summaryrefslogtreecommitdiff
path: root/arch/mips/kernel/process.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-08-13 19:24:32 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-13 19:24:32 -0700
commite5a32b5b21a18d24e9d735891550c194b4c60bd2 (patch)
treea5c78286f8e6794a5760ab9f3f029c57ea624183 /arch/mips/kernel/process.c
parent2280a5360e4ff9320bfb12f760a8e9916ff5e7bc (diff)
parent22f20a110321efb7cde3e87ae99862e1036ca285 (diff)
Merge tag 'mips_4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux
Pull MIPS updates from Paul Burton: "Here are the main MIPS changes for 4.19. An overview of the general architecture changes: - Massive DMA ops refactoring from Christoph Hellwig (huzzah for deleting crufty code!). - We introduce NT_MIPS_DSP & NT_MIPS_FP_MODE ELF notes & corresponding regsets to expose DSP ASE & floating point mode state respectively, both for live debugging & core dumps. - We better optimize our code by hard-coding cpu_has_* macros at compile time where their values are known due to the ISA revision that the kernel build is targeting. - The EJTAG exception handler now better handles SMP systems, where it was previously possible for CPUs to clobber a register value saved by another CPU. - Our implementation of memset() gained a couple of fixes for MIPSr6 systems to return correct values in some cases where stores fault. - We now implement ioremap_wc() using the uncached-accelerated cache coherency attribute where supported, which is detected during boot, and fall back to plain uncached access where necessary. The MIPS-specific (and unused in tree) ioremap_uncached_accelerated() & ioremap_cacheable_cow() are removed. - The prctl(PR_SET_FP_MODE, ...) syscall is better supported for SMP systems by reworking the way we ensure remote CPUs that may be running threads within the affected process switch mode. - Systems using the MIPS Coherence Manager will now set the MIPS_IC_SNOOPS_REMOTE flag to avoid some unnecessary cache maintenance overhead when flushing the icache. - A few fixes were made for building with clang/LLVM, which now sucessfully builds kernels for many of our platforms. - Miscellaneous cleanups all over. And some platform-specific changes: - ar7 gained stubs for a few clock API functions to fix build failures for some drivers. - ath79 gained support for a few new SoCs, a few fixes & better gpio-keys support. - Ci20 now exposes its SPI bus using the spi-gpio driver. - The generic platform can now auto-detect a suitable value for PHYS_OFFSET based upon the memory map described by the device tree, allowing us to avoid wasting memory on page book-keeping for systems where RAM starts at a non-zero physical address. - Ingenic systems using the jz4740 platform code now link their vmlinuz higher to allow for kernels of a realistic size. - Loongson32 now builds the kernel targeting MIPSr1 rather than MIPSr2 to avoid CPU errata. - Loongson64 gains a couple of fixes, a workaround for a write buffering issue & support for the Loongson 3A R3.1 CPU. - Malta now uses the piix4-poweroff driver to handle powering down. - Microsemi Ocelot gained support for its SPI bus & NOR flash, its second MDIO bus and can now be supported by a FIT/.itb image. - Octeon saw a bunch of header cleanups which remove a lot of duplicate or unused code" * tag 'mips_4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux: (123 commits) MIPS: Remove remnants of UASM_ISA MIPS: netlogic: xlr: Remove erroneous check in nlm_fmn_send() MIPS: VDSO: Force link endianness MIPS: Always specify -EB or -EL when using clang MIPS: Use dins to simplify __write_64bit_c0_split() MIPS: Use read-write output operand in __write_64bit_c0_split() MIPS: Avoid using array as parameter to write_c0_kpgd() MIPS: vdso: Allow clang's --target flag in VDSO cflags MIPS: genvdso: Remove GOT checks MIPS: Remove obsolete MIPS checks for DST node "chosen@0" MIPS: generic: Remove input symbols from defconfig MIPS: Delete unused code in linux32.c MIPS: Remove unused sys_32_mmap2 MIPS: Remove nabi_no_regargs mips: dts: mscc: enable spi and NOR flash support on ocelot PCB123 mips: dts: mscc: Add spi on Ocelot MIPS: Loongson: Merge load addresses MIPS: Loongson: Set Loongson32 to MIPS32R1 MIPS: mscc: ocelot: add interrupt controller properties to GPIO controller MIPS: generic: Select MIPS_AUTO_PFN_OFFSET ...
Diffstat (limited to 'arch/mips/kernel/process.c')
-rw-r--r--arch/mips/kernel/process.c80
1 files changed, 42 insertions, 38 deletions
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 9670e70139fd..8fc69891e117 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -30,6 +30,7 @@
#include <linux/random.h>
#include <linux/prctl.h>
#include <linux/nmi.h>
+#include <linux/cpu.h>
#include <asm/asm.h>
#include <asm/bootinfo.h>
@@ -706,19 +707,25 @@ int mips_get_process_fp_mode(struct task_struct *task)
return value;
}
-static void prepare_for_fp_mode_switch(void *info)
+static long prepare_for_fp_mode_switch(void *unused)
{
- struct mm_struct *mm = info;
-
- if (current->mm == mm)
- lose_fpu(1);
+ /*
+ * This is icky, but we use this to simply ensure that all CPUs have
+ * context switched, regardless of whether they were previously running
+ * kernel or user code. This ensures that no CPU currently has its FPU
+ * enabled, or is about to attempt to enable it through any path other
+ * than enable_restore_fp_context() which will wait appropriately for
+ * fp_mode_switching to be zero.
+ */
+ return 0;
}
int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
{
const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
struct task_struct *t;
- int max_users;
+ struct cpumask process_cpus;
+ int cpu;
/* If nothing to change, return right away, successfully. */
if (value == mips_get_process_fp_mode(task))
@@ -751,35 +758,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
- /* Proceed with the mode switch */
- preempt_disable();
-
- /* Save FP & vector context, then disable FPU & MSA */
- if (task->signal == current->signal)
- lose_fpu(1);
-
- /* Prevent any threads from obtaining live FP context */
- atomic_set(&task->mm->context.fp_mode_switching, 1);
- smp_mb__after_atomic();
-
- /*
- * If there are multiple online CPUs then force any which are running
- * threads in this process to lose their FPU context, which they can't
- * regain until fp_mode_switching is cleared later.
- */
- if (num_online_cpus() > 1) {
- /* No need to send an IPI for the local CPU */
- max_users = (task->mm == current->mm) ? 1 : 0;
-
- if (atomic_read(&current->mm->mm_users) > max_users)
- smp_call_function(prepare_for_fp_mode_switch,
- (void *)current->mm, 1);
- }
-
- /*
- * There are now no threads of the process with live FP context, so it
- * is safe to proceed with the FP mode switch.
- */
+ /* Indicate the new FP mode in each thread */
for_each_thread(task, t) {
/* Update desired FP register width */
if (value & PR_FP_MODE_FR) {
@@ -796,9 +775,34 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
}
- /* Allow threads to use FP again */
- atomic_set(&task->mm->context.fp_mode_switching, 0);
- preempt_enable();
+ /*
+ * We need to ensure that all threads in the process have switched mode
+ * before returning, in order to allow userland to not worry about
+ * races. We can do this by forcing all CPUs that any thread in the
+ * process may be running on to schedule something else - in this case
+ * prepare_for_fp_mode_switch().
+ *
+ * We begin by generating a mask of all CPUs that any thread in the
+ * process may be running on.
+ */
+ cpumask_clear(&process_cpus);
+ for_each_thread(task, t)
+ cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+ /*
+ * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+ *
+ * The CPUs may have rescheduled already since we switched mode or
+ * generated the cpumask, but that doesn't matter. If the task in this
+ * process is scheduled out then our scheduling
+ * prepare_for_fp_mode_switch() will simply be redundant. If it's
+ * scheduled in then it will already have picked up the new FP mode
+ * whilst doing so.
+ */
+ get_online_cpus();
+ for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+ work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+ put_online_cpus();
wake_up_var(&task->mm->context.fp_mode_switching);