x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

4 files changed, 998 insertions, 0 deletions

diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig
new file mode 100644
index 000000000..bb729e915
--- /dev/null
+++ b/drivers/dma-buf/heaps/Kconfig
@@ -0,0 +1,22 @@
+config DMABUF_HEAPS_SYSTEM
+	tristate "DMA-BUF System Heap"
+	depends on DMABUF_HEAPS
+	help
+	  Choose this option to enable the system dmabuf heap. The system heap
+	  is backed by pages from the buddy allocator. If in doubt, say Y.
+
+config DMABUF_HEAPS_SYSTEM_CC_SHARED
+	bool "DMA-BUF System Heap for decrypted CoCo VMs"
+	depends on DMABUF_HEAPS && ARCH_HAS_MEM_ENCRYPT && DMABUF_HEAPS_SYSTEM=y
+	help
+	  Choose this option to enable the system_cc_shared dmabuf heap. This
+	  allows allocating shared (decrypted) memory for confidential computing
+	  (CoCo) VMs.
+
+config DMABUF_HEAPS_CMA
+	tristate "DMA-BUF CMA Heap"
+	depends on DMABUF_HEAPS && DMA_CMA
+	help
+	  Choose this option to enable dma-buf CMA heap. This heap is backed
+	  by the Contiguous Memory Allocator (CMA). If your system has these
+	  regions, you should say Y here.
diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile
new file mode 100644
index 000000000..974467791
--- /dev/null
+++ b/drivers/dma-buf/heaps/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DMABUF_HEAPS_SYSTEM)	+= system_heap.o
+obj-$(CONFIG_DMABUF_HEAPS_CMA)		+= cma_heap.o
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
new file mode 100644
index 000000000..3fb4b946c
--- /dev/null
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -0,0 +1,425 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF CMA heap exporter
+ *
+ * Copyright (C) 2012, 2019, 2020 Linaro Ltd.
+ * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson.
+ *
+ * Also utilizing parts of Andrew Davis' SRAM heap:
+ * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+ *	Andrew F. Davis <afd@ti.com>
+ */
+
+#define pr_fmt(fmt) "cma_heap: " fmt
+
+#include <linux/cma.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/dma-map-ops.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#define DEFAULT_CMA_NAME "default_cma_region"
+
+struct cma_heap {
+	struct dma_heap *heap;
+	struct cma *cma;
+};
+
+struct cma_heap_buffer {
+	struct cma_heap *heap;
+	struct list_head attachments;
+	struct mutex lock;
+	unsigned long len;
+	struct page *cma_pages;
+	struct page **pages;
+	pgoff_t pagecount;
+	int vmap_cnt;
+	void *vaddr;
+};
+
+struct dma_heap_attachment {
+	struct device *dev;
+	struct sg_table table;
+	struct list_head list;
+	bool mapped;
+};
+
+static int cma_heap_attach(struct dma_buf *dmabuf,
+			   struct dma_buf_attachment *attachment)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+	int ret;
+
+	a = kzalloc_obj(*a);
+	if (!a)
+		return -ENOMEM;
+
+	ret = sg_alloc_table_from_pages(&a->table, buffer->pages,
+					buffer->pagecount, 0,
+					buffer->pagecount << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret) {
+		kfree(a);
+		return ret;
+	}
+
+	a->dev = attachment->dev;
+	INIT_LIST_HEAD(&a->list);
+	a->mapped = false;
+
+	attachment->priv = a;
+
+	mutex_lock(&buffer->lock);
+	list_add(&a->list, &buffer->attachments);
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void cma_heap_detach(struct dma_buf *dmabuf,
+			    struct dma_buf_attachment *attachment)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a = attachment->priv;
+
+	mutex_lock(&buffer->lock);
+	list_del(&a->list);
+	mutex_unlock(&buffer->lock);
+
+	sg_free_table(&a->table);
+	kfree(a);
+}
+
+static struct sg_table *cma_heap_map_dma_buf(struct dma_buf_attachment *attachment,
+					     enum dma_data_direction direction)
+{
+	struct dma_heap_attachment *a = attachment->priv;
+	struct sg_table *table = &a->table;
+	int ret;
+
+	ret = dma_map_sgtable(attachment->dev, table, direction, 0);
+	if (ret)
+		return ERR_PTR(-ENOMEM);
+	a->mapped = true;
+	return table;
+}
+
+static void cma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
+				   struct sg_table *table,
+				   enum dma_data_direction direction)
+{
+	struct dma_heap_attachment *a = attachment->priv;
+
+	a->mapped = false;
+	dma_unmap_sgtable(attachment->dev, table, direction, 0);
+}
+
+static int cma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+					     enum dma_data_direction direction)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		invalidate_kernel_vmap_range(buffer->vaddr, buffer->len);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		if (!a->mapped)
+			continue;
+		dma_sync_sgtable_for_cpu(a->dev, &a->table, direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static int cma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					   enum dma_data_direction direction)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		flush_kernel_vmap_range(buffer->vaddr, buffer->len);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		if (!a->mapped)
+			continue;
+		dma_sync_sgtable_for_device(a->dev, &a->table, direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct cma_heap_buffer *buffer = vma->vm_private_data;
+
+	if (vmf->pgoff >= buffer->pagecount)
+		return VM_FAULT_SIGBUS;
+
+	return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff]));
+}
+
+static const struct vm_operations_struct dma_heap_vm_ops = {
+	.fault = cma_heap_vm_fault,
+};
+
+static int cma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
+	vma->vm_ops = &dma_heap_vm_ops;
+	vma->vm_private_data = buffer;
+
+	return 0;
+}
+
+static void *cma_heap_do_vmap(struct cma_heap_buffer *buffer)
+{
+	void *vaddr;
+
+	vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL);
+	if (!vaddr)
+		return ERR_PTR(-ENOMEM);
+
+	return vaddr;
+}
+
+static int cma_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	void *vaddr;
+	int ret = 0;
+
+	mutex_lock(&buffer->lock);
+	if (buffer->vmap_cnt) {
+		buffer->vmap_cnt++;
+		iosys_map_set_vaddr(map, buffer->vaddr);
+		goto out;
+	}
+
+	vaddr = cma_heap_do_vmap(buffer);
+	if (IS_ERR(vaddr)) {
+		ret = PTR_ERR(vaddr);
+		goto out;
+	}
+	buffer->vaddr = vaddr;
+	buffer->vmap_cnt++;
+	iosys_map_set_vaddr(map, buffer->vaddr);
+out:
+	mutex_unlock(&buffer->lock);
+
+	return ret;
+}
+
+static void cma_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	if (!--buffer->vmap_cnt) {
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+	mutex_unlock(&buffer->lock);
+	iosys_map_clear(map);
+}
+
+static void cma_heap_dma_buf_release(struct dma_buf *dmabuf)
+{
+	struct cma_heap_buffer *buffer = dmabuf->priv;
+	struct cma_heap *cma_heap = buffer->heap;
+
+	if (buffer->vmap_cnt > 0) {
+		WARN(1, "%s: buffer still mapped in the kernel\n", __func__);
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+
+	/* free page list */
+	kfree(buffer->pages);
+	/* release memory */
+	cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
+	kfree(buffer);
+}
+
+static const struct dma_buf_ops cma_heap_buf_ops = {
+	.attach = cma_heap_attach,
+	.detach = cma_heap_detach,
+	.map_dma_buf = cma_heap_map_dma_buf,
+	.unmap_dma_buf = cma_heap_unmap_dma_buf,
+	.begin_cpu_access = cma_heap_dma_buf_begin_cpu_access,
+	.end_cpu_access = cma_heap_dma_buf_end_cpu_access,
+	.mmap = cma_heap_mmap,
+	.vmap = cma_heap_vmap,
+	.vunmap = cma_heap_vunmap,
+	.release = cma_heap_dma_buf_release,
+};
+
+static struct dma_buf *cma_heap_allocate(struct dma_heap *heap,
+					 unsigned long len,
+					 u32 fd_flags,
+					 u64 heap_flags)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
+	struct cma_heap_buffer *buffer;
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	size_t size = PAGE_ALIGN(len);
+	pgoff_t pagecount = size >> PAGE_SHIFT;
+	unsigned long align = get_order(size);
+	struct page *cma_pages;
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	buffer = kzalloc_obj(*buffer);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&buffer->attachments);
+	mutex_init(&buffer->lock);
+	buffer->len = size;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false);
+	if (!cma_pages)
+		goto free_buffer;
+
+	/* Clear the cma pages */
+	if (PageHighMem(cma_pages)) {
+		unsigned long nr_clear_pages = pagecount;
+		struct page *page = cma_pages;
+
+		while (nr_clear_pages > 0) {
+			clear_highpage(page);
+			/*
+			 * Avoid wasting time zeroing memory if the process
+			 * has been killed by SIGKILL.
+			 */
+			if (fatal_signal_pending(current))
+				goto free_cma;
+			page++;
+			nr_clear_pages--;
+		}
+	} else {
+		clear_pages(page_address(cma_pages), pagecount);
+	}
+
+	buffer->pages = kmalloc_objs(*buffer->pages, pagecount);
+	if (!buffer->pages) {
+		ret = -ENOMEM;
+		goto free_cma;
+	}
+
+	for (pg = 0; pg < pagecount; pg++)
+		buffer->pages[pg] = &cma_pages[pg];
+
+	buffer->cma_pages = cma_pages;
+	buffer->heap = cma_heap;
+	buffer->pagecount = pagecount;
+
+	/* create the dmabuf */
+	exp_info.exp_name = dma_heap_get_name(heap);
+	exp_info.ops = &cma_heap_buf_ops;
+	exp_info.size = buffer->len;
+	exp_info.flags = fd_flags;
+	exp_info.priv = buffer;
+	dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto free_pages;
+	}
+	return dmabuf;
+
+free_pages:
+	kfree(buffer->pages);
+free_cma:
+	cma_release(cma_heap->cma, cma_pages, pagecount);
+free_buffer:
+	kfree(buffer);
+
+	return ERR_PTR(ret);
+}
+
+static const struct dma_heap_ops cma_heap_ops = {
+	.allocate = cma_heap_allocate,
+};
+
+static int __init __add_cma_heap(struct cma *cma, const char *name)
+{
+	struct dma_heap_export_info exp_info;
+	struct cma_heap *cma_heap;
+
+	cma_heap = kzalloc_obj(*cma_heap);
+	if (!cma_heap)
+		return -ENOMEM;
+	cma_heap->cma = cma;
+
+	exp_info.name = name;
+	exp_info.ops = &cma_heap_ops;
+	exp_info.priv = cma_heap;
+
+	cma_heap->heap = dma_heap_add(&exp_info);
+	if (IS_ERR(cma_heap->heap)) {
+		int ret = PTR_ERR(cma_heap->heap);
+
+		kfree(cma_heap);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init add_cma_heaps(void)
+{
+	struct cma *default_cma = dev_get_cma_area(NULL);
+	struct cma *cma;
+	unsigned int i;
+	int ret;
+
+	if (default_cma) {
+		ret = __add_cma_heap(default_cma, DEFAULT_CMA_NAME);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; (cma = dma_contiguous_get_area_by_idx(i)) != NULL; i++) {
+		ret = __add_cma_heap(cma, cma_get_name(cma));
+		if (ret) {
+			pr_warn("Failed to add CMA heap %s", cma_get_name(cma));
+			continue;
+		}
+
+	}
+
+	return 0;
+}
+module_init(add_cma_heaps);
+MODULE_DESCRIPTION("DMA-BUF CMA Heap");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("DMA_BUF");
+MODULE_IMPORT_NS("DMA_BUF_HEAP");
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
new file mode 100644
index 000000000..c8959eadc
--- /dev/null
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF System heap exporter
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019, 2020 Linaro Ltd.
+ *
+ * Portions based off of Andrew Davis' SRAM heap:
+ * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+ *	Andrew F. Davis <afd@ti.com>
+ */
+
+#include <linux/cc_platform.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-heap.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mem_encrypt.h>
+#include <linux/mm.h>
+#include <linux/set_memory.h>
+#include <linux/module.h>
+#include <linux/pgtable.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+struct system_heap_priv {
+	bool cc_shared;
+};
+
+struct system_heap_buffer {
+	struct dma_heap *heap;
+	struct list_head attachments;
+	struct mutex lock;
+	unsigned long len;
+	struct sg_table sg_table;
+	int vmap_cnt;
+	void *vaddr;
+	bool cc_shared;
+};
+
+struct dma_heap_attachment {
+	struct device *dev;
+	struct sg_table table;
+	struct list_head list;
+	bool mapped;
+	bool cc_shared;
+};
+
+#define cc_shared_buffer(b) (IS_ENABLED(CONFIG_DMABUF_HEAPS_SYSTEM_CC_SHARED) && \
+				(b)->cc_shared)
+
+#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO)
+#define HIGH_ORDER_GFP  (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \
+				| __GFP_NORETRY) & ~__GFP_RECLAIM) \
+				| __GFP_COMP)
+static gfp_t order_flags[] = {HIGH_ORDER_GFP, HIGH_ORDER_GFP, LOW_ORDER_GFP};
+/*
+ * The selection of the orders used for allocation (1MB, 64K, 4K) is designed
+ * to match with the sizes often found in IOMMUs. Using order 4 pages instead
+ * of order 0 pages can significantly improve the performance of many IOMMUs
+ * by reducing TLB pressure and time spent updating page tables.
+ */
+static const unsigned int orders[] = {8, 4, 0};
+#define NUM_ORDERS ARRAY_SIZE(orders)
+
+static int system_heap_set_page_decrypted(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+	unsigned int nr_pages = 1 << compound_order(page);
+	int ret;
+
+	ret = set_memory_decrypted(addr, nr_pages);
+	if (ret)
+		pr_warn_ratelimited("dma-buf system heap: failed to decrypt page at %p\n",
+				    page_address(page));
+
+	return ret;
+}
+
+static int system_heap_set_page_encrypted(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+	unsigned int nr_pages = 1 << compound_order(page);
+	int ret;
+
+	ret = set_memory_encrypted(addr, nr_pages);
+	if (ret)
+		pr_warn_ratelimited("dma-buf system heap: failed to re-encrypt page at %p, leaking memory\n",
+				    page_address(page));
+
+	return ret;
+}
+
+static int dup_sg_table(struct sg_table *from, struct sg_table *to)
+{
+	struct scatterlist *sg, *new_sg;
+	int ret, i;
+
+	ret = sg_alloc_table(to, from->orig_nents, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	new_sg = to->sgl;
+	for_each_sgtable_sg(from, sg, i) {
+		sg_set_page(new_sg, sg_page(sg), sg->length, sg->offset);
+		new_sg = sg_next(new_sg);
+	}
+
+	return 0;
+}
+
+static int system_heap_attach(struct dma_buf *dmabuf,
+			      struct dma_buf_attachment *attachment)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+	int ret;
+
+	a = kzalloc_obj(*a);
+	if (!a)
+		return -ENOMEM;
+
+	ret = dup_sg_table(&buffer->sg_table, &a->table);
+	if (ret) {
+		kfree(a);
+		return ret;
+	}
+
+	a->dev = attachment->dev;
+	INIT_LIST_HEAD(&a->list);
+	a->mapped = false;
+	a->cc_shared = buffer->cc_shared;
+
+	attachment->priv = a;
+
+	mutex_lock(&buffer->lock);
+	list_add(&a->list, &buffer->attachments);
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void system_heap_detach(struct dma_buf *dmabuf,
+			       struct dma_buf_attachment *attachment)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a = attachment->priv;
+
+	mutex_lock(&buffer->lock);
+	list_del(&a->list);
+	mutex_unlock(&buffer->lock);
+
+	sg_free_table(&a->table);
+	kfree(a);
+}
+
+static struct sg_table *system_heap_map_dma_buf(struct dma_buf_attachment *attachment,
+						enum dma_data_direction direction)
+{
+	struct dma_heap_attachment *a = attachment->priv;
+	struct sg_table *table = &a->table;
+	unsigned long attrs;
+	int ret;
+
+	attrs = cc_shared_buffer(a) ? DMA_ATTR_CC_SHARED : 0;
+	ret = dma_map_sgtable(attachment->dev, table, direction, attrs);
+	if (ret)
+		return ERR_PTR(ret);
+
+	a->mapped = true;
+	return table;
+}
+
+static void system_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
+				      struct sg_table *table,
+				      enum dma_data_direction direction)
+{
+	struct dma_heap_attachment *a = attachment->priv;
+
+	a->mapped = false;
+	dma_unmap_sgtable(attachment->dev, table, direction, 0);
+}
+
+static int system_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+						enum dma_data_direction direction)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		invalidate_kernel_vmap_range(buffer->vaddr, buffer->len);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		if (!a->mapped)
+			continue;
+		dma_sync_sgtable_for_cpu(a->dev, &a->table, direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static int system_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					      enum dma_data_direction direction)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct dma_heap_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		flush_kernel_vmap_range(buffer->vaddr, buffer->len);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		if (!a->mapped)
+			continue;
+		dma_sync_sgtable_for_device(a->dev, &a->table, direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static int system_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct sg_table *table = &buffer->sg_table;
+	unsigned long addr = vma->vm_start;
+	unsigned long pgoff = vma->vm_pgoff;
+	struct scatterlist *sg;
+	pgprot_t prot;
+	int i, ret;
+
+	prot = vma->vm_page_prot;
+	if (cc_shared_buffer(buffer))
+		prot = pgprot_decrypted(prot);
+
+	for_each_sgtable_sg(table, sg, i) {
+		unsigned long n = sg->length >> PAGE_SHIFT;
+
+		if (pgoff < n)
+			break;
+		pgoff -= n;
+	}
+
+	for (; sg && addr < vma->vm_end; sg = sg_next(sg)) {
+		unsigned long n = (sg->length >> PAGE_SHIFT) - pgoff;
+		struct page *page = sg_page(sg) + pgoff;
+		unsigned long size = n << PAGE_SHIFT;
+
+		if (addr + size > vma->vm_end)
+			size = vma->vm_end - addr;
+
+		ret = remap_pfn_range(vma, addr, page_to_pfn(page), size, prot);
+		if (ret)
+			return ret;
+
+		addr += size;
+		pgoff = 0;
+	}
+
+	return 0;
+}
+
+static void *system_heap_do_vmap(struct system_heap_buffer *buffer)
+{
+	struct sg_table *table = &buffer->sg_table;
+	int npages = PAGE_ALIGN(buffer->len) / PAGE_SIZE;
+	struct page **pages = vmalloc(sizeof(struct page *) * npages);
+	struct page **tmp = pages;
+	struct sg_page_iter piter;
+	pgprot_t prot;
+	void *vaddr;
+
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	for_each_sgtable_page(table, &piter, 0) {
+		WARN_ON(tmp - pages >= npages);
+		*tmp++ = sg_page_iter_page(&piter);
+	}
+
+	prot = PAGE_KERNEL;
+	if (cc_shared_buffer(buffer))
+		prot = pgprot_decrypted(prot);
+	vaddr = vmap(pages, npages, VM_MAP, prot);
+	vfree(pages);
+
+	if (!vaddr)
+		return ERR_PTR(-ENOMEM);
+
+	return vaddr;
+}
+
+static int system_heap_vmap(struct dma_buf *dmabuf, struct iosys_map *map)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	void *vaddr;
+	int ret = 0;
+
+	mutex_lock(&buffer->lock);
+	if (buffer->vmap_cnt) {
+		buffer->vmap_cnt++;
+		iosys_map_set_vaddr(map, buffer->vaddr);
+		goto out;
+	}
+
+	vaddr = system_heap_do_vmap(buffer);
+	if (IS_ERR(vaddr)) {
+		ret = PTR_ERR(vaddr);
+		goto out;
+	}
+
+	buffer->vaddr = vaddr;
+	buffer->vmap_cnt++;
+	iosys_map_set_vaddr(map, buffer->vaddr);
+out:
+	mutex_unlock(&buffer->lock);
+
+	return ret;
+}
+
+static void system_heap_vunmap(struct dma_buf *dmabuf, struct iosys_map *map)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	if (!--buffer->vmap_cnt) {
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+	mutex_unlock(&buffer->lock);
+	iosys_map_clear(map);
+}
+
+static void system_heap_dma_buf_release(struct dma_buf *dmabuf)
+{
+	struct system_heap_buffer *buffer = dmabuf->priv;
+	struct sg_table *table;
+	struct scatterlist *sg;
+	int i;
+
+	table = &buffer->sg_table;
+	for_each_sgtable_sg(table, sg, i) {
+		struct page *page = sg_page(sg);
+
+		/*
+		 * Intentionally leak pages that cannot be re-encrypted
+		 * to prevent shared memory from being reused.
+		 */
+		if (cc_shared_buffer(buffer) &&
+		    system_heap_set_page_encrypted(page))
+			continue;
+
+		__free_pages(page, compound_order(page));
+	}
+	sg_free_table(table);
+	kfree(buffer);
+}
+
+static const struct dma_buf_ops system_heap_buf_ops = {
+	.attach = system_heap_attach,
+	.detach = system_heap_detach,
+	.map_dma_buf = system_heap_map_dma_buf,
+	.unmap_dma_buf = system_heap_unmap_dma_buf,
+	.begin_cpu_access = system_heap_dma_buf_begin_cpu_access,
+	.end_cpu_access = system_heap_dma_buf_end_cpu_access,
+	.mmap = system_heap_mmap,
+	.vmap = system_heap_vmap,
+	.vunmap = system_heap_vunmap,
+	.release = system_heap_dma_buf_release,
+};
+
+static struct page *alloc_largest_available(unsigned long size,
+					    unsigned int max_order)
+{
+	struct page *page;
+	int i;
+	gfp_t flags;
+
+	for (i = 0; i < NUM_ORDERS; i++) {
+		if (size <  (PAGE_SIZE << orders[i]))
+			continue;
+		if (max_order < orders[i])
+			continue;
+		flags = order_flags[i];
+		if (mem_accounting)
+			flags |= __GFP_ACCOUNT;
+		page = alloc_pages(flags, orders[i]);
+		if (!page)
+			continue;
+		return page;
+	}
+	return NULL;
+}
+
+static struct dma_buf *system_heap_allocate(struct dma_heap *heap,
+					    unsigned long len,
+					    u32 fd_flags,
+					    u64 heap_flags)
+{
+	struct system_heap_buffer *buffer;
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	unsigned long size_remaining = len;
+	unsigned int max_order = orders[0];
+	struct system_heap_priv *priv = dma_heap_get_drvdata(heap);
+	bool cc_shared = priv->cc_shared;
+	struct dma_buf *dmabuf;
+	struct sg_table *table;
+	struct scatterlist *sg;
+	struct list_head pages;
+	struct page *page, *tmp_page;
+	int i, ret = -ENOMEM;
+
+	buffer = kzalloc_obj(*buffer);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&buffer->attachments);
+	mutex_init(&buffer->lock);
+	buffer->heap = heap;
+	buffer->len = len;
+	buffer->cc_shared = cc_shared;
+
+	INIT_LIST_HEAD(&pages);
+	i = 0;
+	while (size_remaining > 0) {
+		/*
+		 * Avoid trying to allocate memory if the process
+		 * has been killed by SIGKILL
+		 */
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			goto free_buffer;
+		}
+
+		page = alloc_largest_available(size_remaining, max_order);
+		if (!page)
+			goto free_buffer;
+
+		list_add_tail(&page->lru, &pages);
+		size_remaining -= page_size(page);
+		max_order = compound_order(page);
+		i++;
+	}
+
+	table = &buffer->sg_table;
+	if (sg_alloc_table(table, i, GFP_KERNEL))
+		goto free_buffer;
+
+	sg = table->sgl;
+	list_for_each_entry_safe(page, tmp_page, &pages, lru) {
+		sg_set_page(sg, page, page_size(page), 0);
+		sg = sg_next(sg);
+		list_del(&page->lru);
+	}
+
+	if (cc_shared_buffer(buffer)) {
+		for_each_sgtable_sg(table, sg, i) {
+			ret = system_heap_set_page_decrypted(sg_page(sg));
+			if (ret)
+				goto free_pages;
+		}
+	}
+
+	/* create the dmabuf */
+	exp_info.exp_name = dma_heap_get_name(heap);
+	exp_info.ops = &system_heap_buf_ops;
+	exp_info.size = buffer->len;
+	exp_info.flags = fd_flags;
+	exp_info.priv = buffer;
+	dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto free_pages;
+	}
+	return dmabuf;
+
+free_pages:
+	for_each_sgtable_sg(table, sg, i) {
+		struct page *p = sg_page(sg);
+
+		/*
+		 * Intentionally leak pages that cannot be re-encrypted
+		 * to prevent shared memory from being reused.
+		 */
+		if (cc_shared_buffer(buffer) &&
+		    system_heap_set_page_encrypted(p))
+			continue;
+		__free_pages(p, compound_order(p));
+	}
+	sg_free_table(table);
+free_buffer:
+	list_for_each_entry_safe(page, tmp_page, &pages, lru)
+		__free_pages(page, compound_order(page));
+	kfree(buffer);
+
+	return ERR_PTR(ret);
+}
+
+static const struct dma_heap_ops system_heap_ops = {
+	.allocate = system_heap_allocate,
+};
+
+static struct system_heap_priv system_heap_priv = {
+	.cc_shared = false,
+};
+
+static struct system_heap_priv system_heap_cc_shared_priv = {
+	.cc_shared = true,
+};
+
+static int __init system_heap_create(void)
+{
+	struct dma_heap_export_info exp_info;
+	struct dma_heap *sys_heap;
+
+	exp_info.name = "system";
+	exp_info.ops = &system_heap_ops;
+	exp_info.priv = &system_heap_priv;
+
+	sys_heap = dma_heap_add(&exp_info);
+	if (IS_ERR(sys_heap))
+		return PTR_ERR(sys_heap);
+
+	if (IS_ENABLED(CONFIG_HIGHMEM) ||
+	    !IS_ENABLED(CONFIG_DMABUF_HEAPS_SYSTEM_CC_SHARED) ||
+	    !cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return 0;
+
+	exp_info.name = "system_cc_shared";
+	exp_info.priv = &system_heap_cc_shared_priv;
+	sys_heap = dma_heap_add(&exp_info);
+	if (IS_ERR(sys_heap))
+		return PTR_ERR(sys_heap);
+
+	return 0;
+}
+module_init(system_heap_create);
+
+MODULE_DESCRIPTION("DMA-BUF System Heap");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("DMA_BUF");
+MODULE_IMPORT_NS("DMA_BUF_HEAP");