From 1d50e5d0c5052446cb85a3bf11fe8ba4e8d770ca Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Thu, 14 May 2020 00:22:36 +0530 Subject: crash_core, vmcoreinfo: Append 'MAX_PHYSMEM_BITS' to vmcoreinfo Right now user-space tools like 'makedumpfile' and 'crash' need to rely on a best-guess method of determining value of 'MAX_PHYSMEM_BITS' supported by underlying kernel. This value is used in user-space code to calculate the bit-space required to store a section for SPARESMEM (similar to the existing calculation method used in the kernel implementation): #define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) Now, regressions have been reported in user-space utilities like 'makedumpfile' and 'crash' on arm64, with the recently added kernel support for 52-bit physical address space, as there is no clear method of determining this value in user-space (other than reading kernel CONFIG flags). As per suggestion from makedumpfile maintainer (Kazu), it makes more sense to append 'MAX_PHYSMEM_BITS' to vmcoreinfo in the core code itself rather than in arch-specific code, so that the user-space code for other archs can also benefit from this addition to the vmcoreinfo and use it as a standard way of determining 'SECTIONS_SHIFT' value in user-land. A reference 'makedumpfile' implementation which reads the 'MAX_PHYSMEM_BITS' value from vmcoreinfo in a arch-independent fashion is available here: While at it also update vmcoreinfo documentation for 'MAX_PHYSMEM_BITS' variable being added to vmcoreinfo. 'MAX_PHYSMEM_BITS' defines the maximum supported physical address space memory. Signed-off-by: Bhupesh Sharma Tested-by: John Donnelly Acked-by: Dave Young Cc: Boris Petkov Cc: Ingo Molnar Cc: Thomas Gleixner Cc: James Morse Cc: Mark Rutland Cc: Will Deacon Cc: Michael Ellerman Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Dave Anderson Cc: Kazuhito Hagio Cc: x86@kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kexec@lists.infradead.org Link: https://lore.kernel.org/r/1589395957-24628-2-git-send-email-bhsharma@redhat.com Signed-off-by: Catalin Marinas --- kernel/crash_core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 9f1557b98468..18175687133a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -413,6 +413,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); #endif VMCOREINFO_STRUCT_SIZE(page); VMCOREINFO_STRUCT_SIZE(pglist_data); -- cgit v1.2.3-58-ga151 From 1b86abc1c645ad5c9c7bf70910cb3ce73939d2d7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Jul 2020 13:11:24 +0800 Subject: sched_clock: Expose struct clock_read_data In order to support perf_event_mmap_page::cap_time features, an architecture needs, aside from a userspace readable counter register, to expose the exact clock data so that userspace can convert the counter register into a correct timestamp. Provide struct clock_read_data and two (seqcount) helpers so that architectures (arm64 in specific) can expose the numbers to userspace. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Leo Yan Link: https://lore.kernel.org/r/20200716051130.4359-2-leo.yan@linaro.org Signed-off-by: Will Deacon --- include/linux/sched_clock.h | 28 ++++++++++++++++++++++++++++ kernel/time/sched_clock.c | 41 +++++++++++++---------------------------- 2 files changed, 41 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 0bb04a96a6d4..528718e4ed52 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -6,6 +6,34 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { + u64 epoch_ns; + u64 epoch_cyc; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); + u32 mult; + u32 shift; +}; + +extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq); +extern int sched_clock_read_retry(unsigned int seq); + extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index fa3f800d7d76..0acaadc3156c 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -19,31 +19,6 @@ #include "timekeeping.h" -/** - * struct clock_read_data - data required to read from sched_clock() - * - * @epoch_ns: sched_clock() value at last update - * @epoch_cyc: Clock cycle value at last update. - * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit - * clocks. - * @read_sched_clock: Current clock source (or dummy source when suspended). - * @mult: Multipler for scaled math conversion. - * @shift: Shift value for scaled math conversion. - * - * Care must be taken when updating this structure; it is read by - * some very hot code paths. It occupies <=40 bytes and, when combined - * with the seqcount used to synchronize access, comfortably fits into - * a 64 byte cache line. - */ -struct clock_read_data { - u64 epoch_ns; - u64 epoch_cyc; - u64 sched_clock_mask; - u64 (*read_sched_clock)(void); - u32 mult; - u32 shift; -}; - /** * struct clock_data - all data needed for sched_clock() (including * registration of a new clock source) @@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) return (cyc * mult) >> shift; } +struct clock_read_data *sched_clock_read_begin(unsigned int *seq) +{ + *seq = raw_read_seqcount(&cd.seq); + return cd.read_data + (*seq & 1); +} + +int sched_clock_read_retry(unsigned int seq) +{ + return read_seqcount_retry(&cd.seq, seq); +} + unsigned long long notrace sched_clock(void) { u64 cyc, res; @@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void) struct clock_read_data *rd; do { - seq = raw_read_seqcount(&cd.seq); - rd = cd.read_data + (seq & 1); + rd = sched_clock_read_begin(&seq); cyc = (rd->read_sched_clock() - rd->epoch_cyc) & rd->sched_clock_mask; res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); - } while (read_seqcount_retry(&cd.seq, seq)); + } while (sched_clock_read_retry(seq)); return res; } -- cgit v1.2.3-58-ga151 From aadd6e5caaacd6feca9691ba30536e7de5a7d152 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Thu, 16 Jul 2020 13:11:25 +0800 Subject: time/sched_clock: Use raw_read_seqcount_latch() sched_clock uses seqcount_t latching to switch between two storage places protected by the sequence counter. This allows it to have interruptible, NMI-safe, seqcount_t write side critical sections. Since 7fc26327b756 ("seqlock: Introduce raw_read_seqcount_latch()"), raw_read_seqcount_latch() became the standardized way for seqcount_t latch read paths. Due to the dependent load, it also has one read memory barrier less than the currently used raw_read_seqcount() API. Use raw_read_seqcount_latch() for the seqcount_t latch read path. Signed-off-by: Ahmed S. Darwish Signed-off-by: Leo Yan Link: https://lkml.kernel.org/r/20200625085745.GD117543@hirez.programming.kicks-ass.net Link: https://lkml.kernel.org/r/20200715092345.GA231464@debian-buster-darwi.lab.linutronix.de Link: https://lore.kernel.org/r/20200716051130.4359-3-leo.yan@linaro.org References: 1809bfa44e10 ("timers, sched/clock: Avoid deadlock during read from NMI") Signed-off-by: Will Deacon --- kernel/time/sched_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 0acaadc3156c..0deaf4b79fb4 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -70,7 +70,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) struct clock_read_data *sched_clock_read_begin(unsigned int *seq) { - *seq = raw_read_seqcount(&cd.seq); + *seq = raw_read_seqcount_latch(&cd.seq); return cd.read_data + (*seq & 1); } -- cgit v1.2.3-58-ga151