@@ -41,6 +41,9 @@ u64 memory_hotplug_max(void);
#else
#define memory_hotplug_max() memblock_end_of_DRAM()
#endif /* CONFIG_NEED_MULTIPLE_NODES */
+#ifdef CONFIG_FA_DUMP
+#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
+#endif
#endif /* __KERNEL__ */
#endif /* _ASM_MMZONE_H_ */
@@ -333,6 +333,11 @@ int __init fadump_reserve_mem(void)
return 1;
}
+unsigned long __init arch_reserved_kernel_pages(void)
+{
+ return memblock_reserved_size() / PAGE_SIZE;
+}
+
/* Look for fadump= cmdline option. */
static int __init early_fadump_param(char *p)
{
Currently significant amount of memory is reserved only in kernel booted to capture kernel dump using the fa_dump method. Kernels compiled with CONFIG_DEFERRED_STRUCT_PAGE_INIT will initialize only certain size memory per node. The certain size takes into account the dentry and inode cache sizes. Currently the cache sizes are calculated based on the total system memory including the reserved memory. However such a kernel when booting the same kernel as fadump kernel will not be able to allocate the required amount of memory to suffice for the dentry and inode caches. This results in crashes like Hence only implement arch_reserved_kernel_pages() for CONFIG_FA_DUMP configurations. The amount reserved will be reduced while calculating the large caches and will avoid crashes like the below on large systems such as 32 TB systems. Dentry cache hash table entries: 536870912 (order: 16, 4294967296 bytes) vmalloc: allocation failure, allocated 4097114112 of 17179934720 bytes swapper/0: page allocation failure: order:0, mode:0x2080020(GFP_ATOMIC) CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.6-master+ #3 Call Trace: [c00000000108fb10] [c0000000007fac88] dump_stack+0xb0/0xf0 (unreliable) [c00000000108fb50] [c000000000235264] warn_alloc_failed+0x114/0x160 [c00000000108fbf0] [c000000000281484] __vmalloc_node_range+0x304/0x340 [c00000000108fca0] [c00000000028152c] __vmalloc+0x6c/0x90 [c00000000108fd40] [c000000000aecfb0] alloc_large_system_hash+0x1b8/0x2c0 [c00000000108fe00] [c000000000af7240] inode_init+0x94/0xe4 [c00000000108fe80] [c000000000af6fec] vfs_caches_init+0x8c/0x13c [c00000000108ff00] [c000000000ac4014] start_kernel+0x50c/0x578 [c00000000108ff90] [c000000000008c6c] start_here_common+0x20/0xa8 Cc: linux-mm@kvack.org Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Michal Hocko <mhocko@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Cc: Hari Bathini <hbathini@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Balbir Singh <bsingharora@gmail.com> Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> --- arch/powerpc/include/asm/mmzone.h | 3 +++ arch/powerpc/kernel/fadump.c | 5 +++++ 2 files changed, 8 insertions(+)