[PATCH 1/2] doc: update mem= option's spec

[PATCH 1/2] doc: update mem= option's spec

[Wen Congyang]

Current mem= implementation seems buggy because specification and
implementation doesn't match. Current mem= has been working
for many years and it's not buggy, it works as expected. So
we should update the specification.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
 Documentation/kernel-parameters.txt |    7 ++++---
 1 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a92c5eb..924b1a4 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1471,9 +1471,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
 			Amount of memory to be used when the kernel is not able
 			to see the whole system memory or for test.
-			[X86-32] Use together with memmap= to avoid physical
-			address space collisions. Without memmap= PCI devices
-			could be placed at addresses belonging to unused RAM.
+			[X86-32] Work as limiting max address. Use together
+			with memmap= to avoid physical address space collisions.
+			Without memmap= PCI devices could be placed at addresses
+			belonging to unused RAM.
 
 	mem=nopentium	[BUGS=X86-32] Disable usage of 4MB pages for kernel
 			memory.
-- 
1.7.1

[PATCH 2/2] x86: reimplement mem boot option

[Wen Congyang]

Current mem boot option only can work for non efi environment. If the user
specifies add_efi_memmap, it cannot work for efi environment. In
the efi environment, we call e820_add_region() to add the memory map. So
we can modify __e820_add_region() and the mem boot option can work for
efi environment.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
 arch/x86/kernel/e820.c |   29 +++++++++++++++++++++++++----
 1 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 4185797..20bc467 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL(pci_mem_start);
 #endif
+static u64 mem_limit = ~0ULL;
 
 /*
  * This function checks if any part of the range <start,end> is mapped
@@ -119,6 +120,20 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
 		return;
 	}
 
+	if (start >= mem_limit) {
+		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
+		       (unsigned long long)start,
+		       (unsigned long long)(start + size - 1));
+		return;
+	}
+
+	if (mem_limit - start < size) {
+		printk(KERN_ERR "e820: ingoring [mem %#010llx-%#010llx]\n",
+		       (unsigned long long)mem_limit,
+		       (unsigned long long)(start + size - 1));
+		size = mem_limit - start;
+	}
+
 	e820x->map[x].addr = start;
 	e820x->map[x].size = size;
 	e820x->map[x].type = type;
@@ -809,7 +824,7 @@ static int userdef __initdata;
 /* "mem=nopentium" disables the 4MB page tables. */
 static int __init parse_memopt(char *p)
 {
-	u64 mem_size;
+	char *oldp;
 
 	if (!p)
 		return -EINVAL;
@@ -825,11 +840,11 @@ static int __init parse_memopt(char *p)
 	}
 
 	userdef = 1;
-	mem_size = memparse(p, &p);
+	oldp = p;
+	mem_limit = memparse(p, &p);
 	/* don't remove all of memory when handling "mem={invalid}" param */
-	if (mem_size == 0)
+	if (mem_limit == 0 || p == oldp)
 		return -EINVAL;
-	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
 	return 0;
 }
@@ -881,6 +896,12 @@ early_param("memmap", parse_memmap_opt);
 
 void __init finish_e820_parsing(void)
 {
+	if (mem_limit != ~0ULL) {
+		userdef = 1;
+		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
+				  E820_RAM, 1);
+	}
+
 	if (userdef) {
 		u32 nr = e820.nr_map;
 
-- 
1.7.1

Re: [PATCH 2/2] x86: reimplement mem boot option

[Wen Congyang]

Pin......

At 06/14/2012 04:12 PM, Wen Congyang Wrote:
> Current mem boot option only can work for non efi environment. If the user
> specifies add_efi_memmap, it cannot work for efi environment. In
> the efi environment, we call e820_add_region() to add the memory map. So
> we can modify __e820_add_region() and the mem boot option can work for
> efi environment.
> 
> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
> ---
>  arch/x86/kernel/e820.c |   29 +++++++++++++++++++++++++----
>  1 files changed, 25 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
> index 4185797..20bc467 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
>  #ifdef CONFIG_PCI
>  EXPORT_SYMBOL(pci_mem_start);
>  #endif
> +static u64 mem_limit = ~0ULL;
>  
>  /*
>   * This function checks if any part of the range <start,end> is mapped
> @@ -119,6 +120,20 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
>  		return;
>  	}
>  
> +	if (start >= mem_limit) {
> +		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
> +		       (unsigned long long)start,
> +		       (unsigned long long)(start + size - 1));
> +		return;
> +	}
> +
> +	if (mem_limit - start < size) {
> +		printk(KERN_ERR "e820: ingoring [mem %#010llx-%#010llx]\n",
> +		       (unsigned long long)mem_limit,
> +		       (unsigned long long)(start + size - 1));
> +		size = mem_limit - start;
> +	}
> +
>  	e820x->map[x].addr = start;
>  	e820x->map[x].size = size;
>  	e820x->map[x].type = type;
> @@ -809,7 +824,7 @@ static int userdef __initdata;
>  /* "mem=nopentium" disables the 4MB page tables. */
>  static int __init parse_memopt(char *p)
>  {
> -	u64 mem_size;
> +	char *oldp;
>  
>  	if (!p)
>  		return -EINVAL;
> @@ -825,11 +840,11 @@ static int __init parse_memopt(char *p)
>  	}
>  
>  	userdef = 1;
> -	mem_size = memparse(p, &p);
> +	oldp = p;
> +	mem_limit = memparse(p, &p);
>  	/* don't remove all of memory when handling "mem={invalid}" param */
> -	if (mem_size == 0)
> +	if (mem_limit == 0 || p == oldp)
>  		return -EINVAL;
> -	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
>  
>  	return 0;
>  }
> @@ -881,6 +896,12 @@ early_param("memmap", parse_memmap_opt);
>  
>  void __init finish_e820_parsing(void)
>  {
> +	if (mem_limit != ~0ULL) {
> +		userdef = 1;
> +		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
> +				  E820_RAM, 1);
> +	}
> +
>  	if (userdef) {
>  		u32 nr = e820.nr_map;
>  

Re: [PATCH 2/2] x86: reimplement mem boot option

[Wen Congyang]

At 06/28/2012 09:29 AM, Wen Congyang Wrote:
> Pin......

Ping again........

> 
> At 06/14/2012 04:12 PM, Wen Congyang Wrote:
>> Current mem boot option only can work for non efi environment. If the user
>> specifies add_efi_memmap, it cannot work for efi environment. In
>> the efi environment, we call e820_add_region() to add the memory map. So
>> we can modify __e820_add_region() and the mem boot option can work for
>> efi environment.
>>
>> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
>> ---
>>  arch/x86/kernel/e820.c |   29 +++++++++++++++++++++++++----
>>  1 files changed, 25 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
>> index 4185797..20bc467 100644
>> --- a/arch/x86/kernel/e820.c
>> +++ b/arch/x86/kernel/e820.c
>> @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
>>  #ifdef CONFIG_PCI
>>  EXPORT_SYMBOL(pci_mem_start);
>>  #endif
>> +static u64 mem_limit = ~0ULL;
>>  
>>  /*
>>   * This function checks if any part of the range <start,end> is mapped
>> @@ -119,6 +120,20 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
>>  		return;
>>  	}
>>  
>> +	if (start >= mem_limit) {
>> +		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
>> +		       (unsigned long long)start,
>> +		       (unsigned long long)(start + size - 1));
>> +		return;
>> +	}
>> +
>> +	if (mem_limit - start < size) {
>> +		printk(KERN_ERR "e820: ingoring [mem %#010llx-%#010llx]\n",
>> +		       (unsigned long long)mem_limit,
>> +		       (unsigned long long)(start + size - 1));
>> +		size = mem_limit - start;
>> +	}
>> +
>>  	e820x->map[x].addr = start;
>>  	e820x->map[x].size = size;
>>  	e820x->map[x].type = type;
>> @@ -809,7 +824,7 @@ static int userdef __initdata;
>>  /* "mem=nopentium" disables the 4MB page tables. */
>>  static int __init parse_memopt(char *p)
>>  {
>> -	u64 mem_size;
>> +	char *oldp;
>>  
>>  	if (!p)
>>  		return -EINVAL;
>> @@ -825,11 +840,11 @@ static int __init parse_memopt(char *p)
>>  	}
>>  
>>  	userdef = 1;
>> -	mem_size = memparse(p, &p);
>> +	oldp = p;
>> +	mem_limit = memparse(p, &p);
>>  	/* don't remove all of memory when handling "mem={invalid}" param */
>> -	if (mem_size == 0)
>> +	if (mem_limit == 0 || p == oldp)
>>  		return -EINVAL;
>> -	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
>>  
>>  	return 0;
>>  }
>> @@ -881,6 +896,12 @@ early_param("memmap", parse_memmap_opt);
>>  
>>  void __init finish_e820_parsing(void)
>>  {
>> +	if (mem_limit != ~0ULL) {
>> +		userdef = 1;
>> +		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
>> +				  E820_RAM, 1);
>> +	}
>> +
>>  	if (userdef) {
>>  		u32 nr = e820.nr_map;
>>  
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 

Re: [PATCH 2/2] x86: reimplement mem boot option

[Ingo Molnar]

* Wen Congyang <wency@cn.fujitsu.com> wrote:

> At 06/28/2012 09:29 AM, Wen Congyang Wrote:
> > Pin......
> 
> Ping again........

I guess when hpa gets back from the road he'll have a look.

Thanks,

	Ingo

[PATCH v2 2/2] x86: reimplement mem boot option

[Wen Congyang]

Current mem boot option only can work for non efi environment. If the user
specifies add_efi_memmap, it cannot work for efi environment. In
the efi environment, we call e820_add_region() to add the memory map. So
we can modify __e820_add_region() and the mem boot option can work for
efi environment.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
 arch/x86/kernel/e820.c |   29 +++++++++++++++++++++++++----
 1 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 4185797..20bc467 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL(pci_mem_start);
 #endif
+static u64 mem_limit = ~0ULL;
 
 /*
  * This function checks if any part of the range <start,end> is mapped
@@ -119,6 +120,20 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
 		return;
 	}
 
+	if (start >= mem_limit) {
+		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
+		       (unsigned long long)start,
+		       (unsigned long long)(start + size - 1));
+		return;
+	}
+
+	if (mem_limit - start < size) {
+		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
+		       (unsigned long long)mem_limit,
+		       (unsigned long long)(start + size - 1));
+		size = mem_limit - start;
+	}
+
 	e820x->map[x].addr = start;
 	e820x->map[x].size = size;
 	e820x->map[x].type = type;
@@ -809,7 +824,7 @@ static int userdef __initdata;
 /* "mem=nopentium" disables the 4MB page tables. */
 static int __init parse_memopt(char *p)
 {
-	u64 mem_size;
+	char *oldp;
 
 	if (!p)
 		return -EINVAL;
@@ -825,11 +840,11 @@ static int __init parse_memopt(char *p)
 	}
 
 	userdef = 1;
-	mem_size = memparse(p, &p);
+	oldp = p;
+	mem_limit = memparse(p, &p);
 	/* don't remove all of memory when handling "mem={invalid}" param */
-	if (mem_size == 0)
+	if (mem_limit == 0 || p == oldp)
 		return -EINVAL;
-	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
 	return 0;
 }
@@ -881,6 +896,12 @@ early_param("memmap", parse_memmap_opt);
 
 void __init finish_e820_parsing(void)
 {
+	if (mem_limit != ~0ULL) {
+		userdef = 1;
+		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
+				  E820_RAM, 1);
+	}
+
 	if (userdef) {
 		u32 nr = e820.nr_map;
 
-- 
1.7.1

Re: [PATCH v2 2/2] x86: reimplement mem boot option

[Wen Congyang]

Hi, H. Peter Anvin

Do you have time to review this patch?

Thanks
Wen Congyang

At 08/21/2012 04:11 PM, Wen Congyang Wrote:
> Current mem boot option only can work for non efi environment. If the user
> specifies add_efi_memmap, it cannot work for efi environment. In
> the efi environment, we call e820_add_region() to add the memory map. So
> we can modify __e820_add_region() and the mem boot option can work for
> efi environment.
> 
> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
> ---
>  arch/x86/kernel/e820.c |   29 +++++++++++++++++++++++++----
>  1 files changed, 25 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
> index 4185797..20bc467 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
>  #ifdef CONFIG_PCI
>  EXPORT_SYMBOL(pci_mem_start);
>  #endif
> +static u64 mem_limit = ~0ULL;
>  
>  /*
>   * This function checks if any part of the range <start,end> is mapped
> @@ -119,6 +120,20 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
>  		return;
>  	}
>  
> +	if (start >= mem_limit) {
> +		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
> +		       (unsigned long long)start,
> +		       (unsigned long long)(start + size - 1));
> +		return;
> +	}
> +
> +	if (mem_limit - start < size) {
> +		printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
> +		       (unsigned long long)mem_limit,
> +		       (unsigned long long)(start + size - 1));
> +		size = mem_limit - start;
> +	}
> +
>  	e820x->map[x].addr = start;
>  	e820x->map[x].size = size;
>  	e820x->map[x].type = type;
> @@ -809,7 +824,7 @@ static int userdef __initdata;
>  /* "mem=nopentium" disables the 4MB page tables. */
>  static int __init parse_memopt(char *p)
>  {
> -	u64 mem_size;
> +	char *oldp;
>  
>  	if (!p)
>  		return -EINVAL;
> @@ -825,11 +840,11 @@ static int __init parse_memopt(char *p)
>  	}
>  
>  	userdef = 1;
> -	mem_size = memparse(p, &p);
> +	oldp = p;
> +	mem_limit = memparse(p, &p);
>  	/* don't remove all of memory when handling "mem={invalid}" param */
> -	if (mem_size == 0)
> +	if (mem_limit == 0 || p == oldp)
>  		return -EINVAL;
> -	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
>  
>  	return 0;
>  }
> @@ -881,6 +896,12 @@ early_param("memmap", parse_memmap_opt);
>  
>  void __init finish_e820_parsing(void)
>  {
> +	if (mem_limit != ~0ULL) {
> +		userdef = 1;
> +		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
> +				  E820_RAM, 1);
> +	}
> +
>  	if (userdef) {
>  		u32 nr = e820.nr_map;
>  

Re: [PATCH 1/2] doc: update mem= option's spec

[Rob Landley]

On 06/14/2012 03:10 AM, Wen Congyang wrote:
> Current mem= implementation seems buggy because specification and
> implementation doesn't match. Current mem= has been working
> for many years and it's not buggy, it works as expected. So
> we should update the specification.
> 
> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
> ---
>  Documentation/kernel-parameters.txt |    7 ++++---
>  1 files changed, 4 insertions(+), 3 deletions(-)
> 
> diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
> index a92c5eb..924b1a4 100644
> --- a/Documentation/kernel-parameters.txt
> +++ b/Documentation/kernel-parameters.txt
> @@ -1471,9 +1471,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
>  	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
>  			Amount of memory to be used when the kernel is not able
>  			to see the whole system memory or for test.
> -			[X86-32] Use together with memmap= to avoid physical
> -			address space collisions. Without memmap= PCI devices
> -			could be placed at addresses belonging to unused RAM.
> +			[X86-32] Work as limiting max address. Use together
> +			with memmap= to avoid physical address space collisions.
> +			Without memmap= PCI devices could be placed at addresses
> +			belonging to unused RAM.
>  
>  	mem=nopentium	[BUGS=X86-32] Disable usage of 4MB pages for kernel
>  			memory.

I have no objection to this but can't confirm it's true or not without
an awful lot more digging through the code I don't have time for right
now. (All the x86-32 machines I've used just had the 640k->1m hole and
the rest was contiguous memory, so the behavior would be the same either
way...)

Sort-of-tentatively-acked-by: Rob Landley <rob@landley.net>

Rob
-- 
GNU/Linux isn't: Linux=GPLv2, GNU=GPLv3+, they can't share code.
Either it's "mere aggregation", or a license violation.  Pick one.