[PATCH RESEND v1 0/5] powerpc/crash: use generic crashkernel reservation

[PATCH RESEND v1 0/5] powerpc/crash: use generic crashkernel reservation

[Sourabh Jain]

Commit 0ab97169aa05 ("crash_core: add generic function to do
reservation") added a generic function to reserve crashkernel memory.
So let's use the same function on powerpc and remove the
architecture-specific code that essentially does the same thing.

The generic crashkernel reservation also provides a way to split the
crashkernel reservation into high and low memory reservations, which can
be enabled for powerpc in the future.

Additionally move powerpc to use generic APIs to locate memory hole for
kexec segments while loading kdump kernel.

Patch series summary:
=====================
Patch 1-2: generic changes
Patch 3-4: powerpc changes
Patch 5:   generic + powerpc changes

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: sourabhjain@linux.ibm.com

Changelog:

v1 Resend:
 - Rebased on top of 6.13-rc6

Sourabh Jain (5):
  crash: remove an unused argument from reserve_crashkernel_generic()
  crash: let arch decide crash memory export to iomem_resource
  powerpc/kdump: preserve user-specified memory limit
  powerpc/crash: use generic crashkernel reservation
  crash: option to let arch decide mem range is usable

 arch/arm64/mm/init.c                     |   6 +-
 arch/loongarch/kernel/setup.c            |   5 +-
 arch/powerpc/Kconfig                     |   3 +
 arch/powerpc/include/asm/crash_reserve.h |  18 ++
 arch/powerpc/include/asm/kexec.h         |  10 +-
 arch/powerpc/kernel/prom.c               |   2 +-
 arch/powerpc/kexec/core.c                |  96 ++++-----
 arch/powerpc/kexec/file_load_64.c        | 259 +----------------------
 arch/riscv/mm/init.c                     |   6 +-
 arch/x86/kernel/setup.c                  |   6 +-
 include/linux/crash_reserve.h            |  22 +-
 include/linux/kexec.h                    |   9 +
 kernel/crash_reserve.c                   |  12 +-
 kernel/kexec_file.c                      |  12 ++
 14 files changed, 127 insertions(+), 339 deletions(-)
 create mode 100644 arch/powerpc/include/asm/crash_reserve.h

-- 
2.47.1

[PATCH RESEND v1 1/5] crash: remove an unused argument from reserve_crashkernel_generic()

[Sourabh Jain]

cmdline argument is not used in reserve_crashkernel_generic() so remove
it. Correspondingly, all the callers have been updated as well.

No functional change intended.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
---
 arch/arm64/mm/init.c          |  6 ++----
 arch/loongarch/kernel/setup.c |  5 ++---
 arch/riscv/mm/init.c          |  6 ++----
 arch/x86/kernel/setup.c       |  6 ++----
 include/linux/crash_reserve.h | 11 +++++------
 kernel/crash_reserve.c        |  9 ++++-----
 6 files changed, 17 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index ccdef53872a0..2e496209af80 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -98,21 +98,19 @@ static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 56934fe58170..ece9c4266c3f 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -259,18 +259,17 @@ static void __init arch_reserve_crashkernel(void)
 	int ret;
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base, &low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static void __init fdt_setup(void)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index fc53ce748c80..750991df9e52 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1377,21 +1377,19 @@ static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 void __init paging_init(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f1fea506e20f..15b6823556c8 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -469,14 +469,13 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long crash_base, crash_size, low_size = 0;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
@@ -487,8 +486,7 @@ static void __init arch_reserve_crashkernel(void)
 		return;
 	}
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static struct resource standard_io_resources[] = {
diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h
index 5a9df944fb80..1fe7e7d1b214 100644
--- a/include/linux/crash_reserve.h
+++ b/include/linux/crash_reserve.h
@@ -32,13 +32,12 @@ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 #define CRASH_ADDR_HIGH_MAX		memblock_end_of_DRAM()
 #endif
 
-void __init reserve_crashkernel_generic(char *cmdline,
-		unsigned long long crash_size,
-		unsigned long long crash_base,
-		unsigned long long crash_low_size,
-		bool high);
+void __init reserve_crashkernel_generic(unsigned long long crash_size,
+					unsigned long long crash_base,
+					unsigned long long crash_low_size,
+					bool high);
 #else
-static inline void __init reserve_crashkernel_generic(char *cmdline,
+static inline void __init reserve_crashkernel_generic(
 		unsigned long long crash_size,
 		unsigned long long crash_base,
 		unsigned long long crash_low_size,
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index a620fb4b2116..aff7c0fdbefa 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -375,11 +375,10 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 	return 0;
 }
 
-void __init reserve_crashkernel_generic(char *cmdline,
-			     unsigned long long crash_size,
-			     unsigned long long crash_base,
-			     unsigned long long crash_low_size,
-			     bool high)
+void __init reserve_crashkernel_generic(unsigned long long crash_size,
+					unsigned long long crash_base,
+					unsigned long long crash_low_size,
+					bool high)
 {
 	unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0;
 	bool fixed_base = false;
-- 
2.47.1

Re: [PATCH RESEND v1 1/5] crash: remove an unused argument from reserve_crashkernel_generic()

[Baoquan he]

On 01/08/25 at 03:44pm, Sourabh Jain wrote:
> cmdline argument is not used in reserve_crashkernel_generic() so remove
> it. Correspondingly, all the callers have been updated as well.
> 
> No functional change intended.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Baoquan he <bhe@redhat.com>
> Cc: Hari Bathini <hbathini@linux.ibm.com>
> CC: Madhavan Srinivasan <maddy@linux.ibm.com>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: kexec@lists.infradead.org
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
> ---
>  arch/arm64/mm/init.c          |  6 ++----
>  arch/loongarch/kernel/setup.c |  5 ++---
>  arch/riscv/mm/init.c          |  6 ++----
>  arch/x86/kernel/setup.c       |  6 ++----
>  include/linux/crash_reserve.h | 11 +++++------
>  kernel/crash_reserve.c        |  9 ++++-----
>  6 files changed, 17 insertions(+), 26 deletions(-)

Acked-by: Baoquan He <bhe@redhat.com>

Re: [PATCH RESEND v1 1/5] crash: remove an unused argument from reserve_crashkernel_generic()

[Sourabh Jain]

Hello Baoquan,


On 08/01/25 16:46, Baoquan he wrote:
> On 01/08/25 at 03:44pm, Sourabh Jain wrote:
>> cmdline argument is not used in reserve_crashkernel_generic() so remove
>> it. Correspondingly, all the callers have been updated as well.
>>
>> No functional change intended.
>>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: Baoquan he <bhe@redhat.com>
>> Cc: Hari Bathini <hbathini@linux.ibm.com>
>> CC: Madhavan Srinivasan <maddy@linux.ibm.com>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: kexec@lists.infradead.org
>> Cc: linux-kernel@vger.kernel.org
>> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
>> ---
>>   arch/arm64/mm/init.c          |  6 ++----
>>   arch/loongarch/kernel/setup.c |  5 ++---
>>   arch/riscv/mm/init.c          |  6 ++----
>>   arch/x86/kernel/setup.c       |  6 ++----
>>   include/linux/crash_reserve.h | 11 +++++------
>>   kernel/crash_reserve.c        |  9 ++++-----
>>   6 files changed, 17 insertions(+), 26 deletions(-)
> Acked-by: Baoquan He <bhe@redhat.com>
Thanks for the Ack!

- Sourabh Jain

[PATCH RESEND v1 2/5] crash: let arch decide crash memory export to iomem_resource

[Sourabh Jain]

insert_crashkernel_resources() adds crash memory to iomem_resource if
generic crashkernel reservation is enabled on an architecture.

On PowerPC, system RAM is added to iomem_resource. See commit
c40dd2f766440 ("powerpc: Add System RAM to /proc/iomem").

Enabling generic crashkernel reservation on PowerPC leads to a conflict
when system RAM is added to iomem_resource because a part of the system
RAM, the crashkernel memory, has already been added to iomem_resource.

The next commit in the series "powerpc/crash: use generic crashkernel
reservation" enables generic crashkernel reservation on PowerPC. If the
crashkernel is added to iomem_resource, the kernel fails to add
system RAM to /proc/iomem and prints the following traces:

CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.13.0-rc2+
snip...
NIP [c000000002016b3c] add_system_ram_resources+0xf0/0x15c
LR [c000000002016b34] add_system_ram_resources+0xe8/0x15c
Call Trace:
[c00000000484bbc0] [c000000002016b34] add_system_ram_resources+0xe8/0x15c
[c00000000484bc20] [c000000000010a4c] do_one_initcall+0x7c/0x39c
[c00000000484bd00] [c000000002005418] do_initcalls+0x144/0x18c
[c00000000484bd90] [c000000002005714] kernel_init_freeable+0x21c/0x290
[c00000000484bdf0] [c0000000000110f4] kernel_init+0x2c/0x1b8
[c00000000484be50] [c00000000000dd3c] ret_from_kernel_user_thread+0x14/0x1c

To avoid this, an architecture hook is added in
insert_crashkernel_resources(), allowing the architecture to decide
whether crashkernel memory should be added to iomem_resource.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
---
 include/linux/crash_reserve.h | 11 +++++++++++
 kernel/crash_reserve.c        |  3 +++
 2 files changed, 14 insertions(+)

diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h
index 1fe7e7d1b214..f1205d044dae 100644
--- a/include/linux/crash_reserve.h
+++ b/include/linux/crash_reserve.h
@@ -18,6 +18,17 @@ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base,
 		unsigned long long *low_size, bool *high);
 
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+
+#ifndef arch_add_crash_res_to_iomem
+static inline bool arch_add_crash_res_to_iomem(void)
+{
+	return true;
+}
+#endif
+
+#endif
+
 #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
 #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
 #define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index aff7c0fdbefa..190104f32fe1 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -460,6 +460,9 @@ void __init reserve_crashkernel_generic(unsigned long long crash_size,
 #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
+	if (!arch_add_crash_res_to_iomem())
+		return 0;
+
 	if (crashk_res.start < crashk_res.end)
 		insert_resource(&iomem_resource, &crashk_res);
 
-- 
2.47.1

Re: [PATCH RESEND v1 2/5] crash: let arch decide crash memory export to iomem_resource

[Baoquan he]

Hi,

On 01/08/25 at 03:44pm, Sourabh Jain wrote:
> insert_crashkernel_resources() adds crash memory to iomem_resource if
> generic crashkernel reservation is enabled on an architecture.
> 
> On PowerPC, system RAM is added to iomem_resource. See commit
> c40dd2f766440 ("powerpc: Add System RAM to /proc/iomem").
> 
> Enabling generic crashkernel reservation on PowerPC leads to a conflict
> when system RAM is added to iomem_resource because a part of the system
> RAM, the crashkernel memory, has already been added to iomem_resource.
> 
> The next commit in the series "powerpc/crash: use generic crashkernel
> reservation" enables generic crashkernel reservation on PowerPC. If the
> crashkernel is added to iomem_resource, the kernel fails to add
> system RAM to /proc/iomem and prints the following traces:
> 
> CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.13.0-rc2+
> snip...
> NIP [c000000002016b3c] add_system_ram_resources+0xf0/0x15c
> LR [c000000002016b34] add_system_ram_resources+0xe8/0x15c
> Call Trace:
> [c00000000484bbc0] [c000000002016b34] add_system_ram_resources+0xe8/0x15c
> [c00000000484bc20] [c000000000010a4c] do_one_initcall+0x7c/0x39c
> [c00000000484bd00] [c000000002005418] do_initcalls+0x144/0x18c
> [c00000000484bd90] [c000000002005714] kernel_init_freeable+0x21c/0x290
> [c00000000484bdf0] [c0000000000110f4] kernel_init+0x2c/0x1b8
> [c00000000484be50] [c00000000000dd3c] ret_from_kernel_user_thread+0x14/0x1c
> 
> To avoid this, an architecture hook is added in
> insert_crashkernel_resources(), allowing the architecture to decide
> whether crashkernel memory should be added to iomem_resource.

Have you tried defining HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY in ppc to
add crashkernel region to iomem early? Now there are two branches in the
existing code, adding a hook will make three ways.

Re: [PATCH RESEND v1 2/5] crash: let arch decide crash memory export to iomem_resource

[Sourabh Jain]

Hello Baoquan

On 08/01/25 16:55, Baoquan he wrote:
> Hi,
>
> On 01/08/25 at 03:44pm, Sourabh Jain wrote:
>> insert_crashkernel_resources() adds crash memory to iomem_resource if
>> generic crashkernel reservation is enabled on an architecture.
>>
>> On PowerPC, system RAM is added to iomem_resource. See commit
>> c40dd2f766440 ("powerpc: Add System RAM to /proc/iomem").
>>
>> Enabling generic crashkernel reservation on PowerPC leads to a conflict
>> when system RAM is added to iomem_resource because a part of the system
>> RAM, the crashkernel memory, has already been added to iomem_resource.
>>
>> The next commit in the series "powerpc/crash: use generic crashkernel
>> reservation" enables generic crashkernel reservation on PowerPC. If the
>> crashkernel is added to iomem_resource, the kernel fails to add
>> system RAM to /proc/iomem and prints the following traces:
>>
>> CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.13.0-rc2+
>> snip...
>> NIP [c000000002016b3c] add_system_ram_resources+0xf0/0x15c
>> LR [c000000002016b34] add_system_ram_resources+0xe8/0x15c
>> Call Trace:
>> [c00000000484bbc0] [c000000002016b34] add_system_ram_resources+0xe8/0x15c
>> [c00000000484bc20] [c000000000010a4c] do_one_initcall+0x7c/0x39c
>> [c00000000484bd00] [c000000002005418] do_initcalls+0x144/0x18c
>> [c00000000484bd90] [c000000002005714] kernel_init_freeable+0x21c/0x290
>> [c00000000484bdf0] [c0000000000110f4] kernel_init+0x2c/0x1b8
>> [c00000000484be50] [c00000000000dd3c] ret_from_kernel_user_thread+0x14/0x1c
>>
>> To avoid this, an architecture hook is added in
>> insert_crashkernel_resources(), allowing the architecture to decide
>> whether crashkernel memory should be added to iomem_resource.
> Have you tried defining HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY in ppc to
> add crashkernel region to iomem early?


I didn’t try, but I think even if I do, the kernel will run into the 
same issue
because as soon as crashkernel is added to iomem, there will be a resource
conflict when the PowerPC code tries to add system RAM to iomem. Which
happens during subsys_initcall.

Regardless, I will give it a try.

> Now there are two branches in the
> existing code, adding a hook will make three ways.

I agree. I can try updating powerpc code to not consider crashkernel 
memory as
iomem conflict.

Thanks for the review.

- Sourabh Jain

[PATCH RESEND v1 3/5] powerpc/kdump: preserve user-specified memory limit

[Sourabh Jain]

Commit 59d58189f3d9 ("crash: fix crash memory reserve exceed system
memory bug") fails crashkernel parsing if the crash size is found to be
higher than system RAM, which makes the memory_limit adjustment code
ineffective due to an early exit from reserve_crashkernel().

Regardless lets not violated the user-specified memory limit by
adjusting it. Remove this adjustment to ensure all reservations stay
within the limit. Commit f94f5ac07983 ("powerpc/fadump: Don't update
the user-specified memory limit") did the same for fadump.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
---
 arch/powerpc/kexec/core.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index b8333a49ea5d..4945b33322ae 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -150,14 +150,6 @@ void __init reserve_crashkernel(void)
 		return;
 	}
 
-	/* Crash kernel trumps memory limit */
-	if (memory_limit && memory_limit <= crashk_res.end) {
-		memory_limit = crashk_res.end + 1;
-		total_mem_sz = memory_limit;
-		printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
-		       memory_limit);
-	}
-
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
 			(unsigned long)(crash_size >> 20),
-- 
2.47.1

Re: [PATCH RESEND v1 3/5] powerpc/kdump: preserve user-specified memory limit

[Mahesh J Salgaonkar]

On 2025-01-08 15:44:56 Wed, Sourabh Jain wrote:
> Commit 59d58189f3d9 ("crash: fix crash memory reserve exceed system
> memory bug") fails crashkernel parsing if the crash size is found to be
> higher than system RAM, which makes the memory_limit adjustment code
> ineffective due to an early exit from reserve_crashkernel().
> 
> Regardless lets not violated the user-specified memory limit by
> adjusting it. Remove this adjustment to ensure all reservations stay
> within the limit. Commit f94f5ac07983 ("powerpc/fadump: Don't update
> the user-specified memory limit") did the same for fadump.

Agreed.

Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>

Thanks,
-Mahesh.

Re: [PATCH RESEND v1 3/5] powerpc/kdump: preserve user-specified memory limit

[Sourabh Jain]

Hello Mahesh,


On 08/01/25 22:36, Mahesh J Salgaonkar wrote:
> On 2025-01-08 15:44:56 Wed, Sourabh Jain wrote:
>> Commit 59d58189f3d9 ("crash: fix crash memory reserve exceed system
>> memory bug") fails crashkernel parsing if the crash size is found to be
>> higher than system RAM, which makes the memory_limit adjustment code
>> ineffective due to an early exit from reserve_crashkernel().
>>
>> Regardless lets not violated the user-specified memory limit by
>> adjusting it. Remove this adjustment to ensure all reservations stay
>> within the limit. Commit f94f5ac07983 ("powerpc/fadump: Don't update
>> the user-specified memory limit") did the same for fadump.
> Agreed.
>
> Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>

Thanks for the review.

- Sourabh Jain

[PATCH RESEND v1 4/5] powerpc/crash: use generic crashkernel reservation

[Sourabh Jain]

Commit 0ab97169aa05 ("crash_core: add generic function to do
reservation") added a generic function to reserve crashkernel memory.
So let's use the same function on powerpc and remove the
architecture-specific code that essentially does the same thing.

The generic crashkernel reservation also provides a way to split the
crashkernel reservation into high and low memory reservations, which can
be enabled for powerpc in the future.

Along with moving to the generic crashkernel reservation, the code
related to finding the base address for the crashkernel has been
separated into its own function name get_crash_base() for better
readability and maintainability.

To prevent crashkernel memory from being added to iomem_resource, the
function arch_add_crash_res_to_iomem() has been introduced. For further
details on why this should not be done for the PowerPC architecture,
please refer to the previous commit titled "crash: let arch decide crash
memory export to iomem_resource.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
---
 arch/powerpc/Kconfig                     |  3 +
 arch/powerpc/include/asm/crash_reserve.h | 18 +++++
 arch/powerpc/include/asm/kexec.h         |  4 +-
 arch/powerpc/kernel/prom.c               |  2 +-
 arch/powerpc/kexec/core.c                | 90 ++++++++++--------------
 5 files changed, 63 insertions(+), 54 deletions(-)
 create mode 100644 arch/powerpc/include/asm/crash_reserve.h

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a0ce777f9706..8df8871215f8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -717,6 +717,9 @@ config ARCH_SUPPORTS_CRASH_HOTPLUG
 	def_bool y
 	depends on PPC64
 
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_RESERVE
+
 config FA_DUMP
 	bool "Firmware-assisted dump"
 	depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)
diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h
new file mode 100644
index 000000000000..f5e60721de41
--- /dev/null
+++ b/arch/powerpc/include/asm/crash_reserve.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CRASH_RESERVE_H
+#define _ASM_POWERPC_CRASH_RESERVE_H
+
+/* crash kernel regions are Page size agliged */
+#define CRASH_ALIGN             PAGE_SIZE
+
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+
+static inline bool arch_add_crash_res_to_iomem(void)
+{
+	return false;
+}
+#define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem
+#endif
+
+#endif /* _ASM_POWERPC_CRASH_RESERVE_H */
+
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 270ee93a0f7d..64741558071f 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -113,9 +113,9 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
 
 #ifdef CONFIG_CRASH_RESERVE
 int __init overlaps_crashkernel(unsigned long start, unsigned long size);
-extern void reserve_crashkernel(void);
+extern void arch_reserve_crashkernel(void);
 #else
-static inline void reserve_crashkernel(void) {}
+static inline void arch_reserve_crashkernel(void) {}
 static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
 #endif
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index e0059842a1c6..9ed9dde7d231 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -860,7 +860,7 @@ void __init early_init_devtree(void *params)
 	 */
 	if (fadump_reserve_mem() == 0)
 #endif
-		reserve_crashkernel();
+		arch_reserve_crashkernel();
 	early_reserve_mem();
 
 	if (memory_limit > memblock_phys_mem_size())
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 4945b33322ae..b21cfa814492 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -80,38 +80,20 @@ void machine_kexec(struct kimage *image)
 }
 
 #ifdef CONFIG_CRASH_RESERVE
-void __init reserve_crashkernel(void)
-{
-	unsigned long long crash_size, crash_base, total_mem_sz;
-	int ret;
 
-	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
-	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, total_mem_sz,
-			&crash_size, &crash_base, NULL, NULL);
-	if (ret == 0 && crash_size > 0) {
-		crashk_res.start = crash_base;
-		crashk_res.end = crash_base + crash_size - 1;
-	}
-
-	if (crashk_res.end == crashk_res.start) {
-		crashk_res.start = crashk_res.end = 0;
-		return;
-	}
-
-	/* We might have got these values via the command line or the
-	 * device tree, either way sanitise them now. */
-
-	crash_size = resource_size(&crashk_res);
+static unsigned long long __init get_crash_base(unsigned long long crash_base)
+{
 
 #ifndef CONFIG_NONSTATIC_KERNEL
-	if (crashk_res.start != KDUMP_KERNELBASE)
+	if (crash_base != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
-	crashk_res.start = KDUMP_KERNELBASE;
+	return KDUMP_KERNELBASE;
 #else
-	if (!crashk_res.start) {
+	unsigned long long crash_base_align;
+
+	if (!crash_base) {
 #ifdef CONFIG_PPC64
 		/*
 		 * On the LPAR platform place the crash kernel to mid of
@@ -123,45 +105,51 @@ void __init reserve_crashkernel(void)
 		 * kernel starts at 128MB offset on other platforms.
 		 */
 		if (firmware_has_feature(FW_FEATURE_LPAR))
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_512M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_512M);
 		else
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_128M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_128M);
 #else
-		crashk_res.start = KDUMP_KERNELBASE;
+		crash_base = KDUMP_KERNELBASE;
 #endif
 	}
 
-	crash_base = PAGE_ALIGN(crashk_res.start);
-	if (crash_base != crashk_res.start) {
-		printk("Crash kernel base must be aligned to 0x%lx\n",
-				PAGE_SIZE);
-		crashk_res.start = crash_base;
-	}
+	crash_base_align = PAGE_ALIGN(crash_base);
+	if (crash_base != crash_base_align)
+		pr_warn("Crash kernel base must be aligned to 0x%lx\n", PAGE_SIZE);
 
+	return crash_base_align;
 #endif
-	crash_size = PAGE_ALIGN(crash_size);
-	crashk_res.end = crashk_res.start + crash_size - 1;
+}
 
-	/* The crash region must not overlap the current kernel */
-	if (overlaps_crashkernel(__pa(_stext), _end - _stext)) {
-		printk(KERN_WARNING
-			"Crash kernel can not overlap current kernel\n");
-		crashk_res.start = crashk_res.end = 0;
+void __init arch_reserve_crashkernel(void)
+{
+	unsigned long long crash_size, crash_base, crash_end;
+	unsigned long long kernel_start, kernel_size;
+	unsigned long long total_mem_sz;
+	int ret;
+
+	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
+
+	/* use common parsing */
+	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
+				&crash_base, NULL, NULL);
+
+	if (ret)
 		return;
-	}
 
-	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
-			"for crashkernel (System RAM: %ldMB)\n",
-			(unsigned long)(crash_size >> 20),
-			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(total_mem_sz >> 20));
+	crash_base = get_crash_base(crash_base);
+	crash_end = crash_base + crash_size - 1;
 
-	if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
-	    memblock_reserve(crashk_res.start, crash_size)) {
-		pr_err("Failed to reserve memory for crashkernel!\n");
-		crashk_res.start = crashk_res.end = 0;
+	kernel_start = __pa(_stext);
+	kernel_size = _end - _stext;
+
+	/* The crash region must not overlap the current kernel */
+	if ((kernel_start + kernel_size > crash_base) && (kernel_start <= crash_end)) {
+		pr_warn("Crash kernel can not overlap current kernel\n");
 		return;
 	}
+
+	reserve_crashkernel_generic(crash_size, crash_base, 0, false);
 }
 
 int __init overlaps_crashkernel(unsigned long start, unsigned long size)
-- 
2.47.1

Re: [PATCH RESEND v1 4/5] powerpc/crash: use generic crashkernel reservation

[Mahesh J Salgaonkar]

On 2025-01-08 15:44:57 Wed, Sourabh Jain wrote:
> Commit 0ab97169aa05 ("crash_core: add generic function to do
> reservation") added a generic function to reserve crashkernel memory.
> So let's use the same function on powerpc and remove the
> architecture-specific code that essentially does the same thing.
> 
> The generic crashkernel reservation also provides a way to split the
> crashkernel reservation into high and low memory reservations, which can
> be enabled for powerpc in the future.
> 
> Along with moving to the generic crashkernel reservation, the code
> related to finding the base address for the crashkernel has been
> separated into its own function name get_crash_base() for better
> readability and maintainability.
> 
> To prevent crashkernel memory from being added to iomem_resource, the
> function arch_add_crash_res_to_iomem() has been introduced. For further
> details on why this should not be done for the PowerPC architecture,
> please refer to the previous commit titled "crash: let arch decide crash
> memory export to iomem_resource.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Baoquan he <bhe@redhat.com>
> Cc: Hari Bathini <hbathini@linux.ibm.com>
> CC: Madhavan Srinivasan <maddy@linux.ibm.com>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: kexec@lists.infradead.org
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
> ---
>  arch/powerpc/Kconfig                     |  3 +
>  arch/powerpc/include/asm/crash_reserve.h | 18 +++++
>  arch/powerpc/include/asm/kexec.h         |  4 +-
>  arch/powerpc/kernel/prom.c               |  2 +-
>  arch/powerpc/kexec/core.c                | 90 ++++++++++--------------
>  5 files changed, 63 insertions(+), 54 deletions(-)
>  create mode 100644 arch/powerpc/include/asm/crash_reserve.h
[...]
> @@ -113,9 +113,9 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
>  
>  #ifdef CONFIG_CRASH_RESERVE
>  int __init overlaps_crashkernel(unsigned long start, unsigned long size);
> -extern void reserve_crashkernel(void);
> +extern void arch_reserve_crashkernel(void);

Do we really need to rename this ? it is still called from powepc arch
and not from the common code.

>  #else
> -static inline void reserve_crashkernel(void) {}
> +static inline void arch_reserve_crashkernel(void) {}
>  static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
>  #endif
>  
> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
> index e0059842a1c6..9ed9dde7d231 100644
> --- a/arch/powerpc/kernel/prom.c
> +++ b/arch/powerpc/kernel/prom.c
> @@ -860,7 +860,7 @@ void __init early_init_devtree(void *params)
>  	 */
>  	if (fadump_reserve_mem() == 0)
>  #endif
> -		reserve_crashkernel();
> +		arch_reserve_crashkernel();
>  	early_reserve_mem();
>  
>  	if (memory_limit > memblock_phys_mem_size())

Rest looks good to me.

Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>

Thanks,
-Mahesh.

Re: [PATCH RESEND v1 4/5] powerpc/crash: use generic crashkernel reservation

[Sourabh Jain]

Hello Mahesh,

On 08/01/25 22:35, Mahesh J Salgaonkar wrote:
> On 2025-01-08 15:44:57 Wed, Sourabh Jain wrote:
>> Commit 0ab97169aa05 ("crash_core: add generic function to do
>> reservation") added a generic function to reserve crashkernel memory.
>> So let's use the same function on powerpc and remove the
>> architecture-specific code that essentially does the same thing.
>>
>> The generic crashkernel reservation also provides a way to split the
>> crashkernel reservation into high and low memory reservations, which can
>> be enabled for powerpc in the future.
>>
>> Along with moving to the generic crashkernel reservation, the code
>> related to finding the base address for the crashkernel has been
>> separated into its own function name get_crash_base() for better
>> readability and maintainability.
>>
>> To prevent crashkernel memory from being added to iomem_resource, the Mahesh.
>> function arch_add_crash_res_to_iomem() has been introduced. For further
>> details on why this should not be done for the PowerPC architecture,
>> please refer to the previous commit titled "crash: let arch decide crash
>> memory export to iomem_resource.
>>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: Baoquan he <bhe@redhat.com>
>> Cc: Hari Bathini <hbathini@linux.ibm.com>
>> CC: Madhavan Srinivasan <maddy@linux.ibm.com>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: kexec@lists.infradead.org
>> Cc: linux-kernel@vger.kernel.org
>> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
>> ---
>>   arch/powerpc/Kconfig                     |  3 +
>>   arch/powerpc/include/asm/crash_reserve.h | 18 +++++
>>   arch/powerpc/include/asm/kexec.h         |  4 +-
>>   arch/powerpc/kernel/prom.c               |  2 +-
>>   arch/powerpc/kexec/core.c                | 90 ++++++++++--------------
>>   5 files changed, 63 insertions(+), 54 deletions(-)
>>   create mode 100644 arch/powerpc/include/asm/crash_reserve.h
> [...]
>> @@ -113,9 +113,9 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
>>   
>>   #ifdef CONFIG_CRASH_RESERVE
>>   int __init overlaps_crashkernel(unsigned long start, unsigned long size);
>> -extern void reserve_crashkernel(void);
>> +extern void arch_reserve_crashkernel(void); Mahesh. Mahesh
> Do we really need to rename this ? it is still called from powepc arch
> and not from the common code.

You are right, we don’t. However, all architectures (x86, RISC-V, 
LoongArch, ARM64) that use the
generic crash kernel reservation have named their architecture-specific 
function `arch_reserve_crashkernel()`.
So, I did the same for PowerPC, and this helps sometimes.

Maybe I should justify the name change in the commit to avoid confusion.

Please let me know your opinion.

>
>>   #else
>> -static inline void reserve_crashkernel(void) {}
>> +static inline void arch_reserve_crashkernel(void) {}
>>   static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
>>   #endif
>>   
>> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
>> index e0059842a1c6..9ed9dde7d231 100644
>> --- a/arch/powerpc/kernel/prom.c
>> +++ b/arch/powerpc/kernel/prom.c
>> @@ -860,7 +860,7 @@ void __init early_init_devtree(void *params)
>>   	 */
>>   	if (fadump_reserve_mem() == 0)
>>   #endif
>> -		reserve_crashkernel();
>> +		arch_reserve_crashkernel();
>>   	early_reserve_mem();
>>   
>>   	if (memory_limit > memblock_phys_mem_size())
> Rest looks good to me.
>
> Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>

Thank you for reviewing this.

- Sourabh Jain

[PATCH RESEND v1 5/5] crash: option to let arch decide mem range is usable

[Sourabh Jain]

On PowerPC, the memory reserved for the crashkernel can contain
components like RTAS, TCE, OPAL, etc., which should be avoided when
loading kexec segments into crashkernel memory. Due to these special
components, PowerPC has its own set of functions to locate holes in the
crashkernel memory for loading kexec segments for kdump. However, for
loading kexec segments in the kexec case, PowerPC uses generic functions
to locate holes.

So, let's use generic functions to locate memory holes for kdump on
PowerPC by adding an arch hook to handle such special regions while
loading kexec segments, and remove the PowerPC functions to locate
holes.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Baoquan he <bhe@redhat.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
CC: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
---
 arch/powerpc/include/asm/kexec.h  |   6 +-
 arch/powerpc/kexec/file_load_64.c | 259 ++----------------------------
 include/linux/kexec.h             |   9 ++
 kernel/kexec_file.c               |  12 ++
 4 files changed, 34 insertions(+), 252 deletions(-)

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 64741558071f..5e4680f9ff35 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -95,8 +95,10 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long
 int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
 
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf);
-#define arch_kexec_locate_mem_hole arch_kexec_locate_mem_hole
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end);
+#define arch_check_excluded_range  arch_check_excluded_range
+
 
 int load_crashdump_segments_ppc64(struct kimage *image,
 				  struct kexec_buf *kbuf);
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index dc65c1391157..e7ef8b2a2554 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -49,201 +49,18 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL
 };
 
-/**
- * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
- *                              in the memory regions between buf_min & buf_max
- *                              for the buffer. If found, sets kbuf->mem.
- * @kbuf:                       Buffer contents and memory parameters.
- * @buf_min:                    Minimum address for the buffer.
- * @buf_max:                    Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
-				      u64 buf_min, u64 buf_max)
-{
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range_rev(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (start > buf_max)
-			continue;
-
-		/* Memory hole not found */
-		if (end < buf_min)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1,
-					       kbuf->buf_align);
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
- *                                  suitable buffer with top down approach.
- * @kbuf:                           Buffer contents and memory parameters.
- * @buf_min:                        Minimum address for the buffer.
- * @buf_max:                        Maximum address for the buffer.
- * @emem:                           Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
-					  u64 buf_min, u64 buf_max,
-					  const struct crash_mem *emem)
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end)
 {
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmax = buf_max;
-	for (i = (emem->nr_ranges - 1); i >= 0; i--) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (start > tmax)
-			continue;
-
-		if (end < tmax) {
-			tmin = (end < buf_min ? buf_min : end + 1);
-			ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
-
-		tmax = start - 1;
-
-		if (tmax < buf_min) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
-
-	if (!ret) {
-		tmin = buf_min;
-		ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-	}
-	return ret;
-}
-
-/**
- * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole
- *                               in the memory regions between buf_min & buf_max
- *                               for the buffer. If found, sets kbuf->mem.
- * @kbuf:                        Buffer contents and memory parameters.
- * @buf_min:                     Minimum address for the buffer.
- * @buf_max:                     Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
-				       u64 buf_min, u64 buf_max)
-{
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (end < buf_min)
-			continue;
-
-		/* Memory hole not found */
-		if (start > buf_max)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = start;
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
- *                                   suitable buffer with bottom up approach.
- * @kbuf:                            Buffer contents and memory parameters.
- * @buf_min:                         Minimum address for the buffer.
- * @buf_max:                         Maximum address for the buffer.
- * @emem:                            Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
-					   u64 buf_min, u64 buf_max,
-					   const struct crash_mem *emem)
-{
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmin = buf_min;
-	for (i = 0; i < emem->nr_ranges; i++) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (end < tmin)
-			continue;
-
-		if (start > tmin) {
-			tmax = (start > buf_max ? buf_max : start - 1);
-			ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
-
-		tmin = end + 1;
+	struct crash_mem *emem;
+	int i;
 
-		if (tmin > buf_max) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
+	emem = image->arch.exclude_ranges;
+	for (i = 0; i < emem->nr_ranges; i++)
+		if (start < emem->ranges[i].end && end > emem->ranges[i].start)
+			return 1;
 
-	if (!ret) {
-		tmax = buf_max;
-		ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-	}
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_CRASH_DUMP
@@ -1004,64 +821,6 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
 	return ret;
 }
 
-/**
- * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal,
- *                              tce-table, reserved-ranges & such (exclude
- *                              memory ranges) as they can't be used for kexec
- *                              segment buffer. Sets kbuf->mem when a suitable
- *                              memory hole is found.
- * @kbuf:                       Buffer contents and memory parameters.
- *
- * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align.
- *
- * Returns 0 on success, negative errno on error.
- */
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
-{
-	struct crash_mem **emem;
-	u64 buf_min, buf_max;
-	int ret;
-
-	/* Look up the exclude ranges list while locating the memory hole */
-	emem = &(kbuf->image->arch.exclude_ranges);
-	if (!(*emem) || ((*emem)->nr_ranges == 0)) {
-		pr_warn("No exclude range list. Using the default locate mem hole method\n");
-		return kexec_locate_mem_hole(kbuf);
-	}
-
-	buf_min = kbuf->buf_min;
-	buf_max = kbuf->buf_max;
-	/* Segments for kdump kernel should be within crashkernel region */
-	if (IS_ENABLED(CONFIG_CRASH_DUMP) && kbuf->image->type == KEXEC_TYPE_CRASH) {
-		buf_min = (buf_min < crashk_res.start ?
-			   crashk_res.start : buf_min);
-		buf_max = (buf_max > crashk_res.end ?
-			   crashk_res.end : buf_max);
-	}
-
-	if (buf_min > buf_max) {
-		pr_err("Invalid buffer min and/or max values\n");
-		return -EINVAL;
-	}
-
-	if (kbuf->top_down)
-		ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
-						     *emem);
-	else
-		ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
-						      *emem);
-
-	/* Add the buffer allocated to the exclude list for the next lookup */
-	if (!ret) {
-		add_mem_range(emem, kbuf->mem, kbuf->memsz);
-		sort_memory_ranges(*emem, true);
-	} else {
-		pr_err("Failed to locate memory buffer of size %lu\n",
-		       kbuf->memsz);
-	}
-	return ret;
-}
-
 /**
  * arch_kexec_kernel_image_probe - Does additional handling needed to setup
  *                                 kexec segments.
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index f0e9f8eda7a3..407f8b0346aa 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -205,6 +205,15 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image)
 }
 #endif
 
+#ifndef arch_check_excluded_range
+static inline int arch_check_excluded_range(struct kimage *image,
+					    unsigned long start,
+					    unsigned long end)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_KEXEC_SIG
 #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
 int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 3eedb8c226ad..52e1480dbfa1 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -464,6 +464,12 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 			continue;
 		}
 
+		/* Make sure this does not conflict exclude range */
+		if (arch_check_excluded_range(image, temp_start, temp_end)) {
+			temp_start = temp_start - PAGE_SIZE;
+			continue;
+		}
+
 		/* We found a suitable memory range */
 		break;
 	} while (1);
@@ -498,6 +504,12 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 			continue;
 		}
 
+		/* Make sure this does not conflict exclude range */
+		if (arch_check_excluded_range(image, temp_start, temp_end)) {
+			temp_start = temp_start + PAGE_SIZE;
+			continue;
+		}
+
 		/* We found a suitable memory range */
 		break;
 	} while (1);
-- 
2.47.1

Re: [PATCH RESEND v1 5/5] crash: option to let arch decide mem range is usable

[Baoquan he]

On 01/08/25 at 03:44pm, Sourabh Jain wrote:
...snip...
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index f0e9f8eda7a3..407f8b0346aa 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -205,6 +205,15 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image)
>  }
>  #endif
>  
> +#ifndef arch_check_excluded_range
> +static inline int arch_check_excluded_range(struct kimage *image,
> +					    unsigned long start,
> +					    unsigned long end)
> +{
> +	return 0;
> +}
> +#endif
> +
>  #ifdef CONFIG_KEXEC_SIG
>  #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
>  int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len);
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index 3eedb8c226ad..52e1480dbfa1 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -464,6 +464,12 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
>  			continue;
>  		}
>  
> +		/* Make sure this does not conflict exclude range */
                                                   ^
                Make sure this doesn't conflict with excluded range?

> +		if (arch_check_excluded_range(image, temp_start, temp_end)) {
> +			temp_start = temp_start - PAGE_SIZE;
> +			continue;
> +		}
> +
>  		/* We found a suitable memory range */
>  		break;
>  	} while (1);
> @@ -498,6 +504,12 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
>  			continue;
>  		}
>  
> +		/* Make sure this does not conflict exclude range */
                                                   ^
                                                 Ditto.

> +		if (arch_check_excluded_range(image, temp_start, temp_end)) {
> +			temp_start = temp_start + PAGE_SIZE;
> +			continue;
> +		}
> +
>  		/* We found a suitable memory range */
>  		break;
>  	} while (1);
> -- 
> 2.47.1
> 

Re: [PATCH RESEND v1 5/5] crash: option to let arch decide mem range is usable

[Sourabh Jain]

On 08/01/25 17:08, Baoquan he wrote:
> On 01/08/25 at 03:44pm, Sourabh Jain wrote:
> ...snip...
>> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
>> index f0e9f8eda7a3..407f8b0346aa 100644
>> --- a/include/linux/kexec.h
>> +++ b/include/linux/kexec.h
>> @@ -205,6 +205,15 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image)
>>   }
>>   #endif
>>   
>> +#ifndef arch_check_excluded_range
>> +static inline int arch_check_excluded_range(struct kimage *image,
>> +					    unsigned long start,
>> +					    unsigned long end)
>> +{
>> +	return 0;
>> +}
>> +#endif
>> +
>>   #ifdef CONFIG_KEXEC_SIG
>>   #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
>>   int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len);
>> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
>> index 3eedb8c226ad..52e1480dbfa1 100644
>> --- a/kernel/kexec_file.c
>> +++ b/kernel/kexec_file.c
>> @@ -464,6 +464,12 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
>>   			continue;
>>   		}
>>   
>> +		/* Make sure this does not conflict exclude range */
>                                                     ^
>                  Make sure this doesn't conflict with excluded range?
>
>> +		if (arch_check_excluded_range(image, temp_start, temp_end)) {
>> +			temp_start = temp_start - PAGE_SIZE;
>> +			continue;
>> +		}
>> +
>>   		/* We found a suitable memory range */
>>   		break;
>>   	} while (1);
>> @@ -498,6 +504,12 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
>>   			continue;
>>   		}
>>   
>> +		/* Make sure this does not conflict exclude range */
>                                                     ^
>                                                   Ditto.

I will update both comments.

Thanks,
Sourabh Jain