January 2024 - Linux-stable-mirror

[PATCH 5.10 0/2] PCI: Disable ATS for specific Intel IPU E2000 devices

by Bartosz Pawlowski

This patch series addresses the problem with A an B steppings of Intel IPU E2000 which expects incorrect endianness in data field of ATS invalidation request TLP by disabling ATS capability for vulnerable devices. Bartosz Pawlowski (2): PCI: Extract ATS disabling to a helper function PCI: Disable ATS for specific Intel IPU E2000 devices drivers/pci/quirks.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) -- 2.43.0

1 year, 1 month

2
3
0 0

[PATCH stable 5.4.x 1/3] net/dst: use a smaller percpu_counter batch for dst entries accounting

by Suraj Jitindar Singh

From: Eric Dumazet <edumazet(a)google.com> commit cf86a086a18095e33e0637cb78cda1fcf5280852 upstream. percpu_counter_add() uses a default batch size which is quite big on platforms with 256 cpus. (2*256 -> 512) This means dst_entries_get_fast() can be off by +/- 2*(nr_cpus^2) (131072 on servers with 256 cpus) Reduce the batch size to something more reasonable, and add logic to ip6_dst_gc() to call dst_entries_get_slow() before calling the _very_ expensive fib6_run_gc() function. Signed-off-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Suraj Jitindar Singh <surajjs(a)amazon.com> Cc: <stable(a)vger.kernel.org> # 5.4.x --- include/net/dst_ops.h | 4 +++- net/core/dst.c | 8 ++++---- net/ipv6/route.c | 3 +++ 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 443863c7b8da..88ff7bb2bb9b 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -53,9 +53,11 @@ static inline int dst_entries_get_slow(struct dst_ops *dst) return percpu_counter_sum_positive(&dst->pcpuc_entries); } +#define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { - percpu_counter_add(&dst->pcpuc_entries, val); + percpu_counter_add_batch(&dst->pcpuc_entries, val, + DST_PERCPU_COUNTER_BATCH); } static inline int dst_entries_init(struct dst_ops *dst) diff --git a/net/core/dst.c b/net/core/dst.c index 193af526e908..d6b6ced0d451 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -81,11 +81,11 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, { struct dst_entry *dst; - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc && + !(flags & DST_NOCOUNT) && + dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) { - printk_ratelimited(KERN_NOTICE "Route cache is full: " - "consider increasing sysctl " - "net.ipv[4|6].route.max_size.\n"); + pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); return NULL; } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 209d52ebbd19..c38e421ca783 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3218,6 +3218,9 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); + if (entries > rt_max_size) + entries = dst_entries_get_slow(ops); + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out; -- 2.34.1

1 year, 1 month

1
2
0 0

[merged mm-hotfixes-stable] selftests-mm-hugepage-vmemmap-fails-on-64k-page-size-systems.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: selftests: mm: hugepage-vmemmap fails on 64K page size systems has been removed from the -mm tree. Its filename was selftests-mm-hugepage-vmemmap-fails-on-64k-page-size-systems.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Donet Tom <donettom(a)linux.vnet.ibm.com> Subject: selftests: mm: hugepage-vmemmap fails on 64K page size systems Date: Wed, 10 Jan 2024 14:03:35 +0530 The kernel sefltest mm/hugepage-vmemmap fails on architectures which has different page size other than 4K. In hugepage-vmemmap page size used is 4k so the pfn calculation will go wrong on systems which has different page size .The length of MAP_HUGETLB memory must be hugepage aligned but in hugepage-vmemmap map length is 2M so this will not get aligned if the system has differnet hugepage size. Added psize() to get the page size and default_huge_page_size() to get the default hugepage size at run time, hugepage-vmemmap test pass on powerpc with 64K page size and x86 with 4K page size. Result on powerpc without patch (page size 64K) *# ./hugepage-vmemmap Returned address is 0x7effff000000 whose pfn is 0 Head page flags (100000000) is invalid check_page_flags: Invalid argument *# Result on powerpc with patch (page size 64K) *# ./hugepage-vmemmap Returned address is 0x7effff000000 whose pfn is 600 *# Result on x86 with patch (page size 4K) *# ./hugepage-vmemmap Returned address is 0x7fc7c2c00000 whose pfn is 1dac00 *# Link: https://lkml.kernel.org/r/3b3a3ae37ba21218481c482a872bbf7526031600.17048657… Fixes: b147c89cd429 ("selftests: vm: add a hugetlb test case") Signed-off-by: Donet Tom <donettom(a)linux.vnet.ibm.com> Reported-by: Geetika Moolchandani <geetika(a)linux.ibm.com> Tested-by: Geetika Moolchandani <geetika(a)linux.ibm.com> Acked-by: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/hugepage-vmemmap.c | 29 +++++++++------- 1 file changed, 18 insertions(+), 11 deletions(-) --- a/tools/testing/selftests/mm/hugepage-vmemmap.c~selftests-mm-hugepage-vmemmap-fails-on-64k-page-size-systems +++ a/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -10,10 +10,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> - -#define MAP_LENGTH (2UL * 1024 * 1024) - -#define PAGE_SIZE 4096 +#include "vm_util.h" #define PAGE_COMPOUND_HEAD (1UL << 15) #define PAGE_COMPOUND_TAIL (1UL << 16) @@ -39,6 +36,9 @@ #define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) #endif +static size_t pagesize; +static size_t maplength; + static void write_bytes(char *addr, size_t length) { unsigned long i; @@ -56,7 +56,7 @@ static unsigned long virt_to_pfn(void *a if (fd < 0) return -1UL; - lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + lseek(fd, (unsigned long)addr / pagesize * sizeof(pagemap), SEEK_SET); read(fd, &pagemap, sizeof(pagemap)); close(fd); @@ -86,7 +86,7 @@ static int check_page_flags(unsigned lon * this also verifies kernel has correctly set the fake page_head to tail * while hugetlb_free_vmemmap is enabled. */ - for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) { + for (i = 1; i < maplength / pagesize; i++) { read(fd, &pageflags, sizeof(pageflags)); if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { @@ -106,18 +106,25 @@ int main(int argc, char **argv) void *addr; unsigned long pfn; - addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); + pagesize = psize(); + maplength = default_huge_page_size(); + if (!maplength) { + printf("Unable to determine huge page size\n"); + exit(1); + } + + addr = mmap(MAP_ADDR, maplength, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); exit(1); } /* Trigger allocation of HugeTLB page. */ - write_bytes(addr, MAP_LENGTH); + write_bytes(addr, maplength); pfn = virt_to_pfn(addr); if (pfn == -1UL) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("virt_to_pfn"); exit(1); } @@ -125,13 +132,13 @@ int main(int argc, char **argv) printf("Returned address is %p whose pfn is %lx\n", addr, pfn); if (check_page_flags(pfn) < 0) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("check_page_flags"); exit(1); } /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ - if (munmap(addr, MAP_LENGTH)) { + if (munmap(addr, maplength)) { perror("munmap"); exit(1); } _ Patches currently in -mm which might be from donettom(a)linux.vnet.ibm.com are

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] mm-memory_hotplug-fix-memmap_on_memory-sysfs-value-retrieval.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/memory_hotplug: fix memmap_on_memory sysfs value retrieval has been removed from the -mm tree. Its filename was mm-memory_hotplug-fix-memmap_on_memory-sysfs-value-retrieval.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Subject: mm/memory_hotplug: fix memmap_on_memory sysfs value retrieval Date: Wed, 10 Jan 2024 15:01:27 +0100 set_memmap_mode() stores the kernel parameter memmap mode as an integer. However, the get_memmap_mode() function utilizes param_get_bool() to fetch the value as a boolean, leading to potential endianness issue. On Big-endian architectures, the memmap_on_memory is consistently displayed as 'N' regardless of its actual status. To address this endianness problem, the solution involves obtaining the mode as an integer. This adjustment ensures the proper display of the memmap_on_memory parameter, presenting it as one of the following options: Force, Y, or N. Link: https://lkml.kernel.org/r/20240110140127.241451-1-sumanthk@linux.ibm.com Fixes: 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Suggested-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> [6.6+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory_hotplug.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) --- a/mm/memory_hotplug.c~mm-memory_hotplug-fix-memmap_on_memory-sysfs-value-retrieval +++ a/mm/memory_hotplug.c @@ -101,9 +101,11 @@ static int set_memmap_mode(const char *v static int get_memmap_mode(char *buffer, const struct kernel_param *kp) { - if (*((int *)kp->arg) == MEMMAP_ON_MEMORY_FORCE) - return sprintf(buffer, "force\n"); - return param_get_bool(buffer, kp); + int mode = *((int *)kp->arg); + + if (mode == MEMMAP_ON_MEMORY_FORCE) + return sprintf(buffer, "force\n"); + return sprintf(buffer, "%c\n", mode ? 'Y' : 'N'); } static const struct kernel_param_ops memmap_mode_ops = { _ Patches currently in -mm which might be from sumanthk(a)linux.ibm.com are mm-memory_hotplug-introduce-mem_prepare_online-mem_finish_offline-notifiers.patch s390-mm-allocate-vmemmap-pages-from-self-contained-memory-range.patch s390-sclp-remove-unhandled-memory-notifier-type.patch s390-mm-implement-mem_prepare_online-mem_finish_offline-notifiers.patch s390-enable-mhp_memmap_on_memory.patch

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] efi-disable-mirror-feature-during-crashkernel.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: efi: disable mirror feature during crashkernel has been removed from the -mm tree. Its filename was efi-disable-mirror-feature-during-crashkernel.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Ma Wupeng <mawupeng1(a)huawei.com> Subject: efi: disable mirror feature during crashkernel Date: Tue, 9 Jan 2024 12:15:36 +0800 If the system has no mirrored memory or uses crashkernel.high while kernelcore=mirror is enabled on the command line then during crashkernel, there will be limited mirrored memory and this usually leads to OOM. To solve this problem, disable the mirror feature during crashkernel. Link: https://lkml.kernel.org/r/20240109041536.3903042-1-mawupeng1@huawei.com Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Acked-by: Mike Rapoport (IBM) <rppt(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/mm_init.c | 6 ++++++ 1 file changed, 6 insertions(+) --- a/mm/mm_init.c~efi-disable-mirror-feature-during-crashkernel +++ a/mm/mm_init.c @@ -26,6 +26,7 @@ #include <linux/pgtable.h> #include <linux/swap.h> #include <linux/cma.h> +#include <linux/crash_dump.h> #include "internal.h" #include "slab.h" #include "shuffle.h" @@ -381,6 +382,11 @@ static void __init find_zone_movable_pfn goto out; } + if (is_kdump_kernel()) { + pr_warn("The system is under kdump, ignore kernelcore=mirror.\n"); + goto out; + } + for_each_mem_region(r) { if (memblock_is_mirror(r)) continue; _ Patches currently in -mm which might be from mawupeng1(a)huawei.com are

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] kexec-do-syscore_shutdown-in-kernel_kexec.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kexec: do syscore_shutdown() in kernel_kexec has been removed from the -mm tree. Its filename was kexec-do-syscore_shutdown-in-kernel_kexec.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: James Gowans <jgowans(a)amazon.com> Subject: kexec: do syscore_shutdown() in kernel_kexec Date: Wed, 13 Dec 2023 08:40:04 +0200 syscore_shutdown() runs driver and module callbacks to get the system into a state where it can be correctly shut down. In commit 6f389a8f1dd2 ("PM / reboot: call syscore_shutdown() after disable_nonboot_cpus()") syscore_shutdown() was removed from kernel_restart_prepare() and hence got (incorrectly?) removed from the kexec flow. This was innocuous until commit 6735150b6997 ("KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown") changed the way that KVM registered its shutdown callbacks, switching from reboot notifiers to syscore_ops.shutdown. As syscore_shutdown() is missing from kexec, KVM's shutdown hook is not run and virtualisation is left enabled on the boot CPU which results in triple faults when switching to the new kernel on Intel x86 VT-x with VMXE enabled. Fix this by adding syscore_shutdown() to the kexec sequence. In terms of where to add it, it is being added after migrating the kexec task to the boot CPU, but before APs are shut down. It is not totally clear if this is the best place: in commit 6f389a8f1dd2 ("PM / reboot: call syscore_shutdown() after disable_nonboot_cpus()") it is stated that "syscore_ops operations should be carried with one CPU on-line and interrupts disabled." APs are only offlined later in machine_shutdown(), so this syscore_shutdown() is being run while APs are still online. This seems to be the correct place as it matches where syscore_shutdown() is run in the reboot and halt flows - they also run it before APs are shut down. The assumption is that the commit message in commit 6f389a8f1dd2 ("PM / reboot: call syscore_shutdown() after disable_nonboot_cpus()") is no longer valid. KVM has been discussed here as it is what broke loudly by not having syscore_shutdown() in kexec, but this change impacts more than just KVM; all drivers/modules which register a syscore_ops.shutdown callback will now be invoked in the kexec flow. Looking at some of them like x86 MCE it is probably more correct to also shut these down during kexec. Maintainers of all drivers which use syscore_ops.shutdown are added on CC for visibility. They are: arch/powerpc/platforms/cell/spu_base.c .shutdown = spu_shutdown, arch/x86/kernel/cpu/mce/core.c .shutdown = mce_syscore_shutdown, arch/x86/kernel/i8259.c .shutdown = i8259A_shutdown, drivers/irqchip/irq-i8259.c .shutdown = i8259A_shutdown, drivers/irqchip/irq-sun6i-r.c .shutdown = sun6i_r_intc_shutdown, drivers/leds/trigger/ledtrig-cpu.c .shutdown = ledtrig_cpu_syscore_shutdown, drivers/power/reset/sc27xx-poweroff.c .shutdown = sc27xx_poweroff_shutdown, kernel/irq/generic-chip.c .shutdown = irq_gc_shutdown, virt/kvm/kvm_main.c .shutdown = kvm_shutdown, This has been tested by doing a kexec on x86_64 and aarch64. Link: https://lkml.kernel.org/r/20231213064004.2419447-1-jgowans@amazon.com Fixes: 6735150b6997 ("KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown") Signed-off-by: James Gowans <jgowans(a)amazon.com> Cc: Baoquan He <bhe(a)redhat.com> Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Marc Zyngier <maz(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Tony Luck <tony.luck(a)intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Chen-Yu Tsai <wens(a)csie.org> Cc: Jernej Skrabec <jernej.skrabec(a)gmail.com> Cc: Samuel Holland <samuel(a)sholland.org> Cc: Pavel Machek <pavel(a)ucw.cz> Cc: Sebastian Reichel <sre(a)kernel.org> Cc: Orson Zhai <orsonzhai(a)gmail.com> Cc: Alexander Graf <graf(a)amazon.de> Cc: Jan H. Schoenherr <jschoenh(a)amazon.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/kexec_core.c | 1 + 1 file changed, 1 insertion(+) --- a/kernel/kexec_core.c~kexec-do-syscore_shutdown-in-kernel_kexec +++ a/kernel/kexec_core.c @@ -1257,6 +1257,7 @@ int kernel_kexec(void) kexec_in_progress = true; kernel_restart_prepare("kexec reboot"); migrate_to_reboot_cpu(); + syscore_shutdown(); /* * migrate_to_reboot_cpu() disables CPU hotplug assuming that _ Patches currently in -mm which might be from jgowans(a)amazon.com are

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] fs-proc-task_mmu-move-mmu-notification-mechanism-inside-mm-lock.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: fs/proc/task_mmu: move mmu notification mechanism inside mm lock has been removed from the -mm tree. Its filename was fs-proc-task_mmu-move-mmu-notification-mechanism-inside-mm-lock.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Subject: fs/proc/task_mmu: move mmu notification mechanism inside mm lock Date: Tue, 9 Jan 2024 16:24:42 +0500 Move mmu notification mechanism inside mm lock to prevent race condition in other components which depend on it. The notifier will invalidate memory range. Depending upon the number of iterations, different memory ranges would be invalidated. The following warning would be removed by this patch: WARNING: CPU: 0 PID: 5067 at arch/x86/kvm/../../../virt/kvm/kvm_main.c:734 kvm_mmu_notifier_change_pte+0x860/0x960 arch/x86/kvm/../../../virt/kvm/kvm_main.c:734 There is no behavioural and performance change with this patch when there is no component registered with the mmu notifier. [akpm(a)linux-foundation.org: narrow the scope of `range', per Sean] Link: https://lkml.kernel.org/r/20240109112445.590736-1-usama.anjum@collabora.com Fixes: 52526ca7fdb9 ("fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs") Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Reported-by: syzbot+81227d2bd69e9dedb802(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000f6d051060c6785bc@google.com/ Reviewed-by: Sean Christopherson <seanjc(a)google.com> Cc: Andrei Vagin <avagin(a)google.com> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Micha�� Miros��aw <mirq-linux(a)rere.qmqm.pl> Cc: Peter Xu <peterx(a)redhat.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Stephen Rothwell <sfr(a)canb.auug.org.au> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/proc/task_mmu.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) --- a/fs/proc/task_mmu.c~fs-proc-task_mmu-move-mmu-notification-mechanism-inside-mm-lock +++ a/fs/proc/task_mmu.c @@ -2432,7 +2432,6 @@ static long pagemap_scan_flush_buffer(st static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) { - struct mmu_notifier_range range; struct pagemap_scan_private p = {0}; unsigned long walk_start; size_t n_ranges_out = 0; @@ -2448,15 +2447,9 @@ static long do_pagemap_scan(struct mm_st if (ret) return ret; - /* Protection change for the range is going to happen. */ - if (p.arg.flags & PM_SCAN_WP_MATCHING) { - mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, - mm, p.arg.start, p.arg.end); - mmu_notifier_invalidate_range_start(&range); - } - for (walk_start = p.arg.start; walk_start < p.arg.end; walk_start = p.arg.walk_end) { + struct mmu_notifier_range range; long n_out; if (fatal_signal_pending(current)) { @@ -2467,8 +2460,20 @@ static long do_pagemap_scan(struct mm_st ret = mmap_read_lock_killable(mm); if (ret) break; + + /* Protection change for the range is going to happen. */ + if (p.arg.flags & PM_SCAN_WP_MATCHING) { + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, + mm, walk_start, p.arg.end); + mmu_notifier_invalidate_range_start(&range); + } + ret = walk_page_range(mm, walk_start, p.arg.end, &pagemap_scan_ops, &p); + + if (p.arg.flags & PM_SCAN_WP_MATCHING) + mmu_notifier_invalidate_range_end(&range); + mmap_read_unlock(mm); n_out = pagemap_scan_flush_buffer(&p); @@ -2494,9 +2499,6 @@ static long do_pagemap_scan(struct mm_st if (pagemap_scan_writeback_args(&p.arg, uarg)) ret = -EFAULT; - if (p.arg.flags & PM_SCAN_WP_MATCHING) - mmu_notifier_invalidate_range_end(&range); - kfree(p.vec_buf); return ret; } _ Patches currently in -mm which might be from usama.anjum(a)collabora.com are selftests-mm-mremap_test-fix-build-warning.patch selftests-mm-hugepage-shm-conform-test-to-tap-format-output.patch selftests-mm-hugepage-vmemmap-conform-test-to-tap-format-output.patch selftests-mm-hugetlb-madvise-conform-test-to-tap-format-output.patch selftests-mm-khugepaged-conform-test-to-tap-format-output.patch selftests-mm-hugetlb-read-hwpoison-conform-test-to-tap-format-output.patch selftests-mm-ksm_tests-conform-test-to-tap-format-output.patch selftests-mm-config-add-missing-configs.patch

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] scripts-decode_stacktracesh-optionally-use-llvm-utilities.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: scripts/decode_stacktrace.sh: optionally use LLVM utilities has been removed from the -mm tree. Its filename was scripts-decode_stacktracesh-optionally-use-llvm-utilities.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Carlos Llamas <cmllamas(a)google.com> Subject: scripts/decode_stacktrace.sh: optionally use LLVM utilities Date: Fri, 29 Sep 2023 03:48:17 +0000 GNU's addr2line can have problems parsing a vmlinux built with LLVM, particularly when LTO was used. In order to decode the traces correctly this patch adds the ability to switch to LLVM's utilities readelf and addr2line. The same approach is followed by Will in [1]. Before: $ scripts/decode_stacktrace.sh vmlinux < kernel.log [17716.240635] Call trace: [17716.240646] skb_cow_data (??:?) [17716.240654] esp6_input (ld-temp.o:?) [17716.240666] xfrm_input (ld-temp.o:?) [17716.240674] xfrm6_rcv (??:?) [...] After: $ LLVM=1 scripts/decode_stacktrace.sh vmlinux < kernel.log [17716.240635] Call trace: [17716.240646] skb_cow_data (include/linux/skbuff.h:2172 net/core/skbuff.c:4503) [17716.240654] esp6_input (net/ipv6/esp6.c:977) [17716.240666] xfrm_input (net/xfrm/xfrm_input.c:659) [17716.240674] xfrm6_rcv (net/ipv6/xfrm6_input.c:172) [...] Note that one could set CROSS_COMPILE=llvm- instead to hack around this issue. However, doing so can break the decodecode routine as it will force the selection of other LLVM utilities down the line e.g. llvm-as. [1] https://lore.kernel.org/all/20230914131225.13415-3-will@kernel.org/ Link: https://lkml.kernel.org/r/20230929034836.403735-1-cmllamas@google.com Signed-off-by: Carlos Llamas <cmllamas(a)google.com> Reviewed-by: Nick Desaulniers <ndesaulniers(a)google.com> Reviewed-by: Elliot Berman <quic_eberman(a)quicinc.com> Tested-by: Justin Stitt <justinstitt(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: John Stultz <jstultz(a)google.com> Cc: Masahiro Yamada <masahiroy(a)kernel.org> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Tom Rix <trix(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- scripts/decode_stacktrace.sh | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) --- a/scripts/decode_stacktrace.sh~scripts-decode_stacktracesh-optionally-use-llvm-utilities +++ a/scripts/decode_stacktrace.sh @@ -16,6 +16,21 @@ elif type c++filt >/dev/null 2>&1 ; then cppfilt_opts=-i fi +UTIL_SUFFIX= +if [[ -z ${LLVM:-} ]]; then + UTIL_PREFIX=${CROSS_COMPILE:-} +else + UTIL_PREFIX=llvm- + if [[ ${LLVM} == */ ]]; then + UTIL_PREFIX=${LLVM}${UTIL_PREFIX} + elif [[ ${LLVM} == -* ]]; then + UTIL_SUFFIX=${LLVM} + fi +fi + +READELF=${UTIL_PREFIX}readelf${UTIL_SUFFIX} +ADDR2LINE=${UTIL_PREFIX}addr2line${UTIL_SUFFIX} + if [[ $1 == "-r" ]] ; then vmlinux="" basepath="auto" @@ -75,7 +90,7 @@ find_module() { if [[ "$modpath" != "" ]] ; then for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do - if readelf -WS "$fn" | grep -qwF .debug_line ; then + if ${READELF} -WS "$fn" | grep -qwF .debug_line ; then echo $fn return fi @@ -169,7 +184,7 @@ parse_symbol() { if [[ $aarray_support == true && "${cache[$module,$address]+isset}" == "isset" ]]; then local code=${cache[$module,$address]} else - local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address" 2>/dev/null) + local code=$(${ADDR2LINE} -i -e "$objfile" "$address" 2>/dev/null) if [[ $aarray_support == true ]]; then cache[$module,$address]=$code fi _ Patches currently in -mm which might be from cmllamas(a)google.com are

1 year, 1 month

1
0
0 0

[merged mm-hotfixes-stable] kdump-defer-the-insertion-of-crashkernel-resources.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kdump: defer the insertion of crashkernel resources has been removed from the -mm tree. Its filename was kdump-defer-the-insertion-of-crashkernel-resources.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Huacai Chen <chenhuacai(a)loongson.cn> Subject: kdump: defer the insertion of crashkernel resources Date: Fri, 29 Dec 2023 16:02:13 +0800 In /proc/iomem, sub-regions should be inserted after their parent, otherwise the insertion of parent resource fails. But after generic crashkernel reservation applied, in both RISC-V and ARM64 (LoongArch will also use generic reservation later on), crashkernel resources are inserted before their parent, which causes the parent disappear in /proc/iomem. So we defer the insertion of crashkernel resources to an early_initcall(). 1, Without 'crashkernel' parameter: 100d0100-100d01ff : LOON0001:00 100d0100-100d01ff : LOON0001:00 LOON0001:00 100e0000-100e0bff : LOON0002:00 100e0000-100e0bff : LOON0002:00 LOON0002:00 1fe001e0-1fe001e7 : serial 90400000-fa17ffff : System RAM f6220000-f622ffff : Reserved f9ee0000-f9ee3fff : Reserved fa120000-fa17ffff : Reserved fa190000-fe0bffff : System RAM fa190000-fa1bffff : Reserved fe4e0000-47fffffff : System RAM 43c000000-441ffffff : Reserved 47ff98000-47ffa3fff : Reserved 47ffa4000-47ffa7fff : Reserved 47ffa8000-47ffabfff : Reserved 47ffac000-47ffaffff : Reserved 47ffb0000-47ffb3fff : Reserved 2, With 'crashkernel' parameter, before this patch: 100d0100-100d01ff : LOON0001:00 100d0100-100d01ff : LOON0001:00 LOON0001:00 100e0000-100e0bff : LOON0002:00 100e0000-100e0bff : LOON0002:00 LOON0002:00 1fe001e0-1fe001e7 : serial e6200000-f61fffff : Crash kernel fa190000-fe0bffff : System RAM fa190000-fa1bffff : Reserved fe4e0000-47fffffff : System RAM 43c000000-441ffffff : Reserved 47ff98000-47ffa3fff : Reserved 47ffa4000-47ffa7fff : Reserved 47ffa8000-47ffabfff : Reserved 47ffac000-47ffaffff : Reserved 47ffb0000-47ffb3fff : Reserved 3, With 'crashkernel' parameter, after this patch: 100d0100-100d01ff : LOON0001:00 100d0100-100d01ff : LOON0001:00 LOON0001:00 100e0000-100e0bff : LOON0002:00 100e0000-100e0bff : LOON0002:00 LOON0002:00 1fe001e0-1fe001e7 : serial 90400000-fa17ffff : System RAM e6200000-f61fffff : Crash kernel f6220000-f622ffff : Reserved f9ee0000-f9ee3fff : Reserved fa120000-fa17ffff : Reserved fa190000-fe0bffff : System RAM fa190000-fa1bffff : Reserved fe4e0000-47fffffff : System RAM 43c000000-441ffffff : Reserved 47ff98000-47ffa3fff : Reserved 47ffa4000-47ffa7fff : Reserved 47ffa8000-47ffabfff : Reserved 47ffac000-47ffaffff : Reserved 47ffb0000-47ffb3fff : Reserved Link: https://lkml.kernel.org/r/20231229080213.2622204-1-chenhuacai@loongson.cn Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> Fixes: 0ab97169aa05 ("crash_core: add generic function to do reservation") Cc: Baoquan He <bhe(a)redhat.com> Cc: Zhen Lei <thunder.leizhen(a)huawei.com> Cc: <stable(a)vger.kernel.org> [6.6+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/crash_core.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) --- a/kernel/crash_core.c~kdump-defer-the-insertion-of-crashkernel-resources +++ a/kernel/crash_core.c @@ -376,7 +376,6 @@ static int __init reserve_crashkernel_lo crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; - insert_resource(&iomem_resource, &crashk_low_res); #endif return 0; } @@ -458,8 +457,19 @@ retry: crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; - insert_resource(&iomem_resource, &crashk_res); } + +static __init int insert_crashkernel_resources(void) +{ + if (crashk_res.start < crashk_res.end) + insert_resource(&iomem_resource, &crashk_res); + + if (crashk_low_res.start < crashk_low_res.end) + insert_resource(&iomem_resource, &crashk_low_res); + + return 0; +} +early_initcall(insert_crashkernel_resources); #endif int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, _ Patches currently in -mm which might be from chenhuacai(a)loongson.cn are

1 year, 1 month

1
0
0 0

FAILED: patch "[PATCH] nfsd: drop the nfsd_put helper" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 64e6304169f1e1f078e7f0798033f80a7fb0ea46 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024011244-clavicle-disfigure-47f6@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 64e6304169f1 ("nfsd: drop the nfsd_put helper") 2a501f55cd64 ("nfsd: call nfsd_last_thread() before final nfsd_put()") 9f28a971ee9f ("nfsd: separate nfsd_last_thread() from nfsd_put()") c034203b6a9d ("nfsd: fix double fget() bug in __write_ports_addfd()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 64e6304169f1e1f078e7f0798033f80a7fb0ea46 Mon Sep 17 00:00:00 2001 From: Jeff Layton <jlayton(a)kernel.org> Date: Wed, 3 Jan 2024 08:36:52 -0500 Subject: [PATCH] nfsd: drop the nfsd_put helper It's not safe to call nfsd_put once nfsd_last_thread has been called, as that function will zero out the nn->nfsd_serv pointer. Drop the nfsd_put helper altogether and open-code the svc_put in its callers instead. That allows us to not be reliant on the value of that pointer when handling an error. Fixes: 2a501f55cd64 ("nfsd: call nfsd_last_thread() before final nfsd_put()") Reported-by: Zhi Li <yieli(a)redhat.com> Cc: NeilBrown <neilb(a)suse.de> Signed-off-by: Jeffrey Layton <jlayton(a)redhat.com> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 05b55db33424..25b5863bf3c8 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -693,6 +693,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) @@ -703,15 +704,15 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + serv = nn->nfsd_serv; + err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + if (err < 0 && !serv->sv_nrthreads && !nn->keep_active) nfsd_last_thread(net); - else if (err >= 0 && - !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return err; } @@ -725,6 +726,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; @@ -737,32 +739,33 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err != 0) return err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + serv = nn->nfsd_serv; + err = svc_xprt_create(serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + err = svc_xprt_create(serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return 0; out_close: - xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + if (!serv->sv_nrthreads && !nn->keep_active) nfsd_last_thread(net); - nfsd_put(net); + svc_put(serv); return err; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 3286ffacbc56..9ed0e08d16c2 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -113,13 +113,6 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -static inline void nfsd_put(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - svc_put(nn->nfsd_serv); -} - bool i_am_nfsd(void); struct nfsdfs_client {

1 year, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2024