File 67c818d5-x86-fixup-p2m-page-faults-for-PVH-dom0.patch of Package xen
References: bsc#1227301
# Commit 104591f5dd675d7bfb04885dace0e4e5a097fc1e
# Date 2025-03-05 10:26:46 +0100
# Author Roger Pau Monne <roger.pau@citrix.com>
# Committer Roger Pau Monne <roger.pau@citrix.com>
x86/dom0: attempt to fixup p2m page-faults for PVH dom0
When building a PVH dom0 Xen attempts to map all (relevant) MMIO regions
into the p2m for dom0 access. However the information Xen has about the
host memory map is limited. Xen doesn't have access to any resources
described in ACPI dynamic tables, and hence the p2m mappings provided might
not be complete.
PV doesn't suffer from this issue because a PV dom0 is capable of mapping
into it's page-tables any address not explicitly banned in d->iomem_caps.
Introduce a new command line options that allows Xen to attempt to fixup
the p2m page-faults, by creating p2m identity maps in response to p2m
page-faults.
This is aimed as a workaround to small ACPI regions Xen doesn't know about.
Note that missing large MMIO regions mapped in this way will lead to
slowness due to the VM exit processing, plus the mappings will always use
small pages.
The ultimate aim is to attempt to bring better parity with a classic PV
dom0.
Note such fixup rely on the CPU doing the access to the unpopulated
address. If the access is attempted from a device instead there's no
possible way to fixup, as IOMMU page-fault are asynchronous.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Oleksii Kurochko <oleksii.kurochko@gmail.com>
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,12 @@ Notable changes to Xen will be documente
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
+## [4.20.1](https://xenbits.xenproject.org/gitweb/?p=xen.git;a=shortlog;h=RELEASE-4.20.1)
+
+### Added
+ - On x86:
+ - Option to attempt to fixup p2m page-faults on PVH dom0.
+
## [4.20.0](https://xenbits.xenproject.org/gitweb/?p=xen.git;a=shortlog;h=RELEASE-4.20.0) - 2025-03-05
### Changed
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -822,7 +822,8 @@ Specify the bit width of the DMA heap.
### dom0
= List of [ pv | pvh, shadow=<bool>, verbose=<bool>,
- cpuid-faulting=<bool>, msr-relaxed=<bool> ] (x86)
+ cpuid-faulting=<bool>, msr-relaxed=<bool>,
+ pf-fixup=<bool> ] (x86)
= List of [ sve=<integer> ] (Arm64)
@@ -883,6 +884,19 @@ Controls for how dom0 is constructed on
If using this option is necessary to fix an issue, please report a bug.
+* The `pf-fixup` boolean is only applicable when using a PVH dom0 and
+ defaults to false.
+
+ When running dom0 in PVH mode the dom0 kernel has no way to map MMIO
+ regions into its physical memory map, such mode relies on Xen dom0 builder
+ populating the physical memory map with all MMIO regions that dom0 should
+ access. However Xen doesn't have a complete picture of the host memory
+ map, due to not being able to process ACPI dynamic tables.
+
+ The `pf-fixup` option allows Xen to attempt to add missing MMIO regions
+ to the dom0 physical memory map in response to page-faults generated by
+ dom0 trying to access unpopulated entries in the memory map.
+
Enables features on dom0 on Arm systems.
* The `sve` integer parameter enables Arm SVE usage for Dom0 and sets the
--- a/xen/arch/x86/dom0_build.c
+++ b/xen/arch/x86/dom0_build.c
@@ -16,6 +16,7 @@
#include <asm/dom0_build.h>
#include <asm/guest.h>
#include <asm/hpet.h>
+#include <asm/hvm/emulate.h>
#include <asm/io-ports.h>
#include <asm/io_apic.h>
#include <asm/p2m.h>
@@ -286,6 +287,10 @@ int __init parse_arch_dom0_param(const c
opt_dom0_cpuid_faulting = val;
else if ( (val = parse_boolean("msr-relaxed", s, e)) >= 0 )
opt_dom0_msr_relaxed = val;
+#ifdef CONFIG_HVM
+ else if ( (val = parse_boolean("pf-fixup", s, e)) >= 0 )
+ opt_dom0_pf_fixup = val;
+#endif
else
return -EINVAL;
--- a/xen/arch/x86/hvm/emulate.c
+++ b/xen/arch/x86/hvm/emulate.c
@@ -10,12 +10,15 @@
*/
#include <xen/init.h>
+#include <xen/iocap.h>
#include <xen/ioreq.h>
#include <xen/lib.h>
#include <xen/sched.h>
#include <xen/paging.h>
#include <xen/trace.h>
#include <xen/vm_event.h>
+
+#include <asm/altp2m.h>
#include <asm/event.h>
#include <asm/i387.h>
#include <asm/xstate.h>
@@ -161,6 +164,36 @@ void hvmemul_cancel(struct vcpu *v)
hvmemul_cache_disable(v);
}
+bool __ro_after_init opt_dom0_pf_fixup;
+static int hwdom_fixup_p2m(paddr_t addr)
+{
+ unsigned long gfn = paddr_to_pfn(addr);
+ struct domain *currd = current->domain;
+ p2m_type_t type;
+ mfn_t mfn;
+ int rc;
+
+ ASSERT(is_hardware_domain(currd));
+ ASSERT(!altp2m_active(currd));
+
+ /*
+ * Fixups are only applied for MMIO holes, and rely on the hardware domain
+ * having identity mappings for non RAM regions (gfn == mfn).
+ */
+ if ( !iomem_access_permitted(currd, gfn, gfn) ||
+ !is_memory_hole(_mfn(gfn), _mfn(gfn)) )
+ return -EPERM;
+
+ mfn = get_gfn(currd, gfn, &type);
+ if ( !mfn_eq(mfn, INVALID_MFN) || !p2m_is_hole(type) )
+ rc = mfn_eq(mfn, _mfn(gfn)) ? -EEXIST : -ENOTEMPTY;
+ else
+ rc = set_mmio_p2m_entry(currd, _gfn(gfn), _mfn(gfn), 0);
+ put_gfn(currd, gfn);
+
+ return rc;
+}
+
static int hvmemul_do_io(
bool is_mmio, paddr_t addr, unsigned long *reps, unsigned int size,
uint8_t dir, bool df, bool data_is_addr, uintptr_t data)
@@ -338,8 +371,45 @@ static int hvmemul_do_io(
if ( !s )
{
if ( is_mmio && is_hardware_domain(currd) )
- gdprintk(XENLOG_DEBUG, "unhandled memory %s %#lx size %u\n",
- dir ? "read from" : "write to", addr, size);
+ {
+ /*
+ * PVH dom0 is likely missing MMIO mappings on the p2m, due to
+ * the incomplete information Xen has about the memory layout.
+ *
+ * Either print a message to note dom0 attempted to access an
+ * unpopulated GPA, or try to fixup the p2m by creating an
+ * identity mapping for the faulting GPA.
+ */
+ if ( opt_dom0_pf_fixup )
+ {
+ int inner_rc = hwdom_fixup_p2m(addr);
+
+ if ( !inner_rc || inner_rc == -EEXIST )
+ {
+ if ( !inner_rc )
+ gdprintk(XENLOG_DEBUG,
+ "fixup p2m mapping for page %lx added\n",
+ paddr_to_pfn(addr));
+ else
+ gprintk(XENLOG_INFO,
+ "fixup p2m mapping for page %lx already present\n",
+ paddr_to_pfn(addr));
+
+ rc = X86EMUL_RETRY;
+ vio->req.state = STATE_IOREQ_NONE;
+ break;
+ }
+
+ gprintk(XENLOG_WARNING,
+ "unable to fixup memory %s %#lx size %u: %d\n",
+ dir ? "read from" : "write to", addr, size,
+ inner_rc);
+ }
+ else
+ gdprintk(XENLOG_DEBUG,
+ "unhandled memory %s %#lx size %u\n",
+ dir ? "read from" : "write to", addr, size);
+ }
rc = hvm_process_io_intercept(&null_handler, &p);
vio->req.state = STATE_IOREQ_NONE;
}
--- a/xen/arch/x86/include/asm/hvm/emulate.h
+++ b/xen/arch/x86/include/asm/hvm/emulate.h
@@ -148,6 +148,9 @@ static inline void hvmemul_write_cache(c
void hvm_dump_emulation_state(const char *loglvl, const char *prefix,
struct hvm_emulate_ctxt *hvmemul_ctxt, int rc);
+/* For PVH dom0: signal whether to attempt fixup of p2m page-faults. */
+extern bool opt_dom0_pf_fixup;
+
#endif /* __ASM_X86_HVM_EMULATE_H__ */
/*
