NAS-124109 / 24.04 / Merge v6.1.50 to add support for AVX extensions

MAINTAINERS

@@ -6027,7 +6027,7 @@ S:	Supported
 F:	Documentation/networking/devlink
 F:	include/net/devlink.h
 F:	include/uapi/linux/devlink.h
-F:	net/core/devlink.c
+F:	net/devlink/
 
 DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT
 M:	Christoph Niedermaier <[email protected]>

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 1
-SUBLEVEL = 49
+SUBLEVEL = 50
 NAME = Curry Ramen
 
 ifndef EXTRAVERSION

arch/mips/include/asm/cpu-features.h

@@ -121,7 +121,24 @@
 #define cpu_has_4k_cache	__isa_ge_or_opt(1, MIPS_CPU_4K_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
-#define cpu_has_octeon_cache	0
+#define cpu_has_octeon_cache						\
+({									\
+	int __res;							\
+									\
+	switch (boot_cpu_type()) {					\
+	case CPU_CAVIUM_OCTEON:						\
+	case CPU_CAVIUM_OCTEON_PLUS:					\
+	case CPU_CAVIUM_OCTEON2:					\
+	case CPU_CAVIUM_OCTEON3:					\
+		__res = 1;						\
+		break;							\
+									\
+	default:							\
+		__res = 0;						\
+	}								\
+									\
+	__res;								\
+})
 #endif
 /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work.  */
 #ifndef cpu_has_fpu
@@ -351,7 +368,7 @@
 ({									\
 	int __res;							\
 									\
-	switch (current_cpu_type()) {					\
+	switch (boot_cpu_type()) {					\
 	case CPU_M14KC:							\
 	case CPU_74K:							\
 	case CPU_1074K:							\

arch/riscv/Kconfig

@@ -447,24 +447,30 @@ config TOOLCHAIN_HAS_ZIHINTPAUSE
 config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
 	def_bool y
 	# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc
-	depends on AS_IS_GNU && AS_VERSION >= 23800
+	# https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd
+	depends on AS_IS_GNU && AS_VERSION >= 23600
 	help
-	  Newer binutils versions default to ISA spec version 20191213 which
-	  moves some instructions from the I extension to the Zicsr and Zifencei
-	  extensions.
+	  Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer
+	  20191213 version, which moves some instructions from the I extension to
+	  the Zicsr and Zifencei extensions. This requires explicitly specifying
+	  Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr
+	  and Zifencei are supported in binutils from version 2.36 onwards.
+	  To make life easier, and avoid forcing toolchains that default to a
+	  newer ISA spec to version 2.2, relax the check to binutils >= 2.36.
+	  For clang < 17 or GCC < 11.3.0, for which this is not possible or need
+	  special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC.
 
 config TOOLCHAIN_NEEDS_OLD_ISA_SPEC
 	def_bool y
 	depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
 	# https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16
-	depends on CC_IS_CLANG && CLANG_VERSION < 170000
+	# https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671
+	depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300)
 	help
-	  Certain versions of clang do not support zicsr and zifencei via -march
-	  but newer versions of binutils require it for the reasons noted in the
-	  help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This
-	  option causes an older ISA spec compatible with these older versions
-	  of clang to be passed to GAS, which has the same result as passing zicsr
-	  and zifencei to -march.
+	  Certain versions of clang and GCC do not support zicsr and zifencei via
+	  -march. This option causes an older ISA spec compatible with these older
+	  versions of clang and GCC to be passed to GAS, which has the same result
+	  as passing zicsr and zifencei to -march.
 
 config FPU
 	bool "FPU support"

arch/riscv/kernel/compat_vdso/Makefile

@@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache
 COMPAT_CC := $(CC)
 COMPAT_LD := $(LD)
 
-COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32
+# binutils 2.35 does not support the zifencei extension, but in the ISA
+# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI.
+ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
+	COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32
+else
+	COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32
+endif
 COMPAT_LD_FLAGS := -melf32lriscv
 
 # Disable attributes, as they're useless and break the build.

arch/x86/kernel/fpu/context.h

@@ -19,8 +19,7 @@
  * FPU state for a task MUST let the rest of the kernel know that the
  * FPU registers are no longer valid for this task.
  *
- * Either one of these invalidation functions is enough. Invalidate
- * a resource you control: CPU if using the CPU for something else
+ * Invalidate a resource you control: CPU if using the CPU for something else
  * (with preemption disabled), FPU for the current task, or a task that
  * is prevented from running by the current task.
  */

arch/x86/kernel/fpu/core.c

@@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	fpregs_lock();
-	fpu__drop(fpu);
+	__fpu_invalidate_fpregs_state(fpu);
 	/*
 	 * This does not change the actual hardware registers. It just
 	 * resets the memory image and sets TIF_NEED_FPU_LOAD so a

arch/x86/kernel/fpu/xstate.c

@@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		fpu_kernel_cfg.max_features,

arch/x86/kvm/mmu/mmu.c

@@ -4212,7 +4212,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
  * root was invalidated by a memslot update or a relevant mmu_notifier fired.
  */
 static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
-				struct kvm_page_fault *fault, int mmu_seq)
+				struct kvm_page_fault *fault,
+				unsigned long mmu_seq)
 {
 	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);
 

arch/x86/kvm/mmu/tdp_mmu.c

@@ -51,7 +51,17 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	if (!kvm->arch.tdp_mmu_enabled)
 		return;
 
-	/* Also waits for any queued work items.  */
+	/*
+	 * Invalidate all roots, which besides the obvious, schedules all roots
+	 * for zapping and thus puts the TDP MMU's reference to each root, i.e.
+	 * ultimately frees all roots.
+	 */
+	kvm_tdp_mmu_invalidate_all_roots(kvm);
+
+	/*
+	 * Destroying a workqueue also first flushes the workqueue, i.e. no
+	 * need to invoke kvm_tdp_mmu_zap_invalidated_roots().
+	 */
 	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
 
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
@@ -127,16 +137,6 @@ static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root
 	queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work);
 }
 
-static inline bool kvm_tdp_root_mark_invalid(struct kvm_mmu_page *page)
-{
-	union kvm_mmu_page_role role = page->role;
-	role.invalid = true;
-
-	/* No need to use cmpxchg, only the invalid bit can change.  */
-	role.word = xchg(&page->role.word, role.word);
-	return role.invalid;
-}
-
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared)
 {
@@ -145,45 +145,12 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 	if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
 		return;
 
-	WARN_ON(!root->tdp_mmu_page);
-
 	/*
-	 * The root now has refcount=0.  It is valid, but readers already
-	 * cannot acquire a reference to it because kvm_tdp_mmu_get_root()
-	 * rejects it.  This remains true for the rest of the execution
-	 * of this function, because readers visit valid roots only
-	 * (except for tdp_mmu_zap_root_work(), which however
-	 * does not acquire any reference itself).
-	 *
-	 * Even though there are flows that need to visit all roots for
-	 * correctness, they all take mmu_lock for write, so they cannot yet
-	 * run concurrently. The same is true after kvm_tdp_root_mark_invalid,
-	 * since the root still has refcount=0.
-	 *
-	 * However, tdp_mmu_zap_root can yield, and writers do not expect to
-	 * see refcount=0 (see for example kvm_tdp_mmu_invalidate_all_roots()).
-	 * So the root temporarily gets an extra reference, going to refcount=1
-	 * while staying invalid.  Readers still cannot acquire any reference;
-	 * but writers are now allowed to run if tdp_mmu_zap_root yields and
-	 * they might take an extra reference if they themselves yield.
-	 * Therefore, when the reference is given back by the worker,
-	 * there is no guarantee that the refcount is still 1.  If not, whoever
-	 * puts the last reference will free the page, but they will not have to
-	 * zap the root because a root cannot go from invalid to valid.
+	 * The TDP MMU itself holds a reference to each root until the root is
+	 * explicitly invalidated, i.e. the final reference should be never be
+	 * put for a valid root.
 	 */
-	if (!kvm_tdp_root_mark_invalid(root)) {
-		refcount_set(&root->tdp_mmu_root_count, 1);
-
-		/*
-		 * Zapping the root in a worker is not just "nice to have";
-		 * it is required because kvm_tdp_mmu_invalidate_all_roots()
-		 * skips already-invalid roots.  If kvm_tdp_mmu_put_root() did
-		 * not add the root to the workqueue, kvm_tdp_mmu_zap_all_fast()
-		 * might return with some roots not zapped yet.
-		 */
-		tdp_mmu_schedule_zap_root(kvm, root);
-		return;
-	}
+	KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm);
 
 	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	list_del_rcu(&root->link);
@@ -329,7 +296,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	root = tdp_mmu_alloc_sp(vcpu);
 	tdp_mmu_init_sp(root, NULL, 0, role);
 
-	refcount_set(&root->tdp_mmu_root_count, 1);
+	/*
+	 * TDP MMU roots are kept until they are explicitly invalidated, either
+	 * by a memslot update or by the destruction of the VM.  Initialize the
+	 * refcount to two; one reference for the vCPU, and one reference for
+	 * the TDP MMU itself, which is held until the root is invalidated and
+	 * is ultimately put by tdp_mmu_zap_root_work().
+	 */
+	refcount_set(&root->tdp_mmu_root_count, 2);
 
 	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots);
@@ -1027,32 +1001,49 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 /*
  * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
  * is about to be zapped, e.g. in response to a memslots update.  The actual
- * zapping is performed asynchronously, so a reference is taken on all roots.
- * Using a separate workqueue makes it easy to ensure that the destruction is
- * performed before the "fast zap" completes, without keeping a separate list
- * of invalidated roots; the list is effectively the list of work items in
- * the workqueue.
- *
- * Get a reference even if the root is already invalid, the asynchronous worker
- * assumes it was gifted a reference to the root it processes.  Because mmu_lock
- * is held for write, it should be impossible to observe a root with zero refcount,
- * i.e. the list of roots cannot be stale.
+ * zapping is performed asynchronously.  Using a separate workqueue makes it
+ * easy to ensure that the destruction is performed before the "fast zap"
+ * completes, without keeping a separate list of invalidated roots; the list is
+ * effectively the list of work items in the workqueue.
  *
- * This has essentially the same effect for the TDP MMU
- * as updating mmu_valid_gen does for the shadow MMU.
+ * Note, the asynchronous worker is gifted the TDP MMU's reference.
+ * See kvm_tdp_mmu_get_vcpu_root_hpa().
  */
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 {
 	struct kvm_mmu_page *root;
 
-	lockdep_assert_held_write(&kvm->mmu_lock);
-	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
-		if (!root->role.invalid &&
-		    !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) {
+	/*
+	 * mmu_lock must be held for write to ensure that a root doesn't become
+	 * invalid while there are active readers (invalidating a root while
+	 * there are active readers may or may not be problematic in practice,
+	 * but it's uncharted territory and not supported).
+	 *
+	 * Waive the assertion if there are no users of @kvm, i.e. the VM is
+	 * being destroyed after all references have been put, or if no vCPUs
+	 * have been created (which means there are no roots), i.e. the VM is
+	 * being destroyed in an error path of KVM_CREATE_VM.
+	 */
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+	    refcount_read(&kvm->users_count) && kvm->created_vcpus)
+		lockdep_assert_held_write(&kvm->mmu_lock);
+
+	/*
+	 * As above, mmu_lock isn't held when destroying the VM!  There can't
+	 * be other references to @kvm, i.e. nothing else can invalidate roots
+	 * or be consuming roots, but walking the list of roots does need to be
+	 * guarded against roots being deleted by the asynchronous zap worker.
+	 */
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) {
+		if (!root->role.invalid) {
 			root->role.invalid = true;
 			tdp_mmu_schedule_zap_root(kvm, root);
 		}
 	}
+
+	rcu_read_unlock();
 }
 
 /*

drivers/block/ublk_drv.c

@@ -1223,9 +1223,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			__func__, cmd->cmd_op, ub_cmd->q_id, tag,
 			ub_cmd->result);
 
-	if (!(issue_flags & IO_URING_F_SQE128))
-		goto out;
-
 	if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues)
 		goto out;
 

drivers/clk/clk-devres.c

@@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put);
 struct clk *devm_get_clk_from_child(struct device *dev,
 				    struct device_node *np, const char *con_id)
 {
-	struct clk **ptr, *clk;
+	struct devm_clk_state *state;
+	struct clk *clk;
 
-	ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
+	state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL);
+	if (!state)
 		return ERR_PTR(-ENOMEM);
 
 	clk = of_clk_get_by_name(np, con_id);
 	if (!IS_ERR(clk)) {
-		*ptr = clk;
-		devres_add(dev, ptr);
+		state->clk = clk;
+		devres_add(dev, state);
 	} else {
-		devres_free(ptr);
+		devres_free(state);
 	}
 
 	return clk;

drivers/dma-buf/sw_sync.c

@@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
  */
 static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 {
+	LIST_HEAD(signalled);
 	struct sync_pt *pt, *next;
 
 	trace_sync_timeline(obj);
@@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 		if (!timeline_fence_signaled(&pt->base))
 			break;
 
-		list_del_init(&pt->link);
+		dma_fence_get(&pt->base);
+
+		list_move_tail(&pt->link, &signalled);
 		rb_erase(&pt->node, &obj->pt_tree);
 
-		/*
-		 * A signal callback may release the last reference to this
-		 * fence, causing it to be freed. That operation has to be
-		 * last to avoid a use after free inside this loop, and must
-		 * be after we remove the fence from the timeline in order to
-		 * prevent deadlocking on timeline->lock inside
-		 * timeline_fence_release().
-		 */
 		dma_fence_signal_locked(&pt->base);
 	}
 
 	spin_unlock_irq(&obj->lock);
+
+	list_for_each_entry_safe(pt, next, &signalled, link) {
+		list_del_init(&pt->link);
+		dma_fence_put(&pt->base);
+	}
 }
 
 /**