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

Pull arm64 and cross-arch updates from Catalin Marinas: "Here's a slightly wider-spread set of updates for 5.9. Going outside the usual arch/arm64/ area is the removal of read_barrier_depends() series from Will and the MSI/IOMMU ID translation series from Lorenzo. The notable arm64 updates include ARMv8.4 TLBI range operations and translation level hint, time namespace support, and perf. Summary: - Removal of the tremendously unpopular read_barrier_depends() barrier, which is a NOP on all architectures apart from Alpha, in favour of allowing architectures to override READ_ONCE() and do whatever dance they need to do to ensure address dependencies provide LOAD -> LOAD/STORE ordering. This work also offers a potential solution if compilers are shown to convert LOAD -> LOAD address dependencies into control dependencies (e.g. under LTO), as weakly ordered architectures will effectively be able to upgrade READ_ONCE() to smp_load_acquire(). The latter case is not used yet, but will be discussed further at LPC. - Make the MSI/IOMMU input/output ID translation PCI agnostic, augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID bus-specific parameter and apply the resulting changes to the device ID space provided by the Freescale FSL bus. - arm64 support for TLBI range operations and translation table level hints (part of the ARMv8.4 architecture version). - Time namespace support for arm64. - Export the virtual and physical address sizes in vmcoreinfo for makedumpfile and crash utilities. - CPU feature handling cleanups and checks for programmer errors (overlapping bit-fields). - ACPI updates for arm64: disallow AML accesses to EFI code regions and kernel memory. - perf updates for arm64. - Miscellaneous fixes and cleanups, most notably PLT counting optimisation for module loading, recordmcount fix to ignore relocations other than R_AARCH64_CALL26, CMA areas reserved for gigantic pages on 16K and 64K configurations. - Trivial typos, duplicate words" Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits) arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack arm64/mm: save memory access in check_and_switch_context() fast switch path arm64: sigcontext.h: delete duplicated word arm64: ptrace.h: delete duplicated word arm64: pgtable-hwdef.h: delete duplicated words bus: fsl-mc: Add ACPI support for fsl-mc bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver of/irq: Make of_msi_map_rid() PCI bus agnostic of/irq: make of_msi_map_get_device_domain() bus agnostic dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus of/device: Add input id to of_dma_configure() of/iommu: Make of_map_rid() PCI agnostic ACPI/IORT: Add an input ID to acpi_dma_configure() ACPI/IORT: Remove useless PCI bus walk ACPI/IORT: Make iort_msi_map_rid() PCI agnostic ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC arm64: enable time namespace support arm64/vdso: Restrict splitting VVAR VMA arm64/vdso: Handle faults on timens page ...

Linus Torvalds committed 6 years ago

Commit 145ff1e2 parents 8c4e1c0 0e4cd9f98 files · +1892 −1091Browse files

Showing the changes to kernel (2 of 98 files). Show all

Unified · Split

2 files

kernel/crash_core.c +1 −0
kernel/time/sched_clock.c +13 −28

kernel/crash_core.c+1−0

@@ -413,6 +413,7 @@ static int __init crash_save_vmcoreinfo_init(void) · 412 unmodified lines
413	413	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
414	414	VMCOREINFO_STRUCT_SIZE(mem_section);
415	415	VMCOREINFO_OFFSET(mem_section, section_mem_map);
	416	+ VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
416	417	#endif
417	418	VMCOREINFO_STRUCT_SIZE(page);
418	419	VMCOREINFO_STRUCT_SIZE(pglist_data);

kernel/time/sched_clock.c+13−28

@@ -19,31 +19,6 @@ · 18 unmodified lines
19	19
20	20	#include "timekeeping.h"
21	21
22		−/**
23		− * struct clock_read_data - data required to read from sched_clock()
24		− *
25		− * @epoch_ns: sched_clock() value at last update
26		− * @epoch_cyc: Clock cycle value at last update.
27		− * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit
28		− * clocks.
29		− * @read_sched_clock: Current clock source (or dummy source when suspended).
30		− * @mult: Multipler for scaled math conversion.
31		− * @shift: Shift value for scaled math conversion.
32		− *
33		− * Care must be taken when updating this structure; it is read by
34		− * some very hot code paths. It occupies <=40 bytes and, when combined
35		− * with the seqcount used to synchronize access, comfortably fits into
36		− * a 64 byte cache line.
37		− */
38		−struct clock_read_data {
39		− u64 epoch_ns;
40		− u64 epoch_cyc;
41		− u64 sched_clock_mask;
42		− u64 (*read_sched_clock)(void);
43		− u32 mult;
44		− u32 shift;
45		−};
46		−
47	22	/**
48	23	* struct clock_data - all data needed for sched_clock() (including
49	24	* registration of a new clock source)
@@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) · 43 unmodified lines
93	68	return (cyc * mult) >> shift;
94	69	}
95	70
	71	+struct clock_read_data sched_clock_read_begin(unsigned int seq)
	72	+{
	73	+ *seq = raw_read_seqcount_latch(&cd.seq);
	74	+ return cd.read_data + (*seq & 1);
	75	+}
	76	+
	77	+int sched_clock_read_retry(unsigned int seq)
	78	+{
	79	+ return read_seqcount_retry(&cd.seq, seq);
	80	+}
	81	+
96	82	unsigned long long notrace sched_clock(void)
97	83	{
98	84	u64 cyc, res;
@@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void) · 1 unmodified line
100	86	struct clock_read_data *rd;
101	87
102	88	do {
103		− seq = raw_read_seqcount(&cd.seq);
104		− rd = cd.read_data + (seq & 1);
	89	+ rd = sched_clock_read_begin(&seq);
105	90
106	91	cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
107	92	rd->sched_clock_mask;
108	93	res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
109		− } while (read_seqcount_retry(&cd.seq, seq));
	94	+ } while (sched_clock_read_retry(seq));
110	95
111	96	return res;
112	97	}