[V2,1/6] Swiotlb: Add Swiotlb bounce buffer remap function for HV IVM

Commit Message

Tianyu Lan Nov. 23, 2021, 2:30 p.m. UTC

From: Tianyu Lan <[e-mail]>

In Isolation VM with AMD SEV, bounce buffer needs to be accessed via
extra address space which is above shared_gpa_boundary (E.G 39 bit
address line) reported by Hyper-V CPUID ISOLATION_CONFIG. The access
physical address will be original physical address + shared_gpa_boundary.
The shared_gpa_boundary in the AMD SEV SNP spec is called virtual top of
memory(vTOM). Memory addresses below vTOM are automatically treated as
private while memory above vTOM is treated as shared.

Expose swiotlb_unencrypted_base for platforms to set unencrypted
memory base offset and platform calls swiotlb_update_mem_attributes()
to remap swiotlb mem to unencrypted address space. memremap() can
not be called in the early stage and so put remapping code into
swiotlb_update_mem_attributes(). Store remap address and use it to copy
data from/to swiotlb bounce buffer.

Signed-off-by: Tianyu Lan <[e-mail]>
---
Change since v1:
	* Rework comment in the swiotlb_init_io_tlb_mem()
	* Make swiotlb_init_io_tlb_mem() back to return void.
---
 include/linux/swiotlb.h |  6 +++++
 kernel/dma/swiotlb.c    | 53 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 54 insertions(+), 5 deletions(-)

Comments

Michael Kelley (LINUX) Nov. 23, 2021, 5:15 p.m. UTC | #1

From: Tianyu Lan <[e-mail]> Sent: Tuesday, November 23, 2021 6:31 AM
> 
> In Isolation VM with AMD SEV, bounce buffer needs to be accessed via
> extra address space which is above shared_gpa_boundary (E.G 39 bit
> address line) reported by Hyper-V CPUID ISOLATION_CONFIG. The access
> physical address will be original physical address + shared_gpa_boundary.
> The shared_gpa_boundary in the AMD SEV SNP spec is called virtual top of
> memory(vTOM). Memory addresses below vTOM are automatically treated as
> private while memory above vTOM is treated as shared.
> 
> Expose swiotlb_unencrypted_base for platforms to set unencrypted
> memory base offset and platform calls swiotlb_update_mem_attributes()
> to remap swiotlb mem to unencrypted address space. memremap() can
> not be called in the early stage and so put remapping code into
> swiotlb_update_mem_attributes(). Store remap address and use it to copy
> data from/to swiotlb bounce buffer.
> 
> Signed-off-by: Tianyu Lan <[e-mail]>
> ---
> Change since v1:
> 	* Rework comment in the swiotlb_init_io_tlb_mem()
> 	* Make swiotlb_init_io_tlb_mem() back to return void.
> ---
>  include/linux/swiotlb.h |  6 +++++
>  kernel/dma/swiotlb.c    | 53 +++++++++++++++++++++++++++++++++++++----
>  2 files changed, 54 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 569272871375..f6c3638255d5 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -73,6 +73,9 @@ extern enum swiotlb_force swiotlb_force;
>   * @end:	The end address of the swiotlb memory pool. Used to do a quick
>   *		range check to see if the memory was in fact allocated by this
>   *		API.
> + * @vaddr:	The vaddr of the swiotlb memory pool. The swiotlb memory pool
> + *		may be remapped in the memory encrypted case and store virtual
> + *		address for bounce buffer operation.
>   * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
>   *		@end. For default swiotlb, this is command line adjustable via
>   *		setup_io_tlb_npages.
> @@ -92,6 +95,7 @@ extern enum swiotlb_force swiotlb_force;
>  struct io_tlb_mem {
>  	phys_addr_t start;
>  	phys_addr_t end;
> +	void *vaddr;
>  	unsigned long nslabs;
>  	unsigned long used;
>  	unsigned int index;
> @@ -186,4 +190,6 @@ static inline bool is_swiotlb_for_alloc(struct device *dev)
>  }
>  #endif /* CONFIG_DMA_RESTRICTED_POOL */
> 
> +extern phys_addr_t swiotlb_unencrypted_base;
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index 8e840fbbed7c..c303fdeba82f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -50,6 +50,7 @@
>  #include <asm/io.h>
>  #include <asm/dma.h>
> 
> +#include <linux/io.h>
>  #include <linux/init.h>
>  #include <linux/memblock.h>
>  #include <linux/iommu-helper.h>
> @@ -72,6 +73,8 @@ enum swiotlb_force swiotlb_force;
> 
>  struct io_tlb_mem io_tlb_default_mem;
> 
> +phys_addr_t swiotlb_unencrypted_base;
> +
>  /*
>   * Max segment that we can provide which (if pages are contingous) will
>   * not be bounced (unless SWIOTLB_FORCE is set).
> @@ -155,6 +158,31 @@ static inline unsigned long nr_slots(u64 val)
>  	return DIV_ROUND_UP(val, IO_TLB_SIZE);
>  }
> 
> +/*
> + * Remap swioltb memory in the unencrypted physical address space
> + * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP
> + * Isolation VMs).
> + */
> +void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
> +{
> +	void *vaddr;
> +
> +	if (swiotlb_unencrypted_base) {
> +		phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;
> +
> +		vaddr = memremap(paddr, bytes, MEMREMAP_WB);
> +		if (!vaddr) {
> +			pr_err("Failed to map the unencrypted memory %llx size %lx.\n",
> +			       paddr, bytes);
> +			return NULL;
> +		}
> +
> +		return vaddr;
> +	}
> +
> +	return phys_to_virt(mem->start);
> +}
> +
>  /*
>   * Early SWIOTLB allocation may be too early to allow an architecture to
>   * perform the desired operations.  This function allows the architecture to
> @@ -172,7 +200,14 @@ void __init swiotlb_update_mem_attributes(void)
>  	vaddr = phys_to_virt(mem->start);
>  	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
>  	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
> -	memset(vaddr, 0, bytes);
> +
> +	mem->vaddr = swiotlb_mem_remap(mem, bytes);
> +	if (!mem->vaddr) {
> +		pr_err("Fail to remap swiotlb mem.\n");
> +		return;
> +	}
> +
> +	memset(mem->vaddr, 0, bytes);
>  }

In the error case, do you want to leave mem->vaddr as NULL?  Or is it
better to leave it as the virtual address of mem-start?  Your code leaves it
as NULL.

The interaction between swiotlb_update_mem_attributes() and the helper
function swiotlb_memo_remap() seems kind of clunky.  phys_to_virt() gets called
twice, for example, and two error messages are printed.  The code would be
more straightforward by just putting the helper function inline:

mem->vaddr = phys_to_virt(mem->start);
bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
set_memory_decrypted((unsigned long)(mem->vaddr), bytes >> PAGE_SHIFT);

if (swiotlb_unencrypted_base) {
	phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;

	mem->vaddr = memremap(paddr, bytes, MEMREMAP_WB);
	if (!mem->vaddr) {
		pr_err("Failed to map the unencrypted memory %llx size %lx.\n",
			       paddr, bytes);
		return;
	}
}

memset(mem->vaddr, 0, bytes);

(This version also leaves mem->vaddr as NULL in the error case.)

> 
>  static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
> @@ -196,7 +231,18 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
>  		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
>  		mem->slots[i].alloc_size = 0;
>  	}
> +
> +	/*
> +	 * If swiotlb_unencrypted_base is set, the bounce buffer memory will
> +	 * be remapped and cleared in swiotlb_update_mem_attributes.
> +	 */
> +	if (swiotlb_unencrypted_base)
> +		return;
> +
> +	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);

Prior to this patch, and here in the new version as well, the return value from
set_memory_decrypted() is ignored in several places in this file.  As previously
discussed, swiotlb_init_io_tlb_mem() is a void function, so there's no place to
return an error. Is that OK?

>  	memset(vaddr, 0, bytes);
> +	mem->vaddr = vaddr;
> +	return;
>  }
> 
>  int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
> @@ -318,7 +364,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
>  	if (!mem->slots)
>  		return -ENOMEM;
> 
> -	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
>  	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
> 
>  	swiotlb_print_info();
> @@ -371,7 +416,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
>  	phys_addr_t orig_addr = mem->slots[index].orig_addr;
>  	size_t alloc_size = mem->slots[index].alloc_size;
>  	unsigned long pfn = PFN_DOWN(orig_addr);
> -	unsigned char *vaddr = phys_to_virt(tlb_addr);
> +	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
>  	unsigned int tlb_offset, orig_addr_offset;
> 
>  	if (orig_addr == INVALID_PHYS_ADDR)
> @@ -806,8 +851,6 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
>  			return -ENOMEM;
>  		}
> 
> -		set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
> -				     rmem->size >> PAGE_SHIFT);
>  		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false);
>  		mem->force_bounce = true;
>  		mem->for_alloc = true;
> --
> 2.25.1

Tianyu Lan Nov. 24, 2021, 2:07 p.m. UTC | #2

Hi Michael:
	Thanks for your review.

On 11/24/2021 1:15 AM, Michael Kelley (LINUX) wrote:
>> @@ -172,7 +200,14 @@ void __init swiotlb_update_mem_attributes(void)
>>   	vaddr = phys_to_virt(mem->start);
>>   	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
>>   	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
>> -	memset(vaddr, 0, bytes);
>> +
>> +	mem->vaddr = swiotlb_mem_remap(mem, bytes);
>> +	if (!mem->vaddr) {
>> +		pr_err("Fail to remap swiotlb mem.\n");
>> +		return;
>> +	}
>> +
>> +	memset(mem->vaddr, 0, bytes);
>>   }


> In the error case, do you want to leave mem->vaddr as NULL?  Or is it
> better to leave it as the virtual address of mem-start?  Your code leaves it
> as NULL.
> 
> The interaction between swiotlb_update_mem_attributes() and the helper
> function swiotlb_memo_remap() seems kind of clunky.  phys_to_virt() gets called
> twice, for example, and two error messages are printed.  The code would be
> more straightforward by just putting the helper function inline:
> 
> mem->vaddr = phys_to_virt(mem->start);
> bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
> set_memory_decrypted((unsigned long)(mem->vaddr), bytes >> PAGE_SHIFT);
> 
> if (swiotlb_unencrypted_base) {
> 	phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;
> 
> 	mem->vaddr = memremap(paddr, bytes, MEMREMAP_WB);
> 	if (!mem->vaddr) {
> 		pr_err("Failed to map the unencrypted memory %llx size %lx.\n",
> 			       paddr, bytes);
> 		return;
> 	}
> }
> 
> memset(mem->vaddr, 0, bytes);
> 
> (This version also leaves mem->vaddr as NULL in the error case.)

 From Christoph's previous suggestion, there should be a well-documented 
wrapper to explain the remap option and so I split the code. leaving the 
virtual address of mem-start is better.

https://lkml.org/lkml/2021/9/28/51

> 
>>   static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
>> @@ -196,7 +231,18 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
>>   		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
>>   		mem->slots[i].alloc_size = 0;
>>   	}
>> +
>> +	/*
>> +	 * If swiotlb_unencrypted_base is set, the bounce buffer memory will
>> +	 * be remapped and cleared in swiotlb_update_mem_attributes.
>> +	 */
>> +	if (swiotlb_unencrypted_base)
>> +		return;
>> +
>> +	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
> Prior to this patch, and here in the new version as well, the return value from
> set_memory_decrypted() is ignored in several places in this file.  As previously
> discussed, swiotlb_init_io_tlb_mem() is a void function, so there's no place to
> return an error. Is that OK?

Yes, the original code doesn't check the return value and so keep the 
rule。

Christoph, Could you help to check which way do you prefer?

Patch

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 569272871375..f6c3638255d5 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -73,6 +73,9 @@  extern enum swiotlb_force swiotlb_force;
  * @end:	The end address of the swiotlb memory pool. Used to do a quick
  *		range check to see if the memory was in fact allocated by this
  *		API.
+ * @vaddr:	The vaddr of the swiotlb memory pool. The swiotlb memory pool
+ *		may be remapped in the memory encrypted case and store virtual
+ *		address for bounce buffer operation.
  * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
  *		@end. For default swiotlb, this is command line adjustable via
  *		setup_io_tlb_npages.
@@ -92,6 +95,7 @@  extern enum swiotlb_force swiotlb_force;
 struct io_tlb_mem {
 	phys_addr_t start;
 	phys_addr_t end;
+	void *vaddr;
 	unsigned long nslabs;
 	unsigned long used;
 	unsigned int index;
@@ -186,4 +190,6 @@  static inline bool is_swiotlb_for_alloc(struct device *dev)
 }
 #endif /* CONFIG_DMA_RESTRICTED_POOL */
 
+extern phys_addr_t swiotlb_unencrypted_base;
+
 #endif /* __LINUX_SWIOTLB_H */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8e840fbbed7c..c303fdeba82f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -50,6 +50,7 @@ 
 #include <asm/io.h>
 #include <asm/dma.h>
 
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/iommu-helper.h>
@@ -72,6 +73,8 @@  enum swiotlb_force swiotlb_force;
 
 struct io_tlb_mem io_tlb_default_mem;
 
+phys_addr_t swiotlb_unencrypted_base;
+
 /*
  * Max segment that we can provide which (if pages are contingous) will
  * not be bounced (unless SWIOTLB_FORCE is set).
@@ -155,6 +158,31 @@  static inline unsigned long nr_slots(u64 val)
 	return DIV_ROUND_UP(val, IO_TLB_SIZE);
 }
 
+/*
+ * Remap swioltb memory in the unencrypted physical address space
+ * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP
+ * Isolation VMs).
+ */
+void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes)
+{
+	void *vaddr;
+
+	if (swiotlb_unencrypted_base) {
+		phys_addr_t paddr = mem->start + swiotlb_unencrypted_base;
+
+		vaddr = memremap(paddr, bytes, MEMREMAP_WB);
+		if (!vaddr) {
+			pr_err("Failed to map the unencrypted memory %llx size %lx.\n",
+			       paddr, bytes);
+			return NULL;
+		}
+
+		return vaddr;
+	}
+
+	return phys_to_virt(mem->start);
+}
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
@@ -172,7 +200,14 @@  void __init swiotlb_update_mem_attributes(void)
 	vaddr = phys_to_virt(mem->start);
 	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
 	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
-	memset(vaddr, 0, bytes);
+
+	mem->vaddr = swiotlb_mem_remap(mem, bytes);
+	if (!mem->vaddr) {
+		pr_err("Fail to remap swiotlb mem.\n");
+		return;
+	}
+
+	memset(mem->vaddr, 0, bytes);
 }
 
 static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
@@ -196,7 +231,18 @@  static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
 	}
+
+	/*
+	 * If swiotlb_unencrypted_base is set, the bounce buffer memory will
+	 * be remapped and cleared in swiotlb_update_mem_attributes.
+	 */
+	if (swiotlb_unencrypted_base)
+		return;
+
+	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
 	memset(vaddr, 0, bytes);
+	mem->vaddr = vaddr;
+	return;
 }
 
 int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
@@ -318,7 +364,6 @@  swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!mem->slots)
 		return -ENOMEM;
 
-	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
 	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
 
 	swiotlb_print_info();
@@ -371,7 +416,7 @@  static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	phys_addr_t orig_addr = mem->slots[index].orig_addr;
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
-	unsigned char *vaddr = phys_to_virt(tlb_addr);
+	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
 	unsigned int tlb_offset, orig_addr_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
@@ -806,8 +851,6 @@  static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 			return -ENOMEM;
 		}
 
-		set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
-				     rmem->size >> PAGE_SHIFT);
 		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false);
 		mem->force_bounce = true;
 		mem->for_alloc = true;