- Linux-stable-mirror - lists.linaro.org

[PATCH 7u 02/15] resizable namespace.c hashes

by luanshi

From: Al Viro <viro(a)zeniv.linux.org.uk> commit 0818bf27c05b2de56c5b2bd08cfae2a939bd5f52 upstream * switch allocation to alloc_large_system_hash() * make sizes overridable by boot parameters (mhash_entries=, mphash_entries=) * switch mountpoint_hashtable from list_head to hlist_head Cc: stable(a)vger.kernel.org Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: luanshi <zhangliguang(a)linux.alibaba.com> --- 7u/fs/mount.h | 2 +- 7u/fs/namespace.c | 85 +++++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 64 insertions(+), 23 deletions(-) diff --git a/7u/fs/mount.h b/7u/fs/mount.h index 7758dd4..75d5615 100644 --- a/7u/fs/mount.h +++ b/7u/fs/mount.h @@ -19,7 +19,7 @@ struct mnt_pcp { }; struct mountpoint { - struct list_head m_hash; + struct hlist_node m_hash; struct dentry *m_dentry; int m_count; }; diff --git a/7u/fs/namespace.c b/7u/fs/namespace.c index 76ba0d7..6e1231b 100644 --- a/7u/fs/namespace.c +++ b/7u/fs/namespace.c @@ -23,11 +23,34 @@ #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> +#include <linux/bootmem.h> #include "pnode.h" #include "internal.h" -#define HASH_SHIFT 12 -#define HASH_SIZE (1UL << HASH_SHIFT) +static unsigned int m_hash_mask __read_mostly; +static unsigned int m_hash_shift __read_mostly; +static unsigned int mp_hash_mask __read_mostly; +static unsigned int mp_hash_shift __read_mostly; + +static __initdata unsigned long mhash_entries; +static int __init set_mhash_entries(char *str) +{ + if (!str) + return 0; + mhash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mhash_entries=", set_mhash_entries); + +static __initdata unsigned long mphash_entries; +static int __init set_mphash_entries(char *str) +{ + if (!str) + return 0; + mphash_entries = simple_strtoul(str, &str, 0); + return 1; +} +__setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); @@ -36,8 +59,8 @@ static DEFINE_SPINLOCK(mnt_id_lock); static int mnt_id_start = 0; static int mnt_group_start = 1; -static struct list_head mount_hashtable[HASH_SIZE]; -static struct list_head mountpoint_hashtable[HASH_SIZE]; +static struct list_head *mount_hashtable __read_mostly; +static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; @@ -55,12 +78,19 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ DEFINE_BRLOCK(vfsmount_lock); -static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) +static inline struct list_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> HASH_SHIFT); - return tmp & (HASH_SIZE - 1); + tmp = tmp + (tmp >> m_hash_shift); + return &mount_hashtable[tmp & m_hash_mask]; +} + +static inline struct hlist_head *mp_hash(struct dentry *dentry) +{ + unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); + tmp = tmp + (tmp >> mp_hash_shift); + return &mountpoint_hashtable[tmp & mp_hash_mask]; } #define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16) @@ -555,7 +585,7 @@ static void free_vfsmnt(struct mount *mnt) */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); + struct list_head *head = m_hash(mnt, dentry); struct mount *p; list_for_each_entry(p, head, mnt_hash) @@ -570,7 +600,7 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) */ struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) { - struct list_head *head = mount_hashtable + hash(mnt, dentry); + struct list_head *head = m_hash(mnt, dentry); struct mount *p; list_for_each_entry_reverse(p, head, mnt_hash) @@ -613,11 +643,11 @@ struct vfsmount *lookup_mnt(struct path *path) static struct mountpoint *new_mountpoint(struct dentry *dentry) { - struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry); + struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; int ret; - list_for_each_entry(mp, chain, m_hash) { + hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) @@ -639,7 +669,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry) mp->m_dentry = dentry; mp->m_count = 1; - list_add(&mp->m_hash, chain); + hlist_add_head(&mp->m_hash, chain); return mp; } @@ -650,7 +680,7 @@ static void put_mountpoint(struct mountpoint *mp) spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); - list_del(&mp->m_hash); + hlist_del(&mp->m_hash); kfree(mp); } } @@ -719,8 +749,7 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mp->m_dentry)); + list_add_tail(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } @@ -742,8 +771,8 @@ static void commit_tree(struct mount *mnt) list_splice(&head, n->list.prev); - list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); touch_mnt_namespace(n); } @@ -2792,12 +2821,24 @@ void __init mnt_init(void) mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE); - - for (u = 0; u < HASH_SIZE; u++) + mount_hashtable = alloc_large_system_hash("Mount-cache", + sizeof(struct list_head), + mhash_entries, 19, + 0, + &m_hash_shift, &m_hash_mask, 0, 0); + mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", + sizeof(struct hlist_head), + mphash_entries, 19, + 0, + &mp_hash_shift, &mp_hash_mask, 0, 0); + + if (!mount_hashtable || !mountpoint_hashtable) + panic("Failed to allocate mount hash table\n"); + + for (u = 0; u <= m_hash_mask; u++) INIT_LIST_HEAD(&mount_hashtable[u]); - for (u = 0; u < HASH_SIZE; u++) - INIT_LIST_HEAD(&mountpoint_hashtable[u]); + for (u = 0; u <= mp_hash_mask; u++) + INIT_HLIST_HEAD(&mountpoint_hashtable[u]); br_lock_init(&vfsmount_lock); -- 1.8.3.1

5 years, 8 months

1
0
0 0

[PATCH] MIPS: elf_hwcap: Export microMIPS and vz

by Jiaxun Yang

After further discussion with userland library develpoer, we addressed another two ASEs that can be used runtimely in programs. Export them in hwcap as well to benefit userspace programs. Signed-off-by: Jiaxun Yang <jiaxun.yang(a)flygoat.com> Cc: <stable(a)vger.kernel.org> # 4.4+ --- arch/mips/include/uapi/asm/hwcap.h | 2 ++ arch/mips/kernel/cpu-probe.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/uapi/asm/hwcap.h b/arch/mips/include/uapi/asm/hwcap.h index 1ade1daa4921..e1a9bac62149 100644 --- a/arch/mips/include/uapi/asm/hwcap.h +++ b/arch/mips/include/uapi/asm/hwcap.h @@ -17,5 +17,7 @@ #define HWCAP_LOONGSON_MMI (1 << 11) #define HWCAP_LOONGSON_EXT (1 << 12) #define HWCAP_LOONGSON_EXT2 (1 << 13) +#define HWCAP_MIPS_MICROMIPS (1 << 14) +#define HWCAP_MIPS_VZ (1 << 15) #endif /* _UAPI_ASM_HWCAP_H */ diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index f521cbf934e7..11e853d88aae 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -2213,8 +2213,13 @@ void cpu_probe(void) if (cpu_has_loongson_ext2) elf_hwcap |= HWCAP_LOONGSON_EXT2; - if (cpu_has_vz) + if (cpu_has_mmips) + elf_hwcap |= HWCAP_MIPS_MICROMIPS; + + if (cpu_has_vz) { + elf_hwcap |= HWCAP_MIPS_VZ; cpu_probe_vz(c); + } cpu_probe_vmbits(c); -- 2.23.0

5 years, 8 months

3
3
0 0

[PATCH] MIPS: tlbex: Fix build_restore_pagemask KScratch restore

by Paul Burton

build_restore_pagemask() will restore the value of register $1/$at when its restore_scratch argument is non-zero, and aims to do so by filling a branch delay slot. Commit 0b24cae4d535 ("MIPS: Add missing EHB in mtc0 -> mfc0 sequence.") added an EHB instruction (Execution Hazard Barrier) prior to restoring $1 from a KScratch register, in order to resolve a hazard that can result in stale values of the KScratch register being observed. In particular, P-class CPUs from MIPS with out of order execution pipelines such as the P5600 & P6600 are affected. Unfortunately this EHB instruction was inserted in the branch delay slot causing the MFC0 instruction which performs the restoration to no longer execute along with the branch. The result is that the $1 register isn't actually restored, ie. the TLB refill exception handler clobbers it - which is exactly the problem the EHB is meant to avoid for the P-class CPUs. Similarly build_get_pgd_vmalloc() will restore the value of $1/$at when its mode argument equals refill_scratch, and suffers from the same problem. Fix this by in both cases moving the EHB earlier in the emitted code. There's no reason it needs to immediately precede the MFC0 - it simply needs to be between the MTC0 & MFC0. This bug only affects Cavium Octeon systems which use build_fast_tlb_refill_handler(). Signed-off-by: Paul Burton <paulburton(a)kernel.org> Fixes: 0b24cae4d535 ("MIPS: Add missing EHB in mtc0 -> mfc0 sequence.") Cc: Dmitry Korotin <dkorotin(a)wavecomp.com> Cc: stable(a)vger.kernel.org # v3.15+ --- arch/mips/mm/tlbex.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index e01cb33bfa1a..41bb91f05688 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -653,6 +653,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, int restore_scratch) { if (restore_scratch) { + /* + * Ensure the MFC0 below observes the value written to the + * KScratch register by the prior MTC0. + */ + if (scratch_reg >= 0) + uasm_i_ehb(p); + /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16); @@ -667,12 +674,10 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, uasm_i_mtc0(p, 0, C0_PAGEMASK); uasm_il_b(p, r, lid); } - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { @@ -921,6 +926,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } if (mode != not_refill && check_for_high_segbits) { uasm_l_large_segbits_fault(l, *p); + + if (mode == refill_scratch && scratch_reg >= 0) + uasm_i_ehb(p); + /* * We get here if we are an xsseg address, or if we are * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary. @@ -939,12 +948,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, uasm_i_jr(p, ptr); if (mode == refill_scratch) { - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { uasm_i_nop(p); } -- 2.23.0

5 years, 8 months

1
1
0 0

[PATCH] opp: of: drop incorrect lockdep_assert_held()

by Viresh Kumar

_find_opp_of_np() doesn't traverse the list of OPP tables but instead just the entries within an OPP table and so only requires to lock the OPP table itself. The lockdep_assert_held() was added there by mistake and isn't really required. Fixes: 5d6d106fa455 ("OPP: Populate required opp tables from "required-opps" property") Cc: v5.0+ <stable(a)vger.kernel.org> # v5.0+ Reported-by: Niklas Cassel <niklas.cassel(a)linaro.org> Signed-off-by: Viresh Kumar <viresh.kumar(a)linaro.org> --- drivers/opp/of.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 1813f5ad5fa2..6dc41faf74b5 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -77,8 +77,6 @@ static struct dev_pm_opp *_find_opp_of_np(struct opp_table *opp_table, { struct dev_pm_opp *opp; - lockdep_assert_held(&opp_table_lock); - mutex_lock(&opp_table->lock); list_for_each_entry(opp, &opp_table->opp_list, node) { -- 2.21.0.rc0.269.g1a574e7a288b

5 years, 8 months

2
3
0 0

[v2 PATCH] mm: thp: handle page cache THP correctly in PageTransCompoundMap

by Yang Shi

We have usecase to use tmpfs as QEMU memory backend and we would like to take the advantage of THP as well. But, our test shows the EPT is not PMD mapped even though the underlying THP are PMD mapped on host. The number showed by /sys/kernel/debug/kvm/largepage is much less than the number of PMD mapped shmem pages as the below: 7f2778200000-7f2878200000 rw-s 00000000 00:14 262232 /dev/shm/qemu_back_mem.mem.Hz2hSf (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 579584 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 12 And some benchmarks do worse than with anonymous THPs. By digging into the code we figured out that commit 127393fbe597 ("mm: thp: kvm: fix memory corruption in KVM with THP enabled") checks if there is a single PTE mapping on the page for anonymous THP when setting up EPT map. But, the _mapcount < 0 check doesn't fit to page cache THP since every subpage of page cache THP would get _mapcount inc'ed once it is PMD mapped, so PageTransCompoundMap() always returns false for page cache THP. This would prevent KVM from setting up PMD mapped EPT entry. So we need handle page cache THP correctly. However, when page cache THP's PMD gets split, kernel just remove the map instead of setting up PTE map like what anonymous THP does. Before KVM calls get_user_pages() the subpages may get PTE mapped even though it is still a THP since the page cache THP may be mapped by other processes at the mean time. Checking its _mapcount and whether the THP has PTE mapped or not. Although this may report some false negative cases (PTE mapped by other processes), it looks not trivial to make this accurate. With this fix /sys/kernel/debug/kvm/largepage would show reasonable pages are PMD mapped by EPT as the below: 7fbeaee00000-7fbfaee00000 rw-s 00000000 00:14 275464 /dev/shm/qemu_back_mem.mem.SKUvat (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 557056 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 271 And the benchmarks are as same as anonymous THPs. Signed-off-by: Yang Shi <yang.shi(a)linux.alibaba.com> Reported-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Tested-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Suggested-by: Hugh Dickins <hughd(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: <stable(a)vger.kernel.org> 4.8+ --- v2: Adopted the suggestion from Hugh to use _mapcount and compound_mapcount. But I just open coding compound_mapcount to avoid duplicating the definition of compound_mapcount_ptr in two different files. Since "compound_mapcount" looks self-explained so I'm supposed the open coding would not affect the readability. include/linux/page-flags.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f91cb88..954a877 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -622,12 +622,30 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount ot filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + int map_count; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + map_count = atomic_read(&page->_mapcount); + /* File THP is PMD mapped and not double mapped */ + return map_count >= 0 && + map_count == atomic_read(&head[1].compound_mapcount); } /* -- 1.8.3.1

5 years, 8 months

3
7
0 0

[PATCH] of: reserved_mem: add missing of_node_put() for proper ref-counting

by Chris Goldsworthy

Commit d698a388146c ("of: reserved-memory: ignore disabled memory-region nodes") added an early return in of_reserved_mem_device_init_by_idx(), but didn't call of_node_put() on a device_node whose ref-count was incremented in the call to of_parse_phandle() preceding the early exit. Fixes: d698a388146c ("of: reserved-memory: ignore disabled memory-region nodes") Signed-off-by: Chris Goldsworthy <cgoldswo(a)codeaurora.org> To: Rob Herring <robh+dt(a)kernel.org> Cc: devicetree(a)vger.kernel.org Cc: stable(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-arm-msm(a)vger.kernel.org Cc: linux-arm-kernel(a)lists.infradead.org --- drivers/of/of_reserved_mem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 7989703..6bd610e 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -324,8 +324,10 @@ int of_reserved_mem_device_init_by_idx(struct device *dev, if (!target) return -ENODEV; - if (!of_device_is_available(target)) + if (!of_device_is_available(target)) { + of_node_put(target); return 0; + } rmem = __find_rmem(target); of_node_put(target); -- The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project

5 years, 8 months

4
3
0 0

[v3 PATCH] mm: thp: handle page cache THP correctly in PageTransCompoundMap

by Yang Shi

We have usecase to use tmpfs as QEMU memory backend and we would like to take the advantage of THP as well. But, our test shows the EPT is not PMD mapped even though the underlying THP are PMD mapped on host. The number showed by /sys/kernel/debug/kvm/largepage is much less than the number of PMD mapped shmem pages as the below: 7f2778200000-7f2878200000 rw-s 00000000 00:14 262232 /dev/shm/qemu_back_mem.mem.Hz2hSf (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 579584 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 12 And some benchmarks do worse than with anonymous THPs. By digging into the code we figured out that commit 127393fbe597 ("mm: thp: kvm: fix memory corruption in KVM with THP enabled") checks if there is a single PTE mapping on the page for anonymous THP when setting up EPT map. But, the _mapcount < 0 check doesn't fit to page cache THP since every subpage of page cache THP would get _mapcount inc'ed once it is PMD mapped, so PageTransCompoundMap() always returns false for page cache THP. This would prevent KVM from setting up PMD mapped EPT entry. So we need handle page cache THP correctly. However, when page cache THP's PMD gets split, kernel just remove the map instead of setting up PTE map like what anonymous THP does. Before KVM calls get_user_pages() the subpages may get PTE mapped even though it is still a THP since the page cache THP may be mapped by other processes at the mean time. Checking its _mapcount and whether the THP has PTE mapped or not. Although this may report some false negative cases (PTE mapped by other processes), it looks not trivial to make this accurate. With this fix /sys/kernel/debug/kvm/largepage would show reasonable pages are PMD mapped by EPT as the below: 7fbeaee00000-7fbfaee00000 rw-s 00000000 00:14 275464 /dev/shm/qemu_back_mem.mem.SKUvat (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 557056 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 271 And the benchmarks are as same as anonymous THPs. Signed-off-by: Yang Shi <yang.shi(a)linux.alibaba.com> Reported-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Tested-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Suggested-by: Hugh Dickins <hughd(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> 4.8+ --- v3: Took the suggestion from Willy to move the definition of compound_mapcount_ptr to mm_types.h in order to use it instead of open coding it. v2: Adopted the suggestion from Hugh to use _mapcount and compound_mapcount. But I just open coding compound_mapcount to avoid duplicating the definition of compound_mapcount_ptr in two different files. Since "compound_mapcount" looks self-explained so I'm supposed the open coding would not affect the readability. include/linux/mm.h | 5 ----- include/linux/mm_types.h | 5 +++++ include/linux/page-flags.h | 22 ++++++++++++++++++++-- 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index cc29227..a2adf95 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2222fa7..270aa8f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -221,6 +221,11 @@ struct page { #endif } _struct_page_alignment; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f91cb88..e0f2d53 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -622,12 +622,30 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount ot filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + int map_count; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + map_count = atomic_read(&page->_mapcount); + /* File THP is PMD mapped and not double mapped */ + return map_count >= 0 && + map_count == atomic_read(compound_mapcount_ptr(head)); } /* -- 1.8.3.1

5 years, 8 months

1
0
0 0

[RESEND PATCH] ASoC: rsnd: dma: fix SSI9 4/5/6/7 busif dma address

by Eugeniu Rosca

From: Jiada Wang <jiada_wang(a)mentor.com> Currently each SSI unit's busif dma address is calculated by following calculation formula: 0xec540000 + 0x1000 * id + busif / 4 * 0xA000 + busif % 4 * 0x400 But according to R-Car3 HW manual 41.1.4 Register Configuration, ssi9 4/5/6/7 busif data register address (SSI9_4_BUSIF/SSI9_5_BUSIF/SSI9_6_BUSIF/SSI9_7_BUSIF) are out of this rule. This patch updates the calculation formula to correct ssi9 4/5/6/7 busif data register address. Fixes: 5e45a6fab3b9 ("ASoc: rsnd: dma: Calculate dma address with consider of BUSIF") Signed-off-by: Jiada Wang <jiada_wang(a)mentor.com> Signed-off-by: Timo Wischer <twischer(a)de.adit-jv.com> [erosca: minor improvements in commit description] Cc: Andrew Gabbasov <andrew_gabbasov(a)mentor.com> Cc: stable(a)vger.kernel.org # v4.20+ Signed-off-by: Eugeniu Rosca <erosca(a)de.adit-jv.com> --- Originally submitted as https://patchwork.kernel.org/patch/10825513/ ("ASoC: rsnd: dma: fix SSI9 4/5/6/7 busif dma address") --- sound/soc/sh/rcar/dma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index 0324a5c39619..28f65eba2bb4 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -508,10 +508,10 @@ static struct rsnd_mod_ops rsnd_dmapp_ops = { #define RDMA_SSI_I_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0x8) #define RDMA_SSI_O_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0xc) -#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_N(addr, i, j) RDMA_SSIU_I_N(addr, i, j) -#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_P(addr, i, j) RDMA_SSIU_I_P(addr, i, j) #define RDMA_SRC_I_N(addr, i) (addr ##_reg - 0x00500000 + (0x400 * i)) -- 2.23.0

5 years, 8 months

3
3
0 0

[PATCH v4 2/2] sched/topology: Allow sched_asym_cpucapacity to be disabled

by Valentin Schneider

While the static key is correctly initialized as being disabled, it will remain forever enabled once turned on. This means that if we start with an asymmetric system and hotplug out enough CPUs to end up with an SMP system, the static key will remain set - which is obviously wrong. We should detect this and turn off things like misfit migration and capacity aware wakeups. As Quentin pointed out, having separate root domains makes this slightly trickier. We could have exclusive cpusets that create an SMP island - IOW, the domains within this root domain will not see any asymmetry. This means we can't just disable the key on domain destruction, we need to count how many asymmetric root domains we have. Consider the following example using Juno r0 which is 2+4 big.LITTLE, where two identical cpusets are created: they both span both big and LITTLE CPUs: asym0 asym1 [ ][ ] L L B L L B cgcreate -g cpuset:asym0 cgset -r cpuset.cpus=0,1,3 asym0 cgset -r cpuset.mems=0 asym0 cgset -r cpuset.cpu_exclusive=1 asym0 cgcreate -g cpuset:asym1 cgset -r cpuset.cpus=2,4,5 asym1 cgset -r cpuset.mems=0 asym1 cgset -r cpuset.cpu_exclusive=1 asym1 cgset -r cpuset.sched_load_balance=0 . (the CPU numbering may look odd because on the Juno LITTLEs are CPUs 0,3-5 and bigs are CPUs 1-2) If we make one of those SMP (IOW remove asymmetry) by e.g. hotplugging its big core, we would end up with an SMP cpuset and an asymmetric cpuset - the static key must remain set, because we still have one asymmetric root domain. With the above example, this could be done with: echo 0 > /sys/devices/system/cpu/cpu2/online Which would result in: asym0 asym1 [ ][ ] L L B L L When both SMP and asymmetric cpusets are present, all CPUs will observe sched_asym_cpucapacity being set (it is system-wide), but not all CPUs observe asymmetry in their sched domain hierarchy: per_cpu(sd_asym_cpucapacity, <any CPU in asym0>) == <some SD at DIE level> per_cpu(sd_asym_cpucapacity, <any CPU in asym1>) == NULL Change the simple key enablement to an increment, and decrement the key counter when destroying domains that cover asymmetric CPUs. Cc: <stable(a)vger.kernel.org> Fixes: df054e8445a4 ("sched/topology: Add static_key for asymmetric CPU capacity optimizations") Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Signed-off-by: Valentin Schneider <valentin.schneider(a)arm.com> --- kernel/sched/topology.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 2e7af755e17a..6ec1e595b1d4 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2026,7 +2026,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att rcu_read_unlock(); if (has_asym) - static_branch_enable_cpuslocked(&sched_asym_cpucapacity); + static_branch_inc_cpuslocked(&sched_asym_cpucapacity); if (rq && sched_debug_enabled) { pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", @@ -2121,9 +2121,12 @@ int sched_init_domains(const struct cpumask *cpu_map) */ static void detach_destroy_domains(const struct cpumask *cpu_map) { + unsigned int cpu = cpumask_any(cpu_map); int i; + if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu))) + static_branch_dec_cpuslocked(&sched_asym_cpucapacity); + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); -- 2.22.0

5 years, 8 months

1
0
0 0

[PATCH 1/2] perf/x86/amd/ibs: Fix reading of the IBS OpData register and thus precise RIP validity

by Kim Phillips

The loop that reads all the IBS MSRs into *buf stopped one MSR short of reading the IbsOpData register, which contains the RipInvalid status bit. Fix the offset_max assignment so the MSR gets read, so the RIP invalid evaluation is based on what the IBS h/w output, instead of what was left in memory. Signed-off-by: Kim Phillips <kim.phillips(a)amd.com> Fixes: d47e8238cd76 ("perf/x86-ibs: Take instruction pointer from ibs sample") Cc: stable(a)vger.kernel.org Cc: Stephane Eranian <eranian(a)google.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Arnaldo Carvalho de Melo <acme(a)kernel.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Borislav Petkov <bp(a)alien8.de> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: x86(a)kernel.org Cc: linux-kernel(a)vger.kernel.org --- arch/x86/events/amd/ibs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 5b35b7ea5d72..98ba21a588a1 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -614,7 +614,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { -- 2.23.0

5 years, 8 months

1
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror