Skip to contentSkip to conversation

hv: Remove dependencies on guest page size

PATCH Superseded Maya Nakamura 2 participants 12 messages Jun 6, 2019 – Jun 17, 2019 1 message not in the archive

Subsystems (5)

v2 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

v2 cover hv: Remove dependencies on guest page size

The Linux guest page size and hypervisor page size concepts are different, even though they happen to be the same value on x86. Hyper-V code mixes up the two, so this patchset begins to address that by creating and using a set of Hyper-V specific page definitions.

A major benefit of those new definitions is that they support non-x86 architectures, such as ARM64, that use different page sizes. On ARM64, the guest page size may not be 4096, and Hyper-V always runs with a page size of 4096.

In this patchset, the first two patches lay the foundation for the others, creating definitions and preparing for allocation of memory with the size and alignment that Hyper-V expects as a page. Patch 3 applies the page size definition where the guest VM and Hyper-V communicate, and where the code intends to use the Hyper-V page size. The last two patches set the ring buffer size to a fixed value, removing the dependency on the guest page size.

This is the initial set of changes to the Hyper-V code, and future patches will make additional changes using the same foundation, for example, replace __vmalloc() and related functions when Hyper-V pages are intended.

Changes in v2:
- [PATCH 2/5] Replace with a new patch.

Maya Nakamura (5):
x86: hv: hyperv-tlfs.h: Create and use Hyper-V page definitions
x86: hv: hv_init.c: Add functions to allocate/deallocate page for
Hyper-V
hv: vmbus: Replace page definition with Hyper-V specific one
HID: hv: Remove dependencies on PAGE_SIZE for ring buffer
Input: hv: Remove dependencies on PAGE_SIZE for ring buffer

 arch/x86/hyperv/hv_init.c             | 14 ++++++++++++++
 arch/x86/include/asm/hyperv-tlfs.h    | 12 +++++++++++-
 drivers/hid/hid-hyperv.c              |  4 ++--
 drivers/hv/hyperv_vmbus.h             |  8 ++++----
 drivers/input/serio/hyperv-keyboard.c |  4 ++--
 5 files changed, 33 insertions(+), 9 deletions(-)
Signature · 1 line
2.17.1
#1 lore raw

PATCH v2 1/5 x86: hv: hyperv-tlfs.h: Create and use Hyper-V page definitions

Define HV_HYP_PAGE_SHIFT, HV_HYP_PAGE_SIZE, and HV_HYP_PAGE_MASK because the Linux guest page size and hypervisor page size concepts are different, even though they happen to be the same value on x86.

Also, replace PAGE_SIZE with HV_HYP_PAGE_SIZE.

---
 arch/x86/include/asm/hyperv-tlfs.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
arch/x86/include/asm/hyperv-tlfs.h +11 -1
index cdf44aa9a501..44bd68aefd00 100644
@@ -12,6 +12,16 @@
 #include <linux/types.h>
 #include <asm/page.h>
 
+/*
+ * While not explicitly listed in the TLFS, Hyper-V always runs with a page size
+ * of 4096. These definitions are used when communicating with Hyper-V using
+ * guest physical pages and guest physical page addresses, since the guest page
+ * size may not be 4096 on all architectures.
+ */
+#define HV_HYP_PAGE_SHIFT	12
+#define HV_HYP_PAGE_SIZE	BIT(HV_HYP_PAGE_SHIFT)
+#define HV_HYP_PAGE_MASK	(~(HV_HYP_PAGE_SIZE - 1))
+
 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
  * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
@@ -841,7 +851,7 @@ union hv_gpa_page_range {
  * count is equal with how many entries of union hv_gpa_page_range can
  * be populated into the input parameter page.
  */
-#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) /	\
+#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) /	\
 				sizeof(union hv_gpa_page_range))
 
 struct hv_guest_mapping_flush_list {
Signature · 1 line
2.17.1
Reviewed-by on v2 1/5
#2 lore raw

Re: [PATCH v2 1/5] x86: hv: hyperv-tlfs.h: Create and use Hyper-V page definitions

Quoted 33 lines · Maya Nakamura

Define HV_HYP_PAGE_SHIFT, HV_HYP_PAGE_SIZE, and HV_HYP_PAGE_MASK because the Linux guest page size and hypervisor page size concepts are different, even though they happen to be the same value on x86.

Also, replace PAGE_SIZE with HV_HYP_PAGE_SIZE.

---
 arch/x86/include/asm/hyperv-tlfs.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
arch/x86/include/asm/hyperv-tlfs.h +10 -0
index cdf44aa9a501..44bd68aefd00 100644
@@ -12,6 +12,16 @@
 #include <linux/types.h>
 #include <asm/page.h>
 
+/*
+ * While not explicitly listed in the TLFS, Hyper-V always runs with a page size
+ * of 4096. These definitions are used when communicating with Hyper-V using
+ * guest physical pages and guest physical page addresses, since the guest page
+ * size may not be 4096 on all architectures.
+ */
+#define HV_HYP_PAGE_SHIFT	12
+#define HV_HYP_PAGE_SIZE	BIT(HV_HYP_PAGE_SHIFT)
+#define HV_HYP_PAGE_MASK	(~(HV_HYP_PAGE_SIZE - 1))
+
 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
  * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).

arch/x86/include/asm/hyperv-tlfs.h union hv_gpa_page_range { · line 857

Quoted 8 lines
arch/x86/include/asm/hyperv-tlfs.h +1 -1
@@ -841,7 +851,7 @@ union hv_gpa_page_range {
  * count is equal with how many entries of union hv_gpa_page_range can
  * be populated into the input parameter page.
  */
-#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) /	\
+#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) /	\
 				sizeof(union hv_gpa_page_range))
 
 struct hv_guest_mapping_flush_list {
Signature · 1 line
Vitaly
#3 lore raw

PATCH v2 2/5 x86: hv: hv_init.c: Add functions to allocate/deallocate page for Hyper-V

In reply to Maya Nakamura

Introduce two new functions, hv_alloc_hyperv_page() and hv_free_hyperv_page(), to allocate/deallocate memory with the size and alignment that Hyper-V expects as a page. Although currently they are not used, they are ready to be used to allocate/deallocate memory on x86 when their ARM64 counterparts are implemented, keeping symmetry between architectures with potentially different guest page sizes.

---
 arch/x86/hyperv/hv_init.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
arch/x86/hyperv/hv_init.c +14 -0
index e4ba467a9fc6..84baf0e9a2d4 100644
@@ -98,6 +98,20 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
+void *hv_alloc_hyperv_page(void)
+{
+	BUILD_BUG_ON(!(PAGE_SIZE == HV_HYP_PAGE_SIZE));
+
+	return (void *)__get_free_page(GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	free_page(addr);
+}
+EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
Signature · 1 line
2.17.1
Reviewed-by on v2 2/5
#4 lore raw

Re: [PATCH v2 2/5] x86: hv: hv_init.c: Add functions to allocate/deallocate page for Hyper-V

Quoted 17 lines · Maya Nakamura

Introduce two new functions, hv_alloc_hyperv_page() and hv_free_hyperv_page(), to allocate/deallocate memory with the size and alignment that Hyper-V expects as a page. Although currently they are not used, they are ready to be used to allocate/deallocate memory on x86 when their ARM64 counterparts are implemented, keeping symmetry between architectures with potentially different guest page sizes.

---
 arch/x86/hyperv/hv_init.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
arch/x86/hyperv/hv_init.c +0 -0
index e4ba467a9fc6..84baf0e9a2d4 100644

arch/x86/hyperv/hv_init.c EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); · line 103

Quoted 6 lines
arch/x86/hyperv/hv_init.c +3 -0
@@ -98,6 +98,20 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
+void *hv_alloc_hyperv_page(void)
+{
+	BUILD_BUG_ON(!(PAGE_SIZE == HV_HYP_PAGE_SIZE));

(nit)

PAGE_SIZE != HV_HYP_PAGE_SIZE ?

Quoted 4 lines
arch/x86/hyperv/hv_init.c +4 -0
+
+	return (void *)__get_free_page(GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);

arch/x86/hyperv/hv_init.c EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); · line 117

Quoted 10 lines
arch/x86/hyperv/hv_init.c +7 -0
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	free_page(addr);
+}
+EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
Signature · 1 line
Vitaly
#5 lore raw

Re: [PATCH v2 2/5] x86: hv: hv_init.c: Add functions to allocate/deallocate page for Hyper-V

Quoted 30 lines · Vitaly Kuznetsov
Quoted 17 lines · Maya Nakamura

Introduce two new functions, hv_alloc_hyperv_page() and hv_free_hyperv_page(), to allocate/deallocate memory with the size and alignment that Hyper-V expects as a page. Although currently they are not used, they are ready to be used to allocate/deallocate memory on x86 when their ARM64 counterparts are implemented, keeping symmetry between architectures with potentially different guest page sizes.

---
 arch/x86/hyperv/hv_init.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
arch/x86/hyperv/hv_init.c +0 -0
index e4ba467a9fc6..84baf0e9a2d4 100644

arch/x86/hyperv/hv_init.c EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); · line 103

Quoted 6 lines
arch/x86/hyperv/hv_init.c +3 -0
@@ -98,6 +98,20 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
+void *hv_alloc_hyperv_page(void)
+{
+	BUILD_BUG_ON(!(PAGE_SIZE == HV_HYP_PAGE_SIZE));

(nit)

PAGE_SIZE != HV_HYP_PAGE_SIZE ?

Quoted 19 lines
Quoted 4 lines
arch/x86/hyperv/hv_init.c +4 -0
+
+	return (void *)__get_free_page(GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);

arch/x86/hyperv/hv_init.c EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); · line 117

Quoted 10 lines
arch/x86/hyperv/hv_init.c +7 -0
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	free_page(addr);
+}
+EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	u64 msr_vp_index;
Signature · 1 line
Vitaly

Agreed. I will resubmit the patch set with this correction.

#6 lore raw

PATCH v2 3/5 hv: vmbus: Replace page definition with Hyper-V specific one

In reply to Maya Nakamura

Replace PAGE_SIZE with HV_HYP_PAGE_SIZE because the guest page size may not be 4096 on all architectures and Hyper-V always runs with a page size of 4096.

---
 drivers/hv/hyperv_vmbus.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/hv/hyperv_vmbus.h +4 -4
index e5467b821f41..5489b061d261 100644
@@ -208,11 +208,11 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       u64 *requestid, bool raw);
 
 /*
- * Maximum channels is determined by the size of the interrupt page
- * which is PAGE_SIZE. 1/2 of PAGE_SIZE is for send endpoint interrupt
- * and the other is receive endpoint interrupt
+ * Maximum channels, 16348, is determined by the size of the interrupt page,
+ * which is HV_HYP_PAGE_SIZE. 1/2 of HV_HYP_PAGE_SIZE is to send endpoint
+ * interrupt, and the other is to receive endpoint interrupt.
  */
-#define MAX_NUM_CHANNELS	((PAGE_SIZE >> 1) << 3)	/* 16348 channels */
+#define MAX_NUM_CHANNELS	((HV_HYP_PAGE_SIZE >> 1) << 3)
 
 /* The value here must be in multiple of 32 */
 /* TODO: Need to make this configurable */
Signature · 1 line
2.17.1
Reviewed-by on v2 3/5
#7 lore raw

Re: [PATCH v2 3/5] hv: vmbus: Replace page definition with Hyper-V specific one

Quoted 19 lines · Maya Nakamura

Replace PAGE_SIZE with HV_HYP_PAGE_SIZE because the guest page size may not be 4096 on all architectures and Hyper-V always runs with a page size of 4096.

---
 drivers/hv/hyperv_vmbus.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/hv/hyperv_vmbus.h +0 -2
index e5467b821f41..5489b061d261 100644
@@ -208,11 +208,11 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       u64 *requestid, bool raw);
 
 /*
- * Maximum channels is determined by the size of the interrupt page
- * which is PAGE_SIZE. 1/2 of PAGE_SIZE is for send endpoint interrupt

drivers/hv/hyperv_vmbus.h int hv_ringbuffer_read(struct vmbus_channel *channel, · line 218

Quoted 10 lines
drivers/hv/hyperv_vmbus.h +4 -2
- * and the other is receive endpoint interrupt
+ * Maximum channels, 16348, is determined by the size of the interrupt page,
+ * which is HV_HYP_PAGE_SIZE. 1/2 of HV_HYP_PAGE_SIZE is to send endpoint
+ * interrupt, and the other is to receive endpoint interrupt.
  */
-#define MAX_NUM_CHANNELS	((PAGE_SIZE >> 1) << 3)	/* 16348 channels */
+#define MAX_NUM_CHANNELS	((HV_HYP_PAGE_SIZE >> 1) << 3)
 
 /* The value here must be in multiple of 32 */
 /* TODO: Need to make this configurable */
Signature · 1 line
Vitaly
#8 lore raw

PATCH v2 4/5 HID: hv: Remove dependencies on PAGE_SIZE for ring buffer

In reply to Maya Nakamura

Define the ring buffer size as a constant expression because it should not depend on the guest page size.

---
 drivers/hid/hid-hyperv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hid/hid-hyperv.c +2 -2
index d3311d714d35..e8b154fa38e2 100644
@@ -112,8 +112,8 @@ struct synthhid_input_report {
 
 #pragma pack(pop)
 
-#define INPUTVSC_SEND_RING_BUFFER_SIZE		(10*PAGE_SIZE)
-#define INPUTVSC_RECV_RING_BUFFER_SIZE		(10*PAGE_SIZE)
+#define INPUTVSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
+#define INPUTVSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
 
 
 enum pipe_prot_msg_type {
Signature · 1 line
2.17.1
#9 lore raw

Re: [PATCH v2 4/5] HID: hv: Remove dependencies on PAGE_SIZE for ring buffer

Quoted 13 lines · Maya Nakamura

Define the ring buffer size as a constant expression because it should not depend on the guest page size.

---
 drivers/hid/hid-hyperv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hid/hid-hyperv.c +0 -0
index d3311d714d35..e8b154fa38e2 100644

drivers/hid/hid-hyperv.c struct synthhid_input_report { · line 117

Quoted 8 lines
drivers/hid/hid-hyperv.c +2 -2
@@ -112,8 +112,8 @@ struct synthhid_input_report {
 
 #pragma pack(pop)
 
-#define INPUTVSC_SEND_RING_BUFFER_SIZE		(10*PAGE_SIZE)
-#define INPUTVSC_RECV_RING_BUFFER_SIZE		(10*PAGE_SIZE)
+#define INPUTVSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
+#define INPUTVSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
 

My understanding is that this size is pretty arbitrary and as I see you use it for hyperv-keyboard.c as well. It may make sense to have a define, something like HYPERV_STD_RINGBUFFER_SIZE.

Quoted 2 lines
drivers/hid/hid-hyperv.c +0 -0
 enum pipe_prot_msg_type {
Signature · 1 line
Vitaly

A message that is not in the archive (sent off-list or not yet received): BL0PR2101MB134877ED5DCB9F23033C92D9D7EF0@BL0PR2101MB1348.namprd21.prod.outlook.com

#11 lore raw

RE: [PATCH v2 4/5] HID: hv: Remove dependencies on PAGE_SIZE for ring buffer

Quoted 29 lines · Michael Kelley

From: Vitaly Kuznetsov <[email protected]> Sent: Wednesday, June 12, 2019 3:40 AM

Quoted 18 lines
Quoted 16 lines · Maya Nakamura

Define the ring buffer size as a constant expression because it should not depend on the guest page size.

---
 drivers/hid/hid-hyperv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hid/hid-hyperv.c +0 -0
index d3311d714d35..e8b154fa38e2 100644
@@ -112,8 +112,8 @@ struct synthhid_input_report {
 
 #pragma pack(pop)
 
Quoted 9 lines

drivers/hid/hid-hyperv.c struct synthhid_input_report { · line 117

Quoted 5 lines
drivers/hid/hid-hyperv.c +2 -2
-#define INPUTVSC_SEND_RING_BUFFER_SIZE		(10*PAGE_SIZE)
-#define INPUTVSC_RECV_RING_BUFFER_SIZE		(10*PAGE_SIZE)
+#define INPUTVSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
+#define INPUTVSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
 

My understanding is that this size is pretty arbitrary and as I see you use it for hyperv-keyboard.c as well. It may make sense to have a define, something like HYPERV_STD_RINGBUFFER_SIZE.

Quoted 6 lines

Yes, the size is pretty arbitrary because it hasn't been important enough from a memory consumption or performance standpoint to run experiments to see if a smaller value could be used. That said, I would not want to link these two devices (keyboard and mouse) by using a shared ring buffer size definition. Logically, the ring buffer sizes are independent of each other, and using a common #define implies that they are somehow linked.

Ok, makes sense, let's keep them separate.

Signature · 1 line
Vitaly
#12 lore raw

PATCH v2 5/5 Input: hv: Remove dependencies on PAGE_SIZE for ring buffer

In reply to Maya Nakamura

Define the ring buffer size as a constant expression because it should not depend on the guest page size.

---
 drivers/input/serio/hyperv-keyboard.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/input/serio/hyperv-keyboard.c +2 -2
index 7935e52b5435..a3480dbfadd2 100644
@@ -83,8 +83,8 @@ struct synth_kbd_keystroke {
 
 #define HK_MAXIMUM_MESSAGE_SIZE 256
 
-#define KBD_VSC_SEND_RING_BUFFER_SIZE		(10 * PAGE_SIZE)
-#define KBD_VSC_RECV_RING_BUFFER_SIZE		(10 * PAGE_SIZE)
+#define KBD_VSC_SEND_RING_BUFFER_SIZE		(40 * 1024)
+#define KBD_VSC_RECV_RING_BUFFER_SIZE		(40 * 1024)
 
 #define XTKBD_EMUL0     0xe0
 #define XTKBD_EMUL1     0xe1
Signature · 1 line
2.17.1