[PATCH] powerpc/mm: Add validation for platform reserved memory ranges

[PATCH] powerpc/mm: Add validation for platform reserved memory ranges

[Anshuman Khandual]

For partition running on PHYP, there can be a adjunct partition
which shares the virtual address range with the operating system.
Virtual address ranges which can be used by the adjunct partition
are communicated with virtual device node of the device tree with
a property known as "ibm,reserved-virtual-addresses". This patch
introduces a new function named 'validate_reserved_va_range' which
is called  during initialization to validate that these reserved
virtual address ranges do not overlap with the address ranges used
by the kernel for all supported memory contexts. This helps prevent
the possibility of getting return codes similar to H_RESOURCE for
H_PROTECT hcalls for conflicting HPTE entries.

Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
---
- It has been tested on both LE and BE POWER8 platforms

 arch/powerpc/mm/hash_utils_64.c | 77 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index ba59d59..ee14df7 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1564,3 +1564,80 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	/* Finally limit subsequent allocations */
 	memblock_set_current_limit(ppc64_rma_size);
 }
+
+/*
+ * PAPR says that each reserved virtual address range record
+ * contains three be32 elements which is of toal 12 bytes.
+ * First two be32 elements contain the abbreviated virtual
+ * address (high order 32 bits and low order 32 bits that
+ * generate the abbreviated virtual address of 64 bits which
+ * need to be concatenated with 24 bits of 0 at the end) and
+ * the third be32 element contains the size of the reserved
+ * virtual address range as number of consecutive 4K pages.
+ */
+struct reserved_va_record {
+	__be32	high_addr;
+	__be32	low_addr;
+	__be32	nr_pages_4K;
+};
+
+/*
+ * Linux uses 65 bits (CONTEXT_BITS + ESID_BITS + SID_SHIFT)
+ * of virtual address. As reserved virtual address comes in
+ * as an abbreviated form (64 bits) from the device tree, we
+ * will use a partial address bit mask (65 >> 24) to match it
+ * for simplicity.
+ */
+#define RVA_LESS_BITS		24
+#define LINUX_VA_BITS		CONTEXT_BITS + ESID_BITS + SID_SHIFT
+#define	PARTIAL_LINUX_VA_MASK	((1ULL << (LINUX_VA_BITS - RVA_LESS_BITS)) - 1)
+
+static int __init validate_reserved_va_range(void)
+{
+	struct reserved_va_record rva;
+	struct device_node *np;
+	int records, ret, i;
+	__be64 vaddr;
+
+	np = of_find_node_by_name(NULL, "vdevice");
+	if (!np)
+		return -ENODEV;
+
+	records = of_property_count_elems_of_size(np,
+			"ibm,reserved-virtual-addresses",
+				sizeof(struct reserved_va_record));
+	if (records < 0)
+		return records;
+
+	for (i = 0; i < records; i++) {
+		ret = of_property_read_u32_index(np,
+			"ibm,reserved-virtual-addresses",
+				3 * i, &rva.high_addr);
+		if (ret)
+			return ret;
+
+		ret = of_property_read_u32_index(np,
+			"ibm,reserved-virtual-addresses",
+				3 * i + 1, &rva.low_addr);
+		if (ret)
+			return ret;
+
+		ret = of_property_read_u32_index(np,
+			"ibm,reserved-virtual-addresses",
+				3 * i + 2, &rva.nr_pages_4K);
+		if (ret)
+			return ret;
+
+		vaddr =  rva.high_addr;
+		vaddr =  (vaddr << 32) | rva.low_addr;
+		if (vaddr & cpu_to_be64(~PARTIAL_LINUX_VA_MASK))
+			continue;
+
+		pr_err("RVA [0x%llx000000 (0x%x in bytes)] overlapped\n",
+					vaddr, rva.nr_pages_4K * 4096);
+		BUG();
+	}
+	of_node_put(np);
+	return 0;
+}
+__initcall(validate_reserved_va_range);
-- 
1.9.3

Re: [PATCH] powerpc/mm: Add validation for platform reserved memory ranges

[Anshuman Khandual]

On 03/04/2016 03:20 PM, Anshuman Khandual wrote:
> For partition running on PHYP, there can be a adjunct partition
> which shares the virtual address range with the operating system.
> Virtual address ranges which can be used by the adjunct partition
> are communicated with virtual device node of the device tree with
> a property known as "ibm,reserved-virtual-addresses". This patch
> introduces a new function named 'validate_reserved_va_range' which
> is called  during initialization to validate that these reserved
> virtual address ranges do not overlap with the address ranges used
> by the kernel for all supported memory contexts. This helps prevent
> the possibility of getting return codes similar to H_RESOURCE for
> H_PROTECT hcalls for conflicting HPTE entries.
> 
> Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
> ---
> - It has been tested on both LE and BE POWER8 platforms
> 
>  arch/powerpc/mm/hash_utils_64.c | 77 +++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 77 insertions(+)
> 
> diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
> index ba59d59..ee14df7 100644
> --- a/arch/powerpc/mm/hash_utils_64.c
> +++ b/arch/powerpc/mm/hash_utils_64.c
> @@ -1564,3 +1564,80 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
>  	/* Finally limit subsequent allocations */
>  	memblock_set_current_limit(ppc64_rma_size);
>  }
> +
> +/*
> + * PAPR says that each reserved virtual address range record
> + * contains three be32 elements which is of toal 12 bytes.
> + * First two be32 elements contain the abbreviated virtual
> + * address (high order 32 bits and low order 32 bits that
> + * generate the abbreviated virtual address of 64 bits which
> + * need to be concatenated with 24 bits of 0 at the end) and
> + * the third be32 element contains the size of the reserved
> + * virtual address range as number of consecutive 4K pages.
> + */
> +struct reserved_va_record {
> +	__be32	high_addr;
> +	__be32	low_addr;
> +	__be32	nr_pages_4K;
> +};
> +
> +/*
> + * Linux uses 65 bits (CONTEXT_BITS + ESID_BITS + SID_SHIFT)
> + * of virtual address. As reserved virtual address comes in
> + * as an abbreviated form (64 bits) from the device tree, we
> + * will use a partial address bit mask (65 >> 24) to match it
> + * for simplicity.
> + */
> +#define RVA_LESS_BITS		24
> +#define LINUX_VA_BITS		CONTEXT_BITS + ESID_BITS + SID_SHIFT
> +#define	PARTIAL_LINUX_VA_MASK	((1ULL << (LINUX_VA_BITS - RVA_LESS_BITS)) - 1)

Oops, the indentation should have been similar here. Will fix it.