Merge tag 'migration-20230213-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request (take3)

Hi

In this PULL request:
- Added to leonardo fixes:
Fixes: b5eea99ec2 ("migration: Add yank feature")
Reported-by: Li Xiaohui <xiaohli@redhat.com>

Please apply.

[take 2]
- rebase to latest upstream
- fix compilation of linux-user (if have_system was missing) (me)
- cleanup multifd_load_cleanup(leonardo)
- Document RAM flags (me)

Please apply.

[take 1]
This are all the reviewed patches for migration:
- AVX512 support for xbzrle (Ling Xu)
- /dev/userfaultd support (Peter Xu)
- Improve ordering of channels (Peter Xu)
- multifd cleanups (Li Zhang)
- Remove spurious files from last merge (me)
  Rebase makes that to you
- Fix mixup between state_pending_{exact,estimate} (me)
- Cache RAM size during migration (me)
- cleanup several functions (me)

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmPppZYACgkQ9IfvGFhy
# 1yPLvQ//f8D6txzFawaxrfzpSAHnq70Gx+B5GkIwgwB8nlPIC3QELEf5uooM/RGA
# nSaUctUNOJUWqVGK3vp3jDIep02DzdIUrlOfy96h+pnTMpyMWFC2BexDfveVMUId
# dw8WCWZkGCFDfIWuKF+GA8eTu6HM1ouzgCJrRmPtCqsikzAPkogPm60hQSTAQxm9
# Kzdp1SXV1HmyA440vy8rtYf71BKpvb9OJFmwgZ+ICy0rc1aUmgJbKxkwyOgiI2lq
# ONekpbOg7lzlFVAQu1QHTmYN13bsn4uzwUgdifn1PixFQyRE3AVs4jdTmqeLnoPe
# Ac6j8v3pDOw/Xf4kpRWUmhkqTMEJt8/lyneJzu1mQkw0wwiUtDvknFgPG8wJsa+J
# ZQr1cBXQj4IjtkN6+ixF7XYvx3T6pWz0L+/w2+TbFBdLWIrPgFH0yPYjhx7FdDid
# cjUHyS1a0w9ngnXOxRG8+UNHWCpPOUhXeeiyNioogYZNKu77PFxJVDMe3eB6dXAB
# pDfl4P129PloKAPafcz9E6Sxr+lIgrETZmsRJlRz4czg18TxlIukMlDtyrepNWti
# GtIf9xTpP3JKjpHnKbWLaxP5VeFC7kQd0qas4VxD+tDjbJdUZdZMfHcOSS0SMRGe
# q5LVEzMMIPCQJQIqiLEJ0HTUUOtB8i+bGoirNEbDqhLa/oZwPP8=
# =TDnO
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 13 Feb 2023 02:51:02 GMT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20230213-pull-request' of https://gitlab.com/juan.quintela/qemu: (22 commits)
  ram: Document migration ram flags
  migration/multifd: Move load_cleanup inside incoming_state_destroy
  migration/multifd: Join all multifd threads in order to avoid leaks
  migration/multifd: Remove unnecessary assignment on multifd_load_cleanup()
  migration/multifd: Change multifd_load_cleanup() signature and usage
  migration: Postpone postcopy preempt channel to be after main
  migration: Add a semaphore to count PONGs
  migration: Cleanup postcopy_preempt_setup()
  migration: Rework multi-channel checks on URI
  Update bench-code for addressing CI problem
  AVX512 support for xbzrle_encode_buffer
  migration: I messed state_pending_exact/estimate
  migration: Make ram_save_target_page() a pointer
  migration: Calculate ram size once
  migration: Split ram_bytes_total_common() in two functions
  migration: Make find_dirty_block() return a single parameter
  migration: Simplify ram_find_and_save_block()
  util/userfaultfd: Support /dev/userfaultfd
  linux-headers: Update to v6.1
  multifd: Remove some redundant code
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 161 insertions, 0 deletions

diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index ebdafa576d..b2783c5202 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -1175,6 +1175,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
 #define KVM_CAP_S390_ZPCI_OP 221
 #define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/linux-headers/linux/psci.h b/linux-headers/linux/psci.h
index 213b2a0f70..e60dfd8907 100644
--- a/linux-headers/linux/psci.h
+++ b/linux-headers/linux/psci.h
@@ -48,12 +48,26 @@
 #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
 
 #define PSCI_1_0_FN_PSCI_FEATURES		PSCI_0_2_FN(10)
+#define PSCI_1_0_FN_CPU_FREEZE			PSCI_0_2_FN(11)
+#define PSCI_1_0_FN_CPU_DEFAULT_SUSPEND		PSCI_0_2_FN(12)
+#define PSCI_1_0_FN_NODE_HW_STATE		PSCI_0_2_FN(13)
 #define PSCI_1_0_FN_SYSTEM_SUSPEND		PSCI_0_2_FN(14)
 #define PSCI_1_0_FN_SET_SUSPEND_MODE		PSCI_0_2_FN(15)
+#define PSCI_1_0_FN_STAT_RESIDENCY		PSCI_0_2_FN(16)
+#define PSCI_1_0_FN_STAT_COUNT			PSCI_0_2_FN(17)
+
 #define PSCI_1_1_FN_SYSTEM_RESET2		PSCI_0_2_FN(18)
+#define PSCI_1_1_FN_MEM_PROTECT			PSCI_0_2_FN(19)
+#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN(19)
 
+#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND	PSCI_0_2_FN64(12)
+#define PSCI_1_0_FN64_NODE_HW_STATE		PSCI_0_2_FN64(13)
 #define PSCI_1_0_FN64_SYSTEM_SUSPEND		PSCI_0_2_FN64(14)
+#define PSCI_1_0_FN64_STAT_RESIDENCY		PSCI_0_2_FN64(16)
+#define PSCI_1_0_FN64_STAT_COUNT		PSCI_0_2_FN64(17)
+
 #define PSCI_1_1_FN64_SYSTEM_RESET2		PSCI_0_2_FN64(18)
+#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN64(19)
 
 /* PSCI v0.2 power state encoding for CPU_SUSPEND function */
 #define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h
index a3a377cd44..ba5d0df52f 100644
--- a/linux-headers/linux/userfaultfd.h
+++ b/linux-headers/linux/userfaultfd.h
@@ -12,6 +12,10 @@
 
 #include <linux/types.h>
 
+/* ioctls for /dev/userfaultfd */
+#define USERFAULTFD_IOC 0xAA
+#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
+
 /*
  * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
  * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR.  In
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index ede44b5572..bee7e42198 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -986,6 +986,148 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
 };
 
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
+ * state with the platform-based power management.  Device use of lower power
+ * states depends on factors managed by the runtime power management core,
+ * including system level support and coordinating support among dependent
+ * devices.  Enabling device low power entry does not guarantee lower power
+ * usage by the device, nor is a mechanism provided through this feature to
+ * know the current power state of the device.  If any device access happens
+ * (either from the host or through the vfio uAPI) when the device is in the
+ * low power state, then the host will move the device out of the low power
+ * state as necessary prior to the access.  Once the access is completed, the
+ * device may re-enter the low power state.  For single shot low power support
+ * with wake-up notification, see
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below.  Access to mmap'd
+ * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after
+ * calling LOW_POWER_EXIT.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3
+
+/*
+ * This device feature has the same behavior as
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user
+ * provides an eventfd for wake-up notification.  When the device moves out of
+ * the low power state for the wake-up, the host will not allow the device to
+ * re-enter a low power state without a subsequent user call to one of the low
+ * power entry device feature IOCTLs.  Access to mmap'd device regions is
+ * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the
+ * low power exit.  The low power exit can happen either through LOW_POWER_EXIT
+ * or through any other access (where the wake-up notification has been
+ * generated).  The access to mmap'd device regions will not trigger low power
+ * exit.
+ *
+ * The notification through the provided eventfd will be generated only when
+ * the device has entered and is resumed from a low power state after
+ * calling this device feature IOCTL.  A device that has not entered low power
+ * state, as managed through the runtime power management core, will not
+ * generate a notification through the provided eventfd on access.  Calling the
+ * LOW_POWER_EXIT feature is optional in the case where notification has been
+ * signaled on the provided eventfd that a resume from low power has occurred.
+ */
+struct vfio_device_low_power_entry_with_wakeup {
+	__s32 wakeup_eventfd;
+	__u32 reserved;
+};
+
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as
+ * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features.
+ * This device feature IOCTL may itself generate a wakeup eventfd notification
+ * in the latter case if the device had previously entered a low power state.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging.
+ * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports
+ * DMA logging.
+ *
+ * DMA logging allows a device to internally record what DMAs the device is
+ * initiating and report them back to userspace. It is part of the VFIO
+ * migration infrastructure that allows implementing dirty page tracking
+ * during the pre copy phase of live migration. Only DMA WRITEs are logged,
+ * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE.
+ *
+ * When DMA logging is started a range of IOVAs to monitor is provided and the
+ * device can optimize its logging to cover only the IOVA range given. Each
+ * DMA that the device initiates inside the range will be logged by the device
+ * for later retrieval.
+ *
+ * page_size is an input that hints what tracking granularity the device
+ * should try to achieve. If the device cannot do the hinted page size then
+ * it's the driver choice which page size to pick based on its support.
+ * On output the device will return the page size it selected.
+ *
+ * ranges is a pointer to an array of
+ * struct vfio_device_feature_dma_logging_range.
+ *
+ * The core kernel code guarantees to support by minimum num_ranges that fit
+ * into a single kernel page. User space can try higher values but should give
+ * up if the above can't be achieved as of some driver limitations.
+ *
+ * A single call to start device DMA logging can be issued and a matching stop
+ * should follow at the end. Another start is not allowed in the meantime.
+ */
+struct vfio_device_feature_dma_logging_control {
+	__aligned_u64 page_size;
+	__u32 num_ranges;
+	__u32 __reserved;
+	__aligned_u64 ranges;
+};
+
+struct vfio_device_feature_dma_logging_range {
+	__aligned_u64 iova;
+	__aligned_u64 length;
+};
+
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started
+ * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START
+ */
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log
+ *
+ * Query the device's DMA log for written pages within the given IOVA range.
+ * During querying the log is cleared for the IOVA range.
+ *
+ * bitmap is a pointer to an array of u64s that will hold the output bitmap
+ * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits
+ * is given by:
+ *  bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64))
+ *
+ * The input page_size can be any power of two value and does not have to
+ * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver
+ * will format its internal logging to match the reporting page size, possibly
+ * by replicating bits if the internal page size is lower than requested.
+ *
+ * The LOGGING_REPORT will only set bits in the bitmap and never clear or
+ * perform any initialization of the user provided bitmap.
+ *
+ * If any error is returned userspace should assume that the dirty log is
+ * corrupted. Error recovery is to consider all memory dirty and try to
+ * restart the dirty tracking, or to abort/restart the whole migration.
+ *
+ * If DMA logging is not enabled, an error will be returned.
+ *
+ */
+struct vfio_device_feature_dma_logging_report {
+	__aligned_u64 iova;
+	__aligned_u64 length;
+	__aligned_u64 page_size;
+	__aligned_u64 bitmap;
+};
+
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**