Age | Commit message (Collapse) | Author | |
---|---|---|---|
2018-05-04 | perfmon: fix broken global pmc counting.HEADperfmon | Remy Noel | |
When a pmc was freed, the total amount of pmc was not decreased. | |||
2018-05-03 | Merge branch 'master' into perfmon | Remy Noel | |
2018-05-03 | perfmon: Remove useless accessors. | Remy Noel | |
Also rename pmc oveflow handling function. | |||
2018-05-03 | perfmon: add polling overflow implementation in perfmon | Remy Noel | |
2018-05-03 | perfmon: register a pmu_driver in place of pmu_ops. | Remy Noel | |
Replace pmu_get_width with a property. Prepare the default overfow handling. | |||
2018-04-29 | Minor changes | Richard Braun | |
2018-04-27 | kern/atomic: minor improvement | Richard Braun | |
Remove the need from architecture-specific code to check alignment. | |||
2018-04-26 | kern/atomic: minor rework | Richard Braun | |
Allow architectures to specifically override any of the overloaded functions. This removes the need from architecture-specific code to implement selection. | |||
2018-04-24 | Fix missing kern/syscnt.h inclusions | Richard Braun | |
2018-04-24 | kern/atomic: fix alignment check | Richard Braun | |
2018-04-21 | kern/mutex/mutex_adaptive: fix atomic operation calls | Richard Braun | |
2018-04-21 | kern/atomic: rework | Richard Braun | |
This commit restricts atomic operations to 32-bit and 64-bit (when supported). It keeps a similar source interface, but adds restrictions on the supported types. The main drive behind this change is portability, and in particular, upcoming local atomic operations. | |||
2018-04-21 | Fix atomic operations argument types | Richard Braun | |
In preparation of the rework of atomic operations, all atomic function calls are fixed to use fully supported, compatible types. This means that atomic operations ar erestricted to 32-bit and 64-bit, and that value types must be strictly compatible with pointer types. | |||
2018-04-21 | perfmon: fix overflo test only working on 64 bit counters. | Remy Noel | |
2018-04-21 | perfmon: various cosmetics. | Remy Noel | |
2018-04-21 | perfmon: Test overflow in cpu test. | Remy Noel | |
Adds perfmon_event_write as a test-only API. | |||
2018-04-21 | perfmon: Add overflow handling. | Remy Noel | |
Only architectural version 1 handled so far. | |||
2018-04-21 | kern/perfmon: add perfmon_cpu_pmc get/setters. | Remy Noel | |
2018-04-21 | kern/perfmon: Handle overflow on sync. | Remy Noel | |
Add new perfmon driver method "get_pmc_width". | |||
2018-04-21 | kern/perfmon.c: Add pmc id to index map. | Remy Noel | |
Will be used to handle calls from the pmu implementations. | |||
2018-04-21 | Merge branch 'master' into perfmon | Remy Noel | |
2018-04-19 | kern/atomic: remove shortcuts | Richard Braun | |
These shortcuts just don't bring enough value. | |||
2018-04-18 | Merge branch 'master' into perfmon | Remy Noel | |
2018-04-14 | kern/rcu: make the window check interval configurable | Richard Braun | |
2018-04-14 | kern/atomic: fix consume memory order | Richard Braun | |
The consume memory order is known to be problematic in the C11 specification, and as a result, most compilers alias it to acquire. Based on the assumption that the kernel doesn't run on architectures with an Alpha-like memory model, the consume memory order was aliased to relaxed, letting the CPU identify data dependencies. But there may also be issues at compile time, making this hack is dangerous. As a result, the actual consume memory order as implemented by the compiler is now used to define the kernel consume memory order. See https://lwn.net/Articles/588300/. | |||
2018-04-14 | Rename variables in function-like macros | Richard Braun | |
2018-04-14 | Fix left-over reserved identifiers | Richard Braun | |
For some reason, commit be5b9d6ab9f7e7a81c367e4bb0823ba11f85940f didn't take care of all reserved identifiers. | |||
2018-04-14 | Merge branch 'master' into perfmon | Remy Noel | |
2018-04-13 | kern/xcall: upgrade spurious interrupts to errors | Richard Braun | |
2018-04-01 | Merge branch 'bulletin' | Richard Braun | |
2018-04-01 | kern/bulletin: new module | Richard Braun | |
2018-04-01 | kern/rcu: add assertion in rcu_defer | Richard Braun | |
2018-04-01 | kern/{hash,list}: update from upstream | Richard Braun | |
This commit fixes undefined behavior in hash_str, and RCU linked list walking. | |||
2018-03-13 | Merge branch 'master' into perfmon | Remy Noel | |
2018-03-12 | perfmon: Coding style & cosmetic fixes | Remy Noel | |
2018-03-03 | kern/spinlock: minor comment fix | Richard Braun | |
2018-03-02 | kern/spinlock: fix and optimize | Richard Braun | |
Making the unlock operation block allows tricky deadlocks to occur in case a thread is interrupted right before announcing itself as the first waiter in the queue. Since locking is expected to block, the spinlock implementation is reworked to move the hand-off performed by the unlock operation into the lock operation. As a side effect, the common case of a single waiter is also optimized. | |||
2018-03-02 | kern/spinlock: fix direct use of CONFIG_SPINLOCK_DEBUG | Richard Braun | |
2018-02-25 | Merge branch 'master' into perfmon | Remy Noel | |
2018-02-25 | Merge branch 'master' into perfmon | Remy Noel | |
2018-02-24 | kern/kmem: new KMEM_DEBUG option | Richard Braun | |
2018-02-24 | kern/log2: fix naming | Richard Braun | |
2018-02-24 | Update license note about modules from librbraun | Richard Braun | |
2018-02-24 | kern/{cbuf,fmt,hash,hlist,list,plist,rdxtree,shell,slist}: update from upstream | Richard Braun | |
Note that this commit changes the order of some list operations without triggering warnings. | |||
2018-02-24 | New ENOENT error code | Richard Braun | |
2018-02-24 | New errno.h standard header | Richard Braun | |
Use standard errno codes. This change also adds strerror to string.h. | |||
2018-02-24 | Don't use reserved identifiers | Richard Braun | |
2018-02-22 | perfmon: split pmu into amd and intel architectures. | Remy Noel | |
pmu_driver handling is now perfmon's responsibility. | |||
2018-02-22 | kern/spinlock: add ownership tracking as a debugging feature | Richard Braun | |
2018-02-21 | kern/rcu: comment the loop in rcu_cpu_data_check_gp_state | Richard Braun | |