* [PATCH v2 2/7] xen/dt: pass flags to callback in dt_for_each_range()
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 1/7] arm/pci: Add pci-scan boot argument Mykyta Poturai
` (5 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Stewart Hildebrand, Stefano Stabellini, Julien Grall,
Bertrand Marquis, Michal Orzel, Volodymyr Babchuk, Mykyta Poturai
From: Stewart Hildebrand <stewart.hildebrand@amd.com>
PCI ranges have prefetchable / non-prefetchable flags that will be
needed in the callback. Pass the flags to the callback.
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* no changes
---
xen/arch/arm/device.c | 4 ++--
xen/arch/arm/domain_build.c | 3 ++-
xen/arch/arm/include/asm/setup.h | 2 +-
xen/arch/arm/pci/pci-host-common.c | 4 ++--
xen/common/device-tree/device-tree.c | 5 +++--
xen/include/xen/device_tree.h | 2 +-
6 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/xen/arch/arm/device.c b/xen/arch/arm/device.c
index 74b54cad34..cc0759023e 100644
--- a/xen/arch/arm/device.c
+++ b/xen/arch/arm/device.c
@@ -50,7 +50,7 @@ int map_irq_to_domain(struct domain *d, unsigned int irq,
}
int map_range_to_domain(const struct dt_device_node *dev,
- uint64_t addr, uint64_t len, void *data)
+ uint32_t flags, uint64_t addr, uint64_t len, void *data)
{
struct map_range_data *mr_data = data;
struct domain *d = mr_data->d;
@@ -325,7 +325,7 @@ int handle_device(struct domain *d, struct dt_device_node *dev, p2m_type_t p2mt,
return res;
}
- res = map_range_to_domain(dev, addr, size, &mr_data);
+ res = map_range_to_domain(dev, 0, addr, size, &mr_data);
if ( res )
return res;
}
diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c
index fb8fbb1650..4bbffdf535 100644
--- a/xen/arch/arm/domain_build.c
+++ b/xen/arch/arm/domain_build.c
@@ -762,7 +762,8 @@ int __init add_ext_regions(unsigned long s_gfn, unsigned long e_gfn,
}
static int __init handle_pci_range(const struct dt_device_node *dev,
- uint64_t addr, uint64_t len, void *data)
+ uint32_t flags, uint64_t addr, uint64_t len,
+ void *data)
{
struct rangeset *mem_holes = data;
paddr_t start, end;
diff --git a/xen/arch/arm/include/asm/setup.h b/xen/arch/arm/include/asm/setup.h
index 1eaf13bd66..97bc5f90a1 100644
--- a/xen/arch/arm/include/asm/setup.h
+++ b/xen/arch/arm/include/asm/setup.h
@@ -62,7 +62,7 @@ int map_device_irqs_to_domain(struct domain *d, struct dt_device_node *dev,
int map_irq_to_domain(struct domain *d, unsigned int irq,
bool need_mapping, const char *devname);
-int map_range_to_domain(const struct dt_device_node *dev,
+int map_range_to_domain(const struct dt_device_node *dev, uint32_t flags,
uint64_t addr, uint64_t len, void *data);
struct init_info
diff --git a/xen/arch/arm/pci/pci-host-common.c b/xen/arch/arm/pci/pci-host-common.c
index d3481b05eb..67447d8696 100644
--- a/xen/arch/arm/pci/pci-host-common.c
+++ b/xen/arch/arm/pci/pci-host-common.c
@@ -418,7 +418,7 @@ int __init pci_host_bridge_mappings(struct domain *d)
bridge->child_ops->need_p2m_hwdom_mapping(d, bridge, addr);
if ( need_mapping )
{
- err = map_range_to_domain(dev, addr, size, &mr_data);
+ err = map_range_to_domain(dev, 0, addr, size, &mr_data);
if ( err )
return err;
}
@@ -434,7 +434,7 @@ int __init pci_host_bridge_mappings(struct domain *d)
* right place for alignment check.
*/
static int is_bar_valid(const struct dt_device_node *dev,
- uint64_t addr, uint64_t len, void *data)
+ uint32_t flags, uint64_t addr, uint64_t len, void *data)
{
struct pdev_bar_check *bar_data = data;
paddr_t s = bar_data->start;
diff --git a/xen/common/device-tree/device-tree.c b/xen/common/device-tree/device-tree.c
index 0b5375f151..5ee1fa4eb1 100644
--- a/xen/common/device-tree/device-tree.c
+++ b/xen/common/device-tree/device-tree.c
@@ -976,7 +976,7 @@ int dt_device_get_paddr(const struct dt_device_node *dev, unsigned int index,
int dt_for_each_range(const struct dt_device_node *dev,
int (*cb)(const struct dt_device_node *dev,
- uint64_t addr, uint64_t length,
+ uint32_t flags, uint64_t addr, uint64_t length,
void *data),
void *data)
{
@@ -1041,13 +1041,14 @@ int dt_for_each_range(const struct dt_device_node *dev,
{
uint64_t a, s;
int ret;
+ uint32_t flags = bus->get_flags(ranges);
memcpy(addr, ranges + na, 4 * pna);
a = __dt_translate_address(dev, addr, "ranges");
s = dt_read_number(ranges + na + pna, ns);
- ret = cb(dev, a, s, data);
+ ret = cb(dev, flags, a, s, data);
if ( ret )
{
dt_dprintk(" -> callback failed=%d\n", ret);
diff --git a/xen/include/xen/device_tree.h b/xen/include/xen/device_tree.h
index 06d7643622..1091e34a10 100644
--- a/xen/include/xen/device_tree.h
+++ b/xen/include/xen/device_tree.h
@@ -667,7 +667,7 @@ int dt_for_each_irq_map(const struct dt_device_node *dev,
*/
int dt_for_each_range(const struct dt_device_node *dev,
int (*cb)(const struct dt_device_node *dev,
- uint64_t addr, uint64_t length,
+ uint32_t flags, uint64_t addr, uint64_t length,
void *data),
void *data);
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v2 1/7] arm/pci: Add pci-scan boot argument
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 2/7] xen/dt: pass flags to callback in dt_for_each_range() Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 3/7] xen/pci: update DT for hwdom when it uses vpci Mykyta Poturai
` (4 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Edward Pickup, Andrew Cooper, Anthony PERARD, Michal Orzel,
Jan Beulich, Julien Grall, Roger Pau Monné,
Stefano Stabellini, Bertrand Marquis, Volodymyr Babchuk,
Luca Fancellu, Stewart Hildebrand, Mykyta Poturai
From: Edward Pickup <Edward.Pickup@arm.com>
This patch adds a Xen boot arguments that, if enabled, causes a call to
existing code to scan pci devices enumerated by the firmware.
This will be needed ahead of dom0less support for pci passthrough on
arm.
Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* remove dead code
* don't return errors from pci_init, but report them
changes from previous series:
* remove is_pci_scan_enabled wrapper
* make pci_scan_enabled ro_after_init
* drop debug prints
* drop Edward's SOB
---
docs/misc/xen-command-line.pandoc | 7 +++++++
xen/arch/arm/pci/pci-host-common.c | 1 +
xen/arch/arm/pci/pci.c | 30 ++++++++++++++++++++++++++++--
3 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index 28a98321c7..3a59b2fce1 100644
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -2079,6 +2079,13 @@ This option can be specified more than once (up to 8 times at present).
Flag to enable or disable support for PCI passthrough
+### pci-scan (arm)
+> `= <boolean>`
+
+> Default: `false`
+
+Flag to enable or disable Xen PCI scan at boot.
+
### pcid (x86)
> `= <boolean> | xpti=<bool>`
diff --git a/xen/arch/arm/pci/pci-host-common.c b/xen/arch/arm/pci/pci-host-common.c
index 487c545f3a..d3481b05eb 100644
--- a/xen/arch/arm/pci/pci-host-common.c
+++ b/xen/arch/arm/pci/pci-host-common.c
@@ -284,6 +284,7 @@ pci_host_common_probe(struct dt_device_node *dev,
}
pci_add_host_bridge(bridge);
+ pci_add_segment(bridge->segment);
return bridge;
diff --git a/xen/arch/arm/pci/pci.c b/xen/arch/arm/pci/pci.c
index beb1f971fa..3ddee5cdbb 100644
--- a/xen/arch/arm/pci/pci.c
+++ b/xen/arch/arm/pci/pci.c
@@ -91,8 +91,14 @@ bool arch_pci_device_physdevop(void)
bool __read_mostly pci_passthrough_enabled;
boolean_param("pci-passthrough", pci_passthrough_enabled);
+/* By default pci scan is disabled. */
+static __initdata bool pci_scan_enabled;
+boolean_param("pci-scan", pci_scan_enabled);
+
static int __init pci_init(void)
{
+ int ret;
+
/*
* Enable PCI passthrough when has been enabled explicitly
* (pci-passthrough=on).
@@ -104,9 +110,29 @@ static int __init pci_init(void)
panic("Could not initialize PCI segment 0\n");
if ( acpi_disabled )
- return dt_pci_init();
+ ret = dt_pci_init();
else
- return acpi_pci_init();
+ ret = acpi_pci_init();
+
+ if ( ret < 0 )
+ {
+ printk(XENLOG_ERR "PCI: Failed to initialize PCI host bridges (rc=%d)\n", ret);
+ return 0;
+ }
+
+ if ( pci_scan_enabled )
+ {
+ ret = scan_pci_devices();
+
+ if ( ret < 0 )
+ {
+ printk(XENLOG_ERR "PCI: Failed to scan PCI devices (rc=%d)\n", ret);
+ return 0;
+ }
+
+ }
+
+ return 0;
}
__initcall(pci_init);
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v2 3/7] xen/pci: update DT for hwdom when it uses vpci
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 2/7] xen/dt: pass flags to callback in dt_for_each_range() Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 1/7] arm/pci: Add pci-scan boot argument Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 4/7] xen/pci: introduce has_vpci_bridge Mykyta Poturai
` (3 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Luca Fancellu, Andrew Cooper, Anthony PERARD, Michal Orzel,
Jan Beulich, Julien Grall, Roger Pau Monné,
Stefano Stabellini, Bertrand Marquis, Volodymyr Babchuk,
Stewart Hildebrand, Mykyta Poturai
From: Luca Fancellu <luca.fancellu@arm.com>
When pci-scan is enabled and Xen supports vpci for guests, Xen will
scan the pci bus to find devices and emulate the pci bus, so the hw
domain must see the emulated bus instead of the real one.
A new helper function, hwdom_uses_vpci, is implemented and returns true
when pci-scan is enabled and Xen is built with
CONFIG_HAS_VPCI_GUEST_SUPPORT=y. When hwdom_uses_vpci() is true, a vpci
node is created for the hwdom device tree.
Depending on whether the guest is using vPCI or not, and whether the
domain is using host layout or not, generate the appropriate device tree
nodes for the guest and handle the right MMIO regions traps.
Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* make make_vpci_node static
---
docs/misc/xen-command-line.pandoc | 4 +-
xen/arch/arm/domain_build.c | 151 +++++++++++++++++++++++++++++-
xen/arch/arm/include/asm/pci.h | 16 ++++
xen/arch/arm/pci/pci.c | 2 +-
4 files changed, 170 insertions(+), 3 deletions(-)
diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index 3a59b2fce1..1633116ee4 100644
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -2084,7 +2084,9 @@ Flag to enable or disable support for PCI passthrough
> Default: `false`
-Flag to enable or disable Xen PCI scan at boot.
+Flag to enable or disable Xen PCI scan at boot. When the flag is enabled, the
+hardware domain cannot have access to the real PCI bus, it will see the bus
+emulated by Xen.
### pcid (x86)
> `= <boolean> | xpti=<bool>`
diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c
index 4bbffdf535..87a25396f6 100644
--- a/xen/arch/arm/domain_build.c
+++ b/xen/arch/arm/domain_build.c
@@ -41,6 +41,7 @@
#include <xen/grant_table.h>
#include <asm/grant_table.h>
#include <xen/serial.h>
+#include <xen/resource.h>
static unsigned int __initdata opt_dom0_max_vcpus;
integer_param("dom0_max_vcpus", opt_dom0_max_vcpus);
@@ -1557,6 +1558,142 @@ int __init make_chosen_node(const struct kernel_info *kinfo)
return res;
}
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+struct vpci_param {
+ uint64_t vpci_ecam_base;
+ uint64_t vpci_ecam_size;
+ uint64_t vpci_mem_base;
+ uint64_t vpci_mem_size;
+ uint64_t vpci_mem_prefetch_base;
+ uint64_t vpci_mem_prefetch_size;
+};
+
+static int __init handle_vpci_range(const struct dt_device_node *dev,
+ uint32_t flags, uint64_t addr, uint64_t len,
+ void *data)
+{
+ struct vpci_param *vpci = (struct vpci_param *)data;
+
+ if ( !(flags & IORESOURCE_MEM) )
+ return 0;
+
+ if ( !(flags & IORESOURCE_PREFETCH) && addr < GB(4) )
+ {
+ vpci->vpci_mem_base = addr;
+ vpci->vpci_mem_size = len;
+ }
+ else if ( flags & IORESOURCE_PREFETCH )
+ {
+ vpci->vpci_mem_prefetch_base = addr;
+ vpci->vpci_mem_prefetch_size = len;
+ }
+ return 0;
+}
+
+static int __init make_vpci_node(struct domain *d, void *fdt)
+{
+ /* reg is sized to be used for all the needed properties below */
+ __be32 reg[((GUEST_ROOT_ADDRESS_CELLS * 2) + GUEST_ROOT_SIZE_CELLS + 1)
+ * 2];
+ __be32 *cells;
+ char buf[22]; /* pcie@ + max 16 char address + '\0' */
+ int res;
+ struct vpci_param vpci = {
+ .vpci_ecam_base = GUEST_VPCI_ECAM_BASE,
+ .vpci_ecam_size = GUEST_VPCI_ECAM_SIZE,
+ .vpci_mem_base = GUEST_VPCI_MEM_ADDR,
+ .vpci_mem_size = GUEST_VPCI_MEM_SIZE,
+ .vpci_mem_prefetch_base = GUEST_VPCI_PREFETCH_MEM_ADDR,
+ .vpci_mem_prefetch_size = GUEST_VPCI_PREFETCH_MEM_SIZE
+ };
+
+ if ( domain_use_host_layout(d) )
+ {
+ struct pci_host_bridge *bridge;
+
+ bridge = pci_find_host_bridge(0, 0);
+
+ vpci.vpci_ecam_base = bridge->cfg->phys_addr;
+ vpci.vpci_ecam_size = bridge->cfg->size;
+
+ res = dt_for_each_range(bridge->dt_node, handle_vpci_range, &vpci);
+ if ( res < 0 )
+ return -EINVAL;
+ }
+
+ snprintf(buf, sizeof(buf), "pcie@%"PRIx64, vpci.vpci_ecam_base);
+ dt_dprintk("Create vpci node\n");
+ res = fdt_begin_node(fdt, buf);
+ if ( res )
+ return res;
+
+ res = fdt_property_string(fdt, "compatible", "pci-host-ecam-generic");
+ if ( res )
+ return res;
+
+ res = fdt_property_string(fdt, "device_type", "pci");
+ if ( res )
+ return res;
+
+ /* Create reg property */
+ cells = ®[0];
+ dt_child_set_range(&cells, GUEST_ROOT_ADDRESS_CELLS, GUEST_ROOT_SIZE_CELLS,
+ vpci.vpci_ecam_base, vpci.vpci_ecam_size);
+
+ res = fdt_property(fdt, "reg", reg,
+ (GUEST_ROOT_ADDRESS_CELLS +
+ GUEST_ROOT_SIZE_CELLS) * sizeof(*reg));
+ if ( res )
+ return res;
+
+ /* Create bus-range property */
+ cells = ®[0];
+ dt_set_cell(&cells, 1, 0);
+ dt_set_cell(&cells, 1, 255);
+ res = fdt_property(fdt, "bus-range", reg, 2 * sizeof(*reg));
+ if ( res )
+ return res;
+
+ res = fdt_property_cell(fdt, "#address-cells", 3);
+ if ( res )
+ return res;
+
+ res = fdt_property_cell(fdt, "#size-cells", 2);
+ if ( res )
+ return res;
+
+ res = fdt_property_string(fdt, "status", "okay");
+ if ( res )
+ return res;
+
+ /*
+ * Create ranges property as:
+ * <(PCI bitfield) (PCI address) (CPU address) (Size)>
+ */
+ cells = ®[0];
+ dt_set_cell(&cells, 1, GUEST_VPCI_ADDR_TYPE_MEM);
+ dt_set_cell(&cells, GUEST_ROOT_ADDRESS_CELLS, vpci.vpci_mem_base);
+ dt_set_cell(&cells, GUEST_ROOT_ADDRESS_CELLS, vpci.vpci_mem_base);
+ dt_set_cell(&cells, GUEST_ROOT_SIZE_CELLS, vpci.vpci_mem_size);
+ dt_set_cell(&cells, 1, GUEST_VPCI_ADDR_TYPE_PREFETCH_MEM);
+ dt_set_cell(&cells, GUEST_ROOT_ADDRESS_CELLS, vpci.vpci_mem_prefetch_base);
+ dt_set_cell(&cells, GUEST_ROOT_ADDRESS_CELLS, vpci.vpci_mem_prefetch_base);
+ dt_set_cell(&cells, GUEST_ROOT_SIZE_CELLS, vpci.vpci_mem_prefetch_size);
+ res = fdt_property(fdt, "ranges", reg, sizeof(reg));
+ if ( res )
+ return res;
+
+ res = fdt_end_node(fdt);
+
+ return res;
+}
+#else
+static inline int __init make_vpci_node(struct domain *d, void *fdt)
+{
+ return 0;
+}
+#endif
+
static int __init handle_node(struct domain *d, struct kernel_info *kinfo,
struct dt_device_node *node,
p2m_type_t p2mt)
@@ -1615,7 +1752,12 @@ static int __init handle_node(struct domain *d, struct kernel_info *kinfo,
dt_dprintk(" Skip it (blacklisted)\n");
return 0;
}
-
+ /* If Xen is scanning the PCI devices, don't expose real bus to hwdom */
+ if ( hwdom_uses_vpci() && dt_device_type_is_equal(node, "pci") )
+ {
+ dt_dprintk(" Skip it (pci-scan is enabled)\n");
+ return 0;
+ }
/*
* Replace these nodes with our own. Note that the original may be
* used_by DOMID_XEN so this check comes first.
@@ -1766,6 +1908,13 @@ static int __init handle_node(struct domain *d, struct kernel_info *kinfo,
if ( res )
return res;
}
+
+ if ( hwdom_uses_vpci() )
+ {
+ res = make_vpci_node(d, kinfo->fdt);
+ if ( res )
+ return res;
+ }
}
res = fdt_end_node(kinfo->fdt);
diff --git a/xen/arch/arm/include/asm/pci.h b/xen/arch/arm/include/asm/pci.h
index 08ffcd4438..7db36e7bc3 100644
--- a/xen/arch/arm/include/asm/pci.h
+++ b/xen/arch/arm/include/asm/pci.h
@@ -23,6 +23,7 @@
#define pci_to_dev(pcidev) (&(pcidev)->arch.dev)
extern bool pci_passthrough_enabled;
+extern bool pci_scan_enabled;
struct rangeset;
@@ -173,4 +174,19 @@ static inline int pci_get_new_domain_nr(void)
}
#endif /*!CONFIG_HAS_PCI*/
+
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+static inline bool hwdom_uses_vpci(void)
+{
+ return pci_scan_enabled;
+}
+
+#else /*!CONFIG_HAS_VPCI_GUEST_SUPPORT*/
+
+static inline bool hwdom_uses_vpci(void)
+{
+ return false;
+}
+#endif /*!CONFIG_HAS_VPCI_GUEST_SUPPORT*/
+
#endif /* __ARM_PCI_H__ */
diff --git a/xen/arch/arm/pci/pci.c b/xen/arch/arm/pci/pci.c
index 3ddee5cdbb..31aa34153f 100644
--- a/xen/arch/arm/pci/pci.c
+++ b/xen/arch/arm/pci/pci.c
@@ -92,7 +92,7 @@ bool __read_mostly pci_passthrough_enabled;
boolean_param("pci-passthrough", pci_passthrough_enabled);
/* By default pci scan is disabled. */
-static __initdata bool pci_scan_enabled;
+bool __ro_after_init pci_scan_enabled;
boolean_param("pci-scan", pci_scan_enabled);
static int __init pci_init(void)
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v2 4/7] xen/pci: introduce has_vpci_bridge
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
` (2 preceding siblings ...)
2025-10-22 13:56 ` [PATCH v2 3/7] xen/pci: update DT for hwdom when it uses vpci Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 14:11 ` Jan Beulich
2025-10-22 13:56 ` [PATCH v2 5/7] xen/pci: initialize BARs Mykyta Poturai
` (2 subsequent siblings)
6 siblings, 1 reply; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Stefano Stabellini, Roger Pau Monné, Stewart Hildebrand,
Mykyta Poturai
From: Stefano Stabellini <stefano.stabellini@amd.com>
has_vpci_bridge is a macro to check if the domain is a domU or is dom0
with vPCI (pci-scan=yes) enabled.
Use the macro in drivers/vpci.
Signed-off-by: Stefano Stabellini <stefano.stabellini@amd.com>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* simplify definition
---
| 14 +++++++-------
xen/drivers/vpci/vpci.c | 4 ++--
xen/include/xen/vpci.h | 8 ++++++++
3 files changed, 17 insertions(+), 9 deletions(-)
--git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
index 469f497744..903168ff96 100644
--- a/xen/drivers/vpci/header.c
+++ b/xen/drivers/vpci/header.c
@@ -230,7 +230,7 @@ bool vpci_process_pending(struct vcpu *v)
read_unlock(&v->domain->pci_lock);
- if ( !is_hardware_domain(v->domain) )
+ if ( has_vpci_bridge(v->domain) )
domain_crash(v->domain);
return false;
@@ -492,7 +492,7 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
}
}
- if ( !is_hardware_domain(d) )
+ if ( has_vpci_bridge(d) )
break;
d = dom_xen;
@@ -522,7 +522,7 @@ static void cf_check cmd_write(
{
struct vpci_header *header = data;
- if ( !is_hardware_domain(pdev->domain) )
+ if ( has_vpci_bridge(pdev->domain) )
{
const struct vpci *vpci = pdev->vpci;
@@ -564,7 +564,7 @@ static void cf_check bar_write(
struct vpci_bar *bar = data;
bool hi = false;
- ASSERT(is_hardware_domain(pdev->domain));
+ ASSERT(!has_vpci_bridge(pdev->domain));
if ( bar->type == VPCI_BAR_MEM64_HI )
{
@@ -747,7 +747,7 @@ static int vpci_init_capability_list(struct pci_dev *pdev)
{
int rc;
bool mask_cap_list = false;
- bool is_hwdom = is_hardware_domain(pdev->domain);
+ bool is_hwdom = !has_vpci_bridge(pdev->domain);
if ( pci_conf_read16(pdev->sbdf, PCI_STATUS) & PCI_STATUS_CAP_LIST )
{
@@ -829,7 +829,7 @@ static int vpci_init_ext_capability_list(const struct pci_dev *pdev)
{
unsigned int pos = PCI_CFG_SPACE_SIZE;
- if ( !is_hardware_domain(pdev->domain) )
+ if ( has_vpci_bridge(pdev->domain) )
/* Extended capabilities read as zero, write ignore for DomU */
return vpci_add_register(pdev->vpci, vpci_read_val, NULL,
pos, 4, (void *)0);
@@ -866,7 +866,7 @@ int vpci_init_header(struct pci_dev *pdev)
struct vpci_header *header = &pdev->vpci->header;
struct vpci_bar *bars = header->bars;
int rc;
- bool is_hwdom = is_hardware_domain(pdev->domain);
+ bool is_hwdom = !has_vpci_bridge(pdev->domain);
ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index 07c7071d0a..8ea89b9805 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -48,7 +48,7 @@ static int assign_virtual_sbdf(struct pci_dev *pdev)
ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
- if ( is_hardware_domain(d) )
+ if ( !has_vpci_bridge(d) )
return 0;
/*
@@ -429,7 +429,7 @@ static const struct pci_dev *translate_virtual_device(const struct domain *d,
#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
const struct pci_dev *pdev;
- ASSERT(!is_hardware_domain(d));
+ ASSERT(has_vpci_bridge(d));
ASSERT(rw_is_locked(&d->pci_lock));
for_each_pdev ( d, pdev )
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 9ae75d946a..d4695cb353 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -339,6 +339,14 @@ static inline int __must_check vpci_reset_device(struct pci_dev *pdev)
return vpci_assign_device(pdev);
}
+#ifdef CONFIG_ARM
+#include <asm/pci.h>
+
+#define has_vpci_bridge(d) (!is_hardware_domain(d) || pci_scan_enabled)
+#else
+#define has_vpci_bridge(d) (!is_hardware_domain(d))
+#endif
+
#endif
/*
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH v2 4/7] xen/pci: introduce has_vpci_bridge
2025-10-22 13:56 ` [PATCH v2 4/7] xen/pci: introduce has_vpci_bridge Mykyta Poturai
@ 2025-10-22 14:11 ` Jan Beulich
0 siblings, 0 replies; 11+ messages in thread
From: Jan Beulich @ 2025-10-22 14:11 UTC (permalink / raw)
To: Mykyta Poturai
Cc: Stefano Stabellini, Roger Pau Monné, Stewart Hildebrand,
xen-devel@lists.xenproject.org
On 22.10.2025 15:56, Mykyta Poturai wrote:
> From: Stefano Stabellini <stefano.stabellini@amd.com>
>
> has_vpci_bridge is a macro to check if the domain is a domU or is dom0
> with vPCI (pci-scan=yes) enabled.
>
> Use the macro in drivers/vpci.
>
> Signed-off-by: Stefano Stabellini <stefano.stabellini@amd.com>
> Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
> Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
> ---
> v1->v2:
> * simplify definition
> ---
> xen/drivers/vpci/header.c | 14 +++++++-------
> xen/drivers/vpci/vpci.c | 4 ++--
> xen/include/xen/vpci.h | 8 ++++++++
> 3 files changed, 17 insertions(+), 9 deletions(-)
With this diffstat, its the subject prefix missing a 'v' (xen/vpci:)?
> --- a/xen/drivers/vpci/header.c
> +++ b/xen/drivers/vpci/header.c
> @@ -230,7 +230,7 @@ bool vpci_process_pending(struct vcpu *v)
>
> read_unlock(&v->domain->pci_lock);
>
> - if ( !is_hardware_domain(v->domain) )
> + if ( has_vpci_bridge(v->domain) )
> domain_crash(v->domain);
Here and perhaps everywhere else I wonder: Is this really an appropriately
named predicate for the purpose / context?
Jan
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v2 5/7] xen/pci: initialize BARs
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
` (3 preceding siblings ...)
2025-10-22 13:56 ` [PATCH v2 4/7] xen/pci: introduce has_vpci_bridge Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 14:30 ` Jan Beulich
2025-10-22 13:56 ` [PATCH v2 7/7] arm/pci: enable vpci for hwdom when pci-scan is enabled Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 6/7] xen/pci: assign discovered devices to hwdom Mykyta Poturai
6 siblings, 1 reply; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Stewart Hildebrand, Stefano Stabellini, Julien Grall,
Bertrand Marquis, Michal Orzel, Volodymyr Babchuk, Andrew Cooper,
Anthony PERARD, Jan Beulich, Roger Pau Monné, Mykyta Poturai
From: Stewart Hildebrand <stewart.hildebrand@amd.com>
A PCI device must have valid BARs in order to assign it to a domain. On
ARM, firmware is unlikely to have initialized the BARs, so we must do
this in Xen. During setup_hwdom_pci_devices(), check if each BAR is
valid. If the BAR happens to already be valid, remove the BAR range from
a rangeset of valid PCI ranges so as to avoid overlap when reserving a
new BAR. If not valid, reserve a new BAR address from the rangeset and
write it to the device.
Avaliable ranges are read from DT during init and stored in distinct
rangesets.
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* move hwdom_uses_vpci to this patch
* fixup error reporting
---
xen/arch/arm/include/asm/pci.h | 7 +++
xen/arch/arm/pci/pci-host-common.c | 76 ++++++++++++++++++++++++++++
xen/arch/x86/include/asm/pci.h | 20 ++++++++
xen/common/rangeset.c | 35 +++++++++++++
xen/drivers/passthrough/pci.c | 79 ++++++++++++++++++++++++++++++
xen/include/xen/rangeset.h | 6 ++-
6 files changed, 222 insertions(+), 1 deletion(-)
diff --git a/xen/arch/arm/include/asm/pci.h b/xen/arch/arm/include/asm/pci.h
index 7db36e7bc3..46bdc7713b 100644
--- a/xen/arch/arm/include/asm/pci.h
+++ b/xen/arch/arm/include/asm/pci.h
@@ -74,6 +74,8 @@ struct pci_host_bridge {
struct pci_config_window *child_cfg;
const struct pci_ops *child_ops;
void *priv; /* Private data of the bridge. */
+ struct rangeset *bar_ranges;
+ struct rangeset *bar_ranges_prefetch;
};
struct pci_ops {
@@ -154,6 +156,11 @@ void pci_generic_init_bus_range_child(struct dt_device_node *dev,
bool arch_pci_device_physdevop(void);
+uint64_t pci_get_new_bar_addr(const struct pci_dev *pdev, uint64_t size,
+ bool is_64bit, bool prefetch);
+int pci_reserve_bar_range(const struct pci_dev *pdev, uint64_t addr,
+ uint64_t size, bool prefetch);
+
#else /*!CONFIG_HAS_PCI*/
struct pci_dev;
diff --git a/xen/arch/arm/pci/pci-host-common.c b/xen/arch/arm/pci/pci-host-common.c
index 67447d8696..86467e7cf6 100644
--- a/xen/arch/arm/pci/pci-host-common.c
+++ b/xen/arch/arm/pci/pci-host-common.c
@@ -21,6 +21,7 @@
#include <xen/rwlock.h>
#include <xen/sched.h>
#include <xen/vmap.h>
+#include <xen/resource.h>
#include <asm/setup.h>
@@ -232,6 +233,21 @@ static int pci_bus_find_domain_nr(struct dt_device_node *dev)
return domain;
}
+static int add_bar_range(const struct dt_device_node *dev, uint32_t flags,
+ uint64_t addr, uint64_t len, void *data)
+{
+ struct pci_host_bridge *bridge = data;
+
+ if ( !(flags & IORESOURCE_MEM) )
+ return 0;
+
+ if ( flags & IORESOURCE_PREFETCH )
+ return rangeset_add_range(bridge->bar_ranges_prefetch, addr,
+ addr + len - 1);
+ else
+ return rangeset_add_range(bridge->bar_ranges, addr, addr + len - 1);
+}
+
struct pci_host_bridge *
pci_host_common_probe(struct dt_device_node *dev,
const struct pci_ecam_ops *ops,
@@ -286,6 +302,14 @@ pci_host_common_probe(struct dt_device_node *dev,
pci_add_host_bridge(bridge);
pci_add_segment(bridge->segment);
+ bridge->bar_ranges = rangeset_new(NULL, "BAR ranges",
+ RANGESETF_prettyprint_hex);
+ bridge->bar_ranges_prefetch = rangeset_new(NULL,
+ "BAR ranges (prefetchable)",
+ RANGESETF_prettyprint_hex);
+ if ( bridge->bar_ranges && bridge->bar_ranges_prefetch )
+ dt_for_each_range(bridge->dt_node, add_bar_range, bridge);
+
return bridge;
err_child:
@@ -476,6 +500,58 @@ bool pci_check_bar(const struct pci_dev *pdev, mfn_t start, mfn_t end)
return bar_data.is_valid;
}
+
+uint64_t pci_get_new_bar_addr(const struct pci_dev *pdev, uint64_t size,
+ bool is_64bit, bool prefetch)
+{
+ struct pci_host_bridge *bridge;
+ struct rangeset *range;
+ uint64_t addr;
+
+ bridge = pci_find_host_bridge(pdev->seg, pdev->bus);
+ if ( !bridge )
+ return 0;
+
+ range = prefetch ? bridge->bar_ranges_prefetch : bridge->bar_ranges;
+
+ if ( size < PAGE_SIZE )
+ size = PAGE_SIZE;
+
+ if ( is_64bit && !rangeset_find_aligned_range(range, size, GB(4), &addr) )
+ {
+ if ( rangeset_remove_range(range, addr, addr + size - 1) )
+ printk(XENLOG_ERR "Failed to remove BAR range %lx-%lx from rangeset\n",
+ addr, addr + size - 1);
+ return addr;
+ }
+ if ( !rangeset_find_aligned_range(range, size, 0, &addr) )
+ {
+ if ( !is_64bit && addr >= GB(4) )
+ return 0;
+ if ( rangeset_remove_range(range, addr, addr + size - 1) )
+ printk(XENLOG_ERR "Failed to remove BAR range %lx-%lx from rangeset\n",
+ addr, addr + size - 1);
+ return addr;
+ }
+
+ return 0;
+}
+
+int pci_reserve_bar_range(const struct pci_dev *pdev, uint64_t addr,
+ uint64_t size, bool prefetch)
+{
+ struct pci_host_bridge *bridge;
+ struct rangeset *range;
+
+ bridge = pci_find_host_bridge(pdev->seg, pdev->bus);
+ if ( !bridge )
+ return 0;
+
+ range = prefetch ? bridge->bar_ranges_prefetch : bridge->bar_ranges;
+
+ return rangeset_remove_range(range, addr, addr + size - 1);
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/arch/x86/include/asm/pci.h b/xen/arch/x86/include/asm/pci.h
index 0b98081aea..4cc3f2e853 100644
--- a/xen/arch/x86/include/asm/pci.h
+++ b/xen/arch/x86/include/asm/pci.h
@@ -76,4 +76,24 @@ int pci_sanitize_bar_memory(struct rangeset *r);
void pci_setup(void);
+/* Unlike ARM, HW domain alyways uses vpci for x86 */
+static inline bool hwdom_uses_vpci(void)
+{
+ return true;
+}
+
+static inline uint64_t pci_get_new_bar_addr(const struct pci_dev *pdev,
+ uint64_t size, bool is_64bit,
+ bool prefetch)
+{
+ return 0;
+}
+
+static inline int pci_reserve_bar_range(const struct pci_dev *pdev,
+ uint64_t addr, uint64_t size,
+ bool prefetch)
+{
+ return 0;
+}
+
#endif /* __X86_PCI_H__ */
diff --git a/xen/common/rangeset.c b/xen/common/rangeset.c
index 0e3b9acd35..c1c6f8610c 100644
--- a/xen/common/rangeset.c
+++ b/xen/common/rangeset.c
@@ -357,6 +357,41 @@ int rangeset_claim_range(struct rangeset *r, unsigned long size,
return 0;
}
+int rangeset_find_aligned_range(struct rangeset *r, unsigned long size,
+ unsigned long min, unsigned long *s)
+{
+ struct range *x;
+
+ /* Power of 2 check */
+ if ( (size & (size - 1)) != 0 )
+ {
+ *s = 0;
+ return -EINVAL;
+ }
+
+ read_lock(&r->lock);
+
+ for ( x = first_range(r); x; x = next_range(r, x) )
+ {
+ /* Assumes size is a power of 2 */
+ unsigned long start_aligned = (x->s + size - 1) & ~(size - 1);
+
+ if ( x->e > start_aligned &&
+ (x->e - start_aligned) >= size &&
+ start_aligned >= min )
+ {
+ read_unlock(&r->lock);
+ *s = start_aligned;
+ return 0;
+ }
+ }
+
+ read_unlock(&r->lock);
+ *s = 0;
+
+ return -ENOSPC;
+}
+
int rangeset_consume_ranges(struct rangeset *r,
int (*cb)(unsigned long s, unsigned long e,
void *ctxt, unsigned long *c),
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 3edcfa8a04..4f5de9a542 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -1172,6 +1172,80 @@ int __init scan_pci_devices(void)
return ret;
}
+static void __init cf_check reserve_bar_range(struct pci_dev *pdev, uint8_t reg,
+ uint64_t addr, uint64_t size,
+ bool is_64bit, bool prefetch)
+{
+ if ( pci_check_bar(pdev, maddr_to_mfn(addr),
+ maddr_to_mfn(addr + size - 1)) )
+ pci_reserve_bar_range(pdev, addr, size, prefetch);
+}
+
+static void __init cf_check get_new_bar_addr(struct pci_dev *pdev, uint8_t reg,
+ uint64_t addr, uint64_t size,
+ bool is_64bit, bool prefetch)
+{
+ if ( !pci_check_bar(pdev, maddr_to_mfn(addr),
+ maddr_to_mfn(addr + size - 1)) )
+ {
+ uint16_t cmd = pci_conf_read16(pdev->sbdf, PCI_COMMAND);
+
+ addr = pci_get_new_bar_addr(pdev, size, is_64bit, prefetch);
+
+ pci_conf_write16(pdev->sbdf, PCI_COMMAND,
+ cmd & ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO));
+
+ pci_conf_write32(pdev->sbdf, reg,
+ (addr & GENMASK(31, 0)) |
+ (is_64bit ? PCI_BASE_ADDRESS_MEM_TYPE_64 : 0));
+
+ if ( is_64bit )
+ pci_conf_write32(pdev->sbdf, reg + 4, addr >> 32);
+
+ pci_conf_write16(pdev->sbdf, PCI_COMMAND, cmd);
+ }
+}
+
+static int __init cf_check bars_iterate(struct pci_seg *pseg, void *arg)
+{
+ struct pci_dev *pdev;
+ unsigned int i, ret, num_bars = PCI_HEADER_NORMAL_NR_BARS;
+ uint64_t addr, size;
+ void (*cb)(struct pci_dev *, uint8_t, uint64_t, uint64_t, bool, bool) = arg;
+
+ list_for_each_entry ( pdev, &pseg->alldevs_list, alldevs_list )
+ {
+ if ( (pci_conf_read8(pdev->sbdf, PCI_HEADER_TYPE) & 0x7f) ==
+ PCI_HEADER_TYPE_NORMAL )
+ {
+ for ( i = 0; i < num_bars; i += ret )
+ {
+ uint8_t reg = PCI_BASE_ADDRESS_0 + i * 4;
+ bool prefetch;
+
+ if ( (pci_conf_read32(pdev->sbdf, reg) & PCI_BASE_ADDRESS_SPACE)
+ == PCI_BASE_ADDRESS_SPACE_IO )
+ {
+ ret = 1;
+ continue;
+ }
+
+ ret = pci_size_mem_bar(pdev->sbdf, reg, &addr, &size,
+ (i == num_bars - 1) ? PCI_BAR_LAST : 0);
+
+ if ( !size )
+ continue;
+ prefetch = !!(pci_conf_read32(pdev->sbdf, reg) &
+ PCI_BASE_ADDRESS_MEM_PREFETCH);
+
+ cb(pdev, reg, addr, size, ret == 2, prefetch);
+ }
+ }
+ }
+
+ return 0;
+}
+
struct setup_hwdom {
struct domain *d;
int (*handler)(uint8_t devfn, struct pci_dev *pdev);
@@ -1263,6 +1337,11 @@ void __hwdom_init setup_hwdom_pci_devices(
struct setup_hwdom ctxt = { .d = d, .handler = handler };
pcidevs_lock();
+ if ( hwdom_uses_vpci() )
+ {
+ pci_segments_iterate(bars_iterate, reserve_bar_range);
+ pci_segments_iterate(bars_iterate, get_new_bar_addr);
+ }
pci_segments_iterate(_setup_hwdom_pci_devices, &ctxt);
pcidevs_unlock();
}
diff --git a/xen/include/xen/rangeset.h b/xen/include/xen/rangeset.h
index 817505badf..e71e810f82 100644
--- a/xen/include/xen/rangeset.h
+++ b/xen/include/xen/rangeset.h
@@ -56,11 +56,15 @@ void rangeset_limit(
bool __must_check rangeset_is_empty(
const struct rangeset *r);
-/* Add/claim/remove/query/purge a numeric range. */
+/* Add/claim/find/remove/query/purge a numeric range. */
int __must_check rangeset_add_range(
struct rangeset *r, unsigned long s, unsigned long e);
int __must_check rangeset_claim_range(struct rangeset *r, unsigned long size,
unsigned long *s);
+int __must_check rangeset_find_aligned_range(struct rangeset *r,
+ unsigned long size,
+ unsigned long min,
+ unsigned long *s);
int __must_check rangeset_remove_range(
struct rangeset *r, unsigned long s, unsigned long e);
bool __must_check rangeset_contains_range(
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH v2 5/7] xen/pci: initialize BARs
2025-10-22 13:56 ` [PATCH v2 5/7] xen/pci: initialize BARs Mykyta Poturai
@ 2025-10-22 14:30 ` Jan Beulich
0 siblings, 0 replies; 11+ messages in thread
From: Jan Beulich @ 2025-10-22 14:30 UTC (permalink / raw)
To: Mykyta Poturai
Cc: Stewart Hildebrand, Stefano Stabellini, Julien Grall,
Bertrand Marquis, Michal Orzel, Volodymyr Babchuk, Andrew Cooper,
Anthony PERARD, Roger Pau Monné,
xen-devel@lists.xenproject.org
On 22.10.2025 15:56, Mykyta Poturai wrote:
> @@ -232,6 +233,21 @@ static int pci_bus_find_domain_nr(struct dt_device_node *dev)
> return domain;
> }
>
> +static int add_bar_range(const struct dt_device_node *dev, uint32_t flags,
> + uint64_t addr, uint64_t len, void *data)
> +{
> + struct pci_host_bridge *bridge = data;
> +
> + if ( !(flags & IORESOURCE_MEM) )
> + return 0;
> +
> + if ( flags & IORESOURCE_PREFETCH )
> + return rangeset_add_range(bridge->bar_ranges_prefetch, addr,
> + addr + len - 1);
> + else
> + return rangeset_add_range(bridge->bar_ranges, addr, addr + len - 1);
Here and everywhere else you use rangesets: This loses significant bits on
Arm32. Iirc the plan was to select HAS_PCI only for Arm64, but that's entirely
invisible here. I think there want to be perhaps multiple BUILD_BUG_ON()s, at
the very least.
> --- a/xen/arch/x86/include/asm/pci.h
> +++ b/xen/arch/x86/include/asm/pci.h
> @@ -76,4 +76,24 @@ int pci_sanitize_bar_memory(struct rangeset *r);
>
> void pci_setup(void);
>
> +/* Unlike ARM, HW domain alyways uses vpci for x86 */
> +static inline bool hwdom_uses_vpci(void)
> +{
> + return true;
> +}
What the comment says is not true. It is true for PVH Dom0. The sole use
of the predicate therefore is questionable, too.
> +static inline uint64_t pci_get_new_bar_addr(const struct pci_dev *pdev,
> + uint64_t size, bool is_64bit,
> + bool prefetch)
> +{
> + return 0;
> +}
> +
> +static inline int pci_reserve_bar_range(const struct pci_dev *pdev,
> + uint64_t addr, uint64_t size,
> + bool prefetch)
> +{
> + return 0;
> +}
Neither here nor elsewhere is any word said on what these do, what a
"new BAR range" is, or what "reserving" would mean.
> --- a/xen/common/rangeset.c
> +++ b/xen/common/rangeset.c
> @@ -357,6 +357,41 @@ int rangeset_claim_range(struct rangeset *r, unsigned long size,
> return 0;
> }
>
> +int rangeset_find_aligned_range(struct rangeset *r, unsigned long size,
> + unsigned long min, unsigned long *s)
> +{
> + struct range *x;
> +
> + /* Power of 2 check */
> + if ( (size & (size - 1)) != 0 )
> + {
> + *s = 0;
> + return -EINVAL;
> + }
> +
> + read_lock(&r->lock);
> +
> + for ( x = first_range(r); x; x = next_range(r, x) )
> + {
> + /* Assumes size is a power of 2 */
> + unsigned long start_aligned = (x->s + size - 1) & ~(size - 1);
> +
> + if ( x->e > start_aligned &&
> + (x->e - start_aligned) >= size &&
> + start_aligned >= min )
> + {
> + read_unlock(&r->lock);
With this and ...
> + *s = start_aligned;
> + return 0;
> + }
> + }
> +
> + read_unlock(&r->lock);
... this, how can the caller be sure the result they receive is not stale by
the time they get to look at and use it?
> --- a/xen/drivers/passthrough/pci.c
> +++ b/xen/drivers/passthrough/pci.c
> @@ -1172,6 +1172,80 @@ int __init scan_pci_devices(void)
> return ret;
> }
>
> +static void __init cf_check reserve_bar_range(struct pci_dev *pdev, uint8_t reg,
> + uint64_t addr, uint64_t size,
> + bool is_64bit, bool prefetch)
> +{
> + if ( pci_check_bar(pdev, maddr_to_mfn(addr),
> + maddr_to_mfn(addr + size - 1)) )
> + pci_reserve_bar_range(pdev, addr, size, prefetch);
> +}
> +
> +static void __init cf_check get_new_bar_addr(struct pci_dev *pdev, uint8_t reg,
> + uint64_t addr, uint64_t size,
> + bool is_64bit, bool prefetch)
> +{
> + if ( !pci_check_bar(pdev, maddr_to_mfn(addr),
> + maddr_to_mfn(addr + size - 1)) )
> + {
> + uint16_t cmd = pci_conf_read16(pdev->sbdf, PCI_COMMAND);
> +
> + addr = pci_get_new_bar_addr(pdev, size, is_64bit, prefetch);
> +
> + pci_conf_write16(pdev->sbdf, PCI_COMMAND,
> + cmd & ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO));
> +
> + pci_conf_write32(pdev->sbdf, reg,
> + (addr & GENMASK(31, 0)) |
> + (is_64bit ? PCI_BASE_ADDRESS_MEM_TYPE_64 : 0));
> +
> + if ( is_64bit )
> + pci_conf_write32(pdev->sbdf, reg + 4, addr >> 32);
> +
> + pci_conf_write16(pdev->sbdf, PCI_COMMAND, cmd);
> + }
> +}
> +
> +static int __init cf_check bars_iterate(struct pci_seg *pseg, void *arg)
> +{
> + struct pci_dev *pdev;
> + unsigned int i, ret, num_bars = PCI_HEADER_NORMAL_NR_BARS;
> + uint64_t addr, size;
> + void (*cb)(struct pci_dev *, uint8_t, uint64_t, uint64_t, bool, bool) = arg;
There needs to be some build-time checking that this and the two callbacks
above actually match in type. Likely by way of using a function typedef.
> --- a/xen/include/xen/rangeset.h
> +++ b/xen/include/xen/rangeset.h
> @@ -56,11 +56,15 @@ void rangeset_limit(
> bool __must_check rangeset_is_empty(
> const struct rangeset *r);
>
> -/* Add/claim/remove/query/purge a numeric range. */
> +/* Add/claim/find/remove/query/purge a numeric range. */
> int __must_check rangeset_add_range(
> struct rangeset *r, unsigned long s, unsigned long e);
> int __must_check rangeset_claim_range(struct rangeset *r, unsigned long size,
> unsigned long *s);
> +int __must_check rangeset_find_aligned_range(struct rangeset *r,
> + unsigned long size,
> + unsigned long min,
> + unsigned long *s);
From these parameter names I'm unable to tell what the "aligned" part of
the name is referring to. IOW it may be necessary to have an accompanying
comment.
Jan
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v2 7/7] arm/pci: enable vpci for hwdom when pci-scan is enabled
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
` (4 preceding siblings ...)
2025-10-22 13:56 ` [PATCH v2 5/7] xen/pci: initialize BARs Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 13:56 ` [PATCH v2 6/7] xen/pci: assign discovered devices to hwdom Mykyta Poturai
6 siblings, 0 replies; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykyta Poturai, Stefano Stabellini, Julien Grall,
Bertrand Marquis, Michal Orzel, Volodymyr Babchuk
With pci-scan implemented it is now possible to use vpci for hardware
domains. Update has_vpci to reflect this change.
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* fix typo in commit message
---
xen/arch/arm/include/asm/domain.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/xen/arch/arm/include/asm/domain.h b/xen/arch/arm/include/asm/domain.h
index af3e168374..dbe3347cea 100644
--- a/xen/arch/arm/include/asm/domain.h
+++ b/xen/arch/arm/include/asm/domain.h
@@ -305,8 +305,7 @@ static inline void arch_vcpu_block(struct vcpu *v) {}
#define arch_vm_assist_valid_mask(d) (1UL << VMASST_TYPE_runstate_update_flag)
-/* vPCI is not available on Arm */
-#define has_vpci(d) ({ (void)(d); false; })
+#define has_vpci(d) (is_hardware_domain(d) && hwdom_uses_vpci())
struct arch_vcpu_io {
struct instr_details dabt_instr; /* when the instruction is decoded */
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v2 6/7] xen/pci: assign discovered devices to hwdom
2025-10-22 13:56 [PATCH v2 0/7] Implement PCI device enumeration on Arm Mykyta Poturai
` (5 preceding siblings ...)
2025-10-22 13:56 ` [PATCH v2 7/7] arm/pci: enable vpci for hwdom when pci-scan is enabled Mykyta Poturai
@ 2025-10-22 13:56 ` Mykyta Poturai
2025-10-22 14:44 ` Jan Beulich
6 siblings, 1 reply; 11+ messages in thread
From: Mykyta Poturai @ 2025-10-22 13:56 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Luca Fancellu, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Jan Beulich,
Roger Pau Monné, Stewart Hildebrand, Mykyta Poturai
From: Luca Fancellu <luca.fancellu@arm.com>
Hook up existing PCI setup routines for hwdom into Arm iommu
initialization sequence, only assign endpoint devices.
During scanned PCI device assignment, also permit access to the BAR
ranges if hwdom is using vpci and hide host bridges from domains that
use the fully emulated one.
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
---
v1->v2:
* add host bridge hiding
* fix build without CONFIG_HAS_PCI
---
xen/drivers/passthrough/arm/iommu.c | 13 +++++++++
xen/drivers/passthrough/pci.c | 41 ++++++++++++++++++++++++++++-
2 files changed, 53 insertions(+), 1 deletion(-)
diff --git a/xen/drivers/passthrough/arm/iommu.c b/xen/drivers/passthrough/arm/iommu.c
index 100545e23f..340659853d 100644
--- a/xen/drivers/passthrough/arm/iommu.c
+++ b/xen/drivers/passthrough/arm/iommu.c
@@ -19,6 +19,7 @@
#include <xen/device_tree.h>
#include <xen/iommu.h>
#include <xen/lib.h>
+#include <xen/sched.h>
#include <asm/device.h>
@@ -133,6 +134,14 @@ void arch_iommu_domain_destroy(struct domain *d)
{
}
+#ifdef CONFIG_HAS_PCI
+static int iommu_add_hwdom_pci_device(u8 devfn, struct pci_dev *pdev)
+{
+ const struct domain_iommu *hd = dom_iommu(hardware_domain);
+ return iommu_call(hd->platform_ops, add_device, devfn, pci_to_dev(pdev));
+}
+#endif
+
void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
{
/* Set to false options not supported on ARM. */
@@ -142,6 +151,10 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
if ( iommu_hwdom_reserved == 1 )
printk(XENLOG_WARNING "map-reserved dom0-iommu option is not supported on ARM\n");
iommu_hwdom_reserved = 0;
+
+#ifdef CONFIG_HAS_PCI
+ setup_hwdom_pci_devices(d, iommu_add_hwdom_pci_device);
+#endif
}
/*
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 4f5de9a542..076739031b 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -20,6 +20,7 @@
#include <xen/pci_ids.h>
#include <xen/list.h>
#include <xen/prefetch.h>
+#include <xen/iocap.h>
#include <xen/iommu.h>
#include <xen/irq.h>
#include <xen/param.h>
@@ -1040,6 +1041,12 @@ enum pdev_type pdev_type(u16 seg, u8 bus, u8 devfn)
return pos ? DEV_TYPE_PCIe_ENDPOINT : DEV_TYPE_PCI;
}
+static bool pdev_is_endpoint(struct pci_dev *pdev)
+{
+ enum pdev_type type = pdev_type(pdev->seg, pdev->bus, pdev->devfn);
+ return type == DEV_TYPE_PCIe_ENDPOINT || type == DEV_TYPE_PCI;
+}
+
/*
* find the upstream PCIe-to-PCI/PCIX bridge or PCI legacy bridge
* return 0: the device is integrated PCI device or PCIe
@@ -1255,7 +1262,7 @@ static void __hwdom_init setup_one_hwdom_device(const struct setup_hwdom *ctxt,
struct pci_dev *pdev)
{
u8 devfn = pdev->devfn;
- int err;
+ int err, i, rc;
do {
err = ctxt->handler(devfn, pdev);
@@ -1276,6 +1283,34 @@ static void __hwdom_init setup_one_hwdom_device(const struct setup_hwdom *ctxt,
if ( err )
printk(XENLOG_ERR "setup of vPCI for d%d failed: %d\n",
ctxt->d->domain_id, err);
+
+ if ( !has_vpci_bridge(hardware_domain) )
+ return;
+
+ for ( i = 0; i < PCI_HEADER_NORMAL_NR_BARS; i += rc )
+ {
+ uint64_t addr, size;
+ uint8_t reg = PCI_BASE_ADDRESS_0 + i * 4;
+
+ if ( (pci_conf_read32(pdev->sbdf, reg) & PCI_BASE_ADDRESS_SPACE)
+ == PCI_BASE_ADDRESS_SPACE_IO )
+ {
+ rc = 1;
+ continue;
+ }
+
+ rc = pci_size_mem_bar(pdev->sbdf, reg, &addr, &size,
+ (i == PCI_HEADER_NORMAL_NR_BARS - 1)
+ ? PCI_BAR_LAST : 0);
+
+ if ( !size )
+ continue;
+
+ err = iomem_permit_access(hardware_domain, paddr_to_pfn(addr),
+ paddr_to_pfn(PAGE_ALIGN(addr + size - 1)));
+ if ( err )
+ break;
+ }
}
static int __hwdom_init cf_check _setup_hwdom_pci_devices(
@@ -1294,6 +1329,10 @@ static int __hwdom_init cf_check _setup_hwdom_pci_devices(
if ( !pdev )
continue;
+ /* Hide real bridges from HWdom when it's using the emulated one */
+ if ( has_vpci_bridge(hardware_domain) && !pdev_is_endpoint(pdev) )
+ pci_hide_device(pdev->seg, pdev->bus, pdev->devfn);
+
if ( !pdev->domain )
{
pdev->domain = ctxt->d;
--
2.34.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH v2 6/7] xen/pci: assign discovered devices to hwdom
2025-10-22 13:56 ` [PATCH v2 6/7] xen/pci: assign discovered devices to hwdom Mykyta Poturai
@ 2025-10-22 14:44 ` Jan Beulich
0 siblings, 0 replies; 11+ messages in thread
From: Jan Beulich @ 2025-10-22 14:44 UTC (permalink / raw)
To: Mykyta Poturai
Cc: Luca Fancellu, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Roger Pau Monné,
Stewart Hildebrand, xen-devel@lists.xenproject.org
On 22.10.2025 15:56, Mykyta Poturai wrote:
> From: Luca Fancellu <luca.fancellu@arm.com>
>
> Hook up existing PCI setup routines for hwdom into Arm iommu
> initialization sequence, only assign endpoint devices.
>
> During scanned PCI device assignment, also permit access to the BAR
> ranges if hwdom is using vpci and hide host bridges from domains that
> use the fully emulated one.
>
> Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>
> Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
> Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
From: and first S-o-b don't match, which either is wrong or needs an explanation.
> @@ -1255,7 +1262,7 @@ static void __hwdom_init setup_one_hwdom_device(const struct setup_hwdom *ctxt,
> struct pci_dev *pdev)
> {
> u8 devfn = pdev->devfn;
> - int err;
> + int err, i, rc;
I doubt i wants to be signed, and as per its use below rc also wants to be
unsigned. rc (generally standing for "return code") also may be a misleading
name for the variable. Elsewhere we use "ret".
> @@ -1276,6 +1283,34 @@ static void __hwdom_init setup_one_hwdom_device(const struct setup_hwdom *ctxt,
> if ( err )
> printk(XENLOG_ERR "setup of vPCI for d%d failed: %d\n",
> ctxt->d->domain_id, err);
> +
> + if ( !has_vpci_bridge(hardware_domain) )
> + return;
This (and the other one further down) is odd to see, as it'll expand to
!is_hardware_domain(hardware_domain) (with, for Arm, some 2nd check, yes).
> + for ( i = 0; i < PCI_HEADER_NORMAL_NR_BARS; i += rc )
What about the ROM BAR?
> + {
> + uint64_t addr, size;
> + uint8_t reg = PCI_BASE_ADDRESS_0 + i * 4;
> +
> + if ( (pci_conf_read32(pdev->sbdf, reg) & PCI_BASE_ADDRESS_SPACE)
> + == PCI_BASE_ADDRESS_SPACE_IO )
> + {
> + rc = 1;
> + continue;
> + }
> +
> + rc = pci_size_mem_bar(pdev->sbdf, reg, &addr, &size,
> + (i == PCI_HEADER_NORMAL_NR_BARS - 1)
> + ? PCI_BAR_LAST : 0);
Nit: Indentation.
> + if ( !size )
> + continue;
> +
> + err = iomem_permit_access(hardware_domain, paddr_to_pfn(addr),
> + paddr_to_pfn(PAGE_ALIGN(addr + size - 1)));
Again.
Also this one may read better when you use PFN_DOWN() and PFN_UP(). Of course
I wonder what the result would be if there were non-page-aligned, multiple-of-
page-size BARs.
Jan
^ permalink raw reply [flat|nested] 11+ messages in thread