ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 288 insertions, 0 deletions

diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
new file mode 100644
index 000000000..57b2c6419
--- /dev/null
+++ b/drivers/hv/hv_proc.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+#include <linux/minmax.h>
+#include <linux/export.h>
+#include <asm/mshyperv.h>
+
+/*
+ * See struct hv_deposit_memory. The first u64 is partition ID, the rest
+ * are GPAs.
+ */
+#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1)
+
+/* Deposits exact number of pages. Must be called with interrupts enabled.  */
+int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
+{
+	struct page **pages, *page;
+	int *counts;
+	int num_allocations;
+	int i, j, page_count;
+	int order;
+	u64 status;
+	int ret;
+	u64 base_pfn;
+	struct hv_deposit_memory *input_page;
+	unsigned long flags;
+
+	if (num_pages > HV_DEPOSIT_MAX)
+		return -E2BIG;
+	if (!num_pages)
+		return 0;
+
+	/* One buffer for page pointers and counts */
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+	pages = page_address(page);
+
+	counts = kzalloc_objs(int, HV_DEPOSIT_MAX);
+	if (!counts) {
+		free_page((unsigned long)pages);
+		return -ENOMEM;
+	}
+
+	/* Allocate all the pages before disabling interrupts */
+	i = 0;
+
+	while (num_pages) {
+		/* Find highest order we can actually allocate */
+		order = 31 - __builtin_clz(num_pages);
+
+		while (1) {
+			pages[i] = alloc_pages_node(node, GFP_KERNEL, order);
+			if (pages[i])
+				break;
+			if (!order) {
+				ret = -ENOMEM;
+				num_allocations = i;
+				goto err_free_allocations;
+			}
+			--order;
+		}
+
+		split_page(pages[i], order);
+		counts[i] = 1 << order;
+		num_pages -= counts[i];
+		i++;
+	}
+	num_allocations = i;
+
+	local_irq_save(flags);
+
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	input_page->partition_id = partition_id;
+
+	/* Populate gpa_page_list - these will fit on the input page */
+	for (i = 0, page_count = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j, ++page_count)
+			input_page->gpa_page_list[page_count] = base_pfn + j;
+	}
+	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
+				     page_count, 0, input_page, NULL);
+	local_irq_restore(flags);
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		ret = hv_result_to_errno(status);
+		goto err_free_allocations;
+	}
+
+	ret = 0;
+	goto free_buf;
+
+err_free_allocations:
+	for (i = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j)
+			__free_page(pfn_to_page(base_pfn + j));
+	}
+
+free_buf:
+	free_page((unsigned long)pages);
+	kfree(counts);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_call_deposit_pages);
+
+int hv_deposit_memory_node(int node, u64 partition_id,
+			   u64 hv_status)
+{
+	u32 num_pages = 1;
+
+	switch (hv_result(hv_status)) {
+	case HV_STATUS_INSUFFICIENT_MEMORY:
+		break;
+	case HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY:
+		num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
+		break;
+
+	case HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY:
+		num_pages = HV_MAX_CONTIGUOUS_ALLOCATION_PAGES;
+		fallthrough;
+	case HV_STATUS_INSUFFICIENT_ROOT_MEMORY:
+		if (!hv_root_partition()) {
+			hv_status_err(hv_status, "Unexpected root memory deposit\n");
+			return -ENOMEM;
+		}
+		partition_id = HV_PARTITION_ID_SELF;
+		break;
+
+	default:
+		hv_status_err(hv_status, "Unexpected!\n");
+		return -ENOMEM;
+	}
+	return hv_call_deposit_pages(node, partition_id, num_pages);
+}
+EXPORT_SYMBOL_GPL(hv_deposit_memory_node);
+
+bool hv_result_needs_memory(u64 status)
+{
+	switch (hv_result(status)) {
+	case HV_STATUS_INSUFFICIENT_MEMORY:
+	case HV_STATUS_INSUFFICIENT_CONTIGUOUS_MEMORY:
+	case HV_STATUS_INSUFFICIENT_ROOT_MEMORY:
+	case HV_STATUS_INSUFFICIENT_CONTIGUOUS_ROOT_MEMORY:
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(hv_result_needs_memory);
+
+int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
+{
+	struct hv_input_add_logical_processor *input;
+	struct hv_output_add_logical_processor *output;
+	u64 status;
+	unsigned long flags;
+	int ret = 0;
+
+	/*
+	 * When adding a logical processor, the hypervisor may return
+	 * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more
+	 * pages and retry.
+	 */
+	do {
+		local_irq_save(flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+		/* We don't do anything with the output right now */
+		output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+		input->lp_index = lp_index;
+		input->apic_id = apic_id;
+		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
+		status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
+					 input, output);
+		local_irq_restore(flags);
+
+		if (!hv_result_needs_memory(status)) {
+			if (!hv_result_success(status)) {
+				hv_status_err(status, "cpu %u apic ID: %u\n",
+					      lp_index, apic_id);
+				ret = hv_result_to_errno(status);
+			}
+			break;
+		}
+		ret = hv_deposit_memory_node(node, hv_current_partition_id,
+					     status);
+	} while (!ret);
+
+	return ret;
+}
+
+int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
+{
+	struct hv_create_vp *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	/* Root VPs don't seem to need pages deposited */
+	if (partition_id != hv_current_partition_id) {
+		/* The value 90 is empirically determined. It may change. */
+		ret = hv_call_deposit_pages(node, partition_id, 90);
+		if (ret)
+			return ret;
+	}
+
+	do {
+		local_irq_save(irq_flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+		input->partition_id = partition_id;
+		input->vp_index = vp_index;
+		input->flags = flags;
+		input->subnode_type = HV_SUBNODE_ANY;
+		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
+		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
+		local_irq_restore(irq_flags);
+
+		if (!hv_result_needs_memory(status)) {
+			if (!hv_result_success(status)) {
+				hv_status_err(status, "vcpu: %u, lp: %u\n",
+					      vp_index, flags);
+				ret = hv_result_to_errno(status);
+			}
+			break;
+		}
+		ret = hv_deposit_memory_node(node, partition_id, status);
+
+	} while (!ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_call_create_vp);
+
+int hv_call_notify_all_processors_started(void)
+{
+	struct hv_input_notify_partition_event *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	local_irq_save(irq_flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(input, 0, sizeof(*input));
+	input->event = HV_PARTITION_ALL_LOGICAL_PROCESSORS_STARTED;
+	status = hv_do_hypercall(HVCALL_NOTIFY_PARTITION_EVENT,
+				 input, NULL);
+	local_irq_restore(irq_flags);
+
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		ret = hv_result_to_errno(status);
+	}
+	return ret;
+}
+
+bool hv_lp_exists(u32 lp_index)
+{
+	struct hv_input_get_logical_processor_run_time *input;
+	struct hv_output_get_logical_processor_run_time *output;
+	unsigned long flags;
+	u64 status;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	input->lp_index = lp_index;
+	status = hv_do_hypercall(HVCALL_GET_LOGICAL_PROCESSOR_RUN_TIME,
+				 input, output);
+	local_irq_restore(flags);
+
+	if (!hv_result_success(status) &&
+	    hv_result(status) != HV_STATUS_INVALID_LP_INDEX) {
+		hv_status_err(status, "\n");
+		BUG();
+	}
+
+	return hv_result_success(status);
+}