diff options
Diffstat (limited to 'include/linux')
91 files changed, 1568 insertions, 564 deletions
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index dc7ed2f46886..2b90c48a6a87 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -85,8 +85,10 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value); struct amd_iommu *get_amd_iommu(unsigned int idx); -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void); +#ifdef CONFIG_KVM_AMD_SEV +int amd_iommu_snp_disable(void); +#else +static inline int amd_iommu_snp_disable(void) { return 0; } #endif #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/include/linux/async.h b/include/linux/async.h index 33c9ff4afb49..19b778d08600 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -120,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie); extern void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain); extern bool current_is_async(void); +extern void async_init(void); #endif diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 5e95faa959c4..956bcba5dbf2 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2005,6 +2005,7 @@ raw_atomic_xchg_relaxed(atomic_t *v, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere. * @@ -2033,6 +2034,7 @@ raw_atomic_cmpxchg(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere. * @@ -2061,6 +2063,7 @@ raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere. * @@ -2088,6 +2091,7 @@ raw_atomic_cmpxchg_release(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere. * @@ -2112,7 +2116,8 @@ raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere. * @@ -2145,7 +2150,8 @@ raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere. * @@ -2178,7 +2184,8 @@ raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere. * @@ -2210,7 +2217,8 @@ raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere. * @@ -2403,6 +2411,7 @@ raw_atomic_add_negative_relaxed(int i, atomic_t *v) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere. * @@ -2432,6 +2441,7 @@ raw_atomic_fetch_add_unless(atomic_t *v, int a, int u) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere. * @@ -2452,6 +2462,7 @@ raw_atomic_add_unless(atomic_t *v, int a, int u) * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere. * @@ -2472,6 +2483,7 @@ raw_atomic_inc_not_zero(atomic_t *v) * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere. * @@ -2499,6 +2511,7 @@ raw_atomic_inc_unless_negative(atomic_t *v) * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere. * @@ -2526,6 +2539,7 @@ raw_atomic_dec_unless_positive(atomic_t *v) * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere. * @@ -4117,6 +4131,7 @@ raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere. * @@ -4145,6 +4160,7 @@ raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere. * @@ -4173,6 +4189,7 @@ raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere. * @@ -4200,6 +4217,7 @@ raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere. * @@ -4224,7 +4242,8 @@ raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere. * @@ -4257,7 +4276,8 @@ raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere. * @@ -4290,7 +4310,8 @@ raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere. * @@ -4322,7 +4343,8 @@ raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere. * @@ -4515,6 +4537,7 @@ raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere. * @@ -4544,6 +4567,7 @@ raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere. * @@ -4564,6 +4588,7 @@ raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere. * @@ -4584,6 +4609,7 @@ raw_atomic64_inc_not_zero(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere. * @@ -4611,6 +4637,7 @@ raw_atomic64_inc_unless_negative(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere. * @@ -4638,6 +4665,7 @@ raw_atomic64_dec_unless_positive(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere. * @@ -4662,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// eec048affea735b8464f58e6d96992101f8f85f1 +// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 54d7bbe0aeaa..debd487fe971 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1182,6 +1182,7 @@ atomic_xchg_relaxed(atomic_t *v, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there. * @@ -1202,6 +1203,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there. * @@ -1221,6 +1223,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there. * @@ -1241,6 +1244,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there. * @@ -1260,7 +1264,8 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there. * @@ -1282,7 +1287,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there. * @@ -1303,7 +1309,8 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there. * @@ -1325,7 +1332,8 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there. * @@ -1475,6 +1483,7 @@ atomic_add_negative_relaxed(int i, atomic_t *v) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there. * @@ -1495,6 +1504,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_add_unless() there. * @@ -1513,6 +1523,7 @@ atomic_add_unless(atomic_t *v, int a, int u) * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there. * @@ -1531,6 +1542,7 @@ atomic_inc_not_zero(atomic_t *v) * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there. * @@ -1549,6 +1561,7 @@ atomic_inc_unless_negative(atomic_t *v) * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there. * @@ -1567,6 +1580,7 @@ atomic_dec_unless_positive(atomic_t *v) * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there. * @@ -2746,6 +2760,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there. * @@ -2766,6 +2781,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there. * @@ -2785,6 +2801,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there. * @@ -2805,6 +2822,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there. * @@ -2824,7 +2842,8 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there. * @@ -2846,7 +2865,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there. * @@ -2867,7 +2887,8 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there. * @@ -2889,7 +2910,8 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there. * @@ -3039,6 +3061,7 @@ atomic64_add_negative_relaxed(s64 i, atomic64_t *v) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there. * @@ -3059,6 +3082,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there. * @@ -3077,6 +3101,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there. * @@ -3095,6 +3120,7 @@ atomic64_inc_not_zero(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there. * @@ -3113,6 +3139,7 @@ atomic64_inc_unless_negative(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there. * @@ -3131,6 +3158,7 @@ atomic64_dec_unless_positive(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there. * @@ -4310,6 +4338,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there. * @@ -4330,6 +4359,7 @@ atomic_long_cmpxchg(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there. * @@ -4349,6 +4379,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there. * @@ -4369,6 +4400,7 @@ atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there. * @@ -4388,7 +4420,8 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there. * @@ -4410,7 +4443,8 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there. * @@ -4431,7 +4465,8 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there. * @@ -4453,7 +4488,8 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there. * @@ -4603,6 +4639,7 @@ atomic_long_add_negative_relaxed(long i, atomic_long_t *v) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there. * @@ -4623,6 +4660,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there. * @@ -4641,6 +4679,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u) * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there. * @@ -4659,6 +4698,7 @@ atomic_long_inc_not_zero(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there. * @@ -4677,6 +4717,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there. * @@ -4695,6 +4736,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there. * @@ -5008,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 2cc4bc990fef44d3836ec108f11b610f3f438184 +// ce5b65e0f1f8a276268b667194581d24bed219d4 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index c82947170ddc..3ef844b3ab8a 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1352,6 +1352,7 @@ raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere. * @@ -1374,6 +1375,7 @@ raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere. * @@ -1396,6 +1398,7 @@ raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere. * @@ -1418,6 +1421,7 @@ raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere. * @@ -1440,7 +1444,8 @@ raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere. * @@ -1463,7 +1468,8 @@ raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere. * @@ -1486,7 +1492,8 @@ raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere. * @@ -1509,7 +1516,8 @@ raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere. * @@ -1677,6 +1685,7 @@ raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere. * @@ -1699,6 +1708,7 @@ raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere. * @@ -1719,6 +1729,7 @@ raw_atomic_long_add_unless(atomic_long_t *v, long a, long u) * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere. * @@ -1739,6 +1750,7 @@ raw_atomic_long_inc_not_zero(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere. * @@ -1759,6 +1771,7 @@ raw_atomic_long_inc_unless_negative(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere. * @@ -1779,6 +1792,7 @@ raw_atomic_long_dec_unless_positive(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere. * @@ -1795,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 4ef23f98c73cff96d239896175fd26b10b88899e +// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 1a97277f99b1..8e7af9a03b41 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); -void wb_wakeup_delayed(struct bdi_writeback *wb); void wb_wait_for_completion(struct wb_completion *done); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 99451431e4d6..df24c8fb1009 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include <linux/align.h> #include <linux/bitops.h> +#include <linux/cleanup.h> #include <linux/errno.h> #include <linux/find.h> #include <linux/limits.h> @@ -127,6 +128,8 @@ unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node); void bitmap_free(const unsigned long *bitmap); +DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T)) + /* Managed variants of the above. */ unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags); diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 378b2459efe2..e253e7bd0d17 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -20,6 +20,7 @@ struct blk_integrity_iter { unsigned int data_size; unsigned short interval; unsigned char tuple_size; + unsigned char pi_offset; const char *disk_name; }; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7a8150a5f051..d3d8fd8e229b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -8,6 +8,7 @@ #include <linux/scatterlist.h> #include <linux/prefetch.h> #include <linux/srcu.h> +#include <linux/rw_hint.h> struct blk_mq_tags; struct blk_flush_queue; @@ -135,6 +136,7 @@ struct request { struct blk_crypto_keyslot *crypt_keyslot; #endif + enum rw_hint write_hint; unsigned short ioprio; enum mq_rq_state state; @@ -682,17 +684,19 @@ enum { #define BLK_MQ_NO_HCTX_IDX (-1U) -struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); -#define blk_mq_alloc_disk(set, queuedata) \ +#define blk_mq_alloc_disk(set, lim, queuedata) \ ({ \ static struct lock_class_key __key; \ \ - __blk_mq_alloc_disk(set, queuedata, &__key); \ + __blk_mq_alloc_disk(set, lim, queuedata, &__key); \ }) struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass); -struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); +struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, + struct queue_limits *lim, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_destroy_queue(struct request_queue *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f288c94374b3..cb1526ec44b5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -10,6 +10,7 @@ #include <linux/bvec.h> #include <linux/device.h> #include <linux/ktime.h> +#include <linux/rw_hint.h> struct bio_set; struct bio; @@ -206,52 +207,10 @@ static inline bool blk_path_error(blk_status_t error) return true; } -/* - * From most significant bit: - * 1 bit: reserved for other usage, see below - * 12 bits: original size of bio - * 51 bits: issue time of bio - */ -#define BIO_ISSUE_RES_BITS 1 -#define BIO_ISSUE_SIZE_BITS 12 -#define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS) -#define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS) -#define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1) -#define BIO_ISSUE_SIZE_MASK \ - (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT) -#define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1)) - -/* Reserved bit for blk-throtl */ -#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63) - struct bio_issue { u64 value; }; -static inline u64 __bio_issue_time(u64 time) -{ - return time & BIO_ISSUE_TIME_MASK; -} - -static inline u64 bio_issue_time(struct bio_issue *issue) -{ - return __bio_issue_time(issue->value); -} - -static inline sector_t bio_issue_size(struct bio_issue *issue) -{ - return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT); -} - -static inline void bio_issue_init(struct bio_issue *issue, - sector_t size) -{ - size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1; - issue->value = ((issue->value & BIO_ISSUE_RES_MASK) | - (ktime_get_ns() & BIO_ISSUE_TIME_MASK) | - ((u64)size << BIO_ISSUE_SIZE_SHIFT)); -} - typedef __u32 __bitwise blk_opf_t; typedef unsigned int blk_qc_t; @@ -269,6 +228,7 @@ struct bio { */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; + enum rw_hint bi_write_hint; blk_status_t bi_status; atomic_t __bi_remaining; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99e4f5e72213..f9b87c39cab0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include <linux/sbitmap.h> #include <linux/uuid.h> #include <linux/xarray.h> +#include <linux/file.h> struct module; struct request_queue; @@ -42,7 +43,7 @@ struct blk_crypto_profile; extern const struct device_type disk_type; extern const struct device_type part_type; -extern struct class block_class; +extern const struct class block_class; /* * Maximum number of blkcg policies allowed to be registered concurrently. @@ -108,6 +109,7 @@ struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; unsigned char tuple_size; + unsigned char pi_offset; unsigned char interval_exp; unsigned char tag_size; }; @@ -189,8 +191,6 @@ struct gendisk { * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; - unsigned int max_open_zones; - unsigned int max_active_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -292,6 +292,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; @@ -307,6 +308,8 @@ struct queue_limits { unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; bool zoned; + unsigned int max_open_zones; + unsigned int max_active_zones; /* * Drivers that set dma_alignment to less than 511 must be prepared to @@ -325,7 +328,7 @@ void disk_set_zoned(struct gendisk *disk); int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, - sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); + sector_t sectors, sector_t nr_sectors); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); @@ -473,6 +476,7 @@ struct request_queue { struct mutex sysfs_lock; struct mutex sysfs_dir_lock; + struct mutex limits_lock; /* * for reusing dead hctx instance in case of updating @@ -639,23 +643,23 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { - disk->max_open_zones = max_open_zones; + disk->queue->limits.max_open_zones = max_open_zones; } static inline void disk_set_max_active_zones(struct gendisk *disk, unsigned int max_active_zones) { - disk->max_active_zones = max_active_zones; + disk->queue->limits.max_active_zones = max_active_zones; } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { - return bdev->bd_disk->max_open_zones; + return bdev->bd_disk->queue->limits.max_open_zones; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { - return bdev->bd_disk->max_active_zones; + return bdev->bd_disk->queue->limits.max_active_zones; } #else /* CONFIG_BLK_DEV_ZONED */ @@ -763,22 +767,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); -struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); +struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node, + struct lock_class_key *lkclass); /** * blk_alloc_disk - allocate a gendisk structure + * @lim: queue limits to be used for this disk. * @node_id: numa node to allocate on * * Allocate and pre-initialize a gendisk structure for use with BIO based * drivers. * + * Returns an ERR_PTR on error, else the allocated disk. + * * Context: can sleep */ -#define blk_alloc_disk(node_id) \ +#define blk_alloc_disk(lim, node_id) \ ({ \ static struct lock_class_key __key; \ \ - __blk_alloc_disk(node_id, &__key); \ + __blk_alloc_disk(lim, node_id, &__key); \ }) int __register_blkdev(unsigned int major, const char *name, @@ -861,6 +869,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset, return chunk_sectors - (offset & (chunk_sectors - 1)); } +/** + * queue_limits_start_update - start an atomic update of queue limits + * @q: queue to update + * + * This functions starts an atomic update of the queue limits. It takes a lock + * to prevent other updates and returns a snapshot of the current limits that + * the caller can modify. The caller must call queue_limits_commit_update() + * to finish the update. + * + * Context: process context. The caller must have frozen the queue or ensured + * that there is outstanding I/O by other means. + */ +static inline struct queue_limits +queue_limits_start_update(struct request_queue *q) + __acquires(q->limits_lock) +{ + mutex_lock(&q->limits_lock); + return q->limits; +} +int queue_limits_commit_update(struct request_queue *q, + struct queue_limits *lim); +int queue_limits_set(struct request_queue *q, struct queue_limits *lim); + /* * Access functions for manipulating queue properties */ @@ -894,8 +925,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); -extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, - sector_t offset); +void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, + sector_t offset, const char *pfx); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); @@ -942,6 +973,7 @@ struct blk_plug { /* if ios_left is > 1, we can batch tag/rq allocations */ struct request *cached_rq; + u64 cur_ktime; unsigned short nr_ios; unsigned short rq_count; @@ -972,6 +1004,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) __blk_flush_plug(plug, async); } +/* + * tsk == current here + */ +static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + if (plug) + plug->cur_ktime = 0; + current->flags &= ~PF_BLOCK_TS; +} + int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ @@ -995,6 +1039,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } +static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +{ +} + static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; @@ -1474,26 +1522,20 @@ extern const struct blk_holder_ops fs_holder_ops; (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \ (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) -struct bdev_handle { - struct block_device *bdev; - void *holder; - blk_mode_t mode; -}; - -struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, +struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); -struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, +struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void bdev_release(struct bdev_handle *handle); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); struct block_device *I_BDEV(struct inode *inode); +struct block_device *file_bdev(struct file *bdev_file); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 555aae5448ae..bd1e361b351c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -83,7 +83,7 @@ struct bvec_iter { unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -} __packed; +} __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 1d42d4b17327..0ad8b550bb4b 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -291,7 +291,19 @@ static inline void timer_probe(void) {} #define TIMER_ACPI_DECLARE(name, table_id, fn) \ ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) -extern ulong max_cswd_read_retries; +static inline unsigned int clocksource_get_max_watchdog_retry(void) +{ + /* + * When system is in the boot phase or under heavy workload, there + * can be random big latencies during the clocksource/watchdog + * read, so allow retries to filter the noise latency. As the + * latency's frequency and maximum value goes up with the number of + * CPUs, scale the number of retries with the number of online + * CPUs. + */ + return (ilog2(num_online_cpus()) / 2) + 1; +} + void clocksource_verify_percpu(struct clocksource *cs); #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h index 16775d7d8f8d..a4fa3436940c 100644 --- a/include/linux/clocksource_ids.h +++ b/include/linux/clocksource_ids.h @@ -6,6 +6,9 @@ enum clocksource_ids { CSID_GENERIC = 0, CSID_ARM_ARCH_COUNTER, + CSID_X86_TSC_EARLY, + CSID_X86_TSC, + CSID_X86_KVM_CLK, CSID_MAX, }; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c1a963be7d28..75bd1692d2e3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -67,10 +67,9 @@ /* * GCC 'asm goto' with outputs miscompiles certain code sequences: * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 * - * Work it around via the same compiler barrier quirk that we used + * Work around it via the same compiler barrier quirk that we used * to use for the old 'asm goto' workaround. * * Also, always mark such 'asm goto' statements as volatile: all @@ -80,8 +79,10 @@ * * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND #define asm_goto_output(x...) \ do { asm volatile goto(x); asm (""); } while (0) +#endif #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 28566624f008..289810685fc5 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -95,11 +95,11 @@ #endif /* - * Optional: only supported since gcc >= 14 + * Optional: only supported since gcc >= 15 * Optional: only supported since clang >= 18 * * gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896 - * clang: https://reviews.llvm.org/D148381 + * clang: https://github.com/llvm/llvm-project/pull/76348 */ #if __has_attribute(__counted_by__) # define __counted_by(member) __attribute__((__counted_by__(member))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 663d8791c871..0caf354cb94b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -362,8 +362,15 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ #ifndef asm_goto_output -#define asm_goto_output(x...) asm goto(x) +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/include/linux/cpu.h b/include/linux/cpu.h index dcb89c987164..61a0ddf2bef6 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -112,7 +112,7 @@ void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); int bringup_hibernate_cpu(unsigned int sleep_cpu); -void bringup_nonboot_cpus(unsigned int setup_max_cpus); +void bringup_nonboot_cpus(unsigned int max_cpus); #else /* CONFIG_SMP */ #define cpuhp_tasks_frozen 0 diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 172d0a743e5d..35e78ddb2b37 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -184,6 +184,7 @@ enum cpuhp_state { CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_HRTIMERS_DYING, + CPUHP_AP_TICK_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, @@ -231,6 +232,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, CPUHP_AP_PERF_CSKY_ONLINE, + CPUHP_AP_TMIGR_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RANDOM_ONLINE, diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 875d12598bd2..0ce6ff0d9c9a 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -121,11 +121,6 @@ static inline int cpuset_do_page_mem_spread(void) return task_spread_page(current); } -static inline int cpuset_do_slab_mem_spread(void) -{ - return task_spread_slab(current); -} - extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); @@ -264,11 +259,6 @@ static inline int cpuset_do_page_mem_spread(void) return 0; } -static inline int cpuset_do_slab_mem_spread(void) -{ - return 0; -} - static inline bool current_cpuset_is_being_rebound(void) { return false; diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 91125eca4c8a..03fa6d50d46f 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -140,22 +140,4 @@ struct cxl_cper_event_rec { union cxl_event event; } __packed; -typedef void (*cxl_cper_callback)(enum cxl_event_type type, - struct cxl_cper_event_rec *rec); - -#ifdef CONFIG_ACPI_APEI_GHES -int cxl_cper_register_callback(cxl_cper_callback callback); -int cxl_cper_unregister_callback(cxl_cper_callback callback); -#else -static inline int cxl_cper_register_callback(cxl_cper_callback callback) -{ - return 0; -} - -static inline int cxl_cper_unregister_callback(cxl_cper_callback callback) -{ - return 0; -} -#endif - #endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 1666c387861f..bf53e3894aae 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -125,6 +125,11 @@ enum dentry_d_lock_class DENTRY_D_LOCK_NESTED }; +enum d_real_type { + D_REAL_DATA, + D_REAL_METADATA, +}; + struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); @@ -139,7 +144,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *); + struct dentry *(*d_real)(struct dentry *, enum d_real_type type); } ____cacheline_aligned; /* @@ -173,6 +178,7 @@ struct dentry_operations { #define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ #define DCACHE_CANT_MOUNT BIT(8) +#define DCACHE_GENOCIDE BIT(9) #define DCACHE_SHRINK_LIST BIT(10) #define DCACHE_OP_WEAK_REVALIDATE BIT(11) @@ -546,24 +552,23 @@ static inline struct inode *d_backing_inode(const struct dentry *upper) /** * d_real - Return the real dentry * @dentry: the dentry to query - * @inode: inode to select the dentry from multiple layers (can be NULL) + * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ -static inline struct dentry *d_real(struct dentry *dentry, - const struct inode *inode) +static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode); + return dentry->d_op->d_real(dentry, type); else return dentry; } /** - * d_real_inode - Return the real inode + * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. @@ -572,7 +577,7 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL)); + return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 772ab4d74d94..82b2195efaca 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -165,7 +165,7 @@ void dm_error(const char *message); struct dm_dev { struct block_device *bdev; - struct bdev_handle *bdev_handle; + struct file *bdev_file; struct dax_device *dax_dev; blk_mode_t mode; char name[16]; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 9cf896ea1d41..e37344f6a231 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -10,6 +10,8 @@ #include <uapi/linux/dpll.h> #include <linux/device.h> #include <linux/netlink.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> struct dpll_device; struct dpll_pin; @@ -120,15 +122,24 @@ struct dpll_pin_properties { }; #if IS_ENABLED(CONFIG_DPLL) -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void dpll_netdev_pin_clear(struct net_device *dev); + +size_t dpll_netdev_pin_handle_size(const struct net_device *dev); +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev); #else -static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +static inline void +dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { } +static inline void dpll_netdev_pin_clear(struct net_device *dev) { } + +static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev) { return 0; } -static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static inline int +dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev) { return 0; } diff --git a/include/linux/file.h b/include/linux/file.h index 6834a29338c4..169692cb1906 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -24,6 +24,8 @@ struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); +extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *, + const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); diff --git a/include/linux/filelock.h b/include/linux/filelock.h index 95e868e09e29..daee999d05f3 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -27,6 +27,7 @@ #define FILE_LOCK_DEFERRED 1 struct file_lock; +struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); @@ -39,14 +40,17 @@ struct lock_manager_operations { void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); - bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock *, int, struct list_head *); - void (*lm_setup)(struct file_lock *, void **); - bool (*lm_breaker_owns_lease)(struct file_lock *); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; +struct lease_manager_operations { + bool (*lm_break)(struct file_lease *); + int (*lm_change)(struct file_lease *, int, struct list_head *); + void (*lm_setup)(struct file_lease *, void **); + bool (*lm_breaker_owns_lease)(struct file_lease *); +}; + struct lock_manager { struct list_head list; /* @@ -85,31 +89,31 @@ bool opens_in_grace(struct net *); * * Obviously, the last two criteria only matter for POSIX locks. */ -struct file_lock { - struct file_lock *fl_blocker; /* The lock, that is blocking us */ - struct list_head fl_list; /* link into file_lock_context */ - struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_blocked_requests; /* list of requests with + +struct file_lock_core { + struct file_lock_core *flc_blocker; /* The lock that is blocking us */ + struct list_head flc_list; /* link into file_lock_context */ + struct hlist_node flc_link; /* node in global lists */ + struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ - struct list_head fl_blocked_member; /* node in + struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ - fl_owner_t fl_owner; - unsigned int fl_flags; - unsigned char fl_type; - unsigned int fl_pid; - int fl_link_cpu; /* what cpu's list is this on? */ - wait_queue_head_t fl_wait; - struct file *fl_file; + fl_owner_t flc_owner; + unsigned int flc_flags; + unsigned char flc_type; + pid_t flc_pid; + int flc_link_cpu; /* what cpu's list is this on? */ + wait_queue_head_t flc_wait; + struct file *flc_file; +}; + +struct file_lock { + struct file_lock_core c; loff_t fl_start; loff_t fl_end; - struct fasync_struct * fl_fasync; /* for lease break notifications */ - /* for lease breaks: */ - unsigned long fl_break_time; - unsigned long fl_downgrade_time; - const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { @@ -126,6 +130,15 @@ struct file_lock { } fl_u; } __randomize_layout; +struct file_lease { + struct file_lock_core c; + struct fasync_struct * fl_fasync; /* for lease break notifications */ + /* for lease breaks: */ + unsigned long fl_break_time; + unsigned long fl_downgrade_time; + const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ +} __randomize_layout; + struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; @@ -147,11 +160,31 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int, int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); +static inline bool lock_is_unlock(struct file_lock *fl) +{ + return fl->c.flc_type == F_UNLCK; +} + +static inline bool lock_is_read(struct file_lock *fl) +{ + return fl->c.flc_type == F_RDLCK; +} + +static inline bool lock_is_write(struct file_lock *fl) +{ + return fl->c.flc_type == F_WRLCK; +} + +static inline void locks_wake_up(struct file_lock *fl) +{ + wake_up(&fl->c.flc_wait); +} + /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); -struct file_lock * locks_alloc_lock(void); +struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); @@ -165,11 +198,16 @@ int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_l int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); + +void locks_init_lease(struct file_lease *); +void locks_free_lease(struct file_lease *fl); +struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); -int generic_setlease(struct file *, int, struct file_lock **, void **priv); -int vfs_setlease(struct file *, int, struct file_lock **, void **); -int lease_modify(struct file_lock *, int, struct list_head *); +int generic_setlease(struct file *, int, struct file_lease **, void **priv); +int kernel_setlease(struct file *, int, struct file_lease **, void **); +int vfs_setlease(struct file *, int, struct file_lease **, void **); +int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); @@ -223,6 +261,25 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline bool lock_is_unlock(struct file_lock *fl) +{ + return false; +} + +static inline bool lock_is_read(struct file_lock *fl) +{ + return false; +} + +static inline bool lock_is_write(struct file_lock *fl) +{ + return false; +} + +static inline void locks_wake_up(struct file_lock *fl) +{ +} + static inline void locks_free_lock_context(struct inode *inode) { @@ -233,6 +290,11 @@ static inline void locks_init_lock(struct file_lock *fl) return; } +static inline void locks_init_lease(struct file_lease *fl) +{ + return; +} + static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; @@ -307,18 +369,24 @@ static inline void lease_get_mtime(struct inode *inode, } static inline int generic_setlease(struct file *filp, int arg, - struct file_lock **flp, void **priv) + struct file_lease **flp, void **priv) +{ + return -EINVAL; +} + +static inline int kernel_setlease(struct file *filp, int arg, + struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, - struct file_lock **lease, void **priv) + struct file_lease **lease, void **priv) { return -EINVAL; } -static inline int lease_modify(struct file_lock *fl, int arg, +static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; @@ -341,6 +409,9 @@ locks_inode_context(const struct inode *inode) #endif /* !CONFIG_FILE_LOCKING */ +/* for walking lists of file_locks linked by fl_list */ +#define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) + static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..0a22b7245982 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -43,6 +43,8 @@ #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> +#include <linux/maple_tree.h> +#include <linux/rw_hint.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -309,19 +311,6 @@ struct address_space; struct writeback_control; struct readahead_control; -/* - * Write life time hint values. - * Stored in struct inode as u8. - */ -enum rw_hint { - WRITE_LIFE_NOT_SET = 0, - WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, - WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, - WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, - WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, - WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, -}; - /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC @@ -352,6 +341,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -482,10 +473,10 @@ struct address_space { pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; - struct rw_semaphore i_mmap_rwsem; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; + struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* @@ -677,7 +668,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; - u8 i_write_hint; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -907,7 +898,8 @@ static inline loff_t i_size_read(const struct inode *inode) preempt_enable(); return i_size; #else - return inode->i_size; + /* Pairs with smp_store_release() in i_size_write() */ + return smp_load_acquire(&inode->i_size); #endif } @@ -929,7 +921,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) inode->i_size = i_size; preempt_enable(); #else - inode->i_size = i_size; + /* + * Pairs with smp_load_acquire() in i_size_read() to ensure + * changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&inode->i_size, i_size); #endif } @@ -1064,6 +1061,7 @@ struct file *get_file_active(struct file **f); typedef void *fl_owner_t; struct file_lock; +struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX @@ -1078,9 +1076,20 @@ static inline struct inode *file_inode(const struct file *f) return f->f_inode; } +/* + * file_dentry() is a relic from the days that overlayfs was using files with a + * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. + * In those days, file_dentry() was needed to get the underlying fs dentry that + * matches f_inode. + * Files with "fake" path should not exist nowadays, so use an assertion to make + * sure that file_dentry() was not papering over filesystem bugs. + */ static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file)); + struct dentry *dentry = file->f_path.dentry; + + WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); + return dentry; } struct fasync_struct { @@ -1228,8 +1237,8 @@ struct super_block { #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - struct block_device *s_bdev; - struct bdev_handle *s_bdev_handle; + struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ + struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; @@ -1255,8 +1264,22 @@ struct super_block { struct fsnotify_mark_connector __rcu *s_fsnotify_marks; #endif + /* + * q: why are s_id and s_sysfs_name not the same? both are human + * readable strings that identify the filesystem + * a: s_id is allowed to change at runtime; it's used in log messages, + * and we want to when a device starts out as single device (s_id is dev + * name) but then a device is hot added and we have to switch to + * identifying it by UUID + * but s_sysfs_name is a handle for programmatic access, and can't + * change at runtime + */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ + u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ + + /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ + char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; @@ -2005,7 +2028,7 @@ struct file_operations { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); - int (*setlease)(struct file *, int, struct file_lock **, void **); + int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); @@ -2101,9 +2124,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); -extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); @@ -2532,6 +2552,44 @@ extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); +static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) +{ + if (WARN_ON(len > sizeof(sb->s_uuid))) + len = sizeof(sb->s_uuid); + sb->s_uuid_len = len; + memcpy(&sb->s_uuid, uuid, len); +} + +/* set sb sysfs name based on sb->s_bdev */ +static inline void super_set_sysfs_name_bdev(struct super_block *sb) +{ + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); +} + +/* set sb sysfs name based on sb->s_uuid */ +static inline void super_set_sysfs_name_uuid(struct super_block *sb) +{ + WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); +} + +/* set sb sysfs name based on sb->s_id */ +static inline void super_set_sysfs_name_id(struct super_block *sb) +{ + strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); +} + +/* try to use something standard before you use this */ +__printf(2, 3) +static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); + va_end(args); +} + extern int current_umask(void); extern void ihold(struct inode * inode); @@ -2928,6 +2986,17 @@ extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); +/** + * is_dot_dotdot - returns true only if @name is "." or ".." + * @name: file name to check + * @len: length of file name, in bytes + */ +static inline bool is_dot_dotdot(const char *name, size_t len) +{ + return len && unlikely(name[0] == '.') && + (len == 1 || (len == 2 && name[1] == '.')); +} + #include <linux/err.h> /* needed for stackable file system support */ @@ -3238,7 +3307,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping, extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); -extern int simple_nosetlease(struct file *, int, struct file_lock **, void **); +extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); @@ -3260,13 +3329,14 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { - struct xarray xa; - u32 next_offset; + struct maple_tree mt; + unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); +int simple_offset_empty(struct dentry *dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -3280,7 +3350,16 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); +extern void generic_set_sb_d_ops(struct super_block *sb); + +static inline bool sb_has_encoding(const struct super_block *sb) +{ +#if IS_ENABLED(CONFIG_UNICODE) + return !!sb->s_encoding; +#else + return false; +#endif +} int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); @@ -3335,6 +3414,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; + if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) + return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) @@ -3345,6 +3426,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; + if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { + if (IS_APPEND(file_inode(ki->ki_filp))) + return -EPERM; + ki->ki_flags &= ~IOCB_APPEND; + } + ki->ki_flags |= kiocb_flags; return 0; } diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 12f9e455d569..772f822dc6b8 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -192,6 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; +int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); + static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { @@ -221,15 +223,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) } /* - * When d_splice_alias() moves a directory's no-key alias to its plaintext alias - * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be - * cleared. Note that we don't have to support arbitrary moves of this flag - * because fscrypt doesn't allow no-key names to be the source or target of a - * rename(). + * When d_splice_alias() moves a directory's no-key alias to its + * plaintext alias as a result of the encryption key being added, + * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity + * to disable d_revalidate. Note that we don't have to support the + * inverse operation because fscrypt doesn't allow no-key names to be + * the source or target of a rename(). */ static inline void fscrypt_handle_d_move(struct dentry *dentry) { - dentry->d_flags &= ~DCACHE_NOKEY_NAME; + /* + * VFS calls fscrypt_handle_d_move even for non-fscrypt + * filesystems. + */ + if (dentry->d_flags & DCACHE_NOKEY_NAME) { + dentry->d_flags &= ~DCACHE_NOKEY_NAME; + + /* + * Other filesystem features might be handling dentry + * revalidation, in which case it cannot be disabled. + */ + if (dentry->d_op->d_revalidate == fscrypt_d_revalidate) + dentry->d_flags &= ~DCACHE_OP_REVALIDATE; + } } /** @@ -261,6 +277,35 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) return dentry->d_flags & DCACHE_NOKEY_NAME; } +static inline void fscrypt_prepare_dentry(struct dentry *dentry, + bool is_nokey_name) +{ + /* + * This code tries to only take ->d_lock when necessary to write + * to ->d_flags. We shouldn't be peeking on d_flags for + * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case + * there is a race, the worst it can happen is that we fail to + * unset DCACHE_OP_REVALIDATE and pay the cost of an extra + * d_revalidate. + */ + if (is_nokey_name) { + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_NOKEY_NAME; + spin_unlock(&dentry->d_lock); + } else if (dentry->d_flags & DCACHE_OP_REVALIDATE && + dentry->d_op->d_revalidate == fscrypt_d_revalidate) { + /* + * Unencrypted dentries and encrypted dentries where the + * key is available are always valid from fscrypt + * perspective. Avoid the cost of calling + * fscrypt_d_revalidate unnecessarily. + */ + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_OP_REVALIDATE; + spin_unlock(&dentry->d_lock); + } +} + /* crypto.c */ void fscrypt_enqueue_decrypt_work(struct work_struct *); @@ -368,7 +413,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len); u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); /* bio.c */ bool fscrypt_decrypt_bio(struct bio *bio); @@ -425,6 +469,11 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) return false; } +static inline void fscrypt_prepare_dentry(struct dentry *dentry, + bool is_nokey_name) +{ +} + /* crypto.c */ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { @@ -982,6 +1031,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir, fname->usr_fname = &dentry->d_name; fname->disk_name.name = (unsigned char *)dentry->d_name.name; fname->disk_name.len = dentry->d_name.len; + + fscrypt_prepare_dentry(dentry, false); + return 0; } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index de292a007138..e2a916cf29c4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -353,6 +353,15 @@ static inline bool gfp_has_io_fs(gfp_t gfp) return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } +/* + * Check if the gfp flags allow compaction - GFP_NOIO is a really + * tricky context because the migration might require IO. + */ +static inline bool gfp_compaction_allowed(gfp_t gfp_mask) +{ + return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); +} + extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 9a5c6c76e653..7f75c9a51874 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -819,6 +819,24 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) return ERR_PTR(-ENODEV); } +static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc) +{ + WARN_ON(1); + return ERR_PTR(-ENODEV); +} + +static inline int gpio_device_get_base(struct gpio_device *gdev) +{ + WARN_ON(1); + return -ENODEV; +} + +static inline const char *gpio_device_get_label(struct gpio_device *gdev) +{ + WARN_ON(1); + return NULL; +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 641c4567cfa7..aa1e65ccb615 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -18,12 +18,8 @@ #include <linux/list.h> #include <linux/percpu-defs.h> #include <linux/rbtree.h> -#include <linux/seqlock.h> #include <linux/timer.h> -struct hrtimer_clock_base; -struct hrtimer_cpu_base; - /* * Mode arguments of xxx_hrtimer functions: * @@ -98,107 +94,6 @@ struct hrtimer_sleeper { struct task_struct *task; }; -#ifdef CONFIG_64BIT -# define __hrtimer_clock_base_align ____cacheline_aligned -#else -# define __hrtimer_clock_base_align -#endif - -/** - * struct hrtimer_clock_base - the timer base for a specific clock - * @cpu_base: per cpu clock base - * @index: clock type index for per_cpu support when moving a - * timer to a base on another cpu. - * @clockid: clock id for per_cpu support - * @seq: seqcount around __run_hrtimer - * @running: pointer to the currently running hrtimer - * @active: red black tree root node for the active timers - * @get_time: function to retrieve the current time of the clock - * @offset: offset of this clock to the monotonic base - */ -struct hrtimer_clock_base { - struct hrtimer_cpu_base *cpu_base; - unsigned int index; - clockid_t clockid; - seqcount_raw_spinlock_t seq; - struct hrtimer *running; - struct timerqueue_head active; - ktime_t (*get_time)(void); - ktime_t offset; -} __hrtimer_clock_base_align; - -enum hrtimer_base_type { - HRTIMER_BASE_MONOTONIC, - HRTIMER_BASE_REALTIME, - HRTIMER_BASE_BOOTTIME, - HRTIMER_BASE_TAI, - HRTIMER_BASE_MONOTONIC_SOFT, - HRTIMER_BASE_REALTIME_SOFT, - HRTIMER_BASE_BOOTTIME_SOFT, - HRTIMER_BASE_TAI_SOFT, - HRTIMER_MAX_CLOCK_BASES, -}; - -/** - * struct hrtimer_cpu_base - the per cpu clock bases - * @lock: lock protecting the base and associated clock bases - * and timers - * @cpu: cpu number - * @active_bases: Bitfield to mark bases with active timers - * @clock_was_set_seq: Sequence counter of clock was set events - * @hres_active: State of high resolution mode - * @in_hrtirq: hrtimer_interrupt() is currently executing - * @hang_detected: The last hrtimer interrupt detected a hang - * @softirq_activated: displays, if the softirq is raised - update of softirq - * related settings is not required then. - * @nr_events: Total number of hrtimer interrupt events - * @nr_retries: Total number of hrtimer interrupt retries - * @nr_hangs: Total number of hrtimer interrupt hangs - * @max_hang_time: Maximum time spent in hrtimer_interrupt - * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are - * expired - * @online: CPU is online from an hrtimers point of view - * @timer_waiters: A hrtimer_cancel() invocation waits for the timer - * callback to finish. - * @expires_next: absolute time of the next event, is required for remote - * hrtimer enqueue; it is the total first expiry time (hard - * and soft hrtimer are taken into account) - * @next_timer: Pointer to the first expiring timer - * @softirq_expires_next: Time to check, if soft queues needs also to be expired - * @softirq_next_timer: Pointer to the first expiring softirq based timer - * @clock_base: array of clock bases for this cpu - * - * Note: next_timer is just an optimization for __remove_hrtimer(). - * Do not dereference the pointer because it is not reliable on - * cross cpu removals. - */ -struct hrtimer_cpu_base { - raw_spinlock_t lock; - unsigned int cpu; - unsigned int active_bases; - unsigned int clock_was_set_seq; - unsigned int hres_active : 1, - in_hrtirq : 1, - hang_detected : 1, - softirq_activated : 1, - online : 1; -#ifdef CONFIG_HIGH_RES_TIMERS - unsigned int nr_events; - unsigned short nr_retries; - unsigned short nr_hangs; - unsigned int max_hang_time; -#endif -#ifdef CONFIG_PREEMPT_RT - spinlock_t softirq_expiry_lock; - atomic_t timer_waiters; -#endif - ktime_t expires_next; - struct hrtimer *next_timer; - ktime_t softirq_expires_next; - struct hrtimer *softirq_next_timer; - struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; -} ____cacheline_aligned; - static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; @@ -447,20 +342,12 @@ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** - * hrtimer_forward_now - forward the timer expiry so it expires after now + * hrtimer_forward_now() - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * - * Forward the timer expiry so it will expire after the current time - * of the hrtimer clock base. Returns the number of overruns. - * - * Can be safely called from the callback function of @timer. If - * called from other contexts @timer must neither be enqueued nor - * running the callback and the caller needs to take care of - * serialization. - * - * Note: This only updates the timer expiry value and does not requeue - * the timer. + * It is a variant of hrtimer_forward(). The timer will expire after the current + * time of the hrtimer clock base. See hrtimer_forward() for details. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h index 2d3e3c5fb946..c3b4b7ed7c16 100644 --- a/include/linux/hrtimer_defs.h +++ b/include/linux/hrtimer_defs.h @@ -3,6 +3,8 @@ #define _LINUX_HRTIMER_DEFS_H #include <linux/ktime.h> +#include <linux/timerqueue.h> +#include <linux/seqlock.h> #ifdef CONFIG_HIGH_RES_TIMERS @@ -24,4 +26,106 @@ #endif +#ifdef CONFIG_64BIT +# define __hrtimer_clock_base_align ____cacheline_aligned +#else +# define __hrtimer_clock_base_align +#endif + +/** + * struct hrtimer_clock_base - the timer base for a specific clock + * @cpu_base: per cpu clock base + * @index: clock type index for per_cpu support when moving a + * timer to a base on another cpu. + * @clockid: clock id for per_cpu support + * @seq: seqcount around __run_hrtimer + * @running: pointer to the currently running hrtimer + * @active: red black tree root node for the active timers + * @get_time: function to retrieve the current time of the clock + * @offset: offset of this clock to the monotonic base + */ +struct hrtimer_clock_base { + struct hrtimer_cpu_base *cpu_base; + unsigned int index; + clockid_t clockid; + seqcount_raw_spinlock_t seq; + struct hrtimer *running; + struct timerqueue_head active; + ktime_t (*get_time)(void); + ktime_t offset; +} __hrtimer_clock_base_align; + +enum hrtimer_base_type { + HRTIMER_BASE_MONOTONIC, + HRTIMER_BASE_REALTIME, + HRTIMER_BASE_BOOTTIME, + HRTIMER_BASE_TAI, + HRTIMER_BASE_MONOTONIC_SOFT, + HRTIMER_BASE_REALTIME_SOFT, + HRTIMER_BASE_BOOTTIME_SOFT, + HRTIMER_BASE_TAI_SOFT, + HRTIMER_MAX_CLOCK_BASES, +}; + +/** + * struct hrtimer_cpu_base - the per cpu clock bases + * @lock: lock protecting the base and associated clock bases + * and timers + * @cpu: cpu number + * @active_bases: Bitfield to mark bases with active timers + * @clock_was_set_seq: Sequence counter of clock was set events + * @hres_active: State of high resolution mode + * @in_hrtirq: hrtimer_interrupt() is currently executing + * @hang_detected: The last hrtimer interrupt detected a hang + * @softirq_activated: displays, if the softirq is raised - update of softirq + * related settings is not required then. + * @nr_events: Total number of hrtimer interrupt events + * @nr_retries: Total number of hrtimer interrupt retries + * @nr_hangs: Total number of hrtimer interrupt hangs + * @max_hang_time: Maximum time spent in hrtimer_interrupt + * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are + * expired + * @online: CPU is online from an hrtimers point of view + * @timer_waiters: A hrtimer_cancel() invocation waits for the timer + * callback to finish. + * @expires_next: absolute time of the next event, is required for remote + * hrtimer enqueue; it is the total first expiry time (hard + * and soft hrtimer are taken into account) + * @next_timer: Pointer to the first expiring timer + * @softirq_expires_next: Time to check, if soft queues needs also to be expired + * @softirq_next_timer: Pointer to the first expiring softirq based timer + * @clock_base: array of clock bases for this cpu + * + * Note: next_timer is just an optimization for __remove_hrtimer(). + * Do not dereference the pointer because it is not reliable on + * cross cpu removals. + */ +struct hrtimer_cpu_base { + raw_spinlock_t lock; + unsigned int cpu; + unsigned int active_bases; + unsigned int clock_was_set_seq; + unsigned int hres_active : 1, + in_hrtirq : 1, + hang_detected : 1, + softirq_activated : 1, + online : 1; +#ifdef CONFIG_HIGH_RES_TIMERS + unsigned int nr_events; + unsigned short nr_retries; + unsigned short nr_hangs; + unsigned int max_hang_time; +#endif +#ifdef CONFIG_PREEMPT_RT + spinlock_t softirq_expiry_lock; + atomic_t timer_waiters; +#endif + ktime_t expires_next; + struct hrtimer *next_timer; + ktime_t softirq_expires_next; + struct hrtimer *softirq_next_timer; + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; +} ____cacheline_aligned; + + #endif diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2b00faf98017..6ef0557b4bff 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7852f6c9a714..719cf9cc6e1a 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -8,6 +8,8 @@ #ifndef __AD_SIGMA_DELTA_H__ #define __AD_SIGMA_DELTA_H__ +#include <linux/iio/iio.h> + enum ad_sigma_delta_mode { AD_SD_MODE_CONTINUOUS = 0, AD_SD_MODE_SINGLE = 1, @@ -99,7 +101,7 @@ struct ad_sigma_delta { * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp, * rounded to 16 bytes to take into account padding. */ - uint8_t tx_buf[4] ____cacheline_aligned; + uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN); uint8_t rx_buf[16] __aligned(8); }; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 607c3a89a647..f9ae5cdd884f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -258,9 +258,9 @@ struct st_sensor_data { bool hw_irq_trigger; s64 hw_timestamp; - char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; - struct mutex odr_lock; + + char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN); }; #ifdef CONFIG_IIO_BUFFER diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index dc9ea299e088..8898966bc0f0 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -11,6 +11,7 @@ #include <linux/spi/spi.h> #include <linux/interrupt.h> +#include <linux/iio/iio.h> #include <linux/iio/types.h> #define ADIS_WRITE_REG(reg) ((0x80 | (reg))) @@ -131,7 +132,7 @@ struct adis { unsigned long irq_flag; void *buffer; - u8 tx[10] ____cacheline_aligned; + u8 tx[10] __aligned(IIO_DMA_MINALIGN); u8 rx[4]; }; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 854ad67a5f70..e24893625085 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -2,6 +2,7 @@ #define IO_URING_TYPES_H #include <linux/blkdev.h> +#include <linux/hashtable.h> #include <linux/task_work.h> #include <linux/bitmap.h> #include <linux/llist.h> @@ -240,12 +241,14 @@ struct io_ring_ctx { unsigned int poll_activated: 1; unsigned int drain_disabled: 1; unsigned int compat: 1; + unsigned int iowq_limits_set : 1; struct task_struct *submitter_task; struct io_rings *rings; struct percpu_ref refs; enum task_work_notify_mode notify_method; + unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; /* submission data */ @@ -274,10 +277,20 @@ struct io_ring_ctx { */ struct io_rsrc_node *rsrc_node; atomic_t cancel_seq; + + /* + * ->iopoll_list is protected by the ctx->uring_lock for + * io_uring instances that don't use IORING_SETUP_SQPOLL. + * For SQPOLL, only the single threaded io_sq_thread() will + * manipulate the list, hence no extra locking is needed there. + */ + bool poll_multi_queue; + struct io_wq_work_list iopoll_list; + struct io_file_table file_table; + struct io_mapped_ubuf **user_bufs; unsigned nr_user_files; unsigned nr_user_bufs; - struct io_mapped_ubuf **user_bufs; struct io_submit_state submit_state; @@ -289,15 +302,6 @@ struct io_ring_ctx { struct io_alloc_cache netmsg_cache; /* - * ->iopoll_list is protected by the ctx->uring_lock for - * io_uring instances that don't use IORING_SETUP_SQPOLL. - * For SQPOLL, only the single threaded io_sq_thread() will - * manipulate the list, hence no extra locking is needed there. - */ - struct io_wq_work_list iopoll_list; - bool poll_multi_queue; - - /* * Any cancelable uring_cmd is added to this list in * ->uring_cmd() by io_uring_cmd_insert_cancelable() */ @@ -343,8 +347,8 @@ struct io_ring_ctx { spinlock_t completion_lock; /* IRQ completion list, under ->completion_lock */ - struct io_wq_work_list locked_free_list; unsigned int locked_free_nr; + struct io_wq_work_list locked_free_list; struct list_head io_buffers_comp; struct list_head cq_overflow_list; @@ -366,9 +370,6 @@ struct io_ring_ctx { unsigned int file_alloc_start; unsigned int file_alloc_end; - struct xarray personalities; - u32 pers_next; - struct list_head io_buffers_cache; /* deferred free list, protected by ->uring_lock */ @@ -389,6 +390,9 @@ struct io_ring_ctx { struct wait_queue_head rsrc_quiesce_wq; unsigned rsrc_quiesce; + u32 pers_next; + struct xarray personalities; + /* hashed buffered write serialization */ struct io_wq_hash *hash_map; @@ -405,11 +409,22 @@ struct io_ring_ctx { /* io-wq management, e.g. thread count */ u32 iowq_limits[2]; - bool iowq_limits_set; struct callback_head poll_wq_task_work; struct list_head defer_list; - unsigned sq_thread_idle; + +#ifdef CONFIG_NET_RX_BUSY_POLL + struct list_head napi_list; /* track busy poll napi_id */ + spinlock_t napi_lock; /* napi_list lock */ + + /* napi busy poll default timeout */ + unsigned int napi_busy_poll_to; + bool napi_prefer_busy_poll; + bool napi_enabled; + + DECLARE_HASHTABLE(napi_ht, 4); +#endif + /* protected by ->completion_lock */ unsigned evfd_last_cq_tail; @@ -455,7 +470,6 @@ enum { REQ_F_SKIP_LINK_CQES_BIT, REQ_F_SINGLE_POLL_BIT, REQ_F_DOUBLE_POLL_BIT, - REQ_F_PARTIAL_IO_BIT, REQ_F_APOLL_MULTISHOT_BIT, REQ_F_CLEAR_POLLIN_BIT, REQ_F_HASH_LOCKED_BIT, @@ -463,75 +477,88 @@ enum { REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, REQ_F_POLL_NO_LAZY_BIT, + REQ_F_CANCEL_SEQ_BIT, + REQ_F_CAN_POLL_BIT, + REQ_F_BL_EMPTY_BIT, + REQ_F_BL_NO_RECYCLE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, }; +typedef u64 __bitwise io_req_flags_t; +#define IO_REQ_FLAG(bitno) ((__force io_req_flags_t) BIT_ULL((bitno))) + enum { /* ctx owns file */ - REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), + REQ_F_FIXED_FILE = IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT), /* drain existing IO first */ - REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), + REQ_F_IO_DRAIN = IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT), /* linked sqes */ - REQ_F_LINK = BIT(REQ_F_LINK_BIT), + REQ_F_LINK = IO_REQ_FLAG(REQ_F_LINK_BIT), /* doesn't sever on completion < 0 */ - REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), + REQ_F_HARDLINK = IO_REQ_FLAG(REQ_F_HARDLINK_BIT), /* IOSQE_ASYNC */ - REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), + REQ_F_FORCE_ASYNC = IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT), /* IOSQE_BUFFER_SELECT */ - REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + REQ_F_BUFFER_SELECT = IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT), /* IOSQE_CQE_SKIP_SUCCESS */ - REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT), + REQ_F_CQE_SKIP = IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT), /* fail rest of links */ - REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + REQ_F_FAIL = IO_REQ_FLAG(REQ_F_FAIL_BIT), /* on inflight list, should be cancelled and waited on exit reliably */ - REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), + REQ_F_INFLIGHT = IO_REQ_FLAG(REQ_F_INFLIGHT_BIT), /* read/write uses file position */ - REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), + REQ_F_CUR_POS = IO_REQ_FLAG(REQ_F_CUR_POS_BIT), /* must not punt to workers */ - REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), + REQ_F_NOWAIT = IO_REQ_FLAG(REQ_F_NOWAIT_BIT), /* has or had linked timeout */ - REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), + REQ_F_LINK_TIMEOUT = IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT), /* needs cleanup */ - REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), + REQ_F_NEED_CLEANUP = IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ - REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), + REQ_F_POLLED = IO_REQ_FLAG(REQ_F_POLLED_BIT), /* buffer already selected */ - REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + REQ_F_BUFFER_SELECTED = IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT), /* buffer selected from ring, needs commit */ - REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), + REQ_F_BUFFER_RING = IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT), /* caller should reissue async */ - REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + REQ_F_REISSUE = IO_REQ_FLAG(REQ_F_REISSUE_BIT), /* supports async reads/writes */ - REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT), + REQ_F_SUPPORT_NOWAIT = IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT), /* regular file */ - REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + REQ_F_ISREG = IO_REQ_FLAG(REQ_F_ISREG_BIT), /* has creds assigned */ - REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + REQ_F_CREDS = IO_REQ_FLAG(REQ_F_CREDS_BIT), /* skip refcounting if not set */ - REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + REQ_F_REFCOUNT = IO_REQ_FLAG(REQ_F_REFCOUNT_BIT), /* there is a linked timeout that has to be armed */ - REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + REQ_F_ARM_LTIMEOUT = IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT), /* ->async_data allocated */ - REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), + REQ_F_ASYNC_DATA = IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT), /* don't post CQEs while failing linked requests */ - REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT), + REQ_F_SKIP_LINK_CQES = IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT), /* single poll may be active */ - REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT), + REQ_F_SINGLE_POLL = IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT), /* double poll may active */ - REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), - /* request has already done partial IO */ - REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), + REQ_F_DOUBLE_POLL = IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT), /* fast poll multishot mode */ - REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), + REQ_F_APOLL_MULTISHOT = IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT), /* recvmsg special flag, clear EPOLLIN */ - REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT), + REQ_F_CLEAR_POLLIN = IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT), /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ - REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), + REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT), /* don't use lazy poll wake for this request */ - REQ_F_POLL_NO_LAZY = BIT(REQ_F_POLL_NO_LAZY_BIT), + REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), + /* cancel sequence is set and valid */ + REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT), + /* file is pollable */ + REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT), + /* buffer list was empty after selection of buffer */ + REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT), + /* don't recycle provided buffers for this request */ + REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); @@ -592,15 +619,17 @@ struct io_kiocb { * and after selection it points to the buffer ID itself. */ u16 buf_index; - unsigned int flags; + + unsigned nr_tw; + + /* REQ_F_* flags */ + io_req_flags_t flags; struct io_cqe cqe; struct io_ring_ctx *ctx; struct task_struct *task; - struct io_rsrc_node *rsrc_node; - union { /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; @@ -621,10 +650,12 @@ struct io_kiocb { /* cache ->apoll->events */ __poll_t apoll_events; }; + + struct io_rsrc_node *rsrc_node; + atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; - unsigned nr_tw; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; /* internal polling, see IORING_FEAT_FAST_POLL */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 96dd0acbba44..6fc1c858013d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -293,22 +293,32 @@ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ u16 io_type; u16 io_flags; /* IOMAP_F_* */ - u32 io_folios; /* folios added to ioend */ struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ - struct bio *io_bio; /* bio being built */ - struct bio io_inline_bio; /* MUST BE LAST! */ + struct bio io_bio; /* MUST BE LAST! */ }; +static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio) +{ + return container_of(bio, struct iomap_ioend, io_bio); +} + struct iomap_writeback_ops { /* * Required, maps the blocks so that writeback can be performed on * the range starting at offset. + * + * Can return arbitrarily large regions, but we need to call into it at + * least once per folio to allow the file systems to synchronize with + * the write path that could be invalidating mappings. + * + * An existing mapping from a previous call to this method can be reused + * by the file system if it is still valid. */ int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset); + loff_t offset, unsigned len); /* * Optional, allows the file systems to perform actions just before @@ -329,6 +339,7 @@ struct iomap_writepage_ctx { struct iomap iomap; struct iomap_ioend *ioend; const struct iomap_writeback_ops *ops; + u32 nr_folios; /* folios added to the ioend */ }; void iomap_finish_ioends(struct iomap_ioend *ioend, int error); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1ea2a820e1eb..5e27cb3a3be9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -892,11 +892,14 @@ struct iommu_fwspec { struct iommu_sva { struct device *dev; struct iommu_domain *domain; + struct list_head handle_item; + refcount_t users; }; struct iommu_mm_data { u32 pasid; struct list_head sva_domains; + struct list_head sva_handles; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, diff --git a/include/linux/irq.h b/include/linux/irq.h index 90081afa10ce..97baa937ab5b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -179,7 +179,7 @@ struct irq_common_data { struct irq_data { u32 mask; unsigned int irq; - unsigned long hwirq; + irq_hw_number_t hwirq; struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index ee0a82c60508..21ecf582a0fe 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -619,6 +619,23 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain) #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#ifdef CONFIG_GENERIC_MSI_IRQ +int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq, + unsigned int type); +void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq); +#else +static inline int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq, + unsigned int type) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} +static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq) +{ + WARN_ON_ONCE(1); +} +#endif + #else /* CONFIG_IRQ_DOMAIN */ static inline void irq_dispose_mapping(unsigned int virq) { } static inline struct irq_domain *irq_find_matching_fwnode( diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h index c29921fd8cd1..5c1fe6f1fcde 100644 --- a/include/linux/irqdomain_defs.h +++ b/include/linux/irqdomain_defs.h @@ -26,6 +26,8 @@ enum irq_domain_bus_token { DOMAIN_BUS_DMAR, DOMAIN_BUS_AMDVI, DOMAIN_BUS_PCI_DEVICE_IMS, + DOMAIN_BUS_DEVICE_MSI, + DOMAIN_BUS_WIRED_TO_MSI, }; #endif /* _LINUX_IRQDOMAIN_DEFS_H */ diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h index c30f454a9518..72dd1eb3a0e7 100644 --- a/include/linux/irqhandler.h +++ b/include/linux/irqhandler.h @@ -8,7 +8,7 @@ */ struct irq_desc; -struct irq_data; + typedef void (*irq_flow_handler_t)(struct irq_desc *desc); #endif diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index e0ae2a43e0eb..d9f1435a5a13 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -102,12 +102,15 @@ static inline u64 get_jiffies_64(void) } #endif -/* - * These inlines deal with timer wrapping correctly. You are - * strongly encouraged to use them: - * 1. Because people otherwise forget - * 2. Because if the timer wrap changes in future you won't have to - * alter your driver code. +/** + * DOC: General information about time_* inlines + * + * These inlines deal with timer wrapping correctly. You are strongly encouraged + * to use them: + * + * #. Because people otherwise forget + * #. Because if the timer wrap changes in future you won't have to alter your + * driver code. */ /** diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7e7fd25b09b3..179df96b20f8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2031,6 +2031,32 @@ static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, return 1; return 0; } + +/* + * This lockless version of the range-based retry check *must* be paired with a + * call to the locked version after acquiring mmu_lock, i.e. this is safe to + * use only as a pre-check to avoid contending mmu_lock. This version *will* + * get false negatives and false positives. + */ +static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, + unsigned long mmu_seq, + gfn_t gfn) +{ + /* + * Use READ_ONCE() to ensure the in-progress flag and sequence counter + * are always read from memory, e.g. so that checking for retry in a + * loop won't result in an infinite retry loop. Don't force loads for + * start+end, as the key to avoiding infinite retry loops is observing + * the 1=>0 transition of in-progress, i.e. getting false negatives + * due to stale start+end values is acceptable. + */ + if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && + gfn >= kvm->mmu_invalidate_range_start && + gfn < kvm->mmu_invalidate_range_end) + return true; + + return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 9f565416d186..1b95fe31051f 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -375,12 +375,12 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) - && fl1->fl_pid == fl2->fl_pid - && fl1->fl_owner == fl2->fl_owner + return file_inode(fl1->c.flc_file) == file_inode(fl2->c.flc_file) + && fl1->c.flc_pid == fl2->c.flc_pid + && fl1->c.flc_owner == fl2->c.flc_owner && fl1->fl_start == fl2->fl_start && fl1->fl_end == fl2->fl_end - &&(fl1->fl_type == fl2->fl_type || fl2->fl_type == F_UNLCK); + &&(fl1->c.flc_type == fl2->c.flc_type || fl2->c.flc_type == F_UNLCK); } extern const struct lock_manager_operations nlmsvc_lock_operations; diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index b60fbcd8cdfa..80cca9426761 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -52,7 +52,7 @@ struct nlm_lock { * FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to * 32 bytes. */ - + struct nlm_cookie { unsigned char data[NLM_MAXCOOKIELEN]; diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index b3d63123b945..a53ad4dabd7e 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -171,6 +171,7 @@ enum maple_type { #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 +#define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 @@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first, int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); +int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); @@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b695f9e946da..e2082240586d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -121,6 +121,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); int memblock_physmem_add(phys_addr_t base, phys_addr_t size); #endif void memblock_trim_memory(phys_addr_t align); +unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, + phys_addr_t base2, phys_addr_t size2); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); bool memblock_validate_numa_coverage(unsigned long threshold_bytes); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c726f90ab752..486b7492050c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x1]; + u8 roce_cc_general[0x1]; u8 qp_ooo_transmit_default[0x1]; u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; @@ -10261,7 +10261,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_63_to_46[0x12]; u8 mrtc[0x1]; - u8 regs_44_to_32[0xd]; + u8 regs_44_to_41[0x4]; + u8 mfrl[0x1]; + u8 regs_39_to_32[0x8]; u8 regs_31_to_10[0x16]; u8 mtmp[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index bd53cf4be7bd..f0e55bf3ec8b 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg { union { struct { __be16 sz; - u8 start[2]; + union { + u8 start[2]; + DECLARE_FLEX_ARRAY(u8, data); + }; } inline_hdr; struct { __be16 type; diff --git a/include/linux/msi.h b/include/linux/msi.h index ddace8c34dcf..26d07e23052e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -412,6 +412,7 @@ bool arch_restore_msi_irqs(struct pci_dev *dev); struct irq_domain; struct irq_domain_ops; struct irq_chip; +struct irq_fwspec; struct device_node; struct fwnode_handle; struct msi_domain_info; @@ -431,6 +432,8 @@ struct msi_domain_info; * function. * @msi_post_free: Optional function which is invoked after freeing * all interrupts. + * @msi_translate: Optional translate callback to support the odd wire to + * MSI bridges, e.g. MBIGEN * * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying * irqdomain. @@ -468,6 +471,8 @@ struct msi_domain_ops { struct device *dev); void (*msi_post_free)(struct irq_domain *domain, struct device *dev); + int (*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec, + irq_hw_number_t *hwirq, unsigned int *type); }; /** @@ -547,6 +552,10 @@ enum { MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 5), /* Free MSI descriptors */ MSI_FLAG_FREE_MSI_DESCS = (1 << 6), + /* Use dev->fwnode for MSI device domain creation */ + MSI_FLAG_USE_DEV_FWNODE = (1 << 7), + /* Set parent->dev into domain->pm_dev on device domain creation */ + MSI_FLAG_PARENT_PM_DEV = (1 << 8), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), @@ -572,6 +581,11 @@ enum { * struct msi_parent_ops - MSI parent domain callbacks and configuration info * * @supported_flags: Required: The supported MSI flags of the parent domain + * @required_flags: Optional: The required MSI flags of the parent MSI domain + * @bus_select_token: Optional: The bus token of the real parent domain for + * irq_domain::select() + * @bus_select_mask: Optional: A mask of supported BUS_DOMAINs for + * irq_domain::select() * @prefix: Optional: Prefix for the domain and chip name * @init_dev_msi_info: Required: Callback for MSI parent domains to setup parent * domain specific domain flags, domain ops and interrupt chip @@ -579,6 +593,9 @@ enum { */ struct msi_parent_ops { u32 supported_flags; + u32 required_flags; + u32 bus_select_token; + u32 bus_select_mask; const char *prefix; bool (*init_dev_msi_info)(struct device *dev, struct irq_domain *domain, struct irq_domain *msi_parent_domain, @@ -627,9 +644,6 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, - irq_write_msi_msg_t write_msi_msg); -void platform_msi_domain_free_irqs(struct device *dev); /* When an MSI domain is used as an intermediate domain */ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, @@ -656,6 +670,10 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); +/* Per device platform MSI */ +int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec, + irq_write_msi_msg_t write_msi_msg); +void platform_device_msi_free_irqs_all(struct device *dev); bool msi_device_has_isolated_msi(struct device *dev); #else /* CONFIG_GENERIC_MSI_IRQ */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 7e208d46ba5b..67edc4ca2bee 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -32,11 +32,9 @@ # define __DEP_MAP_MUTEX_INITIALIZER(lockname) #endif -#ifndef CONFIG_PREEMPT_RT - #ifdef CONFIG_DEBUG_MUTEXES -#define __DEBUG_MUTEX_INITIALIZER(lockname) \ +# define __DEBUG_MUTEX_INITIALIZER(lockname) \ , .magic = &lockname extern void mutex_destroy(struct mutex *lock); @@ -49,6 +47,7 @@ static inline void mutex_destroy(struct mutex *lock) {} #endif +#ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -101,9 +100,6 @@ extern bool mutex_is_locked(struct mutex *lock); extern void __mutex_rt_init(struct mutex *lock, const char *name, struct lock_class_key *key); -extern int mutex_trylock(struct mutex *lock); - -static inline void mutex_destroy(struct mutex *lock) { } #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 118c40258d07..78a09af89e39 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,8 +79,6 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; -/* DPLL specific */ -struct dpll_pin; typedef u32 xdp_features_t; @@ -2141,6 +2139,11 @@ struct net_device { /* TXRX read-mostly hotpath */ __cacheline_group_begin(net_device_read_txrx); + union { + struct pcpu_lstats __percpu *lstats; + struct pcpu_sw_netstats __percpu *tstats; + struct pcpu_dstats __percpu *dstats; + }; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2395,11 +2398,6 @@ struct net_device { enum netdev_ml_priv_type ml_priv_type; enum netdev_stat_type pcpu_stat_type:8; - union { - struct pcpu_lstats __percpu *lstats; - struct pcpu_sw_netstats __percpu *tstats; - struct pcpu_dstats __percpu *dstats; - }; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; @@ -2469,7 +2467,7 @@ struct net_device { struct devlink_port *devlink_port; #if IS_ENABLED(CONFIG_DPLL) - struct dpll_pin *dpll_pin; + struct dpll_pin __rcu *dpll_pin; #endif #if IS_ENABLED(CONFIG_PAGE_POOL) /** @page_pools: page pools created for this netdevice */ @@ -3499,6 +3497,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue #endif } +static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) +{ +#ifdef CONFIG_BQL + /* Non-BQL migrated drivers will return 0, too. */ + return dql_avail(&txq->dql); +#else + return 0; +#endif +} + /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue @@ -4032,17 +4040,6 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); -void netdev_dpll_pin_clear(struct net_device *dev); - -static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_DPLL) - return dev->dpll_pin; -#else - return NULL; -#endif -} struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 80900d910992..ce660d51549b 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -474,6 +474,7 @@ struct nf_ct_hook { const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); void (*set_closing)(struct nf_conntrack *nfct); + int (*confirm)(struct sk_buff *skb); }; extern const struct nf_ct_hook __rcu *nf_ct_hook; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index cd797e00fe35..92de074e63b9 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -124,6 +124,7 @@ struct nfs_client { char cl_ipaddr[48]; struct net *cl_net; struct list_head pending_cb_stateids; + struct rcu_head rcu; }; /* @@ -265,6 +266,7 @@ struct nfs_server { const struct cred *cred; bool has_sec_mnt_opts; struct kobject kobj; + struct rcu_head rcu; }; /* Server capabilities */ diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 0f1d024bd958..7d22ea50b098 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -7,7 +7,7 @@ struct proc_ns_operations; struct ns_common { - atomic_long_t stashed; + struct dentry *stashed; const struct proc_ns_operations *ops; unsigned int inum; refcount_t count; diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index 4dd7e6fe92fb..eb2f04d636c8 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -6,7 +6,11 @@ #ifndef _LINUX_NVME_RDMA_H #define _LINUX_NVME_RDMA_H -#define NVME_RDMA_MAX_QUEUE_SIZE 128 +#define NVME_RDMA_IP_PORT 4420 + +#define NVME_RDMA_MAX_QUEUE_SIZE 256 +#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128 +#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128 enum nvme_rdma_cm_fmt { NVME_RDMA_CM_FMT_1_0 = 0x0, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bc605ec4a3fd..425573202295 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -23,8 +23,6 @@ #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" -#define NVME_RDMA_IP_PORT 4420 - #define NVME_NSID_ALL 0xffffffff enum nvme_subsys_type { @@ -646,6 +644,7 @@ enum { NVME_CMD_EFFECTS_NCC = 1 << 2, NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, + NVME_CMD_EFFECTS_CSER_MASK = GENMASK(15, 14), NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16), NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, NVME_CMD_EFFECTS_SCOPE_MASK = GENMASK(31, 20), diff --git a/include/linux/pid.h b/include/linux/pid.h index 395cacce1179..c79a0efd0258 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -55,6 +55,10 @@ struct pid refcount_t count; unsigned int level; spinlock_t lock; +#ifdef CONFIG_FS_PID + struct dentry *stashed; + unsigned long ino; +#endif /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; @@ -66,15 +70,13 @@ struct pid extern struct pid init_struct_pid; -extern const struct file_operations pidfd_fops; - struct file; -extern struct pid *pidfd_pid(const struct file *file); +struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); -int pidfd_create(struct pid *pid, unsigned int flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); +void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h new file mode 100644 index 000000000000..40dd325a32a6 --- /dev/null +++ b/include/linux/pidfs.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PID_FS_H +#define _LINUX_PID_FS_H + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); +void __init pidfs_init(void); +bool is_pidfs_sb(const struct super_block *sb); + +#endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 79594aeb160d..2f1b952d596a 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -154,9 +154,9 @@ struct packet_stacked_data struct pktcdvd_device { - struct bdev_handle *bdev_handle; /* dev attached */ + struct file *bdev_file; /* dev attached */ /* handle acquired for bdev during pkt_open_dev() */ - struct bdev_handle *open_bdev_handle; + struct file *f_open_bdev; dev_t pkt_dev; /* our dev */ struct packet_settings settings; struct packet_stats stats; diff --git a/include/linux/poison.h b/include/linux/poison.h index 27a7dad17eef..1f0ee2459f2a 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -92,4 +92,7 @@ /********** VFS **********/ #define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA)) +/********** lib/stackdepot.c **********/ +#define STACK_DEPOT_POISON ((void *)(0xD390 + POISON_POINTER_DELTA)) + #endif diff --git a/include/linux/poll.h b/include/linux/poll.h index a9e0e1c2d1f2..d1ea4f3714a8 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -14,11 +14,7 @@ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ -#ifdef __clang__ -#define MAX_STACK_ALLOC 768 -#else #define MAX_STACK_ALLOC 832 -#endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index de407e7c3b55..0b2a89854440 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -65,6 +65,7 @@ struct proc_fs_info { kgid_t pid_gid; enum proc_hidepid hide_pid; enum proc_pidonly pidonly; + struct rcu_head rcu; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 49539bc416ce..5ea470eb4d76 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -66,7 +66,7 @@ static inline void proc_free_inum(unsigned int inum) {} static inline int ns_alloc_inum(struct ns_common *ns) { - atomic_long_set(&ns->stashed, 0); + WRITE_ONCE(ns->stashed, NULL); return proc_alloc_inum(&ns->inum); } diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 7fd17e82bab4..3705c2044fc0 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -78,6 +78,36 @@ enum sev_cmd { SEV_CMD_DBG_DECRYPT = 0x060, SEV_CMD_DBG_ENCRYPT = 0x061, + /* SNP specific commands */ + SEV_CMD_SNP_INIT = 0x081, + SEV_CMD_SNP_SHUTDOWN = 0x082, + SEV_CMD_SNP_PLATFORM_STATUS = 0x083, + SEV_CMD_SNP_DF_FLUSH = 0x084, + SEV_CMD_SNP_INIT_EX = 0x085, + SEV_CMD_SNP_SHUTDOWN_EX = 0x086, + SEV_CMD_SNP_DECOMMISSION = 0x090, + SEV_CMD_SNP_ACTIVATE = 0x091, + SEV_CMD_SNP_GUEST_STATUS = 0x092, + SEV_CMD_SNP_GCTX_CREATE = 0x093, + SEV_CMD_SNP_GUEST_REQUEST = 0x094, + SEV_CMD_SNP_ACTIVATE_EX = 0x095, + SEV_CMD_SNP_LAUNCH_START = 0x0A0, + SEV_CMD_SNP_LAUNCH_UPDATE = 0x0A1, + SEV_CMD_SNP_LAUNCH_FINISH = 0x0A2, + SEV_CMD_SNP_DBG_DECRYPT = 0x0B0, + SEV_CMD_SNP_DBG_ENCRYPT = 0x0B1, + SEV_CMD_SNP_PAGE_SWAP_OUT = 0x0C0, + SEV_CMD_SNP_PAGE_SWAP_IN = 0x0C1, + SEV_CMD_SNP_PAGE_MOVE = 0x0C2, + SEV_CMD_SNP_PAGE_MD_INIT = 0x0C3, + SEV_CMD_SNP_PAGE_SET_STATE = 0x0C6, + SEV_CMD_SNP_PAGE_RECLAIM = 0x0C7, + SEV_CMD_SNP_PAGE_UNSMASH = 0x0C8, + SEV_CMD_SNP_CONFIG = 0x0C9, + SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX = 0x0CA, + SEV_CMD_SNP_COMMIT = 0x0CB, + SEV_CMD_SNP_VLEK_LOAD = 0x0CD, + SEV_CMD_MAX, }; @@ -523,12 +553,269 @@ struct sev_data_attestation_report { u32 len; /* In/Out */ } __packed; +/** + * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params + * + * @address: physical address of firmware image + * @len: length of the firmware image + */ +struct sev_data_snp_download_firmware { + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_snp_activate - SNP_ACTIVATE command params + * + * @gctx_paddr: system physical address guest context page + * @asid: ASID to bind to the guest + */ +struct sev_data_snp_activate { + u64 gctx_paddr; /* In */ + u32 asid; /* In */ +} __packed; + +/** + * struct sev_data_snp_addr - generic SNP command params + * + * @address: physical address of generic data param + */ +struct sev_data_snp_addr { + u64 address; /* In/Out */ +} __packed; + +/** + * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params + * + * @gctx_paddr: system physical address of guest context page + * @policy: guest policy + * @ma_gctx_paddr: system physical address of migration agent + * @ma_en: the guest is associated with a migration agent + * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the + * purpose of guest-assisted migration. + * @rsvd: reserved + * @gosvw: guest OS-visible workarounds, as defined by hypervisor + */ +struct sev_data_snp_launch_start { + u64 gctx_paddr; /* In */ + u64 policy; /* In */ + u64 ma_gctx_paddr; /* In */ + u32 ma_en:1; /* In */ + u32 imi_en:1; /* In */ + u32 rsvd:30; + u8 gosvw[16]; /* In */ +} __packed; + +/* SNP support page type */ +enum { + SNP_PAGE_TYPE_NORMAL = 0x1, + SNP_PAGE_TYPE_VMSA = 0x2, + SNP_PAGE_TYPE_ZERO = 0x3, + SNP_PAGE_TYPE_UNMEASURED = 0x4, + SNP_PAGE_TYPE_SECRET = 0x5, + SNP_PAGE_TYPE_CPUID = 0x6, + + SNP_PAGE_TYPE_MAX +}; + +/** + * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params + * + * @gctx_paddr: system physical address of guest context page + * @page_size: page size 0 indicates 4K and 1 indicates 2MB page + * @page_type: encoded page type + * @imi_page: indicates that this page is part of the IMI (Incoming Migration + * Image) of the guest + * @rsvd: reserved + * @rsvd2: reserved + * @address: system physical address of destination page to encrypt + * @rsvd3: reserved + * @vmpl1_perms: VMPL permission mask for VMPL1 + * @vmpl2_perms: VMPL permission mask for VMPL2 + * @vmpl3_perms: VMPL permission mask for VMPL3 + * @rsvd4: reserved + */ +struct sev_data_snp_launch_update { + u64 gctx_paddr; /* In */ + u32 page_size:1; /* In */ + u32 page_type:3; /* In */ + u32 imi_page:1; /* In */ + u32 rsvd:27; + u32 rsvd2; + u64 address; /* In */ + u32 rsvd3:8; + u32 vmpl1_perms:8; /* In */ + u32 vmpl2_perms:8; /* In */ + u32 vmpl3_perms:8; /* In */ + u32 rsvd4; +} __packed; + +/** + * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params + * + * @gctx_paddr: system physical address of guest context page + * @id_block_paddr: system physical address of ID block + * @id_auth_paddr: system physical address of ID block authentication structure + * @id_block_en: indicates whether ID block is present + * @auth_key_en: indicates whether author key is present in authentication structure + * @rsvd: reserved + * @host_data: host-supplied data for guest, not interpreted by firmware + */ +struct sev_data_snp_launch_finish { + u64 gctx_paddr; + u64 id_block_paddr; + u64 id_auth_paddr; + u8 id_block_en:1; + u8 auth_key_en:1; + u64 rsvd:62; + u8 host_data[32]; +} __packed; + +/** + * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params + * + * @gctx_paddr: system physical address of guest context page + * @address: system physical address of guest status page + */ +struct sev_data_snp_guest_status { + u64 gctx_paddr; + u64 address; +} __packed; + +/** + * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params + * + * @paddr: system physical address of page to be claimed. The 0th bit in the + * address indicates the page size. 0h indicates 4KB and 1h indicates + * 2MB page. + */ +struct sev_data_snp_page_reclaim { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params + * + * @paddr: system physical address of page to be unsmashed. The 0th bit in the + * address indicates the page size. 0h indicates 4 KB and 1h indicates + * 2 MB page. + */ +struct sev_data_snp_page_unsmash { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters + * + * @gctx_paddr: system physical address of guest context page + * @src_addr: source address of data to operate on + * @dst_addr: destination address of data to operate on + */ +struct sev_data_snp_dbg { + u64 gctx_paddr; /* In */ + u64 src_addr; /* In */ + u64 dst_addr; /* In */ +} __packed; + +/** + * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params + * + * @gctx_paddr: system physical address of guest context page + * @req_paddr: system physical address of request page + * @res_paddr: system physical address of response page + */ +struct sev_data_snp_guest_request { + u64 gctx_paddr; /* In */ + u64 req_paddr; /* In */ + u64 res_paddr; /* In */ +} __packed; + +/** + * struct sev_data_snp_init_ex - SNP_INIT_EX structure + * + * @init_rmp: indicate that the RMP should be initialized. + * @list_paddr_en: indicate that list_paddr is valid + * @rsvd: reserved + * @rsvd1: reserved + * @list_paddr: system physical address of range list + * @rsvd2: reserved + */ +struct sev_data_snp_init_ex { + u32 init_rmp:1; + u32 list_paddr_en:1; + u32 rsvd:30; + u32 rsvd1; + u64 list_paddr; + u8 rsvd2[48]; +} __packed; + +/** + * struct sev_data_range - RANGE structure + * + * @base: system physical address of first byte of range + * @page_count: number of 4KB pages in this range + * @rsvd: reserved + */ +struct sev_data_range { + u64 base; + u32 page_count; + u32 rsvd; +} __packed; + +/** + * struct sev_data_range_list - RANGE_LIST structure + * + * @num_elements: number of elements in RANGE_ARRAY + * @rsvd: reserved + * @ranges: array of num_elements of type RANGE + */ +struct sev_data_range_list { + u32 num_elements; + u32 rsvd; + struct sev_data_range ranges[]; +} __packed; + +/** + * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure + * + * @len: length of the command buffer read by the PSP + * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU + * @rsvd1: reserved + */ +struct sev_data_snp_shutdown_ex { + u32 len; + u32 iommu_snp_shutdown:1; + u32 rsvd1:31; +} __packed; + +/** + * struct sev_platform_init_args + * + * @error: SEV firmware error code + * @probe: True if this is being called as part of CCP module probe, which + * will defer SEV_INIT/SEV_INIT_EX firmware initialization until needed + * unless psp_init_on_probe module param is set + */ +struct sev_platform_init_args { + int error; + bool probe; +}; + +/** + * struct sev_data_snp_commit - SNP_COMMIT structure + * + * @len: length of the command buffer read by the PSP + */ +struct sev_data_snp_commit { + u32 len; +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** * sev_platform_init - perform SEV INIT command * - * @error: SEV command return code + * @args: struct sev_platform_init_args to pass in arguments * * Returns: * 0 if the SEV successfully processed the command @@ -537,7 +824,7 @@ struct sev_data_attestation_report { * -%ETIMEDOUT if the SEV command timed out * -%EIO if the SEV returned a non-zero return code */ -int sev_platform_init(int *error); +int sev_platform_init(struct sev_platform_init_args *args); /** * sev_platform_status - perform SEV PLATFORM_STATUS command @@ -637,14 +924,32 @@ int sev_guest_df_flush(int *error); */ int sev_guest_decommission(struct sev_data_decommission *data, int *error); +/** + * sev_do_cmd - issue an SEV or an SEV-SNP command + * + * @cmd: SEV or SEV-SNP firmware command to issue + * @data: arguments for firmware command + * @psp_ret: SEV command return code + * + * Returns: + * 0 if the SEV device successfully processed the command + * -%ENODEV if the PSP device is not available + * -%ENOTSUPP if PSP device does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if PSP device returned a non-zero return code + */ +int sev_do_cmd(int cmd, void *data, int *psp_ret); + void *psp_copy_user_blob(u64 uaddr, u32 len); +void *snp_alloc_firmware_page(gfp_t mask); +void snp_free_firmware_page(void *addr); #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ static inline int sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; } -static inline int sev_platform_init(int *error) { return -ENODEV; } +static inline int sev_platform_init(struct sev_platform_init_args *args) { return -ENODEV; } static inline int sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; } @@ -653,6 +958,9 @@ static inline int sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; } static inline int +sev_do_cmd(int cmd, void *data, int *psp_ret) { return -ENODEV; } + +static inline int sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; } static inline int sev_guest_df_flush(int *error) { return -ENODEV; } @@ -662,6 +970,13 @@ sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); } +static inline void *snp_alloc_firmware_page(gfp_t mask) +{ + return NULL; +} + +static inline void snp_free_firmware_page(void *addr) { } + #endif /* CONFIG_CRYPTO_DEV_SP_PSP */ #endif /* __PSP_SEV_H__ */ diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h index 746fd67c3480..e8c74fa3f455 100644 --- a/include/linux/ptp_kvm.h +++ b/include/linux/ptp_kvm.h @@ -8,15 +8,15 @@ #ifndef _PTP_KVM_H_ #define _PTP_KVM_H_ +#include <linux/clocksource_ids.h> #include <linux/types.h> struct timespec64; -struct clocksource; int kvm_arch_ptp_init(void); void kvm_arch_ptp_exit(void); int kvm_arch_ptp_get_clock(struct timespec64 *ts); int kvm_arch_ptp_get_crosststamp(u64 *cycle, - struct timespec64 *tspec, struct clocksource **cs); + struct timespec64 *tspec, enum clocksource_ids *cs_id); #endif /* _PTP_KVM_H_ */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eaaef3ffec22..90507d4afcd6 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif +#ifndef exception_ip +#define exception_ip(x) instruction_pointer(x) +#endif + extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); diff --git a/include/linux/ras.h b/include/linux/ras.h index 1f4048bf2674..a64182bc72ad 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -25,6 +25,7 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len); void log_arm_hw_error(struct cper_sec_proc_arm *err); + #else static inline void log_non_standard_event(const guid_t *sec_type, @@ -35,4 +36,21 @@ static inline void log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } #endif +struct atl_err { + u64 addr; + u64 ipid; + u32 cpu; +}; + +#if IS_ENABLED(CONFIG_AMD_ATL) +void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *)); +void amd_atl_unregister_decoder(void); +void amd_retire_dram_row(struct atl_err *err); +unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err); +#else +static inline void amd_retire_dram_row(struct atl_err *err) { } +static inline unsigned long +amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; } +#endif /* CONFIG_AMD_ATL */ + #endif /* __RAS_H__ */ diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h index 0027d4c8087c..3860dbb9107a 100644 --- a/include/linux/rcu_sync.h +++ b/include/linux/rcu_sync.h @@ -37,7 +37,6 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) } extern void rcu_sync_init(struct rcu_sync *); -extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0746b1b0b663..16f519914415 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ - if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 66942d7fba7f..a365f67131ec 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -6,6 +6,12 @@ #include <linux/list.h> #include <linux/pid.h> +/* CLOSID, RMID value used by the default control group */ +#define RESCTRL_RESERVED_CLOSID 0 +#define RESCTRL_RESERVED_RMID 0 + +#define RESCTRL_PICK_ANY_CPU -1 + #ifdef CONFIG_PROC_CPU_RESCTRL int proc_resctrl_show(struct seq_file *m, @@ -153,7 +159,7 @@ struct resctrl_schema; * @cache_level: Which cache level defines scope of this resource * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: All domains for this resource + * @domains: RCU list of all domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. @@ -219,36 +225,70 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_online_cpu(unsigned int cpu); +void resctrl_offline_cpu(unsigned int cpu); /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid * for this resource and domain. * @r: resource that the counter should be read from. * @d: domain that the counter should be read from. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid + * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. * @val: result of the counter read in bytes. + * @arch_mon_ctx: An architecture specific value from + * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies + * the hardware monitor allocated for this read request. * - * Call from process context on a CPU that belongs to domain @d. + * Some architectures need to sleep when first programming some of the counters. + * (specifically: arm64's MPAM cache occupancy counters can return 'not ready' + * for a short period of time). Call from a non-migrateable process context on + * a CPU that belongs to domain @d. e.g. use smp_call_on_cpu() or + * schedule_work_on(). This function can be called with interrupts masked, + * e.g. using smp_call_function_any(), but may consistently return an error. * * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val); + u32 closid, u32 rmid, enum resctrl_event_id eventid, + u64 *val, void *arch_mon_ctx); + +/** + * resctrl_arch_rmid_read_context_check() - warn about invalid contexts + * + * When built with CONFIG_DEBUG_ATOMIC_SLEEP generate a warning when + * resctrl_arch_rmid_read() is called with preemption disabled. + * + * The contract with resctrl_arch_rmid_read() is that if interrupts + * are unmasked, it can sleep. This allows NOHZ_FULL systems to use an + * IPI, (and fail if the call needed to sleep), while most of the time + * the work is scheduled, allowing the call to sleep. + */ +static inline void resctrl_arch_rmid_read_context_check(void) +{ + if (!irqs_disabled()) + might_sleep(); +} /** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid * and eventid. * @r: The domain's resource. * @d: The rmid's domain. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid only. * @rmid: The rmid whose counter values should be reset. * @eventid: The eventid whose counter values should be reset. * * This can be called from any CPU. */ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid); + u32 closid, u32 rmid, + enum resctrl_event_id eventid); /** * resctrl_arch_reset_rmid_all() - Reset all private state associated with diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h new file mode 100644 index 000000000000..309ca72f2dfb --- /dev/null +++ b/include/linux/rw_hint.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RW_HINT_H +#define _LINUX_RW_HINT_H + +#include <linux/build_bug.h> +#include <linux/compiler_attributes.h> +#include <uapi/linux/fcntl.h> + +/* Block storage write lifetime hint values. */ +enum rw_hint { + WRITE_LIFE_NOT_SET = RWH_WRITE_LIFE_NOT_SET, + WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, + WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, + WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, + WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, + WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, +} __packed; + +/* Sparse ignores __packed annotations on enums, hence the #ifndef below. */ +#ifndef __CHECKER__ +static_assert(sizeof(enum rw_hint) == 1); +#endif + +#endif /* _LINUX_RW_HINT_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index ffe8f618ab86..17cb0761ff65 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -858,6 +858,8 @@ struct task_struct { u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; + int rcu_tasks_exit_cpu; + struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU @@ -1642,7 +1644,7 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -#define PF__HOLE__20000000 0x20000000 +#define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 4b7664c56208..0a0e23c45406 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -735,8 +735,6 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) -extern bool thread_group_exited(struct pid *pid); - extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 191b122158fb..18572c9ea724 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -176,6 +176,7 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); +bool cpus_equal_capacity(int this_cpu, int that_cpu); bool cpus_share_cache(int this_cpu, int that_cpu); bool cpus_share_resources(int this_cpu, int that_cpu); @@ -226,6 +227,11 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], { } +static inline bool cpus_equal_capacity(int this_cpu, int that_cpu) +{ + return true; +} + static inline bool cpus_share_cache(int this_cpu, int that_cpu) { return true; diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index c44f4b47b945..fe41da005970 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -2,7 +2,10 @@ #ifndef _LINUX_SEQ_BUF_H #define _LINUX_SEQ_BUF_H -#include <linux/fs.h> +#include <linux/bug.h> +#include <linux/minmax.h> +#include <linux/seq_file.h> +#include <linux/types.h> /* * Trace sequences are used to allow a function to call several other functions @@ -10,7 +13,7 @@ */ /** - * seq_buf - seq buffer structure + * struct seq_buf - seq buffer structure * @buffer: pointer to the buffer * @size: size of the buffer * @len: the amount of data inside the buffer @@ -77,10 +80,10 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) } /** - * seq_buf_str - get %NUL-terminated C string from seq_buf + * seq_buf_str - get NUL-terminated C string from seq_buf * @s: the seq_buf handle * - * This makes sure that the buffer in @s is nul terminated and + * This makes sure that the buffer in @s is NUL-terminated and * safe to read as a string. * * Note, if this is called when the buffer has overflowed, then @@ -90,7 +93,7 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) * After this function is called, s->buffer is safe to use * in string operations. * - * Returns @s->buf after making sure it is terminated. + * Returns: @s->buf after making sure it is terminated. */ static inline const char *seq_buf_str(struct seq_buf *s) { @@ -110,7 +113,7 @@ static inline const char *seq_buf_str(struct seq_buf *s) * @s: the seq_buf handle * @bufp: the beginning of the buffer is stored here * - * Return the number of bytes available in the buffer, or zero if + * Returns: the number of bytes available in the buffer, or zero if * there's no space. */ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp) @@ -132,7 +135,7 @@ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp) * @num: the number of bytes to commit * * Commit @num bytes of data written to a buffer previously acquired - * by seq_buf_get. To signal an error condition, or that the data + * by seq_buf_get_buf(). To signal an error condition, or that the data * didn't fit in the available space, pass a negative @num value. */ static inline void seq_buf_commit(struct seq_buf *s, int num) diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 536b2581d3e2..55b1f3ba48ac 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -748,8 +748,17 @@ struct uart_driver { void uart_write_wakeup(struct uart_port *port); -#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test, \ - for_post) \ +/** + * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() + * + * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer + */ +enum UART_TX_FLAGS { + UART_TX_NOSTOP = BIT(0), +}; + +#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ + for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct circ_buf *xmit = &__port->state->xmit; \ @@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port); if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (pending == 0) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ @@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port); */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ - __uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count, \ + __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) @@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port); * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ - __uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({})) + __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) + +/** + * uart_port_tx_flags -- transmit helper for uart_port with flags + * @port: uart port + * @ch: variable to store a character to be written to the HW + * @flags: %UART_TX_NOSTOP or similar + * @tx_ready: can HW accept more data function + * @put_char: function to write a character + * + * See uart_port_tx_limited() for more details. + */ +#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ + __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ diff --git a/include/linux/smp.h b/include/linux/smp.h index e87520dc2959..7398ce99786c 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -218,6 +218,8 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } +#define setup_max_cpus 0 + #ifdef CONFIG_UP_LATE_INIT extern void __init up_late_init(void); static inline void smp_init(void) { up_late_init(); } @@ -261,7 +263,7 @@ static inline int get_boot_cpu_id(void) * regular asm read for the stable. */ #ifndef __smp_processor_id -#define __smp_processor_id(x) raw_smp_processor_id(x) +#define __smp_processor_id() raw_smp_processor_id() #endif #ifdef CONFIG_DEBUG_PREEMPT diff --git a/include/linux/soc/andes/irq.h b/include/linux/soc/andes/irq.h new file mode 100644 index 000000000000..edc3182d6e66 --- /dev/null +++ b/include/linux/soc/andes/irq.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 Andes Technology Corporation + */ +#ifndef __ANDES_IRQ_H +#define __ANDES_IRQ_H + +/* Andes PMU irq number */ +#define ANDES_RV_IRQ_PMOVI 18 +#define ANDES_RV_IRQ_LAST ANDES_RV_IRQ_PMOVI +#define ANDES_SLI_CAUSE_BASE 256 + +/* Andes PMU related registers */ +#define ANDES_CSR_SLIE 0x9c4 +#define ANDES_CSR_SLIP 0x9c5 +#define ANDES_CSR_SCOUNTEROF 0x9d4 + +#endif /* __ANDES_IRQ_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..378ab1cd23bd 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -298,7 +298,7 @@ struct swap_info_struct { unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ - struct bdev_handle *bdev_handle;/* open handle of the bdev */ + struct file *bdev_file; /* open handle of the bdev */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 89b290d8c8dc..a1c47a6d69b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -221,8 +221,10 @@ struct tcp_sock { u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ u16 tcp_header_len; /* Bytes of tcp header to send */ + u8 scaling_ratio; /* see tcp_win_from_space() */ u8 chrono_type : 2, /* current chronograph type */ repair : 1, + tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ __cacheline_group_end(tcp_sock_read_txrx); @@ -352,7 +354,6 @@ struct tcp_sock { u32 compressed_ack_rcv_nxt; struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ @@ -368,8 +369,7 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - tcp_usec_ts:1, /* TSval values in usec */ - unused:4; + unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ diff --git a/include/linux/tick.h b/include/linux/tick.h index 716d17f31c45..70dc884054f6 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -19,16 +19,22 @@ extern void __init tick_init(void); extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); -extern void tick_handover_do_timer(void); extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } -static inline void tick_handover_do_timer(void) { } static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU) +extern int tick_cpu_dying(unsigned int cpu); +extern void tick_assert_timekeeping_handover(void); +#else +#define tick_cpu_dying NULL +static inline void tick_assert_timekeeping_handover(void) { } +#endif + #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND) extern void tick_freeze(void); extern void tick_unfreeze(void); @@ -69,12 +75,6 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) -extern void tick_offline_cpu(unsigned int cpu); -#else -static inline void tick_offline_cpu(unsigned int cpu) { } -#endif - #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else @@ -164,9 +164,16 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #endif /* !CONFIG_NO_HZ_COMMON */ +/* + * Mask of CPUs that are nohz_full. + * + * Users should be guarded by CONFIG_NO_HZ_FULL or a tick_nohz_full_cpu() + * check. + */ +extern cpumask_var_t tick_nohz_full_mask; + #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; -extern cpumask_var_t tick_nohz_full_mask; static inline bool tick_nohz_full_enabled(void) { diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7c43e98cf211..7e50cbd97f86 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -268,15 +268,17 @@ struct system_device_crosststamp { }; /** - * struct system_counterval_t - system counter value with the pointer to the + * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value - * @cs: Clocksource corresponding to system counter value. Used by - * timekeeping code to verify comparibility of two cycle values + * @cs_id: Clocksource ID corresponding to system counter value. Used by + * timekeeping code to verify comparability of two cycle values. + * The default ID, CSID_GENERIC, does not identify a specific + * clocksource. */ struct system_counterval_t { u64 cycles; - struct clocksource *cs; + enum clocksource_ids cs_id; }; /* diff --git a/include/linux/timer.h b/include/linux/timer.h index f18a2f1eb79e..14a633ba61d6 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -36,16 +36,10 @@ * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! * - * @TIMER_PINNED: A pinned timer will not be affected by any timer - * placement heuristics (like, NOHZ) and will always expire on the CPU - * on which the timer was enqueued. - * - * Note: Because enqueuing of timers can migrate the timer from one - * CPU to another, pinned timers are not guaranteed to stay on the - * initialy selected CPU. They move to the CPU on which the enqueue - * function is invoked via mod_timer() or add_timer(). If the timer - * should be placed on a particular CPU, then add_timer_on() has to be - * used. + * @TIMER_PINNED: A pinned timer will always expire on the CPU on which the + * timer was enqueued. When a particular CPU is required, add_timer_on() + * has to be used. Enqueue via mod_timer() and add_timer() is always done + * on the local CPU. */ #define TIMER_CPUMASK 0x0003FFFF #define TIMER_MIGRATING 0x00040000 @@ -165,6 +159,8 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires); #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) extern void add_timer(struct timer_list *timer); +extern void add_timer_local(struct timer_list *timer); +extern void add_timer_global(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); extern int timer_delete_sync(struct timer_list *timer); diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 9ec229dfddaa..1ef95c0287f0 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -9,9 +9,15 @@ /* * Trace sequences are used to allow a function to call several other functions * to create a string of data to use. + * + * Have the trace seq to be 8K which is typically PAGE_SIZE * 2 on + * most architectures. The TRACE_SEQ_BUFFER_SIZE (which is + * TRACE_SEQ_SIZE minus the other fields of trace_seq), is the + * max size the output of a trace event may be. */ -#define TRACE_SEQ_BUFFER_SIZE (PAGE_SIZE * 2 - \ +#define TRACE_SEQ_SIZE 8192 +#define TRACE_SEQ_BUFFER_SIZE (TRACE_SEQ_SIZE - \ (sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int))) struct trace_seq { diff --git a/include/linux/uio.h b/include/linux/uio.h index bea9c89922d9..00cebe2b70de 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -40,7 +40,6 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; - bool copy_mc; bool nofault; bool data_source; size_t iov_offset; @@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); -static inline void iov_iter_set_copy_mc(struct iov_iter *i) -{ - i->copy_mc = true; -} - -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return i->copy_mc; -} #else #define _copy_mc_to_iter _copy_to_iter -static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return false; -} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, - .copy_mc = false, .data_source = direction, .ubuf = buf, .count = count, diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index a771ccc038ac..6532beb587b1 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -236,7 +236,6 @@ struct usb_ep { unsigned max_streams:16; unsigned mult:2; unsigned maxburst:5; - unsigned fifo_mode:1; u8 address; const struct usb_endpoint_descriptor *desc; const struct usb_ss_ep_comp_descriptor *comp_desc; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index cd77fc6095a1..ac95e7c89df5 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -55,7 +55,7 @@ struct giveback_urb_bh { bool high_prio; spinlock_t lock; struct list_head head; - struct tasklet_struct bh; + struct work_struct bh; struct usb_host_endpoint *completing_ep; }; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2cc0a9606175..158784dd189a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -22,20 +22,54 @@ */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) -enum { +enum work_bits { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ - WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ - WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ + WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */ + WORK_STRUCT_PWQ_BIT, /* data points to pwq */ + WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ -#else - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */ #endif + WORK_STRUCT_FLAG_BITS, + /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_STRUCT_COLOR_BITS = 4, + /* + * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/ + * debugobjects turned off. This makes pwqs aligned to 256 bytes (512 + * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors. + * + * MSB + * [ pwq pointer ] [ flush color ] [ STRUCT flags ] + * 4 bits 4 or 5 bits + */ + WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, + + /* + * data contains off-queue information when !WORK_STRUCT_PWQ. + * + * MSB + * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ] + * 1 bit 4 or 5 bits + */ + WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, + WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT, + WORK_OFFQ_FLAG_END, + WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, + + /* + * When a work item is off queue, the high bits encode off-queue flags + * and the last pool it was on. Cap pool ID to 31 bits and use the + * highest number to indicate that no pool is associated. + */ + WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, + WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, +}; + +enum work_flags { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, @@ -45,35 +79,14 @@ enum { #else WORK_STRUCT_STATIC = 0, #endif +}; +enum wq_misc_consts { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, - /* - * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. - * This makes pwqs aligned to 256 bytes and allows 16 workqueue - * flush colors. - */ - WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + - WORK_STRUCT_COLOR_BITS, - - /* data contains off-queue information when !WORK_STRUCT_PWQ */ - WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, - - __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - - /* - * When a work item is off queue, its high bits point to the last - * pool it was on. Cap at 31 bits and use the highest number to - * indicate that no pool is associated. - */ - WORK_OFFQ_FLAG_BITS = 1, - WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, - WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, - WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, @@ -83,12 +96,10 @@ enum { }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ -#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_CANCELING (1ul << WORK_OFFQ_CANCELING_BIT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) - -#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) -#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) +#define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ @@ -347,7 +358,8 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ -enum { +enum wq_flags { + WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ @@ -386,11 +398,22 @@ enum { __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ - __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ + /* BH wq only allows the following flags */ + __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI, +}; + +enum wq_consts { WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, + + /* + * Per-node default cap on min_active. Unless explicitly set, min_active + * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see + * workqueue_struct->min_active definition. + */ + WQ_DFL_MIN_ACTIVE = 8, }; /* @@ -420,6 +443,9 @@ enum { * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. + * + * system_bh[_highpri]_wq are convenience interface to softirq. BH work items + * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; @@ -428,16 +454,43 @@ extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; +extern struct workqueue_struct *system_bh_wq; +extern struct workqueue_struct *system_bh_highpri_wq; + +void workqueue_softirq_action(bool highpri); +void workqueue_softirq_dead(unsigned int cpu); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags - * @max_active: max in-flight work items per CPU, 0 for default + * @max_active: max in-flight work items, 0 for default * remaining args: args for @fmt * - * Allocate a workqueue with the specified parameters. For detailed - * information on WQ_* flags, please refer to + * For a per-cpu workqueue, @max_active limits the number of in-flight work + * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be + * executing at most one work item for the workqueue. + * + * For unbound workqueues, @max_active limits the number of in-flight work items + * for the whole system. e.g. @max_active of 16 indicates that that there can be + * at most 16 work items executing for the workqueue in the whole system. + * + * As sharing the same active counter for an unbound workqueue across multiple + * NUMA nodes can be expensive, @max_active is distributed to each NUMA node + * according to the proportion of the number of online CPUs and enforced + * independently. + * + * Depending on online CPU distribution, a node may end up with per-node + * max_active which is significantly lower than @max_active, which can lead to + * deadlocks if the per-node concurrency limit is lower than the maximum number + * of interdependent work items for the workqueue. + * + * To guarantee forward progress regardless of online CPU distribution, the + * concurrency limit on every node is guaranteed to be equal to or greater than + * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means + * that the sum of per-node max_active's may be larger than @max_active. + * + * For detailed information on %WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: @@ -460,8 +513,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ - alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ - __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) + alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) @@ -471,6 +523,9 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) +#define from_work(var, callback_work, work_fieldname) \ + container_of(callback_work, typeof(*var), work_fieldname) + extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); @@ -508,6 +563,8 @@ extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); +extern void workqueue_set_min_active(struct workqueue_struct *wq, + int min_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); |