wireguard-linux/arch/um/kernel/irq.c, branch jd/unified-crypt-queue

um: irq: Fix LAST_IRQ usage in init_IRQ()

2019-09-16T06:38:58Z

LAST_IRQ was used incorrectly in init_IRQ. Commit 09ccf0364ca3 forgot to update the for loop. Fix this. Fixes: 49da7e64f33e ("High Performance UML Vector Network Driver") Fixes: 09ccf0364ca3 ("um: Fix off by one error in IRQ enumeration") Signed-off-by: Erel Geron Signed-off-by: Johannes Berg Acked-by: Anton Ivanov Signed-off-by: Richard Weinberger

um: Add SPDX headers to files in arch/um/kernel/

2019-09-15T19:37:17Z

Convert files to use SPDX header. All files are licensed under the GPLv2. Signed-off-by: Alex Dewar Signed-off-by: Richard Weinberger

um: Don't garbage collect in deactivate_all_fds()

2019-07-02T21:27:19Z

My previous commit didn't actually address the whole issue with lockdep shutdown, I had another local modification that disabled lockdep but that wasn't sufficient alone, so had to do the other change. Another issue remained though - during kfree() we acquire locks and lockdep tries to annotate those with exactly the same issue in the other patch - we no longer have "current". So, just remove the garbage collection. There's no value in it anyway since we're going to shut down anyway and marking a slab object as free is now not very useful anymore. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger

um: Remove locking in deactivate_all_fds()

2019-07-02T21:27:05Z

Not only does the locking contradict the comment, and as the comment says is pointless and actually harmful (all the actual OS threads have exited already), but it also causes crashes when lockdep is enabled, because calling into the spinlock calls into lockdep, which then tries to determine the current task, which no longer exists. Remove the locking to let UML shut down cleanly in case lockdep is enabled. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger

um: Fix IRQ controller regression on console read

2019-07-02T21:26:52Z

The conversion of UML to use epoll based IRQ controller claimed that clone_one_chan() can safely call um_free_irq() while starting to ignore the delay_free_irq parameter that explicitly noted that the IRQ cannot be freed because this is being called from chan_interrupt(). This resulted in free_irq() getting called in interrupt context ("Trying to free IRQ 6 from IRQ context!"). Fix this by restoring previously used delay_free_irq processing. Fixes: ff6a17989c08 ("Epoll based IRQ controller") Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger

um: irq: don't set the chip for all irqs

2019-05-07T21:18:28Z

Setting a chip for an interrupt marks it as allocated. Since UM doesn't support dynamic interrupt numbers (yet), it means we cannot simply increase NR_IRQS and then use the free irqs between LAST_IRQ and NR_IRQS with gpio-mockup or iio testing drivers as irq_alloc_descs() will fail after not being able to neither find an unallocated range of interrupts nor expand the range. Only call irq_set_chip_and_handler() for irqs until LAST_IRQ. Signed-off-by: Bartosz Golaszewski Reviewed-by: Anton Ivanov Acked-by: Anton Ivanov Signed-off-by: Richard Weinberger

um: Remove obsolete reenable_XX calls

2018-12-27T21:48:35Z

reenable_fd has been a NOP since the introduction of the EPOLL based interrupt controller. reenable_channel() is no longer needed as the flow control is now handled via the write IRQs on the channel. Signed-off-by: Anton Ivanov Signed-off-by: Richard Weinberger

um: NULL check before kfree is not needed

2018-10-29T21:23:12Z

kfree(NULL) is safe,so this removes NULL check before freeing the mem Signed-off-by: YueHaibing Signed-off-by: Richard Weinberger

um: Add missing EXPORT for free_irq_by_fd()

2018-02-19T18:38:51Z

Fixes: ERROR: "free_irq_by_fd" [arch/um/drivers/random.ko] undefined! Signed-off-by: Anton Ivanov Signed-off-by: Richard Weinberger

Epoll based IRQ controller

2018-02-19T18:38:51Z

1. Removes the need to walk the IRQ/Device list to determine who triggered the IRQ. 2. Improves scalability (up to several times performance improvement for cases with 10s of devices). 3. Improves UML baseline IO performance for one disk + one NIC use case by up to 10%. 4. Introduces write poll triggered IRQs. 5. Prerequisite for introducing high performance mmesg family of functions in network IO. 6. Fixes RNG shutdown which was leaking a file descriptor Signed-off-by: Anton Ivanov Signed-off-by: Richard Weinberger