[PATCH] memblock: add no-map alloc functions

[PATCH] memblock: add no-map alloc functions

[skseofh]

From: Daero Lee <daero_le.lee@samsung.com>

Like reserved-memory with the no-map property, there are memory regions
need to be allocated in memblock.memory marked with the
MEMBLOCK_NOMAP flag, but sholud not be allocated in memblock.reserved.

So, functions were added that find the required memory area in
memblock.memory, but do not allocate it to memblock.reserved.

The early_init_dt_alloc_reserved_memory_arch function was modified
using the no-map alloc function.

Signed-off-by: Daero Lee <daero_le.lee@samsung.com>
---
 drivers/of/of_reserved_mem.c |  9 +++--
 mm/memblock.c                | 78 ++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+), 3 deletions(-)

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 8236ecae2953..504f2f60689c 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -40,15 +40,18 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
 
 	end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end;
 	align = !align ? SMP_CACHE_BYTES : align;
-	base = memblock_phys_alloc_range(size, align, start, end);
+	if (nomap) {
+		base = memblock_phys_alloc_range_nomap(size, align, start, end);
+	} else {
+		base = memblock_phys_alloc_range(size, align, start, end);
+	}
+	
 	if (!base)
 		return -ENOMEM;
 
 	*res_base = base;
 	if (nomap) {
 		err = memblock_mark_nomap(base, size);
-		if (err)
-			memblock_phys_free(base, size);
 	}
 
 	kmemleak_ignore_phys(base);
diff --git a/mm/memblock.c b/mm/memblock.c
index d09136e040d3..f103f1ecbfad 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1506,6 +1506,72 @@ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 	return found;
 }
 
+phys_addr_t __init memblock_alloc_range_nid_nomap(phys_addr_t size,
+                                        phys_addr_t align, phys_addr_t start,
+                                        phys_addr_t end, int nid,
+                                        bool exact_nid)
+{
+        enum memblock_flags flags = choose_memblock_flags();
+        phys_addr_t found;
+
+        if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
+                nid = NUMA_NO_NODE;
+
+        if (!align) {
+                /* Can't use WARNs this early in boot on powerpc */
+                dump_stack();
+                align = SMP_CACHE_BYTES;
+        }
+
+again:
+        found = memblock_find_in_range_node(size, align, start, end, nid,
+                                            flags);
+        if (found)
+                goto done;
+
+        if (nid != NUMA_NO_NODE && !exact_nid) {
+                found = memblock_find_in_range_node(size, align, start,
+                                                    end, NUMA_NO_NODE,
+                                                    flags);
+                if (found)
+                        goto done;
+        }
+
+        if (flags & MEMBLOCK_MIRROR) {
+                flags &= ~MEMBLOCK_MIRROR;
+                pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n",
+                        &size);
+                goto again;
+        }
+
+        return 0;
+
+done:
+        /*
+         * Skip kmemleak for those places like kasan_init() and
+         * early_pgtable_alloc() due to high volume.
+         */
+        if (end != MEMBLOCK_ALLOC_NOLEAKTRACE)
+                /*
+                 * Memblock allocated blocks are never reported as
+                 * leaks. This is because many of these blocks are
+                 * only referred via the physical address which is
+                 * not looked up by kmemleak.
+                 */
+                kmemleak_alloc_phys(found, size, 0);
+
+        /*
+         * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP,
+         * require memory to be accepted before it can be used by the
+         * guest.
+         *
+         * Accept the memory of the allocated buffer.
+         */
+        accept_memory(found, found + size);
+
+        return found;
+}
+
 /**
  * memblock_phys_alloc_range - allocate a memory block inside specified range
  * @size: size of memory block to be allocated in bytes
@@ -1530,6 +1596,18 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size,
 					false);
 }
 
+phys_addr_t __init memblock_phys_alloc_range_nomap(phys_addr_t size,
+                                                   phys_addr_t align,
+                                                   phys_addr_t start,
+                                                   phys_addr_t end)
+{
+        memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n",
+                     __func__, (u64)size, (u64)align, &start, &end,
+                     (void *)_RET_IP_);
+        return memblock_alloc_range_nid_nomap(size, align, start, end, 
+					      NUMA_NO_NODE, false);
+}
+
 /**
  * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node
  * @size: size of memory block to be allocated in bytes
-- 
2.25.1

Re: [PATCH] memblock: add no-map alloc functions

[Mike Rapoport]

On Mon, Apr 15, 2024 at 11:24:48PM +0900, skseofh@gmail.com wrote:
> From: Daero Lee <daero_le.lee@samsung.com>
> 
> Like reserved-memory with the no-map property, there are memory regions
> need to be allocated in memblock.memory marked with the
> MEMBLOCK_NOMAP flag, but sholud not be allocated in memblock.reserved.

Can you please explain your use case?
Why do you need this functionality?
 
> So, functions were added that find the required memory area in
> memblock.memory, but do not allocate it to memblock.reserved.
> 
> The early_init_dt_alloc_reserved_memory_arch function was modified
> using the no-map alloc function.
> 
> Signed-off-by: Daero Lee <daero_le.lee@samsung.com>
> ---
>  drivers/of/of_reserved_mem.c |  9 +++--
>  mm/memblock.c                | 78 ++++++++++++++++++++++++++++++++++++
>  2 files changed, 84 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
> index 8236ecae2953..504f2f60689c 100644
> --- a/drivers/of/of_reserved_mem.c
> +++ b/drivers/of/of_reserved_mem.c
> @@ -40,15 +40,18 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
>  
>  	end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end;
>  	align = !align ? SMP_CACHE_BYTES : align;
> -	base = memblock_phys_alloc_range(size, align, start, end);
> +	if (nomap) {
> +		base = memblock_phys_alloc_range_nomap(size, align, start, end);
> +	} else {
> +		base = memblock_phys_alloc_range(size, align, start, end);
> +	}
> +	

This changes behaviour of internal function, what effect will it have on
the users?

>  	if (!base)
>  		return -ENOMEM;
>  
>  	*res_base = base;
>  	if (nomap) {
>  		err = memblock_mark_nomap(base, size);
> -		if (err)
> -			memblock_phys_free(base, size);
>  	}
>  
>  	kmemleak_ignore_phys(base);

-- 
Sincerely yours,
Mike.

Re: [PATCH] memblock: add no-map alloc functions

[Wei Yang]

On Mon, Apr 15, 2024 at 06:26:55PM +0300, Mike Rapoport wrote:
[...]
>> +	
>
>This changes behaviour of internal function, what effect will it have on
>the users?
>
>>  	if (!base)
>>  		return -ENOMEM;
>>  
>>  	*res_base = base;
>>  	if (nomap) {
>>  		err = memblock_mark_nomap(base, size);

Mike

One question may not directly relevant to this thread.

NOMAP doesn't apply to all arch? I took a look into the direct mapping
function on x86, memory_map_top_down(). It seems iterate all available pfn
instead of skipping NOMAP range. 

>> -		if (err)
>> -			memblock_phys_free(base, size);
>>  	}
>>  
>>  	kmemleak_ignore_phys(base);
>
>-- 
>Sincerely yours,
>Mike.

-- 
Wei Yang
Help you, Help me

Re: [PATCH] memblock: add no-map alloc functions

[Mike Rapoport]

On Wed, Apr 17, 2024 at 02:31:47AM +0000, Wei Yang wrote:
> On Mon, Apr 15, 2024 at 06:26:55PM +0300, Mike Rapoport wrote:
> [...]
> >> +	
> >
> >This changes behaviour of internal function, what effect will it have on
> >the users?
> >
> >>  	if (!base)
> >>  		return -ENOMEM;
> >>  
> >>  	*res_base = base;
> >>  	if (nomap) {
> >>  		err = memblock_mark_nomap(base, size);
> 
> Mike
> 
> One question may not directly relevant to this thread.
> 
> NOMAP doesn't apply to all arch? I took a look into the direct mapping
> function on x86, memory_map_top_down(). It seems iterate all available pfn
> instead of skipping NOMAP range. 

Right, x86 does not use NOMAP.
NOMAP was introduced to ensure that device/firmware memory on arm64 does
not have an alias mapping in the direct map because MMU does not allow
alias mapping with different caching modes.
 
> >> -		if (err)
> >> -			memblock_phys_free(base, size);
> >>  	}
> >>  
> >>  	kmemleak_ignore_phys(base);
> >
> >-- 
> >Sincerely yours,
> >Mike.
> 
> -- 
> Wei Yang
> Help you, Help me

-- 
Sincerely yours,
Mike.

Re: [PATCH] memblock: add no-map alloc functions

[Wei Yang]

On Mon, Apr 15, 2024 at 11:24:48PM +0900, skseofh@gmail.com wrote:
>From: Daero Lee <daero_le.lee@samsung.com>
>
>Like reserved-memory with the no-map property, there are memory regions
>need to be allocated in memblock.memory marked with the
>MEMBLOCK_NOMAP flag, but sholud not be allocated in memblock.reserved.
>
>So, functions were added that find the required memory area in
>memblock.memory, but do not allocate it to memblock.reserved.
>
>The early_init_dt_alloc_reserved_memory_arch function was modified
>using the no-map alloc function.
>
>Signed-off-by: Daero Lee <daero_le.lee@samsung.com>
>---
> drivers/of/of_reserved_mem.c |  9 +++--
> mm/memblock.c                | 78 ++++++++++++++++++++++++++++++++++++
> 2 files changed, 84 insertions(+), 3 deletions(-)
>
>diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
>index 8236ecae2953..504f2f60689c 100644
>--- a/drivers/of/of_reserved_mem.c
>+++ b/drivers/of/of_reserved_mem.c
>@@ -40,15 +40,18 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
> 
> 	end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end;
> 	align = !align ? SMP_CACHE_BYTES : align;
>-	base = memblock_phys_alloc_range(size, align, start, end);
>+	if (nomap) {
>+		base = memblock_phys_alloc_range_nomap(size, align, start, end);
>+	} else {
>+		base = memblock_phys_alloc_range(size, align, start, end);
>+	}
>+	
> 	if (!base)
> 		return -ENOMEM;
> 
> 	*res_base = base;
> 	if (nomap) {
> 		err = memblock_mark_nomap(base, size);
>-		if (err)
>-			memblock_phys_free(base, size);
> 	}
> 
> 	kmemleak_ignore_phys(base);
>diff --git a/mm/memblock.c b/mm/memblock.c
>index d09136e040d3..f103f1ecbfad 100644
>--- a/mm/memblock.c
>+++ b/mm/memblock.c
>@@ -1506,6 +1506,72 @@ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
> 	return found;
> }
> 
>+phys_addr_t __init memblock_alloc_range_nid_nomap(phys_addr_t size,
>+                                        phys_addr_t align, phys_addr_t start,
>+                                        phys_addr_t end, int nid,
>+                                        bool exact_nid)
>+{
>+        enum memblock_flags flags = choose_memblock_flags();
>+        phys_addr_t found;
>+
>+        if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
>+                nid = NUMA_NO_NODE;
>+
>+        if (!align) {
>+                /* Can't use WARNs this early in boot on powerpc */
>+                dump_stack();
>+                align = SMP_CACHE_BYTES;
>+        }
>+
>+again:
>+        found = memblock_find_in_range_node(size, align, start, end, nid,
>+                                            flags);
>+        if (found)
>+                goto done;

Only find without reserve has no effect on memblock meta data. It seems run
but nothing happens.

What you want to achieve for this function?

-- 
Wei Yang
Help you, Help me