From d59f43b5748092557d34244e29a618221a250501 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 9 May 2025 00:46:20 -0700 Subject: memblock: add support for scratch memory With KHO (Kexec HandOver), we need a way to ensure that the new kernel does not allocate memory on top of any memory regions that the previous kernel was handing over. But to know where those are, we need to include them in the memblock.reserved array which may not be big enough to hold all ranges that need to be persisted across kexec. To resize the array, we need to allocate memory. That brings us into a catch 22 situation. The solution to that is limit memblock allocations to the scratch regions: safe regions to operate in the case when there is memory that should remain intact across kexec. KHO provides several "scratch regions" as part of its metadata. These scratch regions are contiguous memory blocks that known not to contain any memory that should be persisted across kexec. These regions should be large enough to accommodate all memblock allocations done by the kexeced kernel. We introduce a new memblock_set_scratch_only() function that allows KHO to indicate that any memblock allocation must happen from the scratch regions. Later, we may want to perform another KHO kexec. For that, we reuse the same scratch regions. To ensure that no eventually handed over data gets allocated inside a scratch region, we flip the semantics of the scratch region with memblock_clear_scratch_only(): After that call, no allocations may happen from scratch memblock regions. We will lift that restriction in the next patch. Link: https://lkml.kernel.org/r/20250509074635.3187114-3-changyuanl@google.com Signed-off-by: Alexander Graf Co-developed-by: Mike Rapoport (Microsoft) Signed-off-by: Mike Rapoport (Microsoft) Signed-off-by: Changyuan Lyu Cc: Andy Lutomirski Cc: Anthony Yznaga Cc: Arnd Bergmann Cc: Ashish Kalra Cc: Ben Herrenschmidt Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David Woodhouse Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Gowans Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Krzysztof Kozlowski Cc: Marc Rutland Cc: Paolo Bonzini Cc: Pasha Tatashin Cc: Peter Zijlstra Cc: Pratyush Yadav Cc: Rob Herring Cc: Saravana Kannan Cc: Stanislav Kinsburskii Cc: Steven Rostedt Cc: Thomas Gleinxer Cc: Thomas Lendacky Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/memblock.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 6c00fbc08513..993937a6b962 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -45,6 +45,11 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use, * either explictitly with memblock_reserve_kern() or via memblock * allocation APIs. All memblock allocations set this flag. + * @MEMBLOCK_KHO_SCRATCH: memory region that kexec can pass to the next + * kernel in handover mode. During early boot, we do not know about all + * memory reservations yet, so we get scratch memory from the previous + * kernel that we know is good to use. It is the only memory that + * allocations may happen from in this phase. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ @@ -54,6 +59,7 @@ enum memblock_flags { MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ MEMBLOCK_RSRV_NOINIT = 0x10, /* don't initialize struct pages */ MEMBLOCK_RSRV_KERN = 0x20, /* memory reserved for kernel use */ + MEMBLOCK_KHO_SCRATCH = 0x40, /* scratch memory for kexec handover */ }; /** @@ -148,6 +154,8 @@ int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size); +int memblock_mark_kho_scratch(phys_addr_t base, phys_addr_t size); +int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size); void memblock_free(void *ptr, size_t size); void reset_all_zones_managed_pages(void); @@ -291,6 +299,11 @@ static inline bool memblock_is_driver_managed(struct memblock_region *m) return m->flags & MEMBLOCK_DRIVER_MANAGED; } +static inline bool memblock_is_kho_scratch(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_KHO_SCRATCH; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -619,5 +632,12 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } static inline void memtest_report_meminfo(struct seq_file *m) { } #endif +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH +void memblock_set_kho_scratch_only(void); +void memblock_clear_kho_scratch_only(void); +#else +static inline void memblock_set_kho_scratch_only(void) { } +static inline void memblock_clear_kho_scratch_only(void) { } +#endif #endif /* _LINUX_MEMBLOCK_H */ -- cgit v1.2.3