* [PATCH 07/27] powerpc/eeh: EEH post initialization operation
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
The patch adds new EEH operation post_init. It's used to notify
the platform that EEH core has completed the EEH probe. By that,
PowerNV platform starts to use the services supplied by EEH
functionality.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 1 +
arch/powerpc/platforms/pseries/eeh.c | 11 +++++++++++
2 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 72611fa..a577d78 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -131,6 +131,7 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
struct eeh_ops {
char *name;
int (*init)(void);
+ int (*post_init)(void);
void* (*of_probe)(struct device_node *dn, void *flag);
int (*dev_probe)(struct pci_dev *dev, void *flag);
int (*set_option)(struct eeh_pe *pe, int option);
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index dbc9d83..ef3b02a 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -720,6 +720,17 @@ int __init eeh_init(void)
return -EINVAL;
}
+ /*
+ * Call platform post-initialization. Actually, It's good chance
+ * to inform platform that EEH is ready to supply service if the
+ * I/O cache stuff has been built up.
+ */
+ if (eeh_ops->post_init) {
+ ret = eeh_ops->post_init();
+ if (ret)
+ return ret;
+ }
+
if (eeh_subsystem_enabled)
pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
else
--
1.7.5.4
^ permalink raw reply related
* [PATCH 10/27] powerpc/eeh: Differentiate EEH events
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
The EEH event is usually produced because of 0xFF's returned from
PCI config or I/O registers. PowerNV platform also can produce EEH
event through interrupts. The patch differentiates the EEH events
produced for different cases in order to process them differently
in future.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 4 ++--
arch/powerpc/include/asm/eeh_event.h | 6 +++++-
arch/powerpc/kernel/rtas_pci.c | 3 ++-
arch/powerpc/platforms/pseries/eeh.c | 7 ++++---
arch/powerpc/platforms/pseries/eeh_event.c | 4 +++-
5 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a577d78..d1fd5d4 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -202,7 +202,7 @@ int __init eeh_ops_register(struct eeh_ops *ops);
int __exit eeh_ops_unregister(const char *name);
unsigned long eeh_check_failure(const volatile void __iomem *token,
unsigned long val);
-int eeh_dev_check_failure(struct eeh_dev *edev);
+int eeh_dev_check_failure(struct eeh_dev *edev, int flag);
void __init eeh_addr_cache_build(void);
void eeh_add_device_tree_early(struct device_node *);
void eeh_add_device_tree_late(struct pci_bus *);
@@ -243,7 +243,7 @@ static inline unsigned long eeh_check_failure(const volatile void __iomem *token
return val;
}
-#define eeh_dev_check_failure(x) (0)
+#define eeh_dev_check_failure(x, f) (0)
static inline void eeh_addr_cache_build(void) { }
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index de67d83..7e00f23 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -26,12 +26,16 @@
* to this struct is passed as the data pointer in a notify
* callback.
*/
+#define EEH_EVENT_NORMAL (1 << 0)
+#define EEH_EVENT_INT (1 << 1)
+
struct eeh_event {
+ int flag; /* Event flag */
struct list_head list; /* to form event queue */
struct eeh_pe *pe; /* EEH PE */
};
-int eeh_send_failure_event(struct eeh_pe *pe);
+int eeh_send_failure_event(struct eeh_pe *pe, int flag);
void eeh_handle_event(struct eeh_pe *pe);
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 6e7b7cd..8d26f92 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -39,6 +39,7 @@
#include <asm/mpic.h>
#include <asm/ppc-pci.h>
#include <asm/eeh.h>
+#include <asm/eeh_event.h>
/* RTAS tokens */
static int read_pci_config;
@@ -81,7 +82,7 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
return PCIBIOS_DEVICE_NOT_FOUND;
if (returnval == EEH_IO_ERROR_VALUE(size) &&
- eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node)))
+ eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node), EEH_EVENT_NORMAL))
return PCIBIOS_DEVICE_NOT_FOUND;
return PCIBIOS_SUCCESSFUL;
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 17d86d7..a42b410 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -272,6 +272,7 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
/**
* eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
* @edev: eeh device
+ * @flag: EEH event flag
*
* Check for an EEH failure for the given device node. Call this
* routine if the result of a read was all 0xff's and you want to
@@ -283,7 +284,7 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
*
* It is safe to call this routine in an interrupt context.
*/
-int eeh_dev_check_failure(struct eeh_dev *edev)
+int eeh_dev_check_failure(struct eeh_dev *edev, int flag)
{
int ret;
unsigned long flags;
@@ -376,7 +377,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
- eeh_send_failure_event(pe);
+ eeh_send_failure_event(pe, flag);
/* Most EEH events are due to device driver bugs. Having
* a stack trace will help the device-driver authors figure
@@ -417,7 +418,7 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
return val;
}
- eeh_dev_check_failure(edev);
+ eeh_dev_check_failure(edev, EEH_EVENT_NORMAL);
pci_dev_put(eeh_dev_to_pci_dev(edev));
return val;
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 185bedd..1f86b80 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -114,12 +114,13 @@ static void eeh_thread_launcher(struct work_struct *dummy)
/**
* eeh_send_failure_event - Generate a PCI error event
* @pe: EEH PE
+ * @flag: EEH event flag
*
* This routine can be called within an interrupt context;
* the actual event will be delivered in a normal context
* (from a workqueue).
*/
-int eeh_send_failure_event(struct eeh_pe *pe)
+int eeh_send_failure_event(struct eeh_pe *pe, int flag)
{
unsigned long flags;
struct eeh_event *event;
@@ -129,6 +130,7 @@ int eeh_send_failure_event(struct eeh_pe *pe)
pr_err("EEH: out of memory, event not handled\n");
return -ENOMEM;
}
+ event->flag = flag;
event->pe = pe;
/* We may or may not be called in an interrupt context */
--
1.7.5.4
^ permalink raw reply related
* [PATCH 09/27] powerpc/eeh: Delay EEH probe during hotplug
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
While doing EEH recovery, the PCI devices of the problematic PE
should be removed and then added to the system again. During the
so-called hotplug event, the PCI devices of the problematic PE
will be probed through early/late phase. We would delay EEH probe
on late point for PowerNV platform since the PCI device isn't
available in early phase.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/eeh.c | 16 +++++++++++++++-
1 files changed, 15 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ba707104..17d86d7 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -758,6 +758,14 @@ static void eeh_add_device_early(struct device_node *dn)
{
struct pci_controller *phb;
+ /*
+ * If we're doing EEH probe based on PCI device, we
+ * would delay the probe until late stage because
+ * the PCI device isn't available this moment.
+ */
+ if (!eeh_probe_mode_devtree())
+ return;
+
if (!of_node_to_eeh_dev(dn))
return;
phb = of_node_to_eeh_dev(dn)->phb;
@@ -766,7 +774,6 @@ static void eeh_add_device_early(struct device_node *dn)
if (NULL == phb || 0 == phb->buid)
return;
- /* FIXME: hotplug support on POWERNV */
eeh_ops->of_probe(dn, NULL);
}
@@ -817,6 +824,13 @@ static void eeh_add_device_late(struct pci_dev *dev)
edev->pdev = dev;
dev->dev.archdata.edev = edev;
+ /*
+ * We have to do the EEH probe here because the PCI device
+ * hasn't been created yet in the early stage.
+ */
+ if (eeh_probe_mode_dev())
+ eeh_ops->dev_probe(dev, NULL);
+
eeh_addr_cache_insert_dev(dev);
}
--
1.7.5.4
^ permalink raw reply related
* [PATCH 08/27] powerpc/eeh: Refactor eeh_reset_pe_once()
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
We shouldn't check that the returned PE status is exactly equal to
(EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) but instead only check
that they are both set.
[benh: changelog]
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/eeh.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ef3b02a..ba707104 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -565,6 +565,7 @@ static void eeh_reset_pe_once(struct eeh_pe *pe)
*/
int eeh_reset_pe(struct eeh_pe *pe)
{
+ int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
int i, rc;
/* Take three shots at resetting the bus */
@@ -572,7 +573,7 @@ int eeh_reset_pe(struct eeh_pe *pe)
eeh_reset_pe_once(pe);
rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
- if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
+ if ((rc & flags) == flags)
return 0;
if (rc < 0) {
--
1.7.5.4
^ permalink raw reply related
* [PATCH 06/27] powerpc/eeh: Make eeh_init() public
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
For EEH on PowerNV platform, we will do EEH probe based on the
real PCI devices. The PCI devices are available after PCI probe.
So we have to call eeh_init() explicitly on PowerNV platform
after PCI probe. The patch also does EEH probe for PowerNV platform
in eeh_init().
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 8 +++++++-
arch/powerpc/platforms/pseries/eeh.c | 22 ++++++++++++++++++++--
2 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 8ba1c39..72611fa 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -132,7 +132,7 @@ struct eeh_ops {
char *name;
int (*init)(void);
void* (*of_probe)(struct device_node *dn, void *flag);
- void* (*dev_probe)(struct pci_dev *dev, void *flag);
+ int (*dev_probe)(struct pci_dev *dev, void *flag);
int (*set_option)(struct eeh_pe *pe, int option);
int (*get_pe_addr)(struct eeh_pe *pe);
int (*get_state)(struct eeh_pe *pe, int *state);
@@ -196,6 +196,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
void *eeh_dev_init(struct device_node *dn, void *data);
void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
+int __init eeh_init(void);
int __init eeh_ops_register(struct eeh_ops *ops);
int __exit eeh_ops_unregister(const char *name);
unsigned long eeh_check_failure(const volatile void __iomem *token,
@@ -224,6 +225,11 @@ void eeh_remove_bus_device(struct pci_dev *, int);
#else /* !CONFIG_EEH */
+static inline int eeh_init(void)
+{
+ return 0;
+}
+
static inline void *eeh_dev_init(struct device_node *dn, void *data)
{
return NULL;
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 6b73d6c..dbc9d83 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -674,11 +674,21 @@ int __exit eeh_ops_unregister(const char *name)
* Even if force-off is set, the EEH hardware is still enabled, so that
* newer systems can boot.
*/
-static int __init eeh_init(void)
+int __init eeh_init(void)
{
struct pci_controller *hose, *tmp;
struct device_node *phb;
- int ret;
+ static int cnt = 0;
+ int ret = 0;
+
+ /*
+ * We have to delay the initialization on PowerNV after
+ * the PCI hierarchy tree has been built because the PEs
+ * are figured out based on PCI devices instead of device
+ * tree nodes
+ */
+ if (machine_is(powernv) && cnt++ <= 0)
+ return ret;
/* call platform initialization function */
if (!eeh_ops) {
@@ -700,6 +710,14 @@ static int __init eeh_init(void)
phb = hose->dn;
traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
}
+ } else if (eeh_probe_mode_dev()) {
+ list_for_each_entry_safe(hose, tmp,
+ &hose_list, list_node)
+ pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
+ } else {
+ pr_warning("%s: Invalid probe mode %d\n",
+ __func__, eeh_probe_mode);
+ return -EINVAL;
}
if (eeh_subsystem_enabled)
--
1.7.5.4
^ permalink raw reply related
* [PATCH 04/27] powerpc/eeh: Make eeh_pe_get() public
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
While processing EEH event interrupt from P7IOC, we need function
to retrieve the PE according to the indicated EEH device. The patch
makes function eeh_pe_get() public so that other source files can call
it for that purpose. Also, the patch fixes referring to wrong BDF
(Bus/Device/Function) address while searching PE in function
__eeh_pe_get().
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 1 +
arch/powerpc/platforms/pseries/eeh_pe.c | 4 ++--
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 4ac6f70..acdfcaa 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -185,6 +185,7 @@ static inline void eeh_unlock(void)
typedef void *(*eeh_traverse_func)(void *data, void *flag);
int eeh_phb_pe_create(struct pci_controller *phb);
struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
int eeh_add_to_parent_pe(struct eeh_dev *edev);
int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
void *eeh_pe_dev_traverse(struct eeh_pe *root,
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index 71c4544..3d2dcf5 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -228,7 +228,7 @@ static void *__eeh_pe_get(void *data, void *flag)
return pe;
/* Try BDF address */
- if (edev->pe_config_addr &&
+ if (edev->config_addr &&
(edev->config_addr == pe->config_addr))
return pe;
@@ -246,7 +246,7 @@ static void *__eeh_pe_get(void *data, void *flag)
* which is composed of PCI bus/device/function number, or unified
* PE address.
*/
-static struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
{
struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
struct eeh_pe *pe;
--
1.7.5.4
^ permalink raw reply related
* [PATCH 05/27] powerpc/eeh: Trace PCI bus from PE
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
There're several types of PEs can be supported for now: PHB, Bus
and Device dependent PE. For PCI bus dependent PE, tracing the
corresponding PCI bus from PE (struct eeh_pe) would make the code
more efficient. The patch also enables the retrieval of PCI bus based
on the PCI bus dependent PE.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 1 +
arch/powerpc/platforms/pseries/eeh_pe.c | 22 ++++++++++++++++++++++
2 files changed, 23 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index acdfcaa..8ba1c39 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -62,6 +62,7 @@ struct eeh_pe {
int check_count; /* Times of ignored error */
int freeze_count; /* Times of froze up */
int false_positives; /* Times of reported #ff's */
+ struct pci_bus *bus; /* Top PCI bus for bus PE */
struct eeh_pe *parent; /* Parent PE */
struct list_head child_list; /* Link PE to the child list */
struct list_head edevs; /* Link list of EEH devices */
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index 3d2dcf5..03f8223 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -304,6 +304,7 @@ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
int eeh_add_to_parent_pe(struct eeh_dev *edev)
{
struct eeh_pe *pe, *parent;
+ struct eeh_dev *first_edev;
eeh_lock();
@@ -326,6 +327,21 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
pe->type = EEH_PE_BUS;
edev->pe = pe;
+ /*
+ * For PCI bus sensitive PE, we can reset the parent
+ * bridge in order for hot-reset. However, the PCI
+ * devices including the associated EEH devices might
+ * be removed when EEH core is doing recovery. So that
+ * won't safe to retrieve the bridge through downstream
+ * EEH device. We have to trace the parent PCI bus, then
+ * the parent bridge explicitly.
+ */
+ if (eeh_probe_mode_dev() && !pe->bus) {
+ first_edev = list_first_entry(&pe->edevs,
+ struct eeh_dev, list);
+ pe->bus = eeh_dev_to_pci_dev(first_edev)->bus;
+ }
+
/* Put the edev to PE */
list_add_tail(&edev->list, &pe->edevs);
eeh_unlock();
@@ -641,12 +657,18 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
bus = pe->phb->bus;
} else if (pe->type & EEH_PE_BUS ||
pe->type & EEH_PE_DEVICE) {
+ if (pe->bus) {
+ bus = pe->bus;
+ goto out;
+ }
+
edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
pdev = eeh_dev_to_pci_dev(edev);
if (pdev)
bus = pdev->bus;
}
+out:
eeh_unlock();
return bus;
--
1.7.5.4
^ permalink raw reply related
* [PATCH 01/27] powerpc/eeh: Fix fetching bus for single-dev-PE
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Steve Best, Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
While running Linux as guest on top of phyp, we possiblly have
PE that includes single PCI device. However, we didn't return
its PCI bus correctly and it leads to failure on recovery from
EEH errors for single-dev-PE. The patch fixes the issue.
Cc: <stable@vger.kernel.org> # v3.7+
Cc: Steve Best <sbest@us.ibm.com>
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/eeh_pe.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index fe43d1a..9d4a9e8 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -639,7 +639,8 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
if (pe->type & EEH_PE_PHB) {
bus = pe->phb->bus;
- } else if (pe->type & EEH_PE_BUS) {
+ } else if (pe->type & EEH_PE_BUS ||
+ pe->type & EEH_PE_DEVICE) {
edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
pdev = eeh_dev_to_pci_dev(edev);
if (pdev)
--
1.7.5.4
^ permalink raw reply related
* [PATCH 02/27] powerpc/eeh: Enhance converting EEH dev
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
Under some special circumstances, the EEH device doesn't have the
associated device tree node or PCI device. The patch enhances those
functions converting EEH device to device tree node or PCI device
accordingly to avoid unnecessary system crash.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a80e32b4..e32c3c5 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -95,12 +95,12 @@ struct eeh_dev {
static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
{
- return edev->dn;
+ return edev ? edev->dn : NULL;
}
static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
{
- return edev->pdev;
+ return edev ? edev->pdev : NULL;
}
/*
--
1.7.5.4
^ permalink raw reply related
* [PATCH 03/27] powerpc/eeh: Make eeh_phb_pe_get() public
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
In-Reply-To: <1370417668-16832-1-git-send-email-shangw@linux.vnet.ibm.com>
One of the possible cases indicated by P7IOC interrupt is fenced
PHB. For that case, we need fetch the PE corresponding to the PHB
and disable the PHB and all subordinate PCI buses/devices, recover
from the fenced state and eventually enable the whole PHB. We need
one function to fetch the PHB PE outside eeh_pe.c and the patch is
going to make eeh_phb_pe_get() public for that purpose.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/eeh.h | 1 +
arch/powerpc/platforms/pseries/eeh_pe.c | 2 +-
2 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index e32c3c5..4ac6f70 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -184,6 +184,7 @@ static inline void eeh_unlock(void)
typedef void *(*eeh_traverse_func)(void *data, void *flag);
int eeh_phb_pe_create(struct pci_controller *phb);
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
int eeh_add_to_parent_pe(struct eeh_dev *edev);
int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
void *eeh_pe_dev_traverse(struct eeh_pe *root,
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index 9d4a9e8..71c4544 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -95,7 +95,7 @@ int eeh_phb_pe_create(struct pci_controller *phb)
* hierarchy tree is composed of PHB PEs. The function is used
* to retrieve the corresponding PHB PE according to the given PHB.
*/
-static struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
{
struct eeh_pe *pe;
--
1.7.5.4
^ permalink raw reply related
* [PATCH v3 00/27] EEH Support for PowerNV platform
From: Gavin Shan @ 2013-06-05 7:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Gavin Shan
Initially, the series of patches is built based on 3.10.RC1 and the patchset
doesn't intend to enable EEH functionality for PHB3 for now. Obviously, PHB3
EEH support on PowerNV platform is something to do in future.
The series of patches intends to support EEH for PowerNV platform. The EEH
core already supports multiple probe methods: device tree nodes and PCI
devices. For EEH on PowerNV, we're using PCI devices to do EEH probe, which
is different from the probe type used on pSeries platform. Another point I
should mention is that the overall EEH would be split up to 3 layers: EEH
core, platform layer and I/O chip layer. It would make the EEH on PowerNV
platform can achieve more flexibility and support more I/O chips in future.
Besides, the EEH event can be produced by detecting 0xFF's from reading
PCI config or I/O registers, or from interrupts dedicated for EEH error
reporting. So we have to handle the EEH error interrupts. On the other hand,
the EEH events will be processed by EEH core like pSeries platform does.
We will have exported debugfs entries ("/sys/kernel/debug/powerpc/PCIxxxx/err_injct"),
which allows you to control the 0xD10 register in order to force errors like
frozen PE and fenced PHB for testing purpose. The following example is usualy
what I'm using to control that register. The patchset has been verified on
Firebird-L machine where I have 2 Emulex ethernet card on PHB#0. I keep pinging
to one of the ethernet cards (eth0) from external and then use following commands
to produce frozen PE or fenced PHB errors. Eventually, the errors can be recovered
and the ethernet card is reachable after temporary connection lost.
Trigger frozen PE:
echo 0x0000000002000000 > /sys/kernel/debug/powerpc/PCI0000/err_injct
sleep 1
echo 0x0 > /sys/kernel/debug/powerpc/PCI0000/err_injct
Trigger fenced PHB:
echo 0x8000000000000000 > /sys/kernel/debug/powerpc/PCI0000/err_injct
Change log
==========
v2 -> v3:
* Rebase to 3.10.RC4
* Replace eeh_pci_dev_traverse() with pci_walk_bus()
* Changlog adjustment to make that more clear
* To call msleep() if possible after opal_pci_poll()
* Make sure we have OPALv3
* OPAL notifier so that we can register callback for the monitored events.
The OPAL notifier is disabled while restarting or powering off the system.
* Make the debugfs entries something like (PCIxxxx/err_injct)
* Split the patch so that can be backported to stable kernel
* Allow to detect fenced PHB proactively (without interrupt)
* Start to use opal_pci_get_phb_diag_data2()
* Stack dump upon fenced PHB
v1 -> v2:
* Rebase to 3.10.RC3
* Don't fetch PE state for the case of fenced PHB. It usually takes long
time and possiblly incurs softlock warning. It requires the corresponding
changes for the underly firmware
* Add debugfs entries so that we can inject errors like frozen PE and
fenced PHB for testing purpose
---
arch/powerpc/include/asm/eeh.h | 26 +-
arch/powerpc/include/asm/eeh_event.h | 6 +-
arch/powerpc/include/asm/opal.h | 138 +++++-
arch/powerpc/kernel/rtas_pci.c | 3 +-
arch/powerpc/platforms/powernv/Makefile | 1 +
arch/powerpc/platforms/powernv/eeh-ioda.c | 550 ++++++++++++++++++++++++
arch/powerpc/platforms/powernv/eeh-powernv.c | 387 +++++++++++++++++
arch/powerpc/platforms/powernv/opal-wrappers.S | 3 +
arch/powerpc/platforms/powernv/opal.c | 79 ++++-
arch/powerpc/platforms/powernv/pci-err.c | 481 +++++++++++++++++++++
arch/powerpc/platforms/powernv/pci-ioda.c | 38 ++-
arch/powerpc/platforms/powernv/pci-p5ioc2.c | 6 +-
arch/powerpc/platforms/powernv/pci.c | 44 ++-
arch/powerpc/platforms/powernv/pci.h | 26 ++
arch/powerpc/platforms/powernv/setup.c | 4 +
arch/powerpc/platforms/pseries/eeh.c | 120 +++++-
arch/powerpc/platforms/pseries/eeh_event.c | 12 +-
arch/powerpc/platforms/pseries/eeh_pe.c | 31 ++-
18 files changed, 1907 insertions(+), 48 deletions(-)
create mode 100644 arch/powerpc/platforms/powernv/eeh-ioda.c
create mode 100644 arch/powerpc/platforms/powernv/eeh-powernv.c
create mode 100644 arch/powerpc/platforms/powernv/pci-err.c
Thanks,
Gavin
^ permalink raw reply
* RE: [RFC PATCH 2/6] KVM: PPC: Book3E: Refactor SPE_FP exit handling
From: Caraman Mihai Claudiu-B02008 @ 2013-06-05 7:29 UTC (permalink / raw)
To: Wood Scott-B07421
Cc: linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org,
kvm-ppc@vger.kernel.org
In-Reply-To: <1370384088.748.17@snotra>
> > + /*
> > + * The interrupt is shared, KVM support for the
> > featured unit
> > + * is detected at run-time.
> > + */
>=20
> This is a decent comment for the changelog, but for the code itself it
> seems fairly obvious if you look at the definition of
> kvmppc_supports_spe().
I will move it to change log.
>=20
> > + bool handled =3D false;
> > +
> > + if (kvmppc_supports_spe()) {
> > +#ifdef CONFIG_SPE
> > + if (cpu_has_feature(CPU_FTR_SPE))
>=20
> Didn't you already check this using kvmppc_supports_spe()?
It makes sense with the next patch. It handles the improbable case of havin=
g
CONFIG_ALTIVEC and CONFIG_SPE defined:
if (kvmppc_supports_altivec() || kvmppc_supports_spe()).
>=20
> > case BOOKE_INTERRUPT_SPE_FP_ROUND:
> > +#ifdef CONFIG_SPE
> > kvmppc_booke_queue_irqprio(vcpu,
> > BOOKE_IRQPRIO_SPE_FP_ROUND);
> > r =3D RESUME_GUEST;
> > break;
>=20
> Why not use kvmppc_supports_spe() here, for consistency?
I added cpu_has_feature(CPU_FTR_SPE) for the case specified above, but here
SPE_FP_ROUND is not shared with ALTIVEC. CONFIG_SPE is used in other places
in KVM without this check, shouldn't be all or nothing?
-Mike
^ permalink raw reply
* Re: powerpc/tm: Fix 32bit non-rt signal return
From: Michael Neuling @ 2013-06-05 7:25 UTC (permalink / raw)
To: benh, Linux PPC dev, matt
In-Reply-To: <17963.1370256973@ale.ozlabs.ibm.com>
benh,
Hold off on taking this for now... I'm seeing a crash with it on power7.
Mikey
Michael Neuling <mikey@neuling.org> wrote:
> Currently sys_sigreturn() is transactional memory unaware, hence if we take a
> 32 bit signal without SIGINFO (non RT) inside a transaction, we don't restore
> the signal frame correctly on return.
>
> This checks if the signal frame being restoring is an active transaction, and
> if so, it copies the additional state to the ptregs so it can be restored.
>
> Signed-off-by: Michael Neuling <mikey@neuling.org>
> cc: <stable@vger.kernel.org> # 3.9 only
>
> diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
> index 201385c..0bc961b 100644
> --- a/arch/powerpc/kernel/signal_32.c
> +++ b/arch/powerpc/kernel/signal_32.c
> @@ -1481,16 +1481,22 @@ badframe:
> long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
> struct pt_regs *regs)
> {
> + struct sigframe __user *sf;
> struct sigcontext __user *sc;
> struct sigcontext sigctx;
> struct mcontext __user *sr;
> void __user *addr;
> sigset_t set;
> +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
> + struct mcontext __user *mcp, *tm_mcp;
> + unsigned long msr_hi;
> +#endif
>
> /* Always make any pending restarted system calls return -EINTR */
> current_thread_info()->restart_block.fn = do_no_restart_syscall;
>
> - sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
> + sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
> + sc = &sf->sctx;
> addr = sc;
> if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
> goto badframe;
> @@ -1507,12 +1513,23 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
> #endif
> set_current_blocked(&set);
>
> - sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
> - addr = sr;
> - if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
> - || restore_user_regs(regs, sr, 1))
> +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
> + mcp = (struct mcontext __user *)&sf->mctx;
> + tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
> + if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
> goto badframe;
> -
> + if MSR_TM_ACTIVE(msr_hi<<32) {
> + if (restore_tm_user_regs(regs, mcp, tm_mcp))
> + goto badframe;
> + } else
> +#endif
> + {
> + sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
> + addr = sr;
> + if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
> + || restore_user_regs(regs, sr, 1))
> + goto badframe;
> + }
> set_thread_flag(TIF_RESTOREALL);
> return 0;
>
>
^ permalink raw reply
* RE: [RFC PATCH 0/6] KVM: PPC: Book3E: AltiVec support
From: Caraman Mihai Claudiu-B02008 @ 2013-06-05 7:10 UTC (permalink / raw)
To: Wood Scott-B07421
Cc: linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org,
kvm-ppc@vger.kernel.org, Alexander Graf
In-Reply-To: <1370381959.748.16@snotra>
> -----Original Message-----
> From: Wood Scott-B07421
> Sent: Wednesday, June 05, 2013 12:39 AM
> To: Caraman Mihai Claudiu-B02008
> Cc: kvm-ppc@vger.kernel.org; kvm@vger.kernel.org; linuxppc-
> dev@lists.ozlabs.org; Alexander Graf
> Subject: Re: [RFC PATCH 0/6] KVM: PPC: Book3E: AltiVec support
>=20
> On 06/03/2013 03:54:22 PM, Mihai Caraman wrote:
> > Mihai Caraman (6):
> > KVM: PPC: Book3E: Fix AltiVec interrupt numbers and build breakage
> > KVM: PPC: Book3E: Refactor SPE_FP exit handling
> > KVM: PPC: Book3E: Rename IRQPRIO names to accommodate ALTIVEC
> > KVM: PPC: Book3E: Add AltiVec support
> > KVM: PPC: Book3E: Add ONE_REG AltiVec support
> > KVM: PPC: Book3E: Enhance FPU laziness
> >
> > arch/powerpc/include/asm/kvm_asm.h | 16 ++-
> > arch/powerpc/kvm/booke.c | 189
> > ++++++++++++++++++++++++++++----
> > arch/powerpc/kvm/booke.h | 4 +-
> > arch/powerpc/kvm/bookehv_interrupts.S | 8 +-
> > arch/powerpc/kvm/e500.c | 10 +-
> > arch/powerpc/kvm/e500_emulate.c | 8 +-
> > arch/powerpc/kvm/e500mc.c | 10 ++-
> > 7 files changed, 199 insertions(+), 46 deletions(-)
>=20
> This looks like a bit much for 3.10 (certainly, subject lines like
> "refactor" and "enhance" and "add support" aren't going to make Linus
> happy given that we're past rc4) so I think we should apply
> http://patchwork.ozlabs.org/patch/242896/ for 3.10. Then for 3.11,
> revert it after applying this patchset.
>=20
Why not 1/6 plus e6500 removal?
-Mike
^ permalink raw reply
* [PATCH 4/4] KVM: PPC: Add hugepage support for IOMMU in-kernel handling
From: Alexey Kardashevskiy @ 2013-06-05 6:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: kvm, Alexey Kardashevskiy, Alexander Graf, kvm-ppc, linux-kernel,
Paul Mackerras, linuxppc-dev, David Gibson
In-Reply-To: <1370412673-1345-1-git-send-email-aik@ozlabs.ru>
This adds special support for huge pages (16MB). The reference
counting cannot be easily done for such pages in real mode (when
MMU is off) so we added a list of huge pages. It is populated in
virtual mode and get_page is called just once per a huge page.
Real mode handlers check if the requested page is huge and in the list,
then no reference counting is done, otherwise an exit to virtual mode
happens. The list is released at KVM exit. At the moment the fastest
card available for tests uses up to 9 huge pages so walking through this
list is not very expensive. However this can change and we may want
to optimize this.
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Changes:
2013/06/05:
* fixed compile error when CONFIG_IOMMU_API=n
2013/05/20:
* the real mode handler now searches for a huge page by gpa (used to be pte)
* the virtual mode handler prints warning if it is called twice for the same
huge page as the real mode handler is expected to fail just once - when a huge
page is not in the list yet.
* the huge page is refcounted twice - when added to the hugepage list and
when used in the virtual mode hcall handler (can be optimized but it will
make the patch less nice).
---
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/include/asm/kvm_ppc.h | 22 +++++++++
arch/powerpc/kvm/book3s_64_vio.c | 88 +++++++++++++++++++++++++++++++++--
arch/powerpc/kvm/book3s_64_vio_hv.c | 40 ++++++++++++++--
4 files changed, 146 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ac0e2fe..4fc0865 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -181,6 +181,8 @@ struct kvmppc_spapr_tce_table {
u64 liobn;
u32 window_size;
struct iommu_group *grp; /* used for IOMMU groups */
+ struct list_head hugepages; /* used for IOMMU groups */
+ spinlock_t hugepages_lock; /* used for IOMMU groups */
struct page *pages[0];
};
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 934e01d..9054df0 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -149,6 +149,28 @@ extern long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
extern long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
unsigned long liobn, unsigned long ioba,
unsigned long tce_value, unsigned long npages);
+
+/*
+ * The KVM guest can be backed with 16MB pages (qemu switch
+ * -mem-path /var/lib/hugetlbfs/global/pagesize-16MB/).
+ * In this case, we cannot do page counting from the real mode
+ * as the compound pages are used - they are linked in a list
+ * with pointers as virtual addresses which are inaccessible
+ * in real mode.
+ *
+ * The code below keeps a 16MB pages list and uses page struct
+ * in real mode if it is already locked in RAM and inserted into
+ * the list or switches to the virtual mode where it can be
+ * handled in a usual manner.
+ */
+struct kvmppc_iommu_hugepage {
+ struct list_head list;
+ pte_t pte; /* Huge page PTE */
+ unsigned long gpa; /* Guest physical address */
+ struct page *page; /* page struct of the very first subpage */
+ unsigned long size; /* Huge page size (always 16MB at the moment) */
+};
+
extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
struct kvm_allocate_rma *rma);
extern struct kvmppc_linear_info *kvm_alloc_rma(void);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index ffb4698..9e2ba4d 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -45,6 +45,71 @@
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
#define ERROR_ADDR ((void *)~(unsigned long)0x0)
+#ifdef CONFIG_IOMMU_API
+/* Adds a new huge page descriptor to the list */
+static long kvmppc_iommu_hugepage_try_add(
+ struct kvmppc_spapr_tce_table *tt,
+ pte_t pte, unsigned long hva, unsigned long gpa,
+ unsigned long pg_size)
+{
+ long ret = 0;
+ struct kvmppc_iommu_hugepage *hp;
+ struct page *p;
+
+ spin_lock(&tt->hugepages_lock);
+ list_for_each_entry(hp, &tt->hugepages, list) {
+ if (hp->pte == pte)
+ goto unlock_exit;
+ }
+
+ hva = hva & ~(pg_size - 1);
+ ret = get_user_pages_fast(hva, 1, true/*write*/, &p);
+ if ((ret != 1) || !p) {
+ ret = -EFAULT;
+ goto unlock_exit;
+ }
+ ret = 0;
+
+ hp = kzalloc(sizeof(*hp), GFP_KERNEL);
+ if (!hp) {
+ ret = -ENOMEM;
+ goto unlock_exit;
+ }
+
+ hp->page = p;
+ hp->pte = pte;
+ hp->gpa = gpa & ~(pg_size - 1);
+ hp->size = pg_size;
+
+ list_add(&hp->list, &tt->hugepages);
+
+unlock_exit:
+ spin_unlock(&tt->hugepages_lock);
+
+ return ret;
+}
+
+static void kvmppc_iommu_hugepages_init(struct kvmppc_spapr_tce_table *tt)
+{
+ INIT_LIST_HEAD(&tt->hugepages);
+ spin_lock_init(&tt->hugepages_lock);
+}
+
+static void kvmppc_iommu_hugepages_cleanup(struct kvmppc_spapr_tce_table *tt)
+{
+ struct kvmppc_iommu_hugepage *hp, *tmp;
+
+ spin_lock(&tt->hugepages_lock);
+ list_for_each_entry_safe(hp, tmp, &tt->hugepages, list) {
+ list_del(&hp->list);
+ put_page(hp->page); /* one for iommu_put_tce_user_mode */
+ put_page(hp->page); /* one for kvmppc_iommu_hugepage_try_add */
+ kfree(hp);
+ }
+ spin_unlock(&tt->hugepages_lock);
+}
+#endif /* CONFIG_IOMMU_API */
+
static long kvmppc_stt_npages(unsigned long window_size)
{
return ALIGN((window_size >> SPAPR_TCE_SHIFT)
@@ -61,6 +126,7 @@ static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
#ifdef CONFIG_IOMMU_API
if (stt->grp) {
iommu_group_put(stt->grp);
+ kvmppc_iommu_hugepages_cleanup(stt);
} else
#endif
for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
@@ -198,6 +264,7 @@ long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
kvm_get_kvm(kvm);
mutex_lock(&kvm->lock);
+ kvmppc_iommu_hugepages_init(tt);
list_add(&tt->list, &kvm->arch.spapr_tce_tables);
mutex_unlock(&kvm->lock);
@@ -218,16 +285,31 @@ long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
/* Converts guest physical address into host virtual */
static void __user *kvmppc_virtmode_gpa_to_hva(struct kvm_vcpu *vcpu,
+ struct kvmppc_spapr_tce_table *tt,
unsigned long gpa)
{
unsigned long hva, gfn = gpa >> PAGE_SHIFT;
struct kvm_memory_slot *memslot;
+ pte_t *ptep;
+ unsigned int shift = 0;
memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
if (!memslot)
return ERROR_ADDR;
hva = __gfn_to_hva_memslot(memslot, gfn) + (gpa & ~PAGE_MASK);
+
+ ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+ WARN_ON(!ptep);
+ if (!ptep)
+ return ERROR_ADDR;
+#ifdef CONFIG_IOMMU_API
+ if (tt && (shift > PAGE_SHIFT)) {
+ if (kvmppc_iommu_hugepage_try_add(tt, *ptep,
+ hva, gpa, 1 << shift))
+ return ERROR_ADDR;
+ }
+#endif
return (void *) hva;
}
@@ -267,7 +349,7 @@ long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
if (iommu_tce_put_param_check(tbl, ioba, tce))
return H_PARAMETER;
- hva = kvmppc_virtmode_gpa_to_hva(vcpu, tce);
+ hva = kvmppc_virtmode_gpa_to_hva(vcpu, tt, tce);
if (hva == ERROR_ADDR)
return H_HARDWARE;
@@ -319,7 +401,7 @@ long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (tce_list & ~IOMMU_PAGE_MASK)
return H_PARAMETER;
- tces = kvmppc_virtmode_gpa_to_hva(vcpu, tce_list);
+ tces = kvmppc_virtmode_gpa_to_hva(vcpu, NULL, tce_list);
if (tces == ERROR_ADDR)
return H_TOO_HARD;
@@ -354,7 +436,7 @@ long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
/* Translate TCEs */
for (i = vcpu->arch.tce_tmp_num; i < npages; ++i) {
- void *hva = kvmppc_virtmode_gpa_to_hva(vcpu,
+ void *hva = kvmppc_virtmode_gpa_to_hva(vcpu, tt,
vcpu->arch.tce_tmp[i]);
if (hva == ERROR_ADDR)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index dc4ae32..6245365 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -178,6 +178,7 @@ static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
* Also returns pte and page size if the page is present in page table.
*/
static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
+ struct kvmppc_spapr_tce_table *tt,
unsigned long gpa, bool do_get_page)
{
struct kvm_memory_slot *memslot;
@@ -185,7 +186,31 @@ static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
unsigned long hva, hpa, pg_size = 0, offset;
unsigned long gfn = gpa >> PAGE_SHIFT;
bool writing = gpa & TCE_PCI_WRITE;
+ struct kvmppc_iommu_hugepage *hp;
+ /*
+ * Try to find an already used hugepage.
+ * If it is not there, the kvmppc_lookup_pte() will return zero
+ * as it won't do get_page() on a huge page in real mode
+ * and therefore the request will be passed to the virtual mode.
+ */
+ if (tt) {
+ spin_lock(&tt->hugepages_lock);
+ list_for_each_entry(hp, &tt->hugepages, list) {
+ if ((gpa < hp->gpa) || (gpa >= hp->gpa + hp->size))
+ continue;
+
+ /* Calculate host phys address keeping flags and offset in the page */
+ offset = gpa & (hp->size - 1);
+
+ /* pte_pfn(pte) should return an address aligned to pg_size */
+ hpa = (pte_pfn(hp->pte) << PAGE_SHIFT) + offset;
+ spin_unlock(&tt->hugepages_lock);
+
+ return hpa;
+ }
+ spin_unlock(&tt->hugepages_lock);
+ }
/* Find a KVM memslot */
memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
if (!memslot)
@@ -237,6 +262,10 @@ static long kvmppc_clear_tce_real_mode(struct kvm_vcpu *vcpu,
if (oldtce & TCE_PCI_WRITE)
SetPageDirty(page);
+ /* Do not put a huge page and continue without error */
+ if (PageCompound(page))
+ continue;
+
if (realmode_put_page(page)) {
ret = H_TOO_HARD;
break;
@@ -282,7 +311,7 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (iommu_tce_put_param_check(tbl, ioba, tce))
return H_PARAMETER;
- hpa = kvmppc_realmode_gpa_to_hpa(vcpu, tce, true);
+ hpa = kvmppc_realmode_gpa_to_hpa(vcpu, tt, tce, true);
if (hpa == ERROR_ADDR) {
vcpu->arch.tce_reason = H_TOO_HARD;
return H_TOO_HARD;
@@ -295,6 +324,11 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (unlikely(ret)) {
struct page *pg = realmode_pfn_to_page(hpa);
BUG_ON(!pg);
+
+ /* Do not put a huge page and return an error */
+ if (!PageCompound(pg))
+ return H_HARDWARE;
+
if (realmode_put_page(pg)) {
vcpu->arch.tce_reason = H_HARDWARE;
return H_TOO_HARD;
@@ -351,7 +385,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
vcpu->arch.tce_tmp_num = 0;
vcpu->arch.tce_reason = 0;
- tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu,
+ tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu, NULL,
tce_list, false);
if ((unsigned long)tces == ERROR_ADDR)
return H_TOO_HARD;
@@ -374,7 +408,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
/* Translate TCEs and go get_page */
for (i = 0; i < npages; ++i) {
- unsigned long hpa = kvmppc_realmode_gpa_to_hpa(vcpu,
+ unsigned long hpa = kvmppc_realmode_gpa_to_hpa(vcpu, tt,
vcpu->arch.tce_tmp[i], true);
if (hpa == ERROR_ADDR) {
vcpu->arch.tce_tmp_num = i;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 3/4] KVM: PPC: Add support for IOMMU in-kernel handling
From: Alexey Kardashevskiy @ 2013-06-05 6:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: kvm, Alexey Kardashevskiy, Alexander Graf, kvm-ppc, linux-kernel,
Paul Mackerras, linuxppc-dev, David Gibson
In-Reply-To: <1370412673-1345-1-git-send-email-aik@ozlabs.ru>
This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
and H_STUFF_TCE requests without passing them to QEMU, which should
save time on switching to QEMU and back.
Both real and virtual modes are supported - whenever the kernel
fails to handle TCE request, it passes it to the virtual mode.
If it the virtual mode handlers fail, then the request is passed
to the user mode, for example, to QEMU.
This adds a new KVM_CAP_SPAPR_TCE_IOMMU ioctl to asssociate
a virtual PCI bus ID (LIOBN) with an IOMMU group, which enables
in-kernel handling of IOMMU map/unmap.
Tests show that this patch increases transmission speed from 220MB/s
to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Changes:
2013/06/05:
* changed capability number
* changed ioctl number
* update the doc article number
2013/05/20:
* removed get_user() from real mode handlers
* kvm_vcpu_arch::tce_tmp usage extended. Now real mode handler puts there
translated TCEs, tries realmode_get_page() on those and if it fails, it
passes control over the virtual mode handler which tries to finish
the request handling
* kvmppc_lookup_pte() now does realmode_get_page() protected by BUSY bit
on a page
* The only reason to pass the request to user mode now is when the user mode
did not register TCE table in the kernel, in all other cases the virtual mode
handler is expected to do the job
---
Documentation/virtual/kvm/api.txt | 28 +++++
arch/powerpc/include/asm/kvm_host.h | 3 +
arch/powerpc/include/asm/kvm_ppc.h | 2 +
arch/powerpc/include/uapi/asm/kvm.h | 7 ++
arch/powerpc/kvm/book3s_64_vio.c | 198 ++++++++++++++++++++++++++++++++++-
arch/powerpc/kvm/book3s_64_vio_hv.c | 193 +++++++++++++++++++++++++++++++++-
arch/powerpc/kvm/powerpc.c | 12 +++
include/uapi/linux/kvm.h | 2 +
8 files changed, 439 insertions(+), 6 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6c082ff..e962e3b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2379,6 +2379,34 @@ the guest. Othwerwise it might be better for the guest to continue using H_PUT_T
hypercall (if KVM_CAP_SPAPR_TCE or KVM_CAP_SPAPR_TCE_IOMMU are present).
+4.84 KVM_CREATE_SPAPR_TCE_IOMMU
+
+Capability: KVM_CAP_SPAPR_TCE_IOMMU
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce_iommu (in)
+Returns: 0 on success, -1 on error
+
+This creates a link between IOMMU group and a hardware TCE (translation
+control entry) table. This link lets the host kernel know what IOMMU
+group (i.e. TCE table) to use for the LIOBN number passed with
+H_PUT_TCE, H_PUT_TCE_INDIRECT, H_STUFF_TCE hypercalls.
+
+/* for KVM_CAP_SPAPR_TCE_IOMMU */
+struct kvm_create_spapr_tce_iommu {
+ __u64 liobn;
+ __u32 iommu_id;
+ __u32 flags;
+};
+
+No flag is supported at the moment.
+
+When the guest issues TCE call on a liobn for which a TCE table has been
+registered, the kernel will handle it in real mode, updating the hardware
+TCE table. TCE table calls for other liobns will cause a vm exit and must
+be handled by userspace.
+
+
5. The kvm_run structure
------------------------
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 85d8f26..ac0e2fe 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -180,6 +180,7 @@ struct kvmppc_spapr_tce_table {
struct kvm *kvm;
u64 liobn;
u32 window_size;
+ struct iommu_group *grp; /* used for IOMMU groups */
struct page *pages[0];
};
@@ -611,6 +612,8 @@ struct kvm_vcpu_arch {
u64 busy_preempt;
unsigned long *tce_tmp; /* TCE cache for TCE_PUT_INDIRECT hall */
+ unsigned long tce_tmp_num; /* Number of handled TCEs in the cache */
+ unsigned long tce_reason; /* The reason of switching to the virtmode */
#endif
};
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index e852921b..934e01d 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -133,6 +133,8 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce *args);
+extern long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+ struct kvm_create_spapr_tce_iommu *args);
extern struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(
struct kvm_vcpu *vcpu, unsigned long liobn);
extern long kvmppc_emulated_validate_tce(unsigned long tce);
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1a6e..cf82af4 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -319,6 +319,13 @@ struct kvm_create_spapr_tce {
__u32 window_size;
};
+/* for KVM_CAP_SPAPR_TCE_IOMMU */
+struct kvm_create_spapr_tce_iommu {
+ __u64 liobn;
+ __u32 iommu_id;
+ __u32 flags;
+};
+
/* for KVM_ALLOCATE_RMA */
struct kvm_allocate_rma {
__u64 rma_size;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 06b7b20..ffb4698 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -27,6 +27,8 @@
#include <linux/hugetlb.h>
#include <linux/list.h>
#include <linux/anon_inodes.h>
+#include <linux/pci.h>
+#include <linux/iommu.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -56,8 +58,13 @@ static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
mutex_lock(&kvm->lock);
list_del(&stt->list);
- for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
- __free_page(stt->pages[i]);
+#ifdef CONFIG_IOMMU_API
+ if (stt->grp) {
+ iommu_group_put(stt->grp);
+ } else
+#endif
+ for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+ __free_page(stt->pages[i]);
kfree(stt);
mutex_unlock(&kvm->lock);
@@ -153,6 +160,62 @@ fail:
return ret;
}
+#ifdef CONFIG_IOMMU_API
+static const struct file_operations kvm_spapr_tce_iommu_fops = {
+ .release = kvm_spapr_tce_release,
+};
+
+long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+ struct kvm_create_spapr_tce_iommu *args)
+{
+ struct kvmppc_spapr_tce_table *tt = NULL;
+ struct iommu_group *grp;
+ struct iommu_table *tbl;
+
+ /* Find an IOMMU table for the given ID */
+ grp = iommu_group_get_by_id(args->iommu_id);
+ if (!grp)
+ return -ENXIO;
+
+ tbl = iommu_group_get_iommudata(grp);
+ if (!tbl)
+ return -ENXIO;
+
+ /* Check this LIOBN hasn't been previously allocated */
+ list_for_each_entry(tt, &kvm->arch.spapr_tce_tables, list) {
+ if (tt->liobn == args->liobn)
+ return -EBUSY;
+ }
+
+ tt = kzalloc(sizeof(*tt), GFP_KERNEL);
+ if (!tt)
+ return -ENOMEM;
+
+ tt->liobn = args->liobn;
+ tt->kvm = kvm;
+ tt->grp = grp;
+
+ kvm_get_kvm(kvm);
+
+ mutex_lock(&kvm->lock);
+ list_add(&tt->list, &kvm->arch.spapr_tce_tables);
+
+ mutex_unlock(&kvm->lock);
+
+ pr_debug("LIOBN=%llX hooked to IOMMU %d, flags=%u\n",
+ args->liobn, args->iommu_id, args->flags);
+
+ return anon_inode_getfd("kvm-spapr-tce-iommu",
+ &kvm_spapr_tce_iommu_fops, tt, O_RDWR);
+}
+#else
+long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+ struct kvm_create_spapr_tce_iommu *args)
+{
+ return -ENOSYS;
+}
+#endif /* CONFIG_IOMMU_API */
+
/* Converts guest physical address into host virtual */
static void __user *kvmppc_virtmode_gpa_to_hva(struct kvm_vcpu *vcpu,
unsigned long gpa)
@@ -180,6 +243,46 @@ long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
if (!tt)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ unsigned long entry = ioba >> IOMMU_PAGE_SHIFT;
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ if (vcpu->arch.tce_reason == H_HARDWARE) {
+ iommu_clear_tces_and_put_pages(tbl, entry, 1);
+ return H_HARDWARE;
+
+ } else if (!(tce & (TCE_PCI_READ | TCE_PCI_WRITE))) {
+ if (iommu_tce_clear_param_check(tbl, ioba, 0, 1))
+ return H_PARAMETER;
+
+ ret = iommu_clear_tces_and_put_pages(tbl, entry, 1);
+ } else {
+ void *hva;
+
+ if (iommu_tce_put_param_check(tbl, ioba, tce))
+ return H_PARAMETER;
+
+ hva = kvmppc_virtmode_gpa_to_hva(vcpu, tce);
+ if (hva == ERROR_ADDR)
+ return H_HARDWARE;
+
+ ret = iommu_put_tce_user_mode(tbl,
+ ioba >> IOMMU_PAGE_SHIFT,
+ (unsigned long) hva);
+ }
+ iommu_flush_tce(tbl);
+
+ if (ret)
+ return H_HARDWARE;
+
+ return H_SUCCESS;
+ }
+#endif
/* Emulated IO */
if (ioba >= tt->window_size)
return H_PARAMETER;
@@ -220,6 +323,70 @@ long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (tces == ERROR_ADDR)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ /* Something bad happened, do cleanup and exit */
+ if (vcpu->arch.tce_reason == H_HARDWARE) {
+ i = vcpu->arch.tce_tmp_num;
+ goto fail_clear_tce;
+ } else if (vcpu->arch.tce_reason != H_TOO_HARD) {
+ /*
+ * We get here only in PR KVM mode, otherwise
+ * the real mode handler would have checked TCEs
+ * already and failed on guest TCE translation.
+ */
+ for (i = 0; i < npages; ++i) {
+ if (get_user(vcpu->arch.tce_tmp[i], tces + i))
+ return H_HARDWARE;
+
+ if (iommu_tce_put_param_check(tbl, ioba +
+ (i << IOMMU_PAGE_SHIFT),
+ vcpu->arch.tce_tmp[i]))
+ return H_PARAMETER;
+ }
+ } /* else: The real mode handler checked TCEs already */
+
+ /* Translate TCEs */
+ for (i = vcpu->arch.tce_tmp_num; i < npages; ++i) {
+ void *hva = kvmppc_virtmode_gpa_to_hva(vcpu,
+ vcpu->arch.tce_tmp[i]);
+
+ if (hva == ERROR_ADDR)
+ goto fail_clear_tce;
+
+ vcpu->arch.tce_tmp[i] = (unsigned long) hva;
+ }
+
+ /* Do get_page and put TCEs for all pages */
+ for (i = 0; i < npages; ++i) {
+ if (iommu_put_tce_user_mode(tbl,
+ (ioba >> IOMMU_PAGE_SHIFT) + i,
+ vcpu->arch.tce_tmp[i])) {
+ i = npages;
+ goto fail_clear_tce;
+ }
+ }
+
+ iommu_flush_tce(tbl);
+
+ return H_SUCCESS;
+
+fail_clear_tce:
+ /* Cannot complete the translation, clean up and exit */
+ iommu_clear_tces_and_put_pages(tbl,
+ ioba >> IOMMU_PAGE_SHIFT, i);
+
+ iommu_flush_tce(tbl);
+
+ return H_HARDWARE;
+ }
+#endif
/* Emulated IO */
if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
return H_PARAMETER;
@@ -253,6 +420,33 @@ long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
if (!tt)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+ unsigned long tmp, entry = ioba >> IOMMU_PAGE_SHIFT;
+
+ vcpu->arch.tce_tmp_num = 0;
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ /* PR KVM? */
+ if (!vcpu->arch.tce_tmp_num &&
+ (vcpu->arch.tce_reason != H_TOO_HARD) &&
+ iommu_tce_clear_param_check(tbl, ioba,
+ tce_value, npages))
+ return H_PARAMETER;
+
+ /* Do actual cleanup */
+ tmp = vcpu->arch.tce_tmp_num;
+ if (iommu_clear_tces_and_put_pages(tbl, entry + tmp,
+ npages - tmp))
+ return H_PARAMETER;
+
+ return H_SUCCESS;
+ }
+#endif
/* Emulated IO */
if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
return H_PARAMETER;
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index c68d538..dc4ae32 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/list.h>
+#include <linux/iommu.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -118,7 +119,7 @@ EXPORT_SYMBOL_GPL(kvmppc_emulated_put_tce);
#ifdef CONFIG_KVM_BOOK3S_64_HV
static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
- unsigned long *pte_sizep)
+ unsigned long *pte_sizep, bool do_get_page)
{
pte_t *ptep;
unsigned int shift = 0;
@@ -135,6 +136,14 @@ static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
if (!pte_present(*ptep))
return __pte(0);
+ /*
+ * Put huge pages handling to the virtual mode.
+ * The only exception is for TCE list pages which we
+ * do need to call get_page() for.
+ */
+ if ((*pte_sizep > PAGE_SIZE) && do_get_page)
+ return __pte(0);
+
/* wait until _PAGE_BUSY is clear then set it atomically */
__asm__ __volatile__ (
"1: ldarx %0,0,%3\n"
@@ -148,6 +157,18 @@ static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
: "cc");
ret = pte;
+ if (do_get_page && pte_present(pte) && (!writing || pte_write(pte))) {
+ struct page *pg = NULL;
+ pg = realmode_pfn_to_page(pte_pfn(pte));
+ if (realmode_get_page(pg)) {
+ ret = __pte(0);
+ } else {
+ pte = pte_mkyoung(pte);
+ if (writing)
+ pte = pte_mkdirty(pte);
+ }
+ }
+ *ptep = pte; /* clears _PAGE_BUSY */
return ret;
}
@@ -157,7 +178,7 @@ static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
* Also returns pte and page size if the page is present in page table.
*/
static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
- unsigned long gpa)
+ unsigned long gpa, bool do_get_page)
{
struct kvm_memory_slot *memslot;
pte_t pte;
@@ -175,7 +196,7 @@ static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
/* Find a PTE and determine the size */
pte = kvmppc_lookup_pte(vcpu->arch.pgdir, hva,
- writing, &pg_size);
+ writing, &pg_size, do_get_page);
if (!pte)
return ERROR_ADDR;
@@ -188,6 +209,52 @@ static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
return hpa;
}
+#ifdef CONFIG_IOMMU_API
+static long kvmppc_clear_tce_real_mode(struct kvm_vcpu *vcpu,
+ struct iommu_table *tbl, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+{
+ long ret = 0, i;
+ unsigned long entry = ioba >> IOMMU_PAGE_SHIFT;
+
+ if (iommu_tce_clear_param_check(tbl, ioba, tce_value, npages))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i) {
+ struct page *page;
+ unsigned long oldtce;
+
+ oldtce = iommu_clear_tce(tbl, entry + i);
+ if (!oldtce)
+ continue;
+
+ page = realmode_pfn_to_page(oldtce >> PAGE_SHIFT);
+ if (!page) {
+ ret = H_TOO_HARD;
+ break;
+ }
+
+ if (oldtce & TCE_PCI_WRITE)
+ SetPageDirty(page);
+
+ if (realmode_put_page(page)) {
+ ret = H_TOO_HARD;
+ break;
+ }
+ }
+
+ if (ret == H_TOO_HARD) {
+ vcpu->arch.tce_tmp_num = i;
+ vcpu->arch.tce_reason = H_TOO_HARD;
+ }
+ /* if (ret < 0)
+ pr_err("iommu_tce: %s failed ioba=%lx, tce_value=%lx ret=%d\n",
+ __func__, ioba, tce_value, ret); */
+
+ return ret;
+}
+#endif /* CONFIG_IOMMU_API */
+
long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
@@ -199,6 +266,52 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
if (!tt)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ vcpu->arch.tce_reason = 0;
+
+ if (tce & (TCE_PCI_READ | TCE_PCI_WRITE)) {
+ unsigned long hpa, hva;
+
+ if (iommu_tce_put_param_check(tbl, ioba, tce))
+ return H_PARAMETER;
+
+ hpa = kvmppc_realmode_gpa_to_hpa(vcpu, tce, true);
+ if (hpa == ERROR_ADDR) {
+ vcpu->arch.tce_reason = H_TOO_HARD;
+ return H_TOO_HARD;
+ }
+
+ hva = (unsigned long) __va(hpa);
+ ret = iommu_tce_build(tbl,
+ ioba >> IOMMU_PAGE_SHIFT,
+ hva, iommu_tce_direction(hva));
+ if (unlikely(ret)) {
+ struct page *pg = realmode_pfn_to_page(hpa);
+ BUG_ON(!pg);
+ if (realmode_put_page(pg)) {
+ vcpu->arch.tce_reason = H_HARDWARE;
+ return H_TOO_HARD;
+ }
+ return H_HARDWARE;
+ }
+ } else {
+ ret = kvmppc_clear_tce_real_mode(vcpu, tbl, ioba, 0, 1);
+ if (ret)
+ return ret;
+ }
+
+ iommu_flush_tce(tbl);
+
+ return H_SUCCESS;
+ }
+#endif
/* Emulated IO */
if (ioba >= tt->window_size)
return H_PARAMETER;
@@ -235,10 +348,62 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
if (tce_list & ~IOMMU_PAGE_MASK)
return H_PARAMETER;
- tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu, tce_list);
+ vcpu->arch.tce_tmp_num = 0;
+ vcpu->arch.tce_reason = 0;
+
+ tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu,
+ tce_list, false);
if ((unsigned long)tces == ERROR_ADDR)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ /* Check all TCEs */
+ for (i = 0; i < npages; ++i) {
+ if (iommu_tce_put_param_check(tbl, ioba +
+ (i << IOMMU_PAGE_SHIFT), tces[i]))
+ return H_PARAMETER;
+ vcpu->arch.tce_tmp[i] = tces[i];
+ }
+
+ /* Translate TCEs and go get_page */
+ for (i = 0; i < npages; ++i) {
+ unsigned long hpa = kvmppc_realmode_gpa_to_hpa(vcpu,
+ vcpu->arch.tce_tmp[i], true);
+ if (hpa == ERROR_ADDR) {
+ vcpu->arch.tce_tmp_num = i;
+ vcpu->arch.tce_reason = H_TOO_HARD;
+ return H_TOO_HARD;
+ }
+ vcpu->arch.tce_tmp[i] = hpa;
+ }
+
+ /* Put TCEs to the table */
+ for (i = 0; i < npages; ++i) {
+ unsigned long hva = (unsigned long)
+ __va(vcpu->arch.tce_tmp[i]);
+
+ ret = iommu_tce_build(tbl,
+ (ioba >> IOMMU_PAGE_SHIFT) + i,
+ hva, iommu_tce_direction(hva));
+ if (ret) {
+ /* All wrong, go virtmode and do cleanup */
+ vcpu->arch.tce_reason = H_HARDWARE;
+ return H_TOO_HARD;
+ }
+ }
+
+ iommu_flush_tce(tbl);
+
+ return H_SUCCESS;
+ }
+#endif
/* Emulated IO */
if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
return H_PARAMETER;
@@ -268,6 +433,26 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
if (!tt)
return H_TOO_HARD;
+#ifdef CONFIG_IOMMU_API
+ if (tt->grp) {
+ struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+ /* Return error if the group is being destroyed */
+ if (!tbl)
+ return H_RESCINDED;
+
+ vcpu->arch.tce_reason = 0;
+
+ ret = kvmppc_clear_tce_real_mode(vcpu, tbl, ioba,
+ tce_value, npages);
+ if (ret)
+ return ret;
+
+ iommu_flush_tce(tbl);
+
+ return H_SUCCESS;
+ }
+#endif
/* Emulated IO */
if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
return H_PARAMETER;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 8465c2a..da6bf61 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -396,6 +396,7 @@ int kvm_dev_ioctl_check_extension(long ext)
break;
#endif
case KVM_CAP_SPAPR_MULTITCE:
+ case KVM_CAP_SPAPR_TCE_IOMMU:
r = 1;
break;
default:
@@ -1025,6 +1026,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
goto out;
}
+ case KVM_CREATE_SPAPR_TCE_IOMMU: {
+ struct kvm_create_spapr_tce_iommu create_tce_iommu;
+ struct kvm *kvm = filp->private_data;
+
+ r = -EFAULT;
+ if (copy_from_user(&create_tce_iommu, argp,
+ sizeof(create_tce_iommu)))
+ goto out;
+ r = kvm_vm_ioctl_create_spapr_tce_iommu(kvm, &create_tce_iommu);
+ goto out;
+ }
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_64_HV
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index fc0d6b9..8cf86dc 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -667,6 +667,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_PPC_RTAS 91
#define KVM_CAP_IRQ_XICS 92
#define KVM_CAP_SPAPR_MULTITCE 93
+#define KVM_CAP_SPAPR_TCE_IOMMU 94
#ifdef KVM_CAP_IRQ_ROUTING
@@ -922,6 +923,7 @@ struct kvm_s390_ucas_mapping {
/* Available with KVM_CAP_PPC_ALLOC_HTAB */
#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32)
#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_IOMMU _IOW(KVMIO, 0xaf, struct kvm_create_spapr_tce_iommu)
/* Available with KVM_CAP_RMA */
#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma)
/* Available with KVM_CAP_PPC_HTAB_FD */
--
1.7.10.4
^ permalink raw reply related
* [PATCH 2/4] powerpc: Prepare to support kernel handling of IOMMU map/unmap
From: Alexey Kardashevskiy @ 2013-06-05 6:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: kvm, Alexey Kardashevskiy, Alexander Graf, kvm-ppc, linux-kernel,
Paul Mackerras, linuxppc-dev, David Gibson
In-Reply-To: <1370412673-1345-1-git-send-email-aik@ozlabs.ru>
The current VFIO-on-POWER implementation supports only user mode
driven mapping, i.e. QEMU is sending requests to map/unmap pages.
However this approach is really slow, so we want to move that to KVM.
Since H_PUT_TCE can be extremely performance sensitive (especially with
network adapters where each packet needs to be mapped/unmapped) we chose
to implement that as a "fast" hypercall directly in "real
mode" (processor still in the guest context but MMU off).
To be able to do that, we need to provide some facilities to
access the struct page count within that real mode environment as things
like the sparsemem vmemmap mappings aren't accessible.
This adds an API to increment/decrement page counter as
get_user_pages API used for user mode mapping does not work
in the real mode.
CONFIG_SPARSEMEM_VMEMMAP and CONFIG_FLATMEM are supported.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Paul Mackerras <paulus@samba.org>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Changes:
2013-05-20:
* PageTail() is replaced by PageCompound() in order to have the same checks
for whether the page is huge in realmode_get_page() and realmode_put_page()
---
arch/powerpc/include/asm/pgtable-ppc64.h | 4 ++
arch/powerpc/mm/init_64.c | 77 +++++++++++++++++++++++++++++-
2 files changed, 80 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index e3d55f6f..7b46e5f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -376,6 +376,10 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
}
#endif /* !CONFIG_HUGETLB_PAGE */
+struct page *realmode_pfn_to_page(unsigned long pfn);
+int realmode_get_page(struct page *page);
+int realmode_put_page(struct page *page);
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a90b9c4..ce3d8d4 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -297,5 +297,80 @@ void vmemmap_free(unsigned long start, unsigned long end)
{
}
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * Any of realmode_XXXX functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ * When 1) or 2) takes place, the API returns an error code to cause
+ * an exit to kernel virtual mode where the operation will be completed.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+ struct vmemmap_backing *vmem_back;
+ struct page *page;
+ unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+ unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+ for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+ if (pg_va < vmem_back->virt_addr)
+ continue;
+ /* Check that page struct is not split between real pages */
+ if ((pg_va + sizeof(struct page)) >
+ (vmem_back->virt_addr + page_size))
+ return NULL;
+
+ page = (struct page *) (vmem_back->phys + pg_va -
+ vmem_back->virt_addr);
+ return page;
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+ return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_FLATMEM)
+int realmode_get_page(struct page *page)
+{
+ if (PageCompound(page))
+ return -EAGAIN;
+
+ get_page(page);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(realmode_get_page);
+
+int realmode_put_page(struct page *page)
+{
+ if (PageCompound(page))
+ return -EAGAIN;
+
+ if (!atomic_add_unless(&page->_count, -1, 1))
+ return -EAGAIN;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(realmode_put_page);
+#endif
--
1.7.10.4
^ permalink raw reply related
* [PATCH 1/4] KVM: PPC: Add support for multiple-TCE hcalls
From: Alexey Kardashevskiy @ 2013-06-05 6:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: kvm, Alexey Kardashevskiy, Alexander Graf, kvm-ppc, linux-kernel,
Paul Mackerras, linuxppc-dev, David Gibson
In-Reply-To: <1370412673-1345-1-git-send-email-aik@ozlabs.ru>
This adds real mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for QEMU emulated devices such as IBMVIO
devices or emulated PCI. These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition to/from real mode.
This adds a tce_tmp cache to kvm_vcpu_arch to save valid TCEs
(copied from user and verified) before writing the whole list into
the TCE table. This cache will be utilized more in the upcoming
VFIO/IOMMU support to continue TCE list processing in the virtual
mode in the case if the real mode handler failed for some reason.
This adds a guest physical to host real address converter
and calls the existing H_PUT_TCE handler. The converting function
is going to be fully utilized by upcoming VFIO supporting patches.
This also implements the KVM_CAP_PPC_MULTITCE capability,
so in order to support the functionality of this patch, QEMU
needs to query for this capability and set the "hcall-multi-tce"
hypertas property only if the capability is present, otherwise
there will be serious performance degradation.
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Changelog:
2013/06/05:
* fixed mistype about IBMVIO in the commit message
* updated doc and moved it to another section
* changed capability number
2013/05/21:
* added kvm_vcpu_arch::tce_tmp
* removed cleanup if put_indirect failed, instead we do not even start
writing to TCE table if we cannot get TCEs from the user and they are
invalid
* kvmppc_emulated_h_put_tce is split to kvmppc_emulated_put_tce
and kvmppc_emulated_validate_tce (for the previous item)
* fixed bug with failthrough for H_IPI
* removed all get_user() from real mode handlers
* kvmppc_lookup_pte() added (instead of making lookup_linux_pte public)
---
Documentation/virtual/kvm/api.txt | 17 ++
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/include/asm/kvm_ppc.h | 16 +-
arch/powerpc/kvm/book3s_64_vio.c | 118 ++++++++++++++
arch/powerpc/kvm/book3s_64_vio_hv.c | 266 +++++++++++++++++++++++++++----
arch/powerpc/kvm/book3s_hv.c | 39 +++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 +
arch/powerpc/kvm/book3s_pr_papr.c | 37 ++++-
arch/powerpc/kvm/powerpc.c | 3 +
include/uapi/linux/kvm.h | 1 +
10 files changed, 473 insertions(+), 32 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 5f91eda..6c082ff 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2362,6 +2362,23 @@ calls by the guest for that service will be passed to userspace to be
handled.
+4.83 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability tells the guest that multiple TCE entry add/remove hypercalls
+handling is supported by the kernel. This significanly accelerates DMA
+operations for PPC KVM guests.
+
+Unlike other capabilities in this section, this one does not have an ioctl.
+Instead, when the capability is present, the H_PUT_TCE_INDIRECT and
+H_STUFF_TCE hypercalls are to be handled in the host kernel and not passed to
+the guest. Othwerwise it might be better for the guest to continue using H_PUT_TCE
+hypercall (if KVM_CAP_SPAPR_TCE or KVM_CAP_SPAPR_TCE_IOMMU are present).
+
+
5. The kvm_run structure
------------------------
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cd..85d8f26 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -609,6 +609,8 @@ struct kvm_vcpu_arch {
spinlock_t tbacct_lock;
u64 busy_stolen;
u64 busy_preempt;
+
+ unsigned long *tce_tmp; /* TCE cache for TCE_PUT_INDIRECT hall */
#endif
};
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe..e852921b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -133,8 +133,20 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce *args);
-extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
- unsigned long ioba, unsigned long tce);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(
+ struct kvm_vcpu *vcpu, unsigned long liobn);
+extern long kvmppc_emulated_validate_tce(unsigned long tce);
+extern void kvmppc_emulated_put_tce(struct kvmppc_spapr_tce_table *tt,
+ unsigned long ioba, unsigned long tce);
+extern long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce);
+extern long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_list, unsigned long npages);
+extern long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages);
extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
struct kvm_allocate_rma *rma);
extern struct kvmppc_linear_info *kvm_alloc_rma(void);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b2d3f3b..06b7b20 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
* Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
*/
#include <linux/types.h>
@@ -36,8 +37,11 @@
#include <asm/ppc-opcode.h>
#include <asm/kvm_host.h>
#include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
+#define ERROR_ADDR ((void *)~(unsigned long)0x0)
static long kvmppc_stt_npages(unsigned long window_size)
{
@@ -148,3 +152,117 @@ fail:
}
return ret;
}
+
+/* Converts guest physical address into host virtual */
+static void __user *kvmppc_virtmode_gpa_to_hva(struct kvm_vcpu *vcpu,
+ unsigned long gpa)
+{
+ unsigned long hva, gfn = gpa >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot;
+
+ memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+ if (!memslot)
+ return ERROR_ADDR;
+
+ hva = __gfn_to_hva_memslot(memslot, gfn) + (gpa & ~PAGE_MASK);
+ return (void *) hva;
+}
+
+long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce)
+{
+ long ret;
+ struct kvmppc_spapr_tce_table *tt;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to userspace */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if (ioba >= tt->window_size)
+ return H_PARAMETER;
+
+ ret = kvmppc_emulated_validate_tce(tce);
+ if (ret)
+ return ret;
+
+ kvmppc_emulated_put_tce(tt, ioba, tce);
+
+ return H_SUCCESS;
+}
+
+long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_list, unsigned long npages)
+{
+ struct kvmppc_spapr_tce_table *tt;
+ long i, ret;
+ unsigned long __user *tces;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to userspace */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /*
+ * The spec says that the maximum size of the list is 512 TCEs so
+ * so the whole table addressed resides in 4K page
+ */
+ if (npages > 512)
+ return H_PARAMETER;
+
+ if (tce_list & ~IOMMU_PAGE_MASK)
+ return H_PARAMETER;
+
+ tces = kvmppc_virtmode_gpa_to_hva(vcpu, tce_list);
+ if (tces == ERROR_ADDR)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i) {
+ if (get_user(vcpu->arch.tce_tmp[i], tces + i))
+ return H_PARAMETER;
+
+ ret = kvmppc_emulated_validate_tce(vcpu->arch.tce_tmp[i]);
+ if (ret)
+ return ret;
+ }
+
+ for (i = 0; i < npages; ++i)
+ kvmppc_emulated_put_tce(tt,
+ ioba + (i << IOMMU_PAGE_SHIFT),
+ vcpu->arch.tce_tmp[i]);
+
+ return H_SUCCESS;
+}
+
+long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+{
+ struct kvmppc_spapr_tce_table *tt;
+ long i, ret;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to userspace */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+ return H_PARAMETER;
+
+ ret = kvmppc_emulated_validate_tce(tce_value);
+ if (ret || (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i, ioba += IOMMU_PAGE_SIZE)
+ kvmppc_emulated_put_tce(tt, ioba, tce_value);
+
+ return H_SUCCESS;
+}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 30c2f3b..c68d538 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -14,6 +14,7 @@
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
* Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
*/
#include <linux/types.h>
@@ -35,42 +36,249 @@
#include <asm/ppc-opcode.h>
#include <asm/kvm_host.h>
#include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
+#define ERROR_ADDR (~(unsigned long)0x0)
-/* WARNING: This will be called in real-mode on HV KVM and virtual
- * mode on PR KVM
+/* Finds a TCE table descriptor by LIOBN */
+struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(struct kvm_vcpu *vcpu,
+ unsigned long liobn)
+{
+ struct kvmppc_spapr_tce_table *tt;
+
+ list_for_each_entry(tt, &vcpu->kvm->arch.spapr_tce_tables, list) {
+ if (tt->liobn == liobn)
+ return tt;
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(kvmppc_find_tce_table);
+
+/*
+ * Validate TCE address.
+ * At the moment only flags are validated
+ * as other check will significantly slow down
+ * or can make it even impossible to handle TCE requests
+ * in real mode.
+ */
+long kvmppc_emulated_validate_tce(unsigned long tce)
+{
+ if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+ return H_PARAMETER;
+
+ return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_emulated_validate_tce);
+
+/*
+ * kvmppc_emulated_put_tce() handles TCE requests for devices emulated
+ * by QEMU. It puts guest TCE values into the table and expects
+ * the QEMU to convert them later in the QEMU device implementation.
+ * Wiorks in both real and virtual modes.
+ * It cannot fail so kvmppc_emulated_validate_tce must be called before it.
*/
+void kvmppc_emulated_put_tce(struct kvmppc_spapr_tce_table *tt,
+ unsigned long ioba, unsigned long tce)
+{
+ unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
+ struct page *page;
+ u64 *tbl;
+
+ /*
+ * Note on the use of page_address() in real mode,
+ *
+ * It is safe to use page_address() in real mode on ppc64 because
+ * page_address() is always defined as lowmem_page_address()
+ * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetial
+ * operation and does not access page struct.
+ *
+ * Theoretically page_address() could be defined different
+ * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL
+ * should be enabled.
+ * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64,
+ * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only
+ * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP
+ * is not expected to be enabled on ppc32, page_address()
+ * is safe for ppc32 as well.
+ */
+#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL)
+#error TODO: fix to avoid page_address() here
+#endif
+ page = tt->pages[idx / TCES_PER_PAGE];
+ tbl = (u64 *)page_address(page);
+
+ /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
+ tbl[idx % TCES_PER_PAGE] = tce;
+}
+EXPORT_SYMBOL_GPL(kvmppc_emulated_put_tce);
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+
+static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
+ unsigned long *pte_sizep)
+{
+ pte_t *ptep;
+ unsigned int shift = 0;
+ pte_t pte, tmp, ret;
+
+ ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift);
+ if (!ptep)
+ return __pte(0);
+ if (shift)
+ *pte_sizep = 1ul << shift;
+ else
+ *pte_sizep = PAGE_SIZE;
+
+ if (!pte_present(*ptep))
+ return __pte(0);
+
+ /* wait until _PAGE_BUSY is clear then set it atomically */
+ __asm__ __volatile__ (
+ "1: ldarx %0,0,%3\n"
+ " andi. %1,%0,%4\n"
+ " bne- 1b\n"
+ " ori %1,%0,%4\n"
+ " stdcx. %1,0,%3\n"
+ " bne- 1b"
+ : "=&r" (pte), "=&r" (tmp), "=m" (*ptep)
+ : "r" (ptep), "i" (_PAGE_BUSY)
+ : "cc");
+
+ ret = pte;
+
+ return ret;
+}
+
+/*
+ * Converts guest physical address into host physical address.
+ * Also returns pte and page size if the page is present in page table.
+ */
+static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
+ unsigned long gpa)
+{
+ struct kvm_memory_slot *memslot;
+ pte_t pte;
+ unsigned long hva, hpa, pg_size = 0, offset;
+ unsigned long gfn = gpa >> PAGE_SHIFT;
+ bool writing = gpa & TCE_PCI_WRITE;
+
+ /* Find a KVM memslot */
+ memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+ if (!memslot)
+ return ERROR_ADDR;
+
+ /* Convert guest physical address to host virtual */
+ hva = __gfn_to_hva_memslot(memslot, gfn);
+
+ /* Find a PTE and determine the size */
+ pte = kvmppc_lookup_pte(vcpu->arch.pgdir, hva,
+ writing, &pg_size);
+ if (!pte)
+ return ERROR_ADDR;
+
+ /* Calculate host phys address keeping flags and offset in the page */
+ offset = gpa & (pg_size - 1);
+
+ /* pte_pfn(pte) should return an address aligned to pg_size */
+ hpa = (pte_pfn(pte) << PAGE_SHIFT) + offset;
+
+ return hpa;
+}
+
long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce)
{
- struct kvm *kvm = vcpu->kvm;
- struct kvmppc_spapr_tce_table *stt;
-
- /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
- /* liobn, ioba, tce); */
-
- list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt->liobn == liobn) {
- unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
- struct page *page;
- u64 *tbl;
-
- /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */
- /* liobn, stt, stt->window_size); */
- if (ioba >= stt->window_size)
- return H_PARAMETER;
-
- page = stt->pages[idx / TCES_PER_PAGE];
- tbl = (u64 *)page_address(page);
-
- /* FIXME: Need to validate the TCE itself */
- /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
- tbl[idx % TCES_PER_PAGE] = tce;
- return H_SUCCESS;
- }
+ long ret;
+ struct kvmppc_spapr_tce_table *tt;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to virtual space */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if (ioba >= tt->window_size)
+ return H_PARAMETER;
+
+ ret = kvmppc_emulated_validate_tce(tce);
+ if (ret)
+ return ret;
+
+ kvmppc_emulated_put_tce(tt, ioba, tce);
+
+ return H_SUCCESS;
+}
+
+long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_list, unsigned long npages)
+{
+ struct kvmppc_spapr_tce_table *tt;
+ long i, ret;
+ unsigned long *tces;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to virtual space */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /*
+ * The spec says that the maximum size of the list is 512 TCEs so
+ * so the whole table addressed resides in 4K page
+ */
+ if (npages > 512)
+ return H_PARAMETER;
+
+ if (tce_list & ~IOMMU_PAGE_MASK)
+ return H_PARAMETER;
+
+ tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu, tce_list);
+ if ((unsigned long)tces == ERROR_ADDR)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i) {
+ ret = kvmppc_emulated_validate_tce(tces[i]);
+ if (ret)
+ return ret;
}
- /* Didn't find the liobn, punt it to userspace */
- return H_TOO_HARD;
+ for (i = 0; i < npages; ++i)
+ kvmppc_emulated_put_tce(tt, ioba + (i << IOMMU_PAGE_SHIFT),
+ tces[i]);
+
+ return H_SUCCESS;
+}
+
+long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+{
+ struct kvmppc_spapr_tce_table *tt;
+ long i, ret;
+
+ tt = kvmppc_find_tce_table(vcpu, liobn);
+ /* Didn't find the liobn, put it to virtual space */
+ if (!tt)
+ return H_TOO_HARD;
+
+ /* Emulated IO */
+ if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+ return H_PARAMETER;
+
+ ret = kvmppc_emulated_validate_tce(tce_value);
+ if (ret || (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i, ioba += IOMMU_PAGE_SIZE)
+ kvmppc_emulated_put_tce(tt, ioba, tce_value);
+
+ return H_SUCCESS;
}
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 550f592..a39039a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -568,6 +568,30 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
ret = kvmppc_xics_hcall(vcpu, req);
break;
} /* fallthrough */
+ return RESUME_HOST;
+ case H_PUT_TCE:
+ ret = kvmppc_virtmode_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_PUT_TCE_INDIRECT:
+ ret = kvmppc_virtmode_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_STUFF_TCE:
+ ret = kvmppc_virtmode_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
default:
return RESUME_HOST;
}
@@ -958,6 +982,20 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ /*
+ * As we want to minimize the chance of having H_PUT_TCE_INDIRECT
+ * half executed, we first read TCEs from the user, check them and
+ * return error if something went wrong and only then put TCEs into
+ * the TCE table.
+ *
+ * tce_tmp is a cache for TCEs to avoid stack allocation or
+ * kmalloc as the whole TCE list can take up to 512 items 8 bytes
+ * each (4096 bytes).
+ */
+ vcpu->arch.tce_tmp = kmalloc(4096, GFP_KERNEL);
+ if (!vcpu->arch.tce_tmp)
+ goto free_vcpu;
+
return vcpu;
free_vcpu:
@@ -980,6 +1018,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
spin_unlock(&vcpu->arch.vpa_update_lock);
+ kfree(vcpu->arch.tce_tmp);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e..d35554e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1490,6 +1490,12 @@ hcall_real_table:
.long 0 /* 0x11c */
.long 0 /* 0x120 */
.long .kvmppc_h_bulk_remove - hcall_real_table
+ .long 0 /* 0x128 */
+ .long 0 /* 0x12c */
+ .long 0 /* 0x130 */
+ .long 0 /* 0x134 */
+ .long .kvmppc_h_stuff_tce - hcall_real_table
+ .long .kvmppc_h_put_tce_indirect - hcall_real_table
hcall_real_table_end:
ignore_hdec:
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index da0e0bc..91d4b45 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -220,7 +220,38 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+ rc = kvmppc_virtmode_h_put_tce(vcpu, liobn, ioba, tce);
+ if (rc == H_TOO_HARD)
+ return EMULATE_FAIL;
+ kvmppc_set_gpr(vcpu, 3, rc);
+ return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+ unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+ unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+ unsigned long tce = kvmppc_get_gpr(vcpu, 6);
+ unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+ long rc;
+
+ rc = kvmppc_virtmode_h_put_tce_indirect(vcpu, liobn, ioba,
+ tce, npages);
+ if (rc == H_TOO_HARD)
+ return EMULATE_FAIL;
+ kvmppc_set_gpr(vcpu, 3, rc);
+ return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+ unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+ unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+ unsigned long tce_value = kvmppc_get_gpr(vcpu, 6);
+ unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+ long rc;
+
+ rc = kvmppc_virtmode_h_stuff_tce(vcpu, liobn, ioba, tce_value, npages);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
@@ -247,6 +278,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
return kvmppc_h_pr_bulk_remove(vcpu);
case H_PUT_TCE:
return kvmppc_h_pr_put_tce(vcpu);
+ case H_PUT_TCE_INDIRECT:
+ return kvmppc_h_pr_put_tce_indirect(vcpu);
+ case H_STUFF_TCE:
+ return kvmppc_h_pr_stuff_tce(vcpu);
case H_CEDE:
vcpu->arch.shared->msr |= MSR_EE;
kvm_vcpu_block(vcpu);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee3..8465c2a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -395,6 +395,9 @@ int kvm_dev_ioctl_check_extension(long ext)
r = 1;
break;
#endif
+ case KVM_CAP_SPAPR_MULTITCE:
+ r = 1;
+ break;
default:
r = 0;
break;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a5c86fc..fc0d6b9 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -666,6 +666,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_IRQ_MPIC 90
#define KVM_CAP_PPC_RTAS 91
#define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_SPAPR_MULTITCE 93
#ifdef KVM_CAP_IRQ_ROUTING
--
1.7.10.4
^ permalink raw reply related
* [PATCH 0/4 v3] KVM: PPC: IOMMU in-kernel handling
From: Alexey Kardashevskiy @ 2013-06-05 6:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: kvm, Alexey Kardashevskiy, Alexander Graf, kvm-ppc, linux-kernel,
Paul Mackerras, linuxppc-dev, David Gibson
Ben, ping! :)
This series has tiny fixes (capability and ioctl numbers,
changed documentation, compile errors in some configuration).
More details are in the commit messages.
Rebased on v3.10-rc4.
Alexey Kardashevskiy (4):
KVM: PPC: Add support for multiple-TCE hcalls
powerpc: Prepare to support kernel handling of IOMMU map/unmap
KVM: PPC: Add support for IOMMU in-kernel handling
KVM: PPC: Add hugepage support for IOMMU in-kernel handling
Documentation/virtual/kvm/api.txt | 45 +++
arch/powerpc/include/asm/kvm_host.h | 7 +
arch/powerpc/include/asm/kvm_ppc.h | 40 ++-
arch/powerpc/include/asm/pgtable-ppc64.h | 4 +
arch/powerpc/include/uapi/asm/kvm.h | 7 +
arch/powerpc/kvm/book3s_64_vio.c | 398 ++++++++++++++++++++++++-
arch/powerpc/kvm/book3s_64_vio_hv.c | 471 ++++++++++++++++++++++++++++--
arch/powerpc/kvm/book3s_hv.c | 39 +++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 +
arch/powerpc/kvm/book3s_pr_papr.c | 37 ++-
arch/powerpc/kvm/powerpc.c | 15 +
arch/powerpc/mm/init_64.c | 77 ++++-
include/uapi/linux/kvm.h | 3 +
13 files changed, 1121 insertions(+), 28 deletions(-)
--
1.7.10.4
^ permalink raw reply
* [PATCH] powerpc/power8: Fix oprofile and perf
From: Michael Neuling @ 2013-06-05 5:38 UTC (permalink / raw)
To: Nishanth Aravamudan, benh; +Cc: linuxppc-dev, Maynard Johnson
In-Reply-To: <26267.1370406880@ale.ozlabs.ibm.com>
In 2ac6f42 powerpc/cputable: Fix oprofile_cpu_type on power8
we broke all power8 hw events.
This reverts this change and uses oprofile_type instead. Perf now works
on POWER8 again and oprofile will revert to using timers on POWER8.
Kudos to mpe this fix.
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
tag: for-3.10
v2: renamed patch
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 1f0937d..2a45d0f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -452,8 +452,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
.mmu_features = MMU_FTRS_POWER8,
.icache_bsize = 128,
.dcache_bsize = 128,
- .oprofile_type = PPC_OPROFILE_POWER4,
- .oprofile_cpu_type = 0,
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .oprofile_cpu_type = "ppc64/ibm-compat-v1",
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.platform = "power8",
@@ -506,8 +506,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
.dcache_bsize = 128,
.num_pmcs = 6,
.pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = 0,
- .oprofile_type = PPC_OPROFILE_POWER4,
+ .oprofile_cpu_type = "ppc64/power8",
+ .oprofile_type = PPC_OPROFILE_INVALID,
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.platform = "power8",
^ permalink raw reply related
* [PATCH] powerpc/cputable: fix oprofile_cpu_type on power8
From: Michael Neuling @ 2013-06-05 5:35 UTC (permalink / raw)
To: Nishanth Aravamudan, benh; +Cc: linuxppc-dev, Maynard Johnson
In-Reply-To: <26267.1370406880@ale.ozlabs.ibm.com>
In 2ac6f42 powerpc/cputable: Fix oprofile_cpu_type on power8
we broke all power8 hw events.
This reverts this change and uses oprofile_type instead. Perf now works
on POWER8 again and oprofile will revert to using timers on POWER8.
Kudos to mpe this fix.
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
tag: for-3.10
benh: disregard my previous revert request and apply this instead
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 1f0937d..2a45d0f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -452,8 +452,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
.mmu_features = MMU_FTRS_POWER8,
.icache_bsize = 128,
.dcache_bsize = 128,
- .oprofile_type = PPC_OPROFILE_POWER4,
- .oprofile_cpu_type = 0,
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .oprofile_cpu_type = "ppc64/ibm-compat-v1",
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.platform = "power8",
@@ -506,8 +506,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
.dcache_bsize = 128,
.num_pmcs = 6,
.pmc_type = PPC_PMC_IBM,
- .oprofile_cpu_type = 0,
- .oprofile_type = PPC_OPROFILE_POWER4,
+ .oprofile_cpu_type = "ppc64/power8",
+ .oprofile_type = PPC_OPROFILE_INVALID,
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.platform = "power8",
^ permalink raw reply related
* Re: [PATCH] powerpc/cputable: fix oprofile_cpu_type on power8
From: Michael Neuling @ 2013-06-05 4:34 UTC (permalink / raw)
To: Nishanth Aravamudan; +Cc: Maynard Johnson, linuxppc-dev
In-Reply-To: <20130528203950.GA30172@linux.vnet.ibm.com>
Benh and Nish,
This breaks all perf HW events on POWER8.
Please revert this. It's
2ac6f427ad837a69561160b282eff80d9f0c2466 upstream.
Noticed by mpe.
Mikey
Nishanth Aravamudan <nacc@linux.vnet.ibm.com> wrote:
> Maynard informed me that neither the oprofile kernel module nor oprofile
> userspace has been updated to support that "legacy" oprofile module
> interface for power8, which is indicated by "ppc64/power8." This results
> in no samples. The solution is to default to the "timer" type, instead.
> The raw entry also should be updated, as "ppc64/ibm-compat-v1" indicates
> to oprofile userspace to use "compatibility events" which are obsolete
> in ISA 2.07.
>
> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
>
> ---
> Ben, if this seems reasonable to you, it would be great to get this into
> 3.10.
>
> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
> index c60bbec..b8808bc 100644
> --- a/arch/powerpc/kernel/cputable.c
> +++ b/arch/powerpc/kernel/cputable.c
> @@ -453,7 +453,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
> .icache_bsize = 128,
> .dcache_bsize = 128,
> .oprofile_type = PPC_OPROFILE_POWER4,
> - .oprofile_cpu_type = "ppc64/ibm-compat-v1",
> + .oprofile_cpu_type = 0,
> .cpu_setup = __setup_cpu_power8,
> .cpu_restore = __restore_cpu_power8,
> .platform = "power8",
> @@ -506,7 +506,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
> .dcache_bsize = 128,
> .num_pmcs = 6,
> .pmc_type = PPC_PMC_IBM,
> - .oprofile_cpu_type = "ppc64/power8",
> + .oprofile_cpu_type = 0,
> .oprofile_type = PPC_OPROFILE_POWER4,
> .cpu_setup = __setup_cpu_power8,
> .cpu_restore = __restore_cpu_power8,
>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
^ permalink raw reply
* [PATCH] powerpc: Align thread->fpr to 16 bytes
From: Anton Blanchard @ 2013-06-05 3:02 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
On newer CPUs we use VSX loads and stores to the thread->fpr array.
For best performance we need to ensure 16 byte alignment.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: b/arch/powerpc/include/asm/processor.h
===================================================================
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -200,7 +200,7 @@ struct thread_struct {
#endif
#endif
/* FP and VSX 0-31 register set */
- double fpr[32][TS_FPRWIDTH];
+ double fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
struct {
unsigned int pad;
^ permalink raw reply
* Re: [RFC PATCH 6/6] KVM: PPC: Book3E: Enhance FPU laziness
From: Scott Wood @ 2013-06-04 22:53 UTC (permalink / raw)
To: Mihai Caraman; +Cc: Mihai Caraman, linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <1370292868-2697-7-git-send-email-mihai.caraman@freescale.com>
On 06/03/2013 03:54:28 PM, Mihai Caraman wrote:
> Adopt AltiVec approach to increase laziness by calling =20
> kvmppc_load_guest_fp()
> just before returning to guest instaed of each sched in.
>=20
> Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
If you did this *before* adding Altivec it would have saved a question =20
in an earlier patch. :-)
> ---
> arch/powerpc/kvm/booke.c | 1 +
> arch/powerpc/kvm/e500mc.c | 2 --
> 2 files changed, 1 insertions(+), 2 deletions(-)
>=20
> diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
> index 019496d..5382238 100644
> --- a/arch/powerpc/kvm/booke.c
> +++ b/arch/powerpc/kvm/booke.c
> @@ -1258,6 +1258,7 @@ int kvmppc_handle_exit(struct kvm_run *run, =20
> struct kvm_vcpu *vcpu,
> } else {
> kvmppc_lazy_ee_enable();
> kvmppc_load_guest_altivec(vcpu);
> + kvmppc_load_guest_fp(vcpu);
> }
> }
>=20
You should probably do these before kvmppc_lazy_ee_enable().
Actually, I don't think this is a good idea at all. As I understand =20
it, you're not supposed to take kernel ownersship of floating point in =20
non-atomic context, because an interrupt could itself call =20
enable_kernel_fp().
Do you have benchmarks showing it's even worthwhile?
-Scott=
^ permalink raw reply
* Re: [RFC PATCH 5/6] KVM: PPC: Book3E: Add ONE_REG AltiVec support
From: Scott Wood @ 2013-06-04 22:40 UTC (permalink / raw)
To: Mihai Caraman; +Cc: Mihai Caraman, linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <1370292868-2697-6-git-send-email-mihai.caraman@freescale.com>
On 06/03/2013 03:54:27 PM, Mihai Caraman wrote:
> Add ONE_REG support for AltiVec on Book3E.
>=20
> Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
> ---
> arch/powerpc/kvm/booke.c | 32 ++++++++++++++++++++++++++++++++
> 1 files changed, 32 insertions(+), 0 deletions(-)
>=20
> diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
> index 01eb635..019496d 100644
> --- a/arch/powerpc/kvm/booke.c
> +++ b/arch/powerpc/kvm/booke.c
> @@ -1570,6 +1570,22 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu =20
> *vcpu, struct kvm_one_reg *reg)
> case KVM_REG_PPC_DEBUG_INST:
> val =3D get_reg_val(reg->id, KVMPPC_INST_EHPRIV);
> break;
> +#ifdef CONFIG_ALTIVEC
> + case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
> + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
> + r =3D -ENXIO;
> + break;
> + }
> + val.vval =3D vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0];
> + break;
> + case KVM_REG_PPC_VSCR:
> + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
> + r =3D -ENXIO;
> + break;
> + }
> + val =3D get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
> + break;
Why u[3]?
-Scott=
^ permalink raw reply
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