Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:

 - Support for including MTE tags in ELF coredumps

 - Instruction encoder updates, including fixes to 64-bit immediate
   generation and support for the LSE atomic instructions

 - Improvements to kselftests for MTE and fpsimd

 - Symbol aliasing and linker script cleanups

 - Reduce instruction cache maintenance performed for user mappings
   created using contiguous PTEs

 - Support for the new "asymmetric" MTE mode, where stores are checked
   asynchronously but loads are checked synchronously

 - Support for the latest pointer authentication algorithm ("QARMA3")

 - Support for the DDR PMU present in the Marvell CN10K platform

 - Support for the CPU PMU present in the Apple M1 platform

 - Use the RNDR instruction for arch_get_random_{int,long}()

 - Update our copy of the Arm optimised string routines for str{n}cmp()

 - Fix signal frame generation for CPUs which have foolishly elected to
   avoid building in support for the fpsimd instructions

 - Workaround for Marvell GICv3 erratum #38545

 - Clarification to our Documentation (booting reqs. and MTE prctl())

 - Miscellanous cleanups and minor fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (90 commits)
  docs: sysfs-devices-system-cpu: document "asymm" value for mte_tcf_preferred
  arm64/mte: Remove asymmetric mode from the prctl() interface
  arm64: Add cavium_erratum_23154_cpus missing sentinel
  perf/marvell: Fix !CONFIG_OF build for CN10K DDR PMU driver
  arm64: mm: Drop 'const' from conditional arm64_dma_phys_limit definition
  Documentation: vmcoreinfo: Fix htmldocs warning
  kasan: fix a missing header include of static_keys.h
  drivers/perf: Add Apple icestorm/firestorm CPU PMU driver
  drivers/perf: arm_pmu: Handle 47 bit counters
  arm64: perf: Consistently make all event numbers as 16-bits
  arm64: perf: Expose some Armv9 common events under sysfs
  perf/marvell: cn10k DDR perf event core ownership
  perf/marvell: cn10k DDR perfmon event overflow handling
  perf/marvell: CN10k DDR performance monitor support
  dt-bindings: perf: marvell: cn10k ddr performance monitor
  arm64: clean up tools Makefile
  perf/arm-cmn: Update watchpoint format
  perf/arm-cmn: Hide XP PUB events for CMN-600
  arm64: drop unused includes of <linux/personality.h>
  arm64: Do not defer reserve_crashkernel() for platforms with no DMA memory zones
  ...

1 files changed, 32 insertions, 4 deletions

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index db63cc885771..9e26ec80d317 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -61,8 +61,34 @@ EXPORT_SYMBOL(memstart_addr);
  * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
+ *
+ * Memory reservation for crash kernel either done early or deferred
+ * depending on DMA memory zones configs (ZONE_DMA) --
+ *
+ * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
+ * here instead of max_zone_phys().  This lets early reservation of
+ * crash kernel memory which has a dependency on arm64_dma_phys_limit.
+ * Reserving memory early for crash kernel allows linear creation of block
+ * mappings (greater than page-granularity) for all the memory bank rangs.
+ * In this scheme a comparatively quicker boot is observed.
+ *
+ * If ZONE_DMA configs are defined, crash kernel memory reservation
+ * is delayed until DMA zone memory range size initilazation performed in
+ * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
+ * memory range to avoid overlap allocation.  So crash kernel memory boundaries
+ * are not known when mapping all bank memory ranges, which otherwise means
+ * not possible to exclude crash kernel range from creating block mappings
+ * so page-granularity mappings are created for the entire memory range.
+ * Hence a slightly slower boot is observed.
+ *
+ * Note: Page-granularity mapppings are necessary for crash kernel memory
+ * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
  */
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
+#endif
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -153,8 +179,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
-	if (!arm64_dma_phys_limit)
-		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -315,6 +339,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
+	if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
+
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -361,7 +388,8 @@ void __init bootmem_init(void)
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
-	reserve_crashkernel();
+	if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
 
 	memblock_dump_all();
 }