if (fw_dump.dump_active)
+ process_fadump(fdm_active);
/* Initialize the kernel dump memory structure for FAD registration. */
- if (fw_dump.reserve_dump_area_size)
+ else if (fw_dump.reserve_dump_area_size)
init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
fadump_init_files();
^ permalink raw reply related
* [RFC PATCH v7 05/10] fadump: Convert firmware-assisted cpu state dump data into elf notes.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
When registered for firmware assisted dump on powerpc, firmware preserves
the registers for the active CPUs during a system crash. This patch reads
the cpu register data stored in Firmware-assisted dump format (except for
crashing cpu) and converts it into elf notes and updates the PT_NOTE program
header accordingly. The exact register state for crashing cpu is saved to
fadump crash info structure in scratch area during crash_fadump() and read
during second kernel boot.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 44 +++++
arch/powerpc/kernel/fadump.c | 314 ++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/setup-common.c | 6 +
arch/powerpc/kernel/traps.c | 3
4 files changed, 365 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 9e172a5..6768195 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -65,6 +65,18 @@
/* Dump status flag */
#define FADUMP_ERROR_FLAG 0x2000
+#define FADUMP_CPU_ID_MASK ((1UL << 32) - 1)
+
+#define CPU_UNKNOWN (~((u32)0))
+
+/* Utility macros */
+#define SKIP_TO_NEXT_CPU(reg_entry) \
+({ \
+ while (reg_entry->reg_id != REG_ID("CPUEND")) \
+ reg_entry++; \
+ reg_entry++; \
+})
+
/* Kernel Dump section info */
struct fadump_section {
u32 request_flag;
@@ -119,6 +131,9 @@ struct fw_dump {
unsigned long reserve_bootvar;
unsigned long fadumphdr_addr;
+ unsigned long cpu_notes_buf;
+ unsigned long cpu_notes_buf_size;
+
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -143,13 +158,40 @@ static inline u64 str_to_u64(const char *str)
return val;
}
#define STR_TO_HEX(x) str_to_u64(x)
+#define REG_ID(x) str_to_u64(x)
#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF")
+#define REGSAVE_AREA_MAGIC STR_TO_HEX("REGSAVE")
+
+/* The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct fadump_reg_save_area_header {
+ u64 magic_number;
+ u32 version;
+ u32 num_cpu_offset;
+};
+
+/* Register entry. */
+struct fadump_reg_entry {
+ u64 reg_id;
+ u64 reg_value;
+};
/* fadump crash info structure */
struct fadump_crash_info_header {
u64 magic_number;
u64 elfcorehdr_addr;
+ u32 crashing_cpu;
+ struct pt_regs regs;
+ struct cpumask cpu_online_mask;
};
/* Crash memory ranges */
@@ -165,7 +207,9 @@ extern int early_init_dt_scan_fw_dump(unsigned long node,
extern int fadump_reserve_mem(void);
extern int setup_fadump(void);
extern int is_fadump_active(void);
+extern void crash_fadump(struct pt_regs *, const char *);
#else /* CONFIG_FA_DUMP */
static inline int is_fadump_active(void) { return 0; }
+static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
#endif
#endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index f85a63f..cab56e7 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -240,6 +240,7 @@ static unsigned long get_fadump_area_size(void)
size += fw_dump.boot_memory_size;
size += sizeof(struct fadump_crash_info_header);
size += sizeof(struct elfhdr); /* ELF core header.*/
+ size += sizeof(struct elf_phdr); /* place holder for cpu notes */
/* Program headers for crash memory regions. */
size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
@@ -393,6 +394,285 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
}
}
+void crash_fadump(struct pt_regs *regs, const char *str)
+{
+ struct fadump_crash_info_header *fdh = NULL;
+
+ if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
+ return;
+
+ fdh = __va(fw_dump.fadumphdr_addr);
+ crashing_cpu = smp_processor_id();
+ fdh->crashing_cpu = crashing_cpu;
+ crash_save_vmcoreinfo();
+
+ if (regs)
+ fdh->regs = *regs;
+ else
+ ppc_save_regs(&fdh->regs);
+
+ fdh->cpu_online_mask = *cpu_online_mask;
+
+ /* Call ibm,os-term rtas call to trigger firmware assisted dump */
+ rtas_os_term((char *)str);
+}
+
+#define GPR_MASK 0xffffff0000000000
+static inline int fadump_gpr_index(u64 id)
+{
+ int i = -1;
+ char str[3];
+
+ if ((id & GPR_MASK) == REG_ID("GPR")) {
+ /* get the digits at the end */
+ id &= ~GPR_MASK;
+ id >>= 24;
+ str[2] = '\0';
+ str[1] = id & 0xff;
+ str[0] = (id >> 8) & 0xff;
+ sscanf(str, "%d", &i);
+ if (i > 31)
+ i = -1;
+ }
+ return i;
+}
+
+static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
+ u64 reg_val)
+{
+ int i;
+
+ i = fadump_gpr_index(reg_id);
+ if (i >= 0)
+ regs->gpr[i] = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("NIA"))
+ regs->nip = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("MSR"))
+ regs->msr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CTR"))
+ regs->ctr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("LR"))
+ regs->link = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("XER"))
+ regs->xer = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CR"))
+ regs->ccr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DAR"))
+ regs->dar = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DSISR"))
+ regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+{
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ while (reg_entry->reg_id != REG_ID("CPUEND")) {
+ fadump_set_regval(regs, reg_entry->reg_id,
+ reg_entry->reg_value);
+ reg_entry++;
+ }
+ reg_entry++;
+ return reg_entry;
+}
+
+static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
+ void *data, size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, ¬e, sizeof(note));
+ buf += (sizeof(note) + 3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+static void fadump_final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, ¬e, sizeof(note));
+}
+
+static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+ struct elf_prstatus prstatus;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ /*
+ * FIXME: How do i get PID? Do I really need it?
+ * prstatus.pr_pid = ????
+ */
+ elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+ buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
+ return buf;
+}
+
+static void fadump_update_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /* First note is a place holder for cpu notes info. */
+ phdr = (struct elf_phdr *)bufp;
+
+ if (phdr->p_type == PT_NOTE) {
+ phdr->p_paddr = fw_dump.cpu_notes_buf;
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_filesz = fw_dump.cpu_notes_buf_size;
+ phdr->p_memsz = fw_dump.cpu_notes_buf_size;
+ }
+ return;
+}
+
+static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+{
+ void *vaddr;
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+ if (!vaddr)
+ return NULL;
+
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ SetPageReserved(page + i);
+ return vaddr;
+}
+
+static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+{
+ struct fadump_reg_save_area_header *reg_header;
+ struct fadump_reg_entry *reg_entry;
+ struct fadump_crash_info_header *fdh = NULL;
+ void *vaddr;
+ unsigned long addr;
+ u32 num_cpus, *note_buf;
+ struct pt_regs regs;
+ int i, rc = 0, cpu = 0;
+
+ if (!fdm->cpu_state_data.bytes_dumped)
+ return -EINVAL;
+
+ addr = fdm->cpu_state_data.destination_address;
+ vaddr = __va(addr);
+
+ reg_header = vaddr;
+ if (reg_header->magic_number != REGSAVE_AREA_MAGIC) {
+ printk(KERN_ERR "Unable to read register save area.\n");
+ return -ENOENT;
+ }
+ pr_debug("--------CPU State Data------------\n");
+ pr_debug("Magic Number: %llx\n", reg_header->magic_number);
+ pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
+
+ vaddr += reg_header->num_cpu_offset;
+ num_cpus = *((u32 *)(vaddr));
+ pr_debug("NumCpus : %u\n", num_cpus);
+ vaddr += sizeof(u32);
+ reg_entry = (struct fadump_reg_entry *)vaddr;
+
+ /* Allocate buffer to hold cpu crash notes. */
+ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
+ fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
+ note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
+ if (!note_buf) {
+ printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
+ "cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
+ return -ENOMEM;
+ }
+ fw_dump.cpu_notes_buf = __pa(note_buf);
+
+ pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
+ (num_cpus * sizeof(note_buf_t)), note_buf);
+
+ if (fw_dump.fadumphdr_addr)
+ fdh = __va(fw_dump.fadumphdr_addr);
+
+ for (i = 0; i < num_cpus; i++) {
+ if (reg_entry->reg_id != REG_ID("CPUSTRT")) {
+ printk(KERN_ERR "Unable to read CPU state data\n");
+ rc = -ENOENT;
+ goto error_out;
+ }
+ /* Lower 4 bytes of reg_value contains logical cpu id */
+ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
+ if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
+ SKIP_TO_NEXT_CPU(reg_entry);
+ continue;
+ }
+ pr_debug("Reading register data for cpu %d...\n", cpu);
+ if (fdh && fdh->crashing_cpu == cpu) {
+ regs = fdh->regs;
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ SKIP_TO_NEXT_CPU(reg_entry);
+ } else {
+ reg_entry++;
+ reg_entry = fadump_read_registers(reg_entry, ®s);
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ }
+ }
+ fadump_final_note(note_buf);
+
+ pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+ fdh->elfcorehdr_addr);
+ fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+ return 0;
+
+error_out:
+ fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ return rc;
+
+}
+
/*
* Validate and process the dump data stored by firmware before exporting
* it through '/proc/vmcore'.
@@ -400,18 +680,21 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
{
struct fadump_crash_info_header *fdh;
+ int rc = 0;
if (!fdm_active || !fw_dump.fadumphdr_addr)
return -EINVAL;
/* Check if the dump data is valid. */
if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+ (fdm_active->cpu_state_data.error_flags != 0) ||
(fdm_active->rmr_region.error_flags != 0)) {
printk(KERN_ERR "Dump taken by platform is not valid\n");
return -EINVAL;
}
- if (fdm_active->rmr_region.bytes_dumped !=
- fdm_active->rmr_region.source_len) {
+ if ((fdm_active->rmr_region.bytes_dumped !=
+ fdm_active->rmr_region.source_len) ||
+ !fdm_active->cpu_state_data.bytes_dumped) {
printk(KERN_ERR "Dump taken by platform is incomplete\n");
return -EINVAL;
}
@@ -423,6 +706,10 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
return -EINVAL;
}
+ rc = fadump_build_cpu_notes(fdm_active);
+ if (rc)
+ return rc;
+
/*
* We are done validating dump info and elfcore header is now ready
* to be exported. set elfcorehdr_addr so that vmcore module will
@@ -537,6 +824,27 @@ static int fadump_create_elfcore_headers(char *bufp)
elf = (struct elfhdr *)bufp;
bufp += sizeof(struct elfhdr);
+ /*
+ * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
+ * will be populated during second kernel boot after crash. Hence
+ * this PT_NOTE will always be the first elf note.
+ *
+ * NOTE: Any new ELF note addition should be placed after this note.
+ */
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_NOTE;
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+
+ phdr->p_offset = 0;
+ phdr->p_paddr = 0;
+ phdr->p_filesz = 0;
+ phdr->p_memsz = 0;
+
+ (elf->e_phnum)++;
+
/* setup PT_LOAD sections. */
for (i = 0; i < crash_mem_ranges; i++) {
@@ -588,6 +896,8 @@ static unsigned long init_fadump_header(unsigned long addr)
memset(fdh, 0, sizeof(struct fadump_crash_info_header));
fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
fdh->elfcorehdr_addr = addr;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = CPU_UNKNOWN;
return addr;
}
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 77bb77d..4e62a56 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -61,6 +61,7 @@
#include <asm/xmon.h>
#include <asm/cputhreads.h>
#include <mm/mmu_decl.h>
+#include <asm/fadump.h>
#include "setup.h"
@@ -639,6 +640,11 @@ EXPORT_SYMBOL(check_legacy_ioport);
static int ppc_panic_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
+ /*
+ * If firmware-assisted dump has been registered then trigger
+ * firmware-assisted dump and let firmware handle everything else.
+ */
+ crash_fadump(NULL, ptr);
ppc_md.panic(ptr); /* May not return */
return NOTIFY_DONE;
}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c091527..5d40e59 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -57,6 +57,7 @@
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>
#include <asm/rio.h>
+#include <asm/fadump.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -145,6 +146,8 @@ static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs,
arch_spin_unlock(&die_lock);
raw_local_irq_restore(flags);
+ crash_fadump(regs, "die oops");
+
/*
* A system reset (0x100) is a request to dump, so we always send
* it through the crashdump code.
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox