Merge 8d8d276ba2 ("Merge tag 'trace-v6.11-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace") into android-mainline

Steps on the way to 6.11

Change-Id: I47a9b6ab0b0e8d53ab98d93312f03a40fabf1f35
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Documentation/virt/hyperv/coco.rst

@@ -0,0 +1,260 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Confidential Computing VMs
+==========================
+Hyper-V can create and run Linux guests that are Confidential Computing
+(CoCo) VMs. Such VMs cooperate with the physical processor to better protect
+the confidentiality and integrity of data in the VM's memory, even in the
+face of a hypervisor/VMM that has been compromised and may behave maliciously.
+CoCo VMs on Hyper-V share the generic CoCo VM threat model and security
+objectives described in Documentation/security/snp-tdx-threat-model.rst. Note
+that Hyper-V specific code in Linux refers to CoCo VMs as "isolated VMs" or
+"isolation VMs".
+
+A Linux CoCo VM on Hyper-V requires the cooperation and interaction of the
+following:
+
+* Physical hardware with a processor that supports CoCo VMs
+
+* The hardware runs a version of Windows/Hyper-V with support for CoCo VMs
+
+* The VM runs a version of Linux that supports being a CoCo VM
+
+The physical hardware requirements are as follows:
+
+* AMD processor with SEV-SNP. Hyper-V does not run guest VMs with AMD SME,
+  SEV, or SEV-ES encryption, and such encryption is not sufficient for a CoCo
+  VM on Hyper-V.
+
+* Intel processor with TDX
+
+To create a CoCo VM, the "Isolated VM" attribute must be specified to Hyper-V
+when the VM is created. A VM cannot be changed from a CoCo VM to a normal VM,
+or vice versa, after it is created.
+
+Operational Modes
+-----------------
+Hyper-V CoCo VMs can run in two modes. The mode is selected when the VM is
+created and cannot be changed during the life of the VM.
+
+* Fully-enlightened mode. In this mode, the guest operating system is
+  enlightened to understand and manage all aspects of running as a CoCo VM.
+
+* Paravisor mode. In this mode, a paravisor layer between the guest and the
+  host provides some operations needed to run as a CoCo VM. The guest operating
+  system can have fewer CoCo enlightenments than is required in the
+  fully-enlightened case.
+
+Conceptually, fully-enlightened mode and paravisor mode may be treated as
+points on a spectrum spanning the degree of guest enlightenment needed to run
+as a CoCo VM. Fully-enlightened mode is one end of the spectrum. A full
+implementation of paravisor mode is the other end of the spectrum, where all
+aspects of running as a CoCo VM are handled by the paravisor, and a normal
+guest OS with no knowledge of memory encryption or other aspects of CoCo VMs
+can run successfully. However, the Hyper-V implementation of paravisor mode
+does not go this far, and is somewhere in the middle of the spectrum. Some
+aspects of CoCo VMs are handled by the Hyper-V paravisor while the guest OS
+must be enlightened for other aspects. Unfortunately, there is no
+standardized enumeration of feature/functions that might be provided in the
+paravisor, and there is no standardized mechanism for a guest OS to query the
+paravisor for the feature/functions it provides. The understanding of what
+the paravisor provides is hard-coded in the guest OS.
+
+Paravisor mode has similarities to the `Coconut project`_, which aims to provide
+a limited paravisor to provide services to the guest such as a virtual TPM.
+However, the Hyper-V paravisor generally handles more aspects of CoCo VMs
+than is currently envisioned for Coconut, and so is further toward the "no
+guest enlightenments required" end of the spectrum.
+
+.. _Coconut project: https://github.com/coconut-svsm/svsm
+
+In the CoCo VM threat model, the paravisor is in the guest security domain
+and must be trusted by the guest OS. By implication, the hypervisor/VMM must
+protect itself against a potentially malicious paravisor just like it
+protects against a potentially malicious guest.
+
+The hardware architectural approach to fully-enlightened vs. paravisor mode
+varies depending on the underlying processor.
+
+* With AMD SEV-SNP processors, in fully-enlightened mode the guest OS runs in
+  VMPL 0 and has full control of the guest context. In paravisor mode, the
+  guest OS runs in VMPL 2 and the paravisor runs in VMPL 0. The paravisor
+  running in VMPL 0 has privileges that the guest OS in VMPL 2 does not have.
+  Certain operations require the guest to invoke the paravisor. Furthermore, in
+  paravisor mode the guest OS operates in "virtual Top Of Memory" (vTOM) mode
+  as defined by the SEV-SNP architecture. This mode simplifies guest management
+  of memory encryption when a paravisor is used.
+
+* With Intel TDX processor, in fully-enlightened mode the guest OS runs in an
+  L1 VM. In paravisor mode, TD partitioning is used. The paravisor runs in the
+  L1 VM, and the guest OS runs in a nested L2 VM.
+
+Hyper-V exposes a synthetic MSR to guests that describes the CoCo mode. This
+MSR indicates if the underlying processor uses AMD SEV-SNP or Intel TDX, and
+whether a paravisor is being used. It is straightforward to build a single
+kernel image that can boot and run properly on either architecture, and in
+either mode.
+
+Paravisor Effects
+-----------------
+Running in paravisor mode affects the following areas of generic Linux kernel
+CoCo VM functionality:
+
+* Initial guest memory setup. When a new VM is created in paravisor mode, the
+  paravisor runs first and sets up the guest physical memory as encrypted. The
+  guest Linux does normal memory initialization, except for explicitly marking
+  appropriate ranges as decrypted (shared). In paravisor mode, Linux does not
+  perform the early boot memory setup steps that are particularly tricky with
+  AMD SEV-SNP in fully-enlightened mode.
+
+* #VC/#VE exception handling. In paravisor mode, Hyper-V configures the guest
+  CoCo VM to route #VC and #VE exceptions to VMPL 0 and the L1 VM,
+  respectively, and not the guest Linux. Consequently, these exception handlers
+  do not run in the guest Linux and are not a required enlightenment for a
+  Linux guest in paravisor mode.
+
+* CPUID flags. Both AMD SEV-SNP and Intel TDX provide a CPUID flag in the
+  guest indicating that the VM is operating with the respective hardware
+  support. While these CPUID flags are visible in fully-enlightened CoCo VMs,
+  the paravisor filters out these flags and the guest Linux does not see them.
+  Throughout the Linux kernel, explicitly testing these flags has mostly been
+  eliminated in favor of the cc_platform_has() function, with the goal of
+  abstracting the differences between SEV-SNP and TDX. But the
+  cc_platform_has() abstraction also allows the Hyper-V paravisor configuration
+  to selectively enable aspects of CoCo VM functionality even when the CPUID
+  flags are not set. The exception is early boot memory setup on SEV-SNP, which
+  tests the CPUID SEV-SNP flag. But not having the flag in Hyper-V paravisor
+  mode VM achieves the desired effect or not running SEV-SNP specific early
+  boot memory setup.
+
+* Device emulation. In paravisor mode, the Hyper-V paravisor provides
+  emulation of devices such as the IO-APIC and TPM. Because the emulation
+  happens in the paravisor in the guest context (instead of the hypervisor/VMM
+  context), MMIO accesses to these devices must be encrypted references instead
+  of the decrypted references that would be used in a fully-enlightened CoCo
+  VM. The __ioremap_caller() function has been enhanced to make a callback to
+  check whether a particular address range should be treated as encrypted
+  (private). See the "is_private_mmio" callback.
+
+* Encrypt/decrypt memory transitions. In a CoCo VM, transitioning guest
+  memory between encrypted and decrypted requires coordinating with the
+  hypervisor/VMM. This is done via callbacks invoked from
+  __set_memory_enc_pgtable(). In fully-enlightened mode, the normal SEV-SNP and
+  TDX implementations of these callbacks are used. In paravisor mode, a Hyper-V
+  specific set of callbacks is used. These callbacks invoke the paravisor so
+  that the paravisor can coordinate the transitions and inform the hypervisor
+  as necessary. See hv_vtom_init() where these callback are set up.
+
+* Interrupt injection. In fully enlightened mode, a malicious hypervisor
+  could inject interrupts into the guest OS at times that violate x86/x64
+  architectural rules. For full protection, the guest OS should include
+  enlightenments that use the interrupt injection management features provided
+  by CoCo-capable processors. In paravisor mode, the paravisor mediates
+  interrupt injection into the guest OS, and ensures that the guest OS only
+  sees interrupts that are "legal". The paravisor uses the interrupt injection
+  management features provided by the CoCo-capable physical processor, thereby
+  masking these complexities from the guest OS.
+
+Hyper-V Hypercalls
+------------------
+When in fully-enlightened mode, hypercalls made by the Linux guest are routed
+directly to the hypervisor, just as in a non-CoCo VM. But in paravisor mode,
+normal hypercalls trap to the paravisor first, which may in turn invoke the
+hypervisor. But the paravisor is idiosyncratic in this regard, and a few
+hypercalls made by the Linux guest must always be routed directly to the
+hypervisor. These hypercall sites test for a paravisor being present, and use
+a special invocation sequence. See hv_post_message(), for example.
+
+Guest communication with Hyper-V
+--------------------------------
+Separate from the generic Linux kernel handling of memory encryption in Linux
+CoCo VMs, Hyper-V has VMBus and VMBus devices that communicate using memory
+shared between the Linux guest and the host. This shared memory must be
+marked decrypted to enable communication. Furthermore, since the threat model
+includes a compromised and potentially malicious host, the guest must guard
+against leaking any unintended data to the host through this shared memory.
+
+These Hyper-V and VMBus memory pages are marked as decrypted:
+
+* VMBus monitor pages
+
+* Synthetic interrupt controller (synic) related pages (unless supplied by
+  the paravisor)
+
+* Per-cpu hypercall input and output pages (unless running with a paravisor)
+
+* VMBus ring buffers. The direct mapping is marked decrypted in
+  __vmbus_establish_gpadl(). The secondary mapping created in
+  hv_ringbuffer_init() must also include the "decrypted" attribute.
+
+When the guest writes data to memory that is shared with the host, it must
+ensure that only the intended data is written. Padding or unused fields must
+be initialized to zeros before copying into the shared memory so that random
+kernel data is not inadvertently given to the host.
+
+Similarly, when the guest reads memory that is shared with the host, it must
+validate the data before acting on it so that a malicious host cannot induce
+the guest to expose unintended data. Doing such validation can be tricky
+because the host can modify the shared memory areas even while or after
+validation is performed. For messages passed from the host to the guest in a
+VMBus ring buffer, the length of the message is validated, and the message is
+copied into a temporary (encrypted) buffer for further validation and
+processing. The copying adds a small amount of overhead, but is the only way
+to protect against a malicious host. See hv_pkt_iter_first().
+
+Many drivers for VMBus devices have been "hardened" by adding code to fully
+validate messages received over VMBus, instead of assuming that Hyper-V is
+acting cooperatively. Such drivers are marked as "allowed_in_isolated" in the
+vmbus_devs[] table. Other drivers for VMBus devices that are not needed in a
+CoCo VM have not been hardened, and they are not allowed to load in a CoCo
+VM. See vmbus_is_valid_offer() where such devices are excluded.
+
+Two VMBus devices depend on the Hyper-V host to do DMA data transfers:
+storvsc for disk I/O and netvsc for network I/O. storvsc uses the normal
+Linux kernel DMA APIs, and so bounce buffering through decrypted swiotlb
+memory is done implicitly. netvsc has two modes for data transfers. The first
+mode goes through send and receive buffer space that is explicitly allocated
+by the netvsc driver, and is used for most smaller packets. These send and
+receive buffers are marked decrypted by __vmbus_establish_gpadl(). Because
+the netvsc driver explicitly copies packets to/from these buffers, the
+equivalent of bounce buffering between encrypted and decrypted memory is
+already part of the data path. The second mode uses the normal Linux kernel
+DMA APIs, and is bounce buffered through swiotlb memory implicitly like in
+storvsc.
+
+Finally, the VMBus virtual PCI driver needs special handling in a CoCo VM.
+Linux PCI device drivers access PCI config space using standard APIs provided
+by the Linux PCI subsystem. On Hyper-V, these functions directly access MMIO
+space, and the access traps to Hyper-V for emulation. But in CoCo VMs, memory
+encryption prevents Hyper-V from reading the guest instruction stream to
+emulate the access. So in a CoCo VM, these functions must make a hypercall
+with arguments explicitly describing the access. See
+_hv_pcifront_read_config() and _hv_pcifront_write_config() and the
+"use_calls" flag indicating to use hypercalls.
+
+load_unaligned_zeropad()
+------------------------
+When transitioning memory between encrypted and decrypted, the caller of
+set_memory_encrypted() or set_memory_decrypted() is responsible for ensuring
+the memory isn't in use and isn't referenced while the transition is in
+progress. The transition has multiple steps, and includes interaction with
+the Hyper-V host. The memory is in an inconsistent state until all steps are
+complete. A reference while the state is inconsistent could result in an
+exception that can't be cleanly fixed up.
+
+However, the kernel load_unaligned_zeropad() mechanism may make stray
+references that can't be prevented by the caller of set_memory_encrypted() or
+set_memory_decrypted(), so there's specific code in the #VC or #VE exception
+handler to fixup this case. But a CoCo VM running on Hyper-V may be
+configured to run with a paravisor, with the #VC or #VE exception routed to
+the paravisor. There's no architectural way to forward the exceptions back to
+the guest kernel, and in such a case, the load_unaligned_zeropad() fixup code
+in the #VC/#VE handlers doesn't run.
+
+To avoid this problem, the Hyper-V specific functions for notifying the
+hypervisor of the transition mark pages as "not present" while a transition
+is in progress. If load_unaligned_zeropad() causes a stray reference, a
+normal page fault is generated instead of #VC or #VE, and the page-fault-
+based handlers for load_unaligned_zeropad() fixup the reference. When the
+encrypted/decrypted transition is complete, the pages are marked as "present"
+again. See hv_vtom_clear_present() and hv_vtom_set_host_visibility().

Documentation/virt/hyperv/index.rst

@@ -11,3 +11,4 @@ Hyper-V Enlightenments
    vmbus
    clocks
    vpci
+   coco

arch/x86/hyperv/hv_init.c

@@ -35,7 +35,6 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 
-int hyperv_init_cpuhp;
 u64 hv_current_partition_id = ~0ull;
 EXPORT_SYMBOL_GPL(hv_current_partition_id);
 
@@ -607,8 +606,6 @@ skip_hypercall_pg_init:
 
 	register_syscore_ops(&hv_syscore_ops);
 
-	hyperv_init_cpuhp = cpuhp;
-
 	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
 
@@ -637,7 +634,7 @@ skip_hypercall_pg_init:
 clean_guest_os_id:
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
-	cpuhp_remove_state(cpuhp);
+	cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
 free_ghcb_page:
 	free_percpu(hv_ghcb_pg);
 free_vp_assist_page:

arch/x86/include/asm/mshyperv.h

@@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void)
 }
 
 #if IS_ENABLED(CONFIG_HYPERV)
-extern int hyperv_init_cpuhp;
 extern bool hyperv_paravisor_present;
 
 extern void *hv_hypercall_pg;

arch/x86/kernel/cpu/mshyperv.c

@@ -199,8 +199,8 @@ static void hv_machine_shutdown(void)
 	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
 	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
 	 */
-	if (kexec_in_progress && hyperv_init_cpuhp > 0)
-		cpuhp_remove_state(hyperv_init_cpuhp);
+	if (kexec_in_progress)
+		cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
 
 	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
@@ -424,6 +424,7 @@ static void __init ms_hyperv_init_platform(void)
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
 		x86_platform.calibrate_tsc = hv_get_tsc_khz;
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
+		setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	}
 
 	if (ms_hyperv.priv_high & HV_ISOLATION) {
@@ -449,9 +450,23 @@ static void __init ms_hyperv_init_platform(void)
 			ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED;
 
 			if (!ms_hyperv.paravisor_present) {
-				/* To be supported: more work is required.  */
+				/*
+				 * Mark the Hyper-V TSC page feature as disabled
+				 * in a TDX VM without paravisor so that the
+				 * Invariant TSC, which is a better clocksource
+				 * anyway, is used instead.
+				 */
 				ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
 
+				/*
+				 * The Invariant TSC is expected to be available
+				 * in a TDX VM without paravisor, but if not,
+				 * print a warning message. The slower Hyper-V MSR-based
+				 * Ref Counter should end up being the clocksource.
+				 */
+				if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+					pr_warn("Hyper-V: Invariant TSC is unavailable\n");
+
 				/* HV_MSR_CRASH_CTL is unsupported. */
 				ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
 

drivers/clocksource/hyperv_timer.c

@@ -137,7 +137,21 @@ static int hv_stimer_init(unsigned int cpu)
 	ce->name = "Hyper-V clockevent";
 	ce->features = CLOCK_EVT_FEAT_ONESHOT;
 	ce->cpumask = cpumask_of(cpu);
-	ce->rating = 1000;
+
+	/*
+	 * Lower the rating of the Hyper-V timer in a TDX VM without paravisor,
+	 * so the local APIC timer (lapic_clockevent) is the default timer in
+	 * such a VM. The Hyper-V timer is not preferred in such a VM because
+	 * it depends on the slow VM Reference Counter MSR (the Hyper-V TSC
+	 * page is not enbled in such a VM because the VM uses Invariant TSC
+	 * as a better clocksource and it's challenging to mark the Hyper-V
+	 * TSC page shared in very early boot).
+	 */
+	if (!ms_hyperv.paravisor_present && hv_isolation_type_tdx())
+		ce->rating = 90;
+	else
+		ce->rating = 1000;
+
 	ce->set_state_shutdown = hv_ce_shutdown;
 	ce->set_state_oneshot = hv_ce_set_oneshot;
 	ce->set_next_event = hv_ce_set_next_event;

drivers/hv/hv.c

@@ -342,9 +342,6 @@ int hv_synic_init(unsigned int cpu)
 	return 0;
 }
 
-/*
- * hv_synic_cleanup - Cleanup routine for hv_synic_init().
- */
 void hv_synic_disable_regs(unsigned int cpu)
 {
 	struct hv_per_cpu_context *hv_cpu =
@@ -436,6 +433,9 @@ retry:
 	return pending;
 }
 
+/*
+ * hv_synic_cleanup - Cleanup routine for hv_synic_init().
+ */
 int hv_synic_cleanup(unsigned int cpu)
 {
 	struct vmbus_channel *channel, *sc;

drivers/hv/hyperv_vmbus.h

@@ -380,12 +380,6 @@ void hv_vss_deinit(void);
 int hv_vss_pre_suspend(void);
 int hv_vss_pre_resume(void);
 void hv_vss_onchannelcallback(void *context);
-
-int hv_fcopy_init(struct hv_util_service *srv);
-void hv_fcopy_deinit(void);
-int hv_fcopy_pre_suspend(void);
-int hv_fcopy_pre_resume(void);
-void hv_fcopy_onchannelcallback(void *context);
 void vmbus_initiate_unload(bool crash);
 
 static inline void hv_poll_channel(struct vmbus_channel *channel,

drivers/hv/vmbus_drv.c

@@ -1803,12 +1803,12 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
 	return attr->mode;
 }
 
-static struct attribute_group vmbus_chan_group = {
+static const struct attribute_group vmbus_chan_group = {
 	.attrs = vmbus_chan_attrs,
 	.is_visible = vmbus_chan_attr_is_visible
 };
 
-static struct kobj_type vmbus_chan_ktype = {
+static const struct kobj_type vmbus_chan_ktype = {
 	.sysfs_ops = &vmbus_chan_sysfs_ops,
 	.release = vmbus_chan_release,
 };

fs/bcachefs/alloc_background.c

@@ -1968,8 +1968,8 @@ static void bch2_do_discards_fast_work(struct work_struct *work)
 			break;
 	}
 
-	bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast);
 	percpu_ref_put(&ca->io_ref);
+	bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast);
 }
 
 static void bch2_discard_one_bucket_fast(struct bch_dev *ca, u64 bucket)
@@ -1979,18 +1979,18 @@ static void bch2_discard_one_bucket_fast(struct bch_dev *ca, u64 bucket)
 	if (discard_in_flight_add(ca, bucket, false))
 		return;
 
-	if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard_fast))
 		return;
 
-	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard_fast))
-		goto put_ioref;
+	if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+		goto put_ref;
 
 	if (queue_work(c->write_ref_wq, &ca->discard_fast_work))
 		return;
 
-	bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast);
-put_ioref:
 	percpu_ref_put(&ca->io_ref);
+put_ref:
+	bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast);
 }
 
 static int invalidate_one_bucket(struct btree_trans *trans,
@@ -2132,26 +2132,26 @@ static void bch2_do_invalidates_work(struct work_struct *work)
 	bch2_trans_iter_exit(trans, &iter);
 err:
 	bch2_trans_put(trans);
-	bch2_write_ref_put(c, BCH_WRITE_REF_invalidate);
 	percpu_ref_put(&ca->io_ref);
+	bch2_write_ref_put(c, BCH_WRITE_REF_invalidate);
 }
 
 void bch2_dev_do_invalidates(struct bch_dev *ca)
 {
 	struct bch_fs *c = ca->fs;
 
-	if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_invalidate))
 		return;
 
-	if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_invalidate))
-		goto put_ioref;
+	if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+		goto put_ref;
 
 	if (queue_work(c->write_ref_wq, &ca->invalidate_work))
 		return;
 
-	bch2_write_ref_put(c, BCH_WRITE_REF_invalidate);
-put_ioref:
 	percpu_ref_put(&ca->io_ref);
+put_ref:
+	bch2_write_ref_put(c, BCH_WRITE_REF_invalidate);
 }
 
 void bch2_do_invalidates(struct bch_fs *c)

fs/bcachefs/btree_journal_iter.c

@@ -530,6 +530,8 @@ static void __journal_keys_sort(struct journal_keys *keys)
 {
 	sort(keys->data, keys->nr, sizeof(keys->data[0]), journal_sort_key_cmp, NULL);
 
+	cond_resched();
+
 	struct journal_key *dst = keys->data;
 
 	darray_for_each(*keys, src) {

fs/bcachefs/buckets.c

@@ -100,12 +100,13 @@ static int bch2_check_fix_ptr(struct btree_trans *trans,
 
 	struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev);
 	if (!ca) {
-		if (fsck_err(trans, ptr_to_invalid_device,
-			     "pointer to missing device %u\n"
-			     "while marking %s",
-			     p.ptr.dev,
-			     (printbuf_reset(&buf),
-			      bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
+		if (fsck_err_on(p.ptr.dev != BCH_SB_MEMBER_INVALID,
+				trans, ptr_to_invalid_device,
+				"pointer to missing device %u\n"
+				"while marking %s",
+				p.ptr.dev,
+				(printbuf_reset(&buf),
+				 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
 			*do_update = true;
 		return 0;
 	}
@@ -562,7 +563,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 	struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev);
 	if (unlikely(!ca)) {
-		if (insert)
+		if (insert && p.ptr.dev != BCH_SB_MEMBER_INVALID)
 			ret = -EIO;
 		goto err;
 	}

fs/bcachefs/ec.h

@@ -97,7 +97,9 @@ static inline bool __bch2_ptr_matches_stripe(const struct bch_extent_ptr *stripe
 					     const struct bch_extent_ptr *data_ptr,
 					     unsigned sectors)
 {
-	return  data_ptr->dev    == stripe_ptr->dev &&
+	return  (data_ptr->dev    == stripe_ptr->dev ||
+		 data_ptr->dev    == BCH_SB_MEMBER_INVALID ||
+		 stripe_ptr->dev  == BCH_SB_MEMBER_INVALID) &&
 		data_ptr->gen    == stripe_ptr->gen &&
 		data_ptr->offset >= stripe_ptr->offset &&
 		data_ptr->offset  < stripe_ptr->offset + sectors;

fs/bcachefs/extents.c

@@ -781,14 +781,17 @@ static union bch_extent_entry *extent_entry_prev(struct bkey_ptrs ptrs,
 /*
  * Returns pointer to the next entry after the one being dropped:
  */
-union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s k,
-						   struct bch_extent_ptr *ptr)
+void bch2_bkey_drop_ptr_noerror(struct bkey_s k, struct bch_extent_ptr *ptr)
 {
 	struct bkey_ptrs ptrs = bch2_bkey_ptrs(k);
 	union bch_extent_entry *entry = to_entry(ptr), *next;
-	union bch_extent_entry *ret = entry;
 	bool drop_crc = true;
 
+	if (k.k->type == KEY_TYPE_stripe) {
+		ptr->dev = BCH_SB_MEMBER_INVALID;
+		return;
+	}
+
 	EBUG_ON(ptr < &ptrs.start->ptr ||
 		ptr >= &ptrs.end->ptr);
 	EBUG_ON(ptr->type != 1 << BCH_EXTENT_ENTRY_ptr);
@@ -811,21 +814,16 @@ union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s k,
 			break;
 
 		if ((extent_entry_is_crc(entry) && drop_crc) ||
-		    extent_entry_is_stripe_ptr(entry)) {
-			ret = (void *) ret - extent_entry_bytes(entry);
+		    extent_entry_is_stripe_ptr(entry))
 			extent_entry_drop(k, entry);
-		}
 	}
-
-	return ret;
 }
 
-union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s k,
-					   struct bch_extent_ptr *ptr)
+void bch2_bkey_drop_ptr(struct bkey_s k, struct bch_extent_ptr *ptr)
 {
 	bool have_dirty = bch2_bkey_dirty_devs(k.s_c).nr;
-	union bch_extent_entry *ret =
-		bch2_bkey_drop_ptr_noerror(k, ptr);
+
+	bch2_bkey_drop_ptr_noerror(k, ptr);
 
 	/*
 	 * If we deleted all the dirty pointers and there's still cached
@@ -837,14 +835,10 @@ union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s k,
 	    !bch2_bkey_dirty_devs(k.s_c).nr) {
 		k.k->type = KEY_TYPE_error;
 		set_bkey_val_u64s(k.k, 0);
-		ret = NULL;
 	} else if (!bch2_bkey_nr_ptrs(k.s_c)) {
 		k.k->type = KEY_TYPE_deleted;
 		set_bkey_val_u64s(k.k, 0);
-		ret = NULL;
 	}
-
-	return ret;
 }
 
 void bch2_bkey_drop_device(struct bkey_s k, unsigned dev)

fs/bcachefs/extents.h

@@ -649,26 +649,21 @@ static inline void bch2_bkey_append_ptr(struct bkey_i *k, struct bch_extent_ptr
 
 void bch2_extent_ptr_decoded_append(struct bkey_i *,
 				    struct extent_ptr_decoded *);
-union bch_extent_entry *bch2_bkey_drop_ptr_noerror(struct bkey_s,
-						   struct bch_extent_ptr *);
-union bch_extent_entry *bch2_bkey_drop_ptr(struct bkey_s,
-					   struct bch_extent_ptr *);
+void bch2_bkey_drop_ptr_noerror(struct bkey_s, struct bch_extent_ptr *);
+void bch2_bkey_drop_ptr(struct bkey_s, struct bch_extent_ptr *);
 
 #define bch2_bkey_drop_ptrs(_k, _ptr, _cond)				\
 do {									\
-	struct bkey_ptrs _ptrs = bch2_bkey_ptrs(_k);			\
+	__label__ _again;						\
+	struct bkey_ptrs _ptrs;						\
+_again:									\
+	_ptrs = bch2_bkey_ptrs(_k);					\
 									\
-	struct bch_extent_ptr *_ptr = &_ptrs.start->ptr;		\
-									\
-	while ((_ptr = bkey_ptr_next(_ptrs, _ptr))) {			\
+	bkey_for_each_ptr(_ptrs, _ptr)					\
 		if (_cond) {						\
-			_ptr = (void *) bch2_bkey_drop_ptr(_k, _ptr);	\
-			_ptrs = bch2_bkey_ptrs(_k);			\
-			continue;					\
+			bch2_bkey_drop_ptr(_k, _ptr);			\
+			goto _again;					\
 		}							\
-									\
-		(_ptr)++;						\
-	}								\
 } while (0)
 
 bool bch2_bkey_matches_ptr(struct bch_fs *, struct bkey_s_c,

fs/bcachefs/fs.c

@@ -177,6 +177,14 @@ static unsigned bch2_inode_hash(subvol_inum inum)
 	return jhash_3words(inum.subvol, inum.inum >> 32, inum.inum, JHASH_INITVAL);
 }
 
+struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
+{
+	return to_bch_ei(ilookup5_nowait(c->vfs_sb,
+					 bch2_inode_hash(inum),
+					 bch2_iget5_test,
+					 &inum));
+}
+
 static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_inode_info *inode)
 {
 	subvol_inum inum = inode_inum(inode);

fs/bcachefs/fs.h

@@ -56,6 +56,8 @@ static inline subvol_inum inode_inum(struct bch_inode_info *inode)
 	};
 }
 
+struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *, subvol_inum);
+
 /*
  * Set if we've gotten a btree error for this inode, and thus the vfs inode and
  * btree inode may be inconsistent:
@@ -194,6 +196,11 @@ int bch2_vfs_init(void);
 
 #define bch2_inode_update_after_write(_trans, _inode, _inode_u, _fields)	({ do {} while (0); })
 
+static inline struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
+{
+	return NULL;
+}
+
 static inline void bch2_evict_subvolume_inodes(struct bch_fs *c,
 					       snapshot_id_list *s) {}
 static inline void bch2_vfs_exit(void) {}

fs/bcachefs/fsck.c

@@ -8,6 +8,7 @@
 #include "darray.h"
 #include "dirent.h"
 #include "error.h"
+#include "fs.h"
 #include "fs-common.h"
 #include "fsck.h"
 #include "inode.h"
@@ -962,6 +963,22 @@ fsck_err:
 	return ret;
 }
 
+static bool bch2_inode_open(struct bch_fs *c, struct bpos p)
+{
+	subvol_inum inum = {
+		.subvol = snapshot_t(c, p.snapshot)->subvol,
+		.inum	= p.offset,
+	};
+
+	/* snapshot tree corruption, can't safely delete */
+	if (!inum.subvol) {
+		bch_err_ratelimited(c, "%s(): snapshot %u has no subvol", __func__, p.snapshot);
+		return true;
+	}
+
+	return __bch2_inode_hash_find(c, inum) != NULL;
+}
+
 static int check_inode(struct btree_trans *trans,
 		       struct btree_iter *iter,
 		       struct bkey_s_c k,
@@ -1040,6 +1057,7 @@ static int check_inode(struct btree_trans *trans,
 	}
 
 	if (u.bi_flags & BCH_INODE_unlinked &&
+	    !bch2_inode_open(c, k.k->p) &&
 	    (!c->sb.clean ||
 	     fsck_err(trans, inode_unlinked_but_clean,
 		      "filesystem marked clean, but inode %llu unlinked",

fs/bcachefs/replicas.c

@@ -796,7 +796,7 @@ bool bch2_have_enough_devs(struct bch_fs *c, struct bch_devs_mask devs,
 			nr_online += test_bit(e->devs[i], devs.d);
 
 			struct bch_dev *ca = bch2_dev_rcu(c, e->devs[i]);
-			nr_failed += ca && ca->mi.state == BCH_MEMBER_STATE_failed;
+			nr_failed += !ca || ca->mi.state == BCH_MEMBER_STATE_failed;
 		}
 		rcu_read_unlock();
 

fs/bcachefs/sysfs.c

@@ -461,7 +461,7 @@ STORE(bch2_fs)
 
 		sc.gfp_mask = GFP_KERNEL;
 		sc.nr_to_scan = strtoul_or_return(buf);
-		c->btree_key_cache.shrink->scan_objects(c->btree_cache.shrink, &sc);
+		c->btree_key_cache.shrink->scan_objects(c->btree_key_cache.shrink, &sc);
 	}
 
 	if (attr == &sysfs_trigger_gc)

kernel/trace/trace.c

@@ -2224,10 +2224,6 @@ static __init int init_trace_selftests(void)
 }
 core_initcall(init_trace_selftests);
 #else
-static inline int run_tracer_selftest(struct tracer *type)
-{
-	return 0;
-}
 static inline int do_run_tracer_selftest(struct tracer *type)
 {
 	return 0;

kernel/trace/trace_osnoise.c

@@ -228,6 +228,11 @@ static inline struct osnoise_variables *this_cpu_osn_var(void)
 	return this_cpu_ptr(&per_cpu_osnoise_var);
 }
 
+/*
+ * Protect the interface.
+ */
+static struct mutex interface_lock;
+
 #ifdef CONFIG_TIMERLAT_TRACER
 /*
  * Runtime information for the timer mode.
@@ -252,11 +257,6 @@ static inline struct timerlat_variables *this_cpu_tmr_var(void)
 	return this_cpu_ptr(&per_cpu_timerlat_var);
 }
 
-/*
- * Protect the interface.
- */
-static struct mutex interface_lock;
-
 /*
  * tlat_var_reset - Reset the values of the given timerlat_variables
  */

tools/hv/Makefile

@@ -52,7 +52,7 @@ $(OUTPUT)hv_fcopy_uio_daemon: $(HV_FCOPY_UIO_DAEMON_IN)
 
 clean:
 	rm -f $(ALL_PROGRAMS)
-	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
 
 install: $(ALL_PROGRAMS)
 	install -d -m 755 $(DESTDIR)$(sbindir); \

tools/hv/lsvmbus

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
 import os