From: Praveen Kumar <kumarpraveen@linux.microsoft.com>
To: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: kys@microsoft.com, haiyangz@microsoft.com,
sthemmin@microsoft.com, wei.liu@kernel.org, decui@microsoft.com,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
x86@kernel.org, hpa@zytor.com, viremana@linux.microsoft.com,
sunilmut@microsoft.com, nunodasneves@linux.microsoft.com
Subject: [PATCH v3] hyperv: root partition faults writing to VP ASSIST MSR PAGE
Date: Tue, 27 Jul 2021 16:10:44 +0530 [thread overview]
Message-ID: <20210727104044.28078-1-kumarpraveen@linux.microsoft.com> (raw)
For Root partition the VP assist pages are pre-determined by the
hypervisor. The Root kernel is not allowed to change them to
different locations. And thus, we are getting below stack as in
current implementation Root is trying to perform write to specific
MSR.
[ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to
write 0x0000000145ac5001) at rIP: 0xffffffff810c1084
(native_write_msr+0x4/0x30)
[ 2.784867] Call Trace:
[ 2.791507] hv_cpu_init+0xf1/0x1c0
[ 2.798144] ? hyperv_report_panic+0xd0/0xd0
[ 2.804806] cpuhp_invoke_callback+0x11a/0x440
[ 2.811465] ? hv_resume+0x90/0x90
[ 2.818137] cpuhp_issue_call+0x126/0x130
[ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0
[ 2.831427] ? hyperv_report_panic+0xd0/0xd0
[ 2.838075] ? hyperv_report_panic+0xd0/0xd0
[ 2.844723] ? hv_resume+0x90/0x90
[ 2.851375] __cpuhp_setup_state+0x3d/0x90
[ 2.858030] hyperv_init+0x14e/0x410
[ 2.864689] ? enable_IR_x2apic+0x190/0x1a0
[ 2.871349] apic_intr_mode_init+0x8b/0x100
[ 2.878017] x86_late_time_init+0x20/0x30
[ 2.884675] start_kernel+0x459/0x4fb
[ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb
Since, the hypervisor already provides the VP assist page for root
partition, we need to memremap the memory from hypervisor for root
kernel to use. The mapping is done in hv_cpu_init during bringup and
is unmaped in hv_cpu_die during teardown.
Signed-off-by: Praveen Kumar <kumarpraveen@linux.microsoft.com>
---
arch/x86/hyperv/hv_init.c | 61 +++++++++++++++++++++---------
arch/x86/include/asm/hyperv-tlfs.h | 9 +++++
2 files changed, 53 insertions(+), 17 deletions(-)
changelog:
v1: initial patch
v2: commit message changes, removal of HV_MSR_APIC_ACCESS_AVAILABLE
check and addition of null check before reading the VP assist MSR
for root partition
v3: added new data structure to handle VP ASSIST MSR page and done
handling in hv_cpu_init and hv_cpu_die
---
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 6f247e7e07eb..b859e42b4943 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -44,6 +44,7 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page);
static int hv_cpu_init(unsigned int cpu)
{
+ union hv_vp_assist_msr_contents msr;
struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
int ret;
@@ -54,27 +55,41 @@ static int hv_cpu_init(unsigned int cpu)
if (!hv_vp_assist_page)
return 0;
- /*
- * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section
- * 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure
- * we always write the EOI MSR in hv_apic_eoi_write() *after* the
- * EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may
- * not be stopped in the case of CPU offlining and the VM will hang.
- */
- if (!*hvp) {
- *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+ if (hv_root_partition) {
+ /*
+ * For Root partition we get the hypervisor provided VP ASSIST
+ * PAGE, instead of allocating a new page.
+ */
+ rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+
+ /* remapping to root partition address space */
+ if (!*hvp)
+ *hvp = memremap(msr.guest_physical_address <<
+ HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
+ PAGE_SIZE, MEMREMAP_WB);
+ } else {
+ /*
+ * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's
+ * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
+ * out to make sure we always write the EOI MSR in
+ * hv_apic_eoi_write() *after* theEOI optimization is disabled
+ * in hv_cpu_die(), otherwise a CPU may not be stopped in the
+ * case of CPU offlining and the VM will hang.
+ */
+ if (!*hvp)
+ *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+
}
- if (*hvp) {
- u64 val;
+ WARN_ON(!(*hvp));
- val = vmalloc_to_pfn(*hvp);
- val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
- HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+ if (*hvp) {
+ if (!hv_root_partition)
+ msr.guest_physical_address = vmalloc_to_pfn(*hvp);
- wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
+ msr.enable = 1;
+ wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
-
return 0;
}
@@ -170,9 +185,21 @@ static int hv_cpu_die(unsigned int cpu)
hv_common_cpu_die(cpu);
- if (hv_vp_assist_page && hv_vp_assist_page[cpu])
+ if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
+ if (hv_root_partition) {
+ /*
+ * For Root partition the VP ASSIST page is mapped to
+ * hypervisor provided page, and thus, we unmap the
+ * page here and nullify it, so that in future we have
+ * correct page address mapped in hv_cpu_init
+ */
+ memunmap(hv_vp_assist_page[cpu]);
+ hv_vp_assist_page[cpu] = NULL;
+ }
+ }
+
if (hv_reenlightenment_cb == NULL)
return 0;
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index f1366ce609e3..2e4e87046aa7 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -288,6 +288,15 @@ union hv_x64_msr_hypercall_contents {
} __packed;
};
+union hv_vp_assist_msr_contents {
+ u64 as_uint64;
+ struct {
+ u64 enable:1;
+ u64 reserved:11;
+ u64 guest_physical_address:52;
+ } __packed;
+};
+
struct hv_reenlightenment_control {
__u64 vector:8;
__u64 reserved1:8;
--
2.25.1
next reply other threads:[~2021-07-27 10:41 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-27 10:40 Praveen Kumar [this message]
2021-07-27 16:35 ` [PATCH v3] hyperv: root partition faults writing to VP ASSIST MSR PAGE Michael Kelley
2021-07-27 16:51 ` Sunil Muthuswamy
2021-07-27 16:58 ` Praveen Kumar
2021-07-27 16:45 ` Sunil Muthuswamy
2021-07-27 17:12 ` Praveen Kumar
2021-07-27 17:23 ` Sunil Muthuswamy
2021-07-27 17:51 ` Wei Liu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210727104044.28078-1-kumarpraveen@linux.microsoft.com \
--to=kumarpraveen@linux.microsoft.com \
--cc=bp@alien8.de \
--cc=decui@microsoft.com \
--cc=haiyangz@microsoft.com \
--cc=hpa@zytor.com \
--cc=kys@microsoft.com \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nunodasneves@linux.microsoft.com \
--cc=sthemmin@microsoft.com \
--cc=sunilmut@microsoft.com \
--cc=tglx@linutronix.de \
--cc=viremana@linux.microsoft.com \
--cc=wei.liu@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).