powerpc/kdump: Add support for crashkernel CMA reservation

Commit 35c18f2933c5 ("Add a new optional ",cma" suffix to the
crashkernel= command line option") and commit ab475510e042 ("kdump:
implement reserve_crashkernel_cma") added CMA support for kdump
crashkernel reservation.

Extend crashkernel CMA reservation support to powerpc.

The following changes are made to enable CMA reservation on powerpc:

- Parse and obtain the CMA reservation size along with other crashkernel
  parameters
- Call reserve_crashkernel_cma() to allocate the CMA region for kdump
- Include the CMA-reserved ranges in the usable memory ranges for the
  kdump kernel to use.
- Exclude the CMA-reserved ranges from the crash kernel memory to
  prevent them from being exported through /proc/vmcore.

With the introduction of the CMA crashkernel regions,
crash_exclude_mem_range() needs to be called multiple times to exclude
both crashk_res and crashk_cma_ranges from the crash memory ranges. To
avoid repetitive logic for validating mem_ranges size and handling
reallocation when required, this functionality is moved to a new wrapper
function crash_exclude_mem_range_guarded().

To ensure proper CMA reservation, reserve_crashkernel_cma() is called
after pageblock_order is initialized.

Update kernel-parameters.txt to document CMA support for crashkernel on
powerpc architecture.

Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20251107080334.708028-1-sourabhjain@linux.ibm.com

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6c42061ca20e581b5192b66c6f25aba38d4f8ff8..1c10190d583d4ab4adf4c4745ba3b470162a9d0c 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1013,7 +1013,7 @@
                        It will be ignored when crashkernel=X,high is not used
                        or memory reserved is below 4G.
        crashkernel=size[KMG],cma
-                       [KNL, X86] Reserve additional crash kernel memory from
+                       [KNL, X86, ppc] Reserve additional crash kernel memory from
                        CMA. This reservation is usable by the first system's
                        userspace memory and kernel movable allocations (memory
                        balloon, zswap). Pages allocated from this memory range

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 4bbf9f699aaaf47c4fcd4b078dd74300aafe0a7e..bd4a6c42a5f38f176290764b6474723f34eea92d 100644 (file)
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -115,9 +115,11 @@ 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 arch_reserve_crashkernel(void);
+extern void kdump_cma_reserve(void);
 #else
 static inline void arch_reserve_crashkernel(void) {}
 static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
+static inline void kdump_cma_reserve(void) { }
 #endif
 
 #if defined(CONFIG_CRASH_DUMP)

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 68d47c53876c6b5d6ddb15031434caa0ab7658aa..c8c42b419742f057b6b1e29dd078c13f471316c5 100644 (file)
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,6 +35,7 @@
 #include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
+#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -995,11 +996,12 @@ void __init setup_arch(char **cmdline_p)
        initmem_init();
 
        /*
-        * Reserve large chunks of memory for use by CMA for fadump, KVM and
+        * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
         * hugetlb. These must be called after initmem_init(), so that
         * pageblock_order is initialised.
         */
        fadump_cma_init();
+       kdump_cma_reserve();
        kvm_cma_reserve();
        gigantic_hugetlb_cma_reserve();
 

diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index d1a2d755381ca52f9086f603c464c8efb65295ad..e59bdfcc6463fabbf72a7f108beadb7850fad503 100644 (file)
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -59,6 +59,8 @@ void machine_kexec(struct kimage *image)
 
 #ifdef CONFIG_CRASH_RESERVE
 
+static unsigned long long crashk_cma_size;
+
 static unsigned long long __init get_crash_base(unsigned long long crash_base)
 {
 
@@ -110,7 +112,7 @@ void __init arch_reserve_crashkernel(void)
 
        /* use common parsing */
        ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
-                               &crash_base, NULL, NULL, NULL);
+                               &crash_base, NULL, &crashk_cma_size, NULL);
 
        if (ret)
                return;
@@ -130,6 +132,12 @@ void __init arch_reserve_crashkernel(void)
        reserve_crashkernel_generic(crash_size, crash_base, 0, false);
 }
 
+void __init kdump_cma_reserve(void)
+{
+       if (crashk_cma_size)
+               reserve_crashkernel_cma(crashk_cma_size);
+}
+
 int __init overlaps_crashkernel(unsigned long start, unsigned long size)
 {
        return (start + size) > crashk_res.start && start <= crashk_res.end;

diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index 3702b0bdab14100b4d2b34b82c587d073b5b1a43..3bd27c38726b5e22bb2de79055936b326f3e39fe 100644 (file)
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -515,7 +515,7 @@ out:
  */
 int get_usable_memory_ranges(struct crash_mem **mem_ranges)
 {
-       int ret;
+       int ret, i;
 
        /*
         * Early boot failure observed on guests when low memory (first memory
@@ -528,6 +528,13 @@ int get_usable_memory_ranges(struct crash_mem **mem_ranges)
        if (ret)
                goto out;
 
+       for (i = 0; i < crashk_cma_cnt; i++) {
+               ret = add_mem_range(mem_ranges, crashk_cma_ranges[i].start,
+                                   crashk_cma_ranges[i].end - crashk_cma_ranges[i].start + 1);
+               if (ret)
+                       goto out;
+       }
+
        ret = add_rtas_mem_range(mem_ranges);
        if (ret)
                goto out;
@@ -546,6 +553,22 @@ out:
 #endif /* CONFIG_KEXEC_FILE */
 
 #ifdef CONFIG_CRASH_DUMP
+static int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges,
+                                          unsigned long long mstart,
+                                          unsigned long long mend)
+{
+       struct crash_mem *tmem = *mem_ranges;
+
+       /* Reallocate memory ranges if there is no space to split ranges */
+       if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
+               tmem = realloc_mem_ranges(mem_ranges);
+               if (!tmem)
+                       return -ENOMEM;
+       }
+
+       return crash_exclude_mem_range(tmem, mstart, mend);
+}
+
 /**
  * get_crash_memory_ranges - Get crash memory ranges. This list includes
  *                           first/crashing kernel's memory regions that
@@ -557,7 +580,6 @@ out:
 int get_crash_memory_ranges(struct crash_mem **mem_ranges)
 {
        phys_addr_t base, end;
-       struct crash_mem *tmem;
        u64 i;
        int ret;
 
@@ -582,19 +604,18 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges)
                        sort_memory_ranges(*mem_ranges, true);
        }
 
-       /* Reallocate memory ranges if there is no space to split ranges */
-       tmem = *mem_ranges;
-       if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
-               tmem = realloc_mem_ranges(mem_ranges);
-               if (!tmem)
-                       goto out;
-       }
-
        /* Exclude crashkernel region */
-       ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
+       ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_res.start, crashk_res.end);
        if (ret)
                goto out;
 
+       for (i = 0; i < crashk_cma_cnt; ++i) {
+               ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_cma_ranges[i].start,
+                                             crashk_cma_ranges[i].end);
+               if (ret)
+                       goto out;
+       }
+
        /*
         * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
         *        regions are exported to save their context at the time of