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

Pull arm64 updates from Will Deacon:
 "I think we have a bit less than usual on the architecture side, but
  that's somewhat balanced out by a large crop of perf/PMU driver
  updates and extensions to our selftests.

  CPU features and system registers:

   - Advertise hinted conditional branch support (FEAT_HBC) to userspace

   - Avoid false positive "SANITY CHECK" warning when xCR registers
     differ outside of the length field

  Documentation:

   - Fix macro name typo in SME documentation

  Entry code:

   - Unmask exceptions earlier on the system call entry path

  Memory management:

   - Don't bother clearing PTE_RDONLY for dirty ptes in pte_wrprotect()
     and pte_modify()

  Perf and PMU drivers:

   - Initial support for Coresight TRBE devices on ACPI systems (the
     coresight driver changes will come later)

   - Fix hw_breakpoint single-stepping when called from bpf

   - Fixes for DDR PMU on i.MX8MP SoC

   - Add NUMA-awareness to Hisilicon PCIe PMU driver

   - Fix locking dependency issue in Arm DMC620 PMU driver

   - Workaround Hisilicon erratum 162001900 in the SMMUv3 PMU driver

   - Add support for Arm CMN-700 r3 parts to the CMN PMU driver

   - Add support for recent Arm Cortex CPU PMUs

   - Update Hisilicon PMU maintainers

  Selftests:

   - Add a bunch of new features to the hwcap test (JSCVT, PMULL, AES,
     SHA1, etc)

   - Fix SSVE test to leave streaming-mode after grabbing the signal
     context

   - Add new test for SVE vector-length changes with SME enabled

  Miscellaneous:

   - Allow compiler to warn on suspicious looking system register
     expressions

   - Work around SDEI firmware bug by aborting any running handlers on a
     kernel crash

   - Fix some harmless warnings when building with W=1

   - Remove some unused function declarations

   - Other minor fixes and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (62 commits)
  drivers/perf: hisi: Update HiSilicon PMU maintainers
  arm_pmu: acpi: Add a representative platform device for TRBE
  arm_pmu: acpi: Refactor arm_spe_acpi_register_device()
  kselftest/arm64: Fix hwcaps selftest build
  hw_breakpoint: fix single-stepping when using bpf_overflow_handler
  arm64/sysreg: refactor deprecated strncpy
  kselftest/arm64: add jscvt feature to hwcap test
  kselftest/arm64: add pmull feature to hwcap test
  kselftest/arm64: add AES feature check to hwcap test
  kselftest/arm64: add SHA1 and related features to hwcap test
  arm64: sysreg: Generate C compiler warnings on {read,write}_sysreg_s arguments
  kselftest/arm64: build BTI tests in output directory
  perf/imx_ddr: don't enable counter0 if none of 4 counters are used
  perf/imx_ddr: speed up overflow frequency of cycle
  drivers/perf: hisi: Schedule perf session according to locality
  kselftest/arm64: fix a memleak in zt_regs_run()
  perf/arm-dmc620: Fix dmc620_pmu_irqs_lock/cpu_hotplug_lock circular lock dependency
  perf/smmuv3: Add MODULE_ALIAS for module auto loading
  perf/smmuv3: Enable HiSilicon Erratum 162001900 quirk for HIP08/09
  kselftest/arm64: Size sycall-abi buffers for the actual maximum VL
  ...

7 files changed, 21 insertions, 31 deletions

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index bd68e1b7f29f..4d537d56eb84 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -42,6 +42,9 @@
 #define ACPI_MADT_GICC_SPE  (offsetof(struct acpi_madt_generic_interrupt, \
 	spe_interrupt) + sizeof(u16))
 
+#define ACPI_MADT_GICC_TRBE  (offsetof(struct acpi_madt_generic_interrupt, \
+	trbe_interrupt) + sizeof(u16))
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 692b1ec663b2..521267478d18 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -138,6 +138,7 @@
 #define KERNEL_HWCAP_SME_B16B16		__khwcap2_feature(SME_B16B16)
 #define KERNEL_HWCAP_SME_F16F16		__khwcap2_feature(SME_F16F16)
 #define KERNEL_HWCAP_MOPS		__khwcap2_feature(MOPS)
+#define KERNEL_HWCAP_HBC		__khwcap2_feature(HBC)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 577773870b66..85d26143faa5 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -118,31 +118,4 @@
 #define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PTE_RDONLY)
 #endif
 
-/*
- * To make optimal use of block mappings when laying out the linear
- * mapping, round down the base of physical memory to a size that can
- * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE
- * (64k granule), or a multiple that can be mapped using contiguous bits
- * in the page tables: 32 * PMD_SIZE (16k granule)
- */
-#if defined(CONFIG_ARM64_4K_PAGES)
-#define ARM64_MEMSTART_SHIFT		PUD_SHIFT
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define ARM64_MEMSTART_SHIFT		CONT_PMD_SHIFT
-#else
-#define ARM64_MEMSTART_SHIFT		PMD_SHIFT
-#endif
-
-/*
- * sparsemem vmemmap imposes an additional requirement on the alignment of
- * memstart_addr, due to the fact that the base of the vmemmap region
- * has a direct correspondence, and needs to appear sufficiently aligned
- * in the virtual address space.
- */
-#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS
-#define ARM64_MEMSTART_ALIGN	(1UL << SECTION_SIZE_BITS)
-#else
-#define ARM64_MEMSTART_ALIGN	(1UL << ARM64_MEMSTART_SHIFT)
-#endif
-
 #endif	/* __ASM_KERNEL_PGTABLE_H */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 4384eaa0aeb7..94b68850cb9f 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -64,7 +64,6 @@ extern void arm64_memblock_init(void);
 extern void paging_init(void);
 extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
-extern void init_mem_pgprot(void);
 extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 				   phys_addr_t size, pgprot_t prot);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0bd18de9fd97..72c2e8431360 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -103,6 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
+#define pte_rdonly(pte)		(!!(pte_val(pte) & PTE_RDONLY))
 #define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
@@ -120,7 +121,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
 })
 
-#define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
+#define pte_hw_dirty(pte)	(pte_write(pte) && !pte_rdonly(pte))
 #define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
@@ -212,7 +213,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
 	 * clear), set the PTE_DIRTY bit.
 	 */
 	if (pte_hw_dirty(pte))
-		pte = pte_mkdirty(pte);
+		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
 
 	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
 	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
@@ -823,7 +824,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 			      PTE_ATTRINDX_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
-		pte = pte_mkdirty(pte);
+		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index 4292d9bafb9d..484cb6972e99 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -17,6 +17,9 @@
 
 #include <asm/virt.h>
 
+DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event);
+DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event);
+
 extern unsigned long sdei_exit_mode;
 
 /* Software Delegated Exception entry point from firmware*/
@@ -29,6 +32,9 @@ asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num,
 						   unsigned long pc,
 						   unsigned long pstate);
 
+/* Abort a running handler. Context is discarded. */
+void __sdei_handler_abort(void);
+
 /*
  * The above entry point does the minimum to call C code. This function does
  * anything else, before calling the driver.
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b481935e9314..16464bf9a8aa 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -803,15 +803,21 @@
 /*
  * For registers without architectural names, or simply unsupported by
  * GAS.
+ *
+ * __check_r forces warnings to be generated by the compiler when
+ * evaluating r which wouldn't normally happen due to being passed to
+ * the assembler via __stringify(r).
  */
 #define read_sysreg_s(r) ({						\
 	u64 __val;							\
+	u32 __maybe_unused __check_r = (u32)(r);			\
 	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
 	__val;								\
 })
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)(v);						\
+	u32 __maybe_unused __check_r = (u32)(r);			\
 	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
 } while (0)