linux.git/arch/riscv/kernel/vdso, branch v4.16 Linux kernel source tree RISC-V: Make __NR_riscv_flush_icache visible to userspace 2018-01-07T23:14:37+00:00 Palmer Dabbelt palmer@dabbelt.com 2017-12-27T03:11:22+00:00 9e49a4ed072ab67b17238c5a45d7cba7f848659e We were hoping to avoid making this visible to userspace, but it looks like we're going to have to because QEMU's user-mode emulation doesn't want to emulate a vDSO. Having vDSO-only system calls was a bit unothodox anyway, so I think in this case it's OK to just make the actual system call number public. This patch simply moves the definition of __NR_riscv_flush_icache availiable to userspace, which results in the deletion of the now empty vdso-syscalls.h. Changes since v1: * I've moved the definition into uapi/asm/syscalls.h rathen than uapi/asm/unistd.h. This allows me to keep asm/unistd.h, so we can keep the syscall table macros sane. * As a side effect of the above, this no longer disables all system calls on RISC-V. Whoops! Signed-off-by: Palmer Dabbelt <palmer@sifive.com> 
We were hoping to avoid making this visible to userspace, but it looks
like we're going to have to because QEMU's user-mode emulation doesn't
want to emulate a vDSO.  Having vDSO-only system calls was a bit
unothodox anyway, so I think in this case it's OK to just make the
actual system call number public.

This patch simply moves the definition of __NR_riscv_flush_icache
availiable to userspace, which results in the deletion of the now empty
vdso-syscalls.h.

Changes since v1:

* I've moved the definition into uapi/asm/syscalls.h rathen than
  uapi/asm/unistd.h.  This allows me to keep asm/unistd.h, so we can
  keep the syscall table macros sane.
* As a side effect of the above, this no longer disables all system
  calls on RISC-V.  Whoops!

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
RISC-V: Allow userspace to flush the instruction cache 2017-11-30T20:58:29+00:00 Andrew Waterman andrew@sifive.com 2017-10-25T21:32:16+00:00 921ebd8f2c081b3cf6c3b29ef4103eef3ff26054 Despite RISC-V having a direct 'fence.i' instruction available to userspace (which we can't trap!), that's not actually viable when running on Linux because the kernel might schedule a process on another hart. There is no way for userspace to handle this without invoking the kernel (as it doesn't know the thread->hart mappings), so we've defined a RISC-V specific system call to flush the instruction cache. This patch adds both a system call and a VDSO entry. If possible, we'd like to avoid having the system call be considered part of the user-facing ABI and instead restrict that to the VDSO entry -- both just in general to avoid having additional user-visible ABI to maintain, and because we'd prefer that users just call the VDSO entry because there might be a better way to do this in the future (ie, one that doesn't require entering the kernel). Signed-off-by: Andrew Waterman <andrew@sifive.com> Signed-off-by: Palmer Dabbelt <palmer@sifive.com> 
Despite RISC-V having a direct 'fence.i' instruction available to
userspace (which we can't trap!), that's not actually viable when
running on Linux because the kernel might schedule a process on another
hart.  There is no way for userspace to handle this without invoking the
kernel (as it doesn't know the thread->hart mappings), so we've defined
a RISC-V specific system call to flush the instruction cache.

This patch adds both a system call and a VDSO entry.  If possible, we'd
like to avoid having the system call be considered part of the
user-facing ABI and instead restrict that to the VDSO entry -- both just
in general to avoid having additional user-visible ABI to maintain, and
because we'd prefer that users just call the VDSO entry because there
might be a better way to do this in the future (ie, one that doesn't
require entering the kernel).

Signed-off-by: Andrew Waterman <andrew@sifive.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
RISC-V: Add VDSO entries for clock_get/gettimeofday/getcpu 2017-11-27T15:51:39+00:00 Andrew Waterman andrew@sifive.com 2017-10-23T22:42:14+00:00 28dfbe6ed483e8a589cce88095d7787d61bf9c16 For now these are just placeholders that execute the syscall. We will later optimize them to avoid kernel crossings, but we'd like to have the VDSO entries from the first released kernel version to make the ABI simpler. Signed-off-by: Andrew Waterman <andrew@sifive.com> Signed-off-by: Palmer Dabbelt <palmer@sifive.com> 
For now these are just placeholders that execute the syscall.  We will
later optimize them to avoid kernel crossings, but we'd like to have the
VDSO entries from the first released kernel version to make the ABI
simpler.

Signed-off-by: Andrew Waterman <andrew@sifive.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
RISC-V: Remove __vdso_cmpxchg{32,64} symbol versions 2017-11-27T15:51:39+00:00 Palmer Dabbelt palmer@sifive.com 2017-11-20T18:33:09+00:00 b7e5a591502b03b4a1408bb93a15968d6ea446ce These were left over from an earlier version of the port. Signed-off-by: Palmer Dabbelt <palmer@sifive.com> 
These were left over from an earlier version of the port.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
RISC-V: User-facing API 2017-09-26T22:26:48+00:00 Palmer Dabbelt palmer@dabbelt.com 2017-07-11T01:07:09+00:00 e2c0cdfba7f69925afc92b20cd9835d81e11a4f1 This patch contains code that is in some way visible to the user: including via system calls, the VDSO, module loading and signal handling. It also contains some generic code that is ABI visible. Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com> 
This patch contains code that is in some way visible to the user:
including via system calls, the VDSO, module loading and signal
handling.  It also contains some generic code that is ABI visible.

Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>