* Re: [PATCH 3/5] powerpc/mpc5121: shared DIU framebuffer support
From: Anatolij Gustschin @ 2010-05-01 15:15 UTC (permalink / raw)
To: Scott Wood
Cc: linux-fbdev, wd, dzu, John Rigby, devicetree-discuss,
linuxppc-dev, Timur Tabi, yorksun
In-Reply-To: <4BDB402C.9080301@freescale.com>
On Fri, 30 Apr 2010 15:40:12 -0500
Scott Wood <scottwood@freescale.com> wrote:
> Timur Tabi wrote:
> > On Fri, Apr 30, 2010 at 11:22 AM, Scott Wood <scottwood@freescale.com> wrote:
> >
> >>> That's what I meant. Actually, I think it's ULL. Regardless, I think
> >>> the compiler will see the "1000000000 ... * 1000" and just combine
> >>> them together. You're not actually outsmarting the compiler.
> >> The compiler will do no such thing. That's a valid transformation when
> >> doing pure math, but not when working with integers.
> >
> > I ran some tests, and it appears you're right. I doesn't make a lot
> > of sense to me, but whatever.
> >
> > However, "(1000000000 / pixclock) * 1000" produces a result that's
> > less accurate than "1000000000000ULL / pixclock".
>
> Precisely, that's what makes it a distinct computation -- as far as the
> compiler knows, it could be intentional. Plus, turning it into 64-bit
> math would invoke a library call for 64-bit division, which wouldn't be
> much of an optimization anyway.
>
> The question is whether the loss of accuracy matters in this case.
Here, this loss of accuracy doesn't matter at all. Max. possible
loss by this current conversion is 999 HZ compared to conversion
using 64-bit division. Further computation tolerates 5% deviation
for pixclock and selects best possible value. This deviation is
by far greater than 999 HZ. It is 156862 HZ for lowest configurable
pixel clock.
Anatolij
^ permalink raw reply
* [PATCH v21 087/100] powerpc: wire up checkpoint and restart syscalls
From: Oren Laadan @ 2010-05-01 14:16 UTC (permalink / raw)
To: Andrew Morton
Cc: containers, linux-kernel, linuxppc-dev, Nathan Lynch,
Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
Changelog [v21]:
- Fix build break with CONFIG_CHECKPOINT=n
Changelog [v19]:
- Checkpoint/powerpc: fix up checkpoint syscall, tidy restart
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
---
arch/powerpc/include/asm/systbl.h | 2 ++
arch/powerpc/include/asm/unistd.h | 4 +++-
arch/powerpc/kernel/checkpoint.c | 18 ++++++++++++++++++
arch/powerpc/kernel/entry_32.S | 23 +++++++++++++++++++++++
arch/powerpc/kernel/entry_64.S | 16 ++++++++++++++++
arch/powerpc/kernel/process.c | 1 +
6 files changed, 63 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f94fc43..b5afba3 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -327,3 +327,5 @@ COMPAT_SYS_SPU(preadv)
COMPAT_SYS_SPU(pwritev)
COMPAT_SYS(rt_tgsigqueueinfo)
PPC_SYS(eclone)
+PPC_SYS(checkpoint)
+PPC_SYS(restart)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 4cdbd5c..54f6ecb 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -346,10 +346,12 @@
#define __NR_pwritev 321
#define __NR_rt_tgsigqueueinfo 322
#define __NR_eclone 323
+#define __NR_checkpoint 324
+#define __NR_restart 325
#ifdef __KERNEL__
-#define __NR_syscalls 324
+#define __NR_syscalls 326
#define __NR__exit __NR_exit
#define NR_syscalls __NR_syscalls
diff --git a/arch/powerpc/kernel/checkpoint.c b/arch/powerpc/kernel/checkpoint.c
index 492c604..9aeab89 100644
--- a/arch/powerpc/kernel/checkpoint.c
+++ b/arch/powerpc/kernel/checkpoint.c
@@ -530,3 +530,21 @@ int restore_mm_context(struct ckpt_ctx *ctx, struct mm_struct *mm)
{
return 0;
}
+
+int sys_checkpoint(unsigned long pid, unsigned long fd, unsigned long flags,
+ unsigned long logfd, unsigned long p5, unsigned long p6,
+ struct pt_regs *regs)
+{
+ CHECK_FULL_REGS(regs);
+
+ return do_sys_checkpoint(pid, fd, flags, logfd);
+}
+
+int sys_restart(unsigned long pid, unsigned long fd, unsigned long flags,
+ unsigned long logfd, unsigned long p5, unsigned long p6,
+ struct pt_regs *regs)
+{
+ CHECK_FULL_REGS(regs);
+
+ return do_sys_restart(pid, fd, flags, logfd);
+}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 579f1da..853814b 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -594,6 +594,29 @@ ppc_eclone:
stw r0,_TRAP(r1) /* register set saved */
b sys_eclone
+/* To handle self-checkpoint we must save nvpgprs */
+ .globl ppc_checkpoint
+ppc_checkpoint:
+ SAVE_NVGPRS(r1)
+ lwz r0,_TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,_TRAP(r1) /* register set saved */
+ b sys_checkpoint
+
+/* The full register set must be restored upon return from restart.
+ * Save nvgprs unconditionally so the caller's state is
+ * restored correctly in case of error.
+ */
+ .globl ppc_restart
+ppc_restart:
+ SAVE_NVGPRS(r1)
+ lwz r0,_TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,_TRAP(r1) /* register set saved */
+ bl sys_restart
+ REST_NVGPRS(r1)
+ b ret_from_syscall
+
.globl ppc_swapcontext
ppc_swapcontext:
SAVE_NVGPRS(r1)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index b763340..228f592 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -349,6 +349,22 @@ _GLOBAL(ppc_eclone)
bl .sys_eclone
b syscall_exit
+/* To handle self-checkpoint we must save nvpgprs */
+_GLOBAL(ppc_checkpoint)
+ bl .save_nvgprs
+ bl .sys_checkpoint
+ b syscall_exit
+
+/* The full register set must be restored upon return from restart.
+ * Save nvgprs unconditionally so the caller's state is
+ * restored correctly in case of error.
+ */
+_GLOBAL(ppc_restart)
+ bl .save_nvgprs
+ bl .sys_restart
+ REST_NVGPRS(r1)
+ b syscall_exit
+
_GLOBAL(ppc32_swapcontext)
bl .save_nvgprs
bl .compat_sys_swapcontext
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b183287..1664586 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -30,6 +30,7 @@
#include <linux/init_task.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/checkpoint.h>
#include <linux/mqueue.h>
#include <linux/hardirq.h>
#include <linux/utsname.h>
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 088/100] powerpc: enable checkpoint support in Kconfig
From: Oren Laadan @ 2010-05-01 14:16 UTC (permalink / raw)
To: Andrew Morton
Cc: containers, linux-kernel, linuxppc-dev, Nathan Lynch,
Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
---
arch/powerpc/Kconfig | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2e19500..16416b0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -26,6 +26,9 @@ config MMU
bool
default y
+config CHECKPOINT_SUPPORT
+ def_bool y
+
config GENERIC_CMOS_UPDATE
def_bool y
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 085/100] powerpc: provide APIs for validating and updating DABR
From: Oren Laadan @ 2010-05-01 14:16 UTC (permalink / raw)
To: Andrew Morton
Cc: containers, linux-kernel, linuxppc-dev, Nathan Lynch,
Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
A checkpointed task image may specify a value for the DABR (Data
Access Breakpoint Register). The restart code needs to validate this
value before making any changes to the current task.
ptrace_set_debugreg encapsulates the bounds checking and platform
dependencies of programming the DABR. Split this into "validate"
(debugreg_valid) and "update" (debugreg_update) functions, and make
them available for use outside of the ptrace code.
Also ptrace_set_debugreg has extern linkage, but no users outside of
ptrace.c. Make it static.
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
---
arch/powerpc/include/asm/ptrace.h | 7 +++
arch/powerpc/kernel/ptrace.c | 83 ++++++++++++++++++++++++++-----------
2 files changed, 66 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 9e2d84c..a88d711 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -87,6 +87,8 @@ struct pt_regs {
#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
#define instruction_pointer(regs) ((regs)->nip)
#define user_stack_pointer(regs) ((regs)->gpr[1])
#define regs_return_value(regs) ((regs)->gpr[3])
@@ -141,6 +143,11 @@ do { \
#define arch_has_block_step() (!cpu_has_feature(CPU_FTR_601))
#define ARCH_HAS_USER_SINGLE_STEP_INFO
+/* for reprogramming DABR/DAC during restart of a checkpointed task */
+extern bool debugreg_valid(unsigned long val, unsigned int index);
+extern void debugreg_update(struct task_struct *task, unsigned long val,
+ unsigned int index);
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index ed2cfe1..972e6a1 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -763,19 +763,23 @@ void user_disable_single_step(struct task_struct *task)
clear_tsk_thread_flag(task, TIF_SINGLESTEP);
}
-int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
- unsigned long data)
+/**
+ * debugreg_valid() - validate the value to be written to a debug register
+ * @val: The prospective contents of the register.
+ * @index: Must be zero.
+ *
+ * Returns true if @val is an acceptable value for the register indicated by
+ * @index, false otherwise.
+ */
+bool debugreg_valid(unsigned long val, unsigned int index)
{
- /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
- * For embedded processors we support one DAC and no IAC's at the
- * moment.
- */
- if (addr > 0)
- return -EINVAL;
+ /* We support only one debug register for now */
+ if (index != 0)
+ return false;
/* The bottom 3 bits in dabr are flags */
- if ((data & ~0x7UL) >= TASK_SIZE)
- return -EIO;
+ if ((val & ~0x7UL) >= TASK_SIZE)
+ return false;
#ifndef CONFIG_PPC_ADV_DEBUG_REGS
/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
@@ -791,19 +795,38 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
*/
/* Ensure breakpoint translation bit is set */
- if (data && !(data & DABR_TRANSLATION))
- return -EIO;
-
- /* Move contents to the DABR register */
- task->thread.dabr = data;
-#else /* CONFIG_PPC_ADV_DEBUG_REGS */
+ if (val && !(val & DABR_TRANSLATION))
+ return false;
+#else
/* As described above, it was assumed 3 bits were passed with the data
* address, but we will assume only the mode bits will be passed
* as to not cause alignment restrictions for DAC-based processors.
*/
+ /* Read or Write bits must be set */
+ if (!(val & 0x3UL))
+ return -EINVAL;
+#endif
+ return true;
+}
+
+/**
+ * debugreg_update() - update a debug register associated with a task
+ * @task: The task whose register state is to be modified.
+ * @val: The value to be written to the debug register.
+ * @index: Specifies the debug register. Currently unused.
+ *
+ * Set a task's DABR/DAC to @val, which should be validated with
+ * debugreg_valid() beforehand.
+ */
+void debugreg_update(struct task_struct *task, unsigned long val,
+ unsigned int index)
+{
+#ifndef CONFIG_PPC_ADV_DEBUG_REGS
+ task->thread.dabr = val;
+#else
/* DAC's hold the whole address without any mode flags */
- task->thread.dac1 = data & ~0x3UL;
+ task->thread.dabr = val & ~0x3UL;
if (task->thread.dac1 == 0) {
dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
@@ -812,13 +835,8 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
task->thread.regs->msr &= ~MSR_DE;
task->thread.dbcr0 &= ~DBCR0_IDM;
}
- return 0;
}
- /* Read or Write bits must be set */
-
- if (!(data & 0x3UL))
- return -EINVAL;
/* Set the Internal Debugging flag (IDM bit 1) for the DBCR0
register */
@@ -827,12 +845,29 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
/* Check for write and read flags and set DBCR0
accordingly */
dbcr_dac(task) &= ~(DBCR_DAC1R|DBCR_DAC1W);
- if (data & 0x1UL)
+ if (val & 0x1UL)
dbcr_dac(task) |= DBCR_DAC1R;
- if (data & 0x2UL)
+ if (val & 0x2UL)
dbcr_dac(task) |= DBCR_DAC1W;
task->thread.regs->msr |= MSR_DE;
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
+}
+
+static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
+ unsigned long data)
+{
+ /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+ * For embedded processors we support one DAC and no IAC's at the
+ * moment.
+ */
+ if (addr > 0)
+ return -EINVAL;
+
+ if (!debugreg_valid(data, 0))
+ return -EIO;
+
+ debugreg_update(task, data, 0);
+
return 0;
}
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 086/100] powerpc: checkpoint/restart implementation
From: Oren Laadan @ 2010-05-01 14:16 UTC (permalink / raw)
To: Andrew Morton
Cc: containers, linux-kernel, linuxppc-dev, Nathan Lynch,
Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
Support for checkpointing and restarting GPRs, FPU state, DABR, and
Altivec state.
The portion of the checkpoint image manipulated by this code begins
with a bitmask of features indicating the various contexts saved.
Fields in image that can vary depending on kernel configuration
(e.g. FP regs due to VSX) have their sizes explicitly recorded, except
for GPRS, so migrating between ppc32 and ppc64 won't work yet.
The restart code ensures that the task is not modified until the
checkpoint image is validated against the current kernel configuration
and hardware features (e.g. can't restart a task using Altivec on
non-Altivec systems).
What works:
* self and external checkpoint of simple (single thread, one open
file) 32- and 64-bit processes on a ppc64 kernel
What doesn't work:
* restarting a 32-bit task from a 64-bit task and vice versa
Untested:
* ppc32 (but it builds)
Changelog[v21]:
- Do not include checkpoint_hdr.h explicitly
Changelog[v19]:
- [Serge Hallyn] Add hook task_has_saved_sigmask()
Changelog[v19-rc3]:
- [Oren Laadan] Move checkpoint.c from arch/powerpc/{mm->kernel}
- [Nathan Lynch] Warn if full register state unavailable
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
[Oren Laadan <orenl@cs.columbia.edu>] Add arch-specific tty support
---
arch/powerpc/include/asm/Kbuild | 1 +
arch/powerpc/include/asm/checkpoint_hdr.h | 37 ++
arch/powerpc/kernel/Makefile | 1 +
arch/powerpc/kernel/checkpoint.c | 532 +++++++++++++++++++++++++++++
arch/powerpc/kernel/signal.c | 6 +
5 files changed, 577 insertions(+), 0 deletions(-)
create mode 100644 arch/powerpc/include/asm/checkpoint_hdr.h
create mode 100644 arch/powerpc/kernel/checkpoint.c
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 5ab7d7f..20379f1 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += shmbuf.h
header-y += socket.h
header-y += termbits.h
header-y += fcntl.h
+header-y += checkpoint_hdr.h
header-y += poll.h
header-y += sockios.h
header-y += ucontext.h
diff --git a/arch/powerpc/include/asm/checkpoint_hdr.h b/arch/powerpc/include/asm/checkpoint_hdr.h
new file mode 100644
index 0000000..fbb1705
--- /dev/null
+++ b/arch/powerpc/include/asm/checkpoint_hdr.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_POWERPC_CKPT_HDR_H
+#define __ASM_POWERPC_CKPT_HDR_H
+
+#include <linux/types.h>
+
+/* arch dependent constants */
+#define CKPT_ARCH_NSIG 64
+#define CKPT_TTY_NCC 10
+
+#ifdef __KERNEL__
+
+#include <asm/signal.h>
+#if CKPT_ARCH_NSIG != _NSIG
+#error CKPT_ARCH_NSIG size is wrong per asm/signal.h and asm/checkpoint_hdr.h
+#endif
+
+#include <linux/tty.h>
+#if CKPT_TTY_NCC != NCC
+#error CKPT_TTY_NCC size is wrong per asm-generic/termios.h
+#endif
+
+#endif /* __KERNEL__ */
+
+#ifdef __KERNEL__
+#ifdef CONFIG_PPC64
+#define CKPT_ARCH_ID CKPT_ARCH_PPC64
+#else
+#define CKPT_ARCH_ID CKPT_ARCH_PPC32
+#endif
+#endif
+
+struct ckpt_hdr_header_arch {
+ struct ckpt_hdr h;
+ __u32 what;
+} __attribute__((aligned(8)));
+
+#endif /* __ASM_POWERPC_CKPT_HDR_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8773263..6d294a4 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -63,6 +63,7 @@ obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o
obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o
obj-$(CONFIG_44x) += cpu_setup_44x.o
obj-$(CONFIG_FSL_BOOKE) += cpu_setup_fsl_booke.o dbell.o
+obj-$(CONFIG_CHECKPOINT) += checkpoint.o
extra-y := head_$(CONFIG_WORD_SIZE).o
extra-$(CONFIG_PPC_BOOK3E_32) := head_new_booke.o
diff --git a/arch/powerpc/kernel/checkpoint.c b/arch/powerpc/kernel/checkpoint.c
new file mode 100644
index 0000000..492c604
--- /dev/null
+++ b/arch/powerpc/kernel/checkpoint.c
@@ -0,0 +1,532 @@
+/*
+ * PowerPC architecture support for checkpoint/restart.
+ * Based on x86 implementation.
+ *
+ * Copyright (C) 2008 Oren Laadan
+ * Copyright 2009 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ */
+
+#if 0
+#define DEBUG
+#endif
+
+#include <linux/checkpoint.h>
+#include <linux/kernel.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+
+enum ckpt_cpu_feature {
+ CKPT_USED_FP,
+ CKPT_USED_DEBUG,
+ CKPT_USED_ALTIVEC,
+ CKPT_USED_SPE,
+ CKPT_USED_VSX,
+ CKPT_FTR_END = 31,
+};
+
+#define x(ftr) (1UL << ftr)
+
+/* features this kernel can handle for restart */
+enum {
+ CKPT_FTRS_POSSIBLE =
+#ifdef CONFIG_PPC_FPU
+ x(CKPT_USED_FP) |
+#endif
+ x(CKPT_USED_DEBUG) |
+#ifdef CONFIG_ALTIVEC
+ x(CKPT_USED_ALTIVEC) |
+#endif
+#ifdef CONFIG_SPE
+ x(CKPT_USED_SPE) |
+#endif
+#ifdef CONFIG_VSX
+ x(CKPT_USED_VSX) |
+#endif
+ 0,
+};
+
+#undef x
+
+struct ckpt_hdr_cpu {
+ struct ckpt_hdr h;
+ u32 features_used;
+ u32 pt_regs_size;
+ u32 fpr_size;
+ u64 orig_gpr3;
+ struct pt_regs pt_regs;
+ /* relevant fields from thread_struct */
+ double fpr[32][TS_FPRWIDTH];
+ u32 fpscr;
+ s32 fpexc_mode;
+ u64 dabr;
+ /* Altivec/VMX state */
+ vector128 vr[32];
+ vector128 vscr;
+ u64 vrsave;
+ /* SPE state */
+ u32 evr[32];
+ u64 acc;
+ u32 spefscr;
+};
+
+/**************************************************************************
+ * Checkpoint
+ */
+
+static void ckpt_cpu_feature_set(struct ckpt_hdr_cpu *hdr,
+ enum ckpt_cpu_feature ftr)
+{
+ hdr->features_used |= 1ULL << ftr;
+}
+
+static bool ckpt_cpu_feature_isset(const struct ckpt_hdr_cpu *hdr,
+ enum ckpt_cpu_feature ftr)
+{
+ return hdr->features_used & (1ULL << ftr);
+}
+
+/* determine whether an image has feature bits set that this kernel
+ * does not support */
+static bool ckpt_cpu_features_unknown(const struct ckpt_hdr_cpu *hdr)
+{
+ return hdr->features_used & ~CKPT_FTRS_POSSIBLE;
+}
+
+static void checkpoint_gprs(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ struct pt_regs *pt_regs;
+
+ pr_debug("%s: saving GPRs\n", __func__);
+
+ cpu_hdr->pt_regs_size = sizeof(*pt_regs);
+ pt_regs = task_pt_regs(task);
+ WARN_ON(!FULL_REGS(pt_regs));
+
+ cpu_hdr->pt_regs = *pt_regs;
+
+ if (task == current)
+ cpu_hdr->pt_regs.gpr[3] = 0;
+
+ cpu_hdr->orig_gpr3 = pt_regs->orig_gpr3;
+}
+
+#ifdef CONFIG_PPC_FPU
+static void checkpoint_fpu(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ /* easiest to save FP state unconditionally */
+
+ pr_debug("%s: saving FPU state\n", __func__);
+
+ if (task == current)
+ flush_fp_to_thread(task);
+
+ cpu_hdr->fpr_size = sizeof(cpu_hdr->fpr);
+ cpu_hdr->fpscr = task->thread.fpscr.val;
+ cpu_hdr->fpexc_mode = task->thread.fpexc_mode;
+
+ memcpy(cpu_hdr->fpr, task->thread.fpr, sizeof(cpu_hdr->fpr));
+
+ ckpt_cpu_feature_set(cpu_hdr, CKPT_USED_FP);
+}
+#else
+static void checkpoint_fpu(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ return;
+}
+#endif
+
+#ifdef CONFIG_ALTIVEC
+static void checkpoint_altivec(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ if (!cpu_has_feature(CPU_FTR_ALTIVEC))
+ return;
+
+ if (!task->thread.used_vr)
+ return;
+
+ pr_debug("%s: saving Altivec state\n", __func__);
+
+ if (task == current)
+ flush_altivec_to_thread(task);
+
+ cpu_hdr->vrsave = task->thread.vrsave;
+ memcpy(cpu_hdr->vr, task->thread.vr, sizeof(cpu_hdr->vr));
+ ckpt_cpu_feature_set(cpu_hdr, CKPT_USED_ALTIVEC);
+}
+#else
+static void checkpoint_altivec(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ return;
+}
+#endif
+
+#ifdef CONFIG_SPE
+static void checkpoint_spe(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ if (!cpu_has_feature(CPU_FTR_SPE))
+ return;
+
+ if (!task->thread.used_spe)
+ return;
+
+ pr_debug("%s: saving SPE state\n", __func__);
+
+ if (task == current)
+ flush_spe_to_thread(task);
+
+ cpu_hdr->acc = task->thread.acc;
+ cpu_hdr->spefscr = task->thread.spefscr;
+ memcpy(cpu_hdr->evr, task->thread.evr, sizeof(cpu_hdr->evr));
+ ckpt_cpu_feature_set(cpu_hdr, CKPT_USED_SPE);
+}
+#else
+static void checkpoint_spe(struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task)
+{
+ return;
+}
+#endif
+
+static void checkpoint_dabr(struct ckpt_hdr_cpu *cpu_hdr,
+ const struct task_struct *task)
+{
+ if (!task->thread.dabr)
+ return;
+
+ cpu_hdr->dabr = task->thread.dabr;
+ ckpt_cpu_feature_set(cpu_hdr, CKPT_USED_DEBUG);
+}
+
+/* dump the thread_struct of a given task */
+int checkpoint_thread(struct ckpt_ctx *ctx, struct task_struct *t)
+{
+ return 0;
+}
+
+/* dump the cpu state and registers of a given task */
+int checkpoint_cpu(struct ckpt_ctx *ctx, struct task_struct *t)
+{
+ struct ckpt_hdr_cpu *cpu_hdr;
+ int rc;
+
+ rc = -ENOMEM;
+ cpu_hdr = ckpt_hdr_get_type(ctx, sizeof(*cpu_hdr), CKPT_HDR_CPU);
+ if (!cpu_hdr)
+ goto err;
+
+ checkpoint_gprs(cpu_hdr, t);
+ checkpoint_fpu(cpu_hdr, t);
+ checkpoint_dabr(cpu_hdr, t);
+ checkpoint_altivec(cpu_hdr, t);
+ checkpoint_spe(cpu_hdr, t);
+
+ rc = ckpt_write_obj(ctx, (struct ckpt_hdr *) cpu_hdr);
+err:
+ ckpt_hdr_put(ctx, cpu_hdr);
+ return rc;
+}
+
+int checkpoint_write_header_arch(struct ckpt_ctx *ctx)
+{
+ struct ckpt_hdr_header_arch *arch_hdr;
+ int ret;
+
+ arch_hdr = ckpt_hdr_get_type(ctx, sizeof(*arch_hdr),
+ CKPT_HDR_HEADER_ARCH);
+ if (!arch_hdr)
+ return -ENOMEM;
+
+ arch_hdr->what = 0xdeadbeef;
+
+ ret = ckpt_write_obj(ctx, &arch_hdr->h);
+ ckpt_hdr_put(ctx, arch_hdr);
+
+ return ret;
+}
+
+/* dump the mm->context state */
+int checkpoint_mm_context(struct ckpt_ctx *ctx, struct mm_struct *mm)
+{
+ return 0;
+}
+
+/**************************************************************************
+ * Restart
+ */
+
+/* read the thread_struct into the current task */
+int restore_thread(struct ckpt_ctx *ctx)
+{
+ return 0;
+}
+
+/* Based on the MSR value from a checkpoint image, produce an MSR
+ * value that is appropriate for the restored task. Right now we only
+ * check for MSR_SF (64-bit) for PPC64.
+ */
+static unsigned long sanitize_msr(unsigned long msr_ckpt)
+{
+#ifdef CONFIG_PPC32
+ return MSR_USER;
+#else
+ if (msr_ckpt & MSR_SF)
+ return MSR_USER64;
+ return MSR_USER32;
+#endif
+}
+
+static int restore_gprs(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ struct pt_regs *regs;
+ int rc;
+
+ rc = -EINVAL;
+ if (cpu_hdr->pt_regs_size != sizeof(*regs))
+ goto out;
+
+ rc = 0;
+ if (!update)
+ goto out;
+
+ regs = task_pt_regs(task);
+ *regs = cpu_hdr->pt_regs;
+
+ regs->orig_gpr3 = cpu_hdr->orig_gpr3;
+
+ regs->msr = sanitize_msr(regs->msr);
+out:
+ return rc;
+}
+
+#ifdef CONFIG_PPC_FPU
+static int restore_fpu(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ int rc;
+
+ rc = -EINVAL;
+ if (cpu_hdr->fpr_size != sizeof(task->thread.fpr))
+ goto out;
+
+ rc = 0;
+ if (!update || !ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_FP))
+ goto out;
+
+ task->thread.fpscr.val = cpu_hdr->fpscr;
+ task->thread.fpexc_mode = cpu_hdr->fpexc_mode;
+
+ memcpy(task->thread.fpr, cpu_hdr->fpr, sizeof(task->thread.fpr));
+out:
+ return rc;
+}
+#else
+static int restore_fpu(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ WARN_ON_ONCE(ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_FP));
+ return 0;
+}
+#endif
+
+static int restore_dabr(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ int rc;
+
+ rc = 0;
+ if (!ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_DEBUG))
+ goto out;
+
+ rc = -EINVAL;
+ if (!debugreg_valid(cpu_hdr->dabr, 0))
+ goto out;
+
+ rc = 0;
+ if (!update)
+ goto out;
+
+ debugreg_update(task, cpu_hdr->dabr, 0);
+out:
+ return rc;
+}
+
+#ifdef CONFIG_ALTIVEC
+static int restore_altivec(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ int rc;
+
+ rc = 0;
+ if (!ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_ALTIVEC))
+ goto out;
+
+ rc = -EINVAL;
+ if (!cpu_has_feature(CPU_FTR_ALTIVEC))
+ goto out;
+
+ rc = 0;
+ if (!update)
+ goto out;
+
+ task->thread.vrsave = cpu_hdr->vrsave;
+ task->thread.used_vr = 1;
+
+ memcpy(task->thread.vr, cpu_hdr->vr, sizeof(cpu_hdr->vr));
+out:
+ return rc;
+}
+#else
+static int restore_altivec(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ WARN_ON_ONCE(ckpt_cpu_feature_isset(CKPT_USED_ALTIVEC));
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SPE
+static int restore_spe(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ int rc;
+
+ rc = 0;
+ if (!ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_SPE))
+ goto out;
+
+ rc = -EINVAL;
+ if (!cpu_has_feature(CPU_FTR_SPE))
+ goto out;
+
+ rc = 0;
+ if (!update)
+ goto out;
+
+ task->thread.acc = cpu_hdr->acc;
+ task->thread.spefscr = cpu_hdr->spefscr;
+ task->thread.used_spe = 1;
+
+ memcpy(task->thread.evr, cpu_hdr->evr, sizeof(cpu_hdr->evr));
+out:
+ return rc;
+}
+#else
+static int restore_spe(const struct ckpt_hdr_cpu *cpu_hdr,
+ struct task_struct *task, bool update)
+{
+ WARN_ON_ONCE(ckpt_cpu_feature_isset(cpu_hdr, CKPT_USED_SPE));
+ return 0;
+}
+#endif
+
+struct restore_func_desc {
+ int (*func)(const struct ckpt_hdr_cpu *, struct task_struct *, bool);
+ const char *info;
+};
+
+typedef int (*restore_func_t)(const struct ckpt_hdr_cpu *,
+ struct task_struct *, bool);
+
+static const restore_func_t restore_funcs[] = {
+ restore_gprs,
+ restore_fpu,
+ restore_dabr,
+ restore_altivec,
+ restore_spe,
+};
+
+static bool bitness_match(const struct ckpt_hdr_cpu *cpu_hdr,
+ const struct task_struct *task)
+{
+ /* 64-bit image */
+ if (cpu_hdr->pt_regs.msr & MSR_SF) {
+ if (task->thread.regs->msr & MSR_SF)
+ return true;
+ else
+ return false;
+ }
+
+ /* 32-bit image */
+ if (task->thread.regs->msr & MSR_SF)
+ return false;
+
+ return true;
+}
+
+int restore_cpu(struct ckpt_ctx *ctx)
+{
+ struct ckpt_hdr_cpu *cpu_hdr;
+ bool update;
+ int rc;
+ int i;
+
+ cpu_hdr = ckpt_read_obj_type(ctx, sizeof(*cpu_hdr), CKPT_HDR_CPU);
+ if (IS_ERR(cpu_hdr))
+ return PTR_ERR(cpu_hdr);
+
+ rc = -EINVAL;
+ if (ckpt_cpu_features_unknown(cpu_hdr))
+ goto err;
+
+ /* temporary: restoring a 32-bit image from a 64-bit task and
+ * vice-versa is known not to work (probably not restoring
+ * thread_info correctly); detect this and fail gracefully.
+ */
+ if (!bitness_match(cpu_hdr, current))
+ goto err;
+
+ /* We want to determine whether there's anything wrong with
+ * the checkpoint image before changing the task at all. Run
+ * a "check" phase (update = false) first.
+ */
+ update = false;
+commit:
+ for (i = 0; i < ARRAY_SIZE(restore_funcs); i++) {
+ rc = restore_funcs[i](cpu_hdr, current, update);
+ if (rc == 0)
+ continue;
+ pr_debug("%s: restore_func[%i] failed\n", __func__, i);
+ WARN_ON_ONCE(update);
+ goto err;
+ }
+
+ if (!update) {
+ update = true;
+ goto commit;
+ }
+
+err:
+ ckpt_hdr_put(ctx, cpu_hdr);
+ return rc;
+}
+
+int restore_read_header_arch(struct ckpt_ctx *ctx)
+{
+ struct ckpt_hdr_header_arch *arch_hdr;
+
+ arch_hdr = ckpt_read_obj_type(ctx, sizeof(*arch_hdr),
+ CKPT_HDR_HEADER_ARCH);
+ if (IS_ERR(arch_hdr))
+ return PTR_ERR(arch_hdr);
+
+ ckpt_hdr_put(ctx, arch_hdr);
+
+ return 0;
+}
+
+int restore_mm_context(struct ckpt_ctx *ctx, struct mm_struct *mm)
+{
+ return 0;
+}
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index a0afb55..b3337ad 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -186,6 +186,12 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
return ret;
}
+int task_has_saved_sigmask(struct task_struct *task)
+{
+ struct thread_info *ti = task_thread_info(task);
+ return !!(ti->local_flags & _TLF_RESTORE_SIGMASK);
+}
+
void do_signal(struct pt_regs *regs, unsigned long thread_info_flags)
{
if (thread_info_flags & _TIF_SIGPENDING)
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 084/100] powerpc: reserve checkpoint arch identifiers
From: Oren Laadan @ 2010-05-01 14:16 UTC (permalink / raw)
To: Andrew Morton
Cc: containers, linux-kernel, linuxppc-dev, Nathan Lynch,
Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
Changelog [v19-rc1]:
- [Matt Helsley] Add cpp definitions for enums
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
---
include/linux/checkpoint_hdr.h | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/include/linux/checkpoint_hdr.h b/include/linux/checkpoint_hdr.h
index f2779d1..90cbc15 100644
--- a/include/linux/checkpoint_hdr.h
+++ b/include/linux/checkpoint_hdr.h
@@ -193,6 +193,10 @@ enum {
#define CKPT_ARCH_X86_64 CKPT_ARCH_X86_64
CKPT_ARCH_S390X,
#define CKPT_ARCH_S390X CKPT_ARCH_S390X
+ CKPT_ARCH_PPC32,
+#define CKPT_ARCH_PPC32 CKPT_ARCH_PPC32
+ CKPT_ARCH_PPC64,
+#define CKPT_ARCH_PPC64 CKPT_ARCH_PPC64
};
/* shared objrects (objref) */
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 021/100] c/r: create syscalls: sys_checkpoint, sys_restart
From: Oren Laadan @ 2010-05-01 14:15 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, Oren Laadan, containers, x86, linux-kernel,
Dave Hansen, linuxppc-dev, Matt Helsley, linux-api, Serge Hallyn,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
Create trivial sys_checkpoint and sys_restore system calls. They will
enable to checkpoint and restart an entire container, to and from a
checkpoint image file descriptor.
The syscalls take a pid, a file descriptor (for the image file) and
flags as arguments. The pid identifies the top-most (root) task in the
process tree, e.g. the container init: for sys_checkpoint the first
argument identifies the pid of the target container/subtree; for
sys_restart it will identify the pid of restarting root task.
A checkpoint, much like a process coredump, dumps the state of multiple
processes at once, including the state of the container. The checkpoint
image is written to (and read from) the file descriptor directly from
the kernel. This way the data is generated and then pushed out naturally
as resources and tasks are scanned to save their state. This is the
approach taken by, e.g., Zap and OpenVZ.
By using a return value and not a file descriptor, we can distinguish
between a return from checkpoint, a return from restart (in case of a
checkpoint that includes self, i.e. a task checkpointing its own
container, or itself), and an error condition, in a manner analogous
to a fork() call.
We don't use copy_from_user()/copy_to_user() because it requires
holding the entire image in user space, and does not make sense for
restart. Also, we don't use a pipe, pseudo-fs file and the like,
because they work by generating data on demand as the user pulls it
(unless the entire image is buffered in the kernel) and would require
more complex logic. They also would significantly complicate
checkpoint that includes self.
Changelog[v21-rc3]:
- Reorganize code:move checkpoint/* to kernel/checkpoint/*
Changelog[v19-rc1]:
- Add 'int logfd' to prototype of sys_{checkpoint,restart}
Changelog[v18]:
- [John Dykstra] Fix no-dot-config-targets pattern in linux/Makefile
Changelog[v17]:
- Move checkpoint closer to namespaces (kconfig)
- Kill "Enable" in c/r config option
Changelog[v16]:
- Change sys_restart() first argument to be 'pid_t pid'
Changelog[v14]:
- Change CONFIG_CHEKCPOINT_RESTART to CONFIG_CHECKPOINT (Ingo)
- Remove line 'def_bool n' (default is already 'n')
- Add CHECKPOINT_SUPPORT in Kconfig (Nathan Lynch)
Changelog[v5]:
- Config is 'def_bool n' by default
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Oren Laadan <orenl@cs.columbia.edu>
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
---
Makefile | 2 +-
arch/x86/Kconfig | 4 +++
arch/x86/include/asm/unistd_32.h | 4 ++-
arch/x86/kernel/syscall_table_32.S | 2 +
include/linux/syscalls.h | 4 +++
init/Kconfig | 2 +
kernel/Makefile | 1 +
kernel/checkpoint/Kconfig | 14 +++++++++++
kernel/checkpoint/Makefile | 5 ++++
kernel/checkpoint/sys.c | 45 ++++++++++++++++++++++++++++++++++++
kernel/sys_ni.c | 4 +++
11 files changed, 85 insertions(+), 2 deletions(-)
create mode 100644 kernel/checkpoint/Kconfig
create mode 100644 kernel/checkpoint/Makefile
create mode 100644 kernel/checkpoint/sys.c
diff --git a/Makefile b/Makefile
index fa1db90..93be4e1 100644
--- a/Makefile
+++ b/Makefile
@@ -409,7 +409,7 @@ endif
# of make so .config is not included in this case either (for *config).
no-dot-config-targets := clean mrproper distclean \
- cscope TAGS tags help %docs check% \
+ cscope TAGS tags help %docs checkstack \
include/linux/version.h headers_% \
kernelrelease kernelversion
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9458685..0874484 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -93,6 +93,10 @@ config STACKTRACE_SUPPORT
config HAVE_LATENCYTOP_SUPPORT
def_bool y
+config CHECKPOINT_SUPPORT
+ bool
+ default y if X86_32
+
config MMU
def_bool y
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index e543b0e..007d7cd 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -344,10 +344,12 @@
#define __NR_perf_event_open 336
#define __NR_recvmmsg 337
#define __NR_eclone 338
+#define __NR_checkpoint 339
+#define __NR_restart 340
#ifdef __KERNEL__
-#define NR_syscalls 339
+#define NR_syscalls 341
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 0c92570..2d5a6b0 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -338,3 +338,5 @@ ENTRY(sys_call_table)
.long sys_perf_event_open
.long sys_recvmmsg
.long ptregs_eclone
+ .long sys_checkpoint
+ .long sys_restart /* 340 */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 057929b..d1d1703 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -834,6 +834,10 @@ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *,
asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int,
struct timespec __user *, const sigset_t __user *,
size_t);
+asmlinkage long sys_checkpoint(pid_t pid, int fd, unsigned long flags,
+ int logfd);
+asmlinkage long sys_restart(pid_t pid, int fd, unsigned long flags,
+ int logfd);
int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
diff --git a/init/Kconfig b/init/Kconfig
index bd8174f..2345902 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -715,6 +715,8 @@ config NET_NS
Allow user space to create what appear to be multiple instances
of the network stack.
+source "kernel/checkpoint/Kconfig"
+
config BLK_DEV_INITRD
bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
depends on BROKEN || !FRV
diff --git a/kernel/Makefile b/kernel/Makefile
index a987aa1..1b78cca 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -105,6 +105,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
obj-$(CONFIG_PADATA) += padata.o
+obj-$(CONFIG_CHECKPOINT) += checkpoint/
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/checkpoint/Kconfig b/kernel/checkpoint/Kconfig
new file mode 100644
index 0000000..ef7d406
--- /dev/null
+++ b/kernel/checkpoint/Kconfig
@@ -0,0 +1,14 @@
+# Architectures should define CHECKPOINT_SUPPORT when they have
+# implemented the hooks for processor state etc. needed by the
+# core checkpoint/restart code.
+
+config CHECKPOINT
+ bool "Checkpoint/restart (EXPERIMENTAL)"
+ depends on CHECKPOINT_SUPPORT && EXPERIMENTAL
+ help
+ Application checkpoint/restart is the ability to save the
+ state of a running application so that it can later resume
+ its execution from the time at which it was checkpointed.
+
+ Turning this option on will enable checkpoint and restart
+ functionality in the kernel.
diff --git a/kernel/checkpoint/Makefile b/kernel/checkpoint/Makefile
new file mode 100644
index 0000000..8a32c6f
--- /dev/null
+++ b/kernel/checkpoint/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for linux checkpoint/restart.
+#
+
+obj-$(CONFIG_CHECKPOINT) += sys.o
diff --git a/kernel/checkpoint/sys.c b/kernel/checkpoint/sys.c
new file mode 100644
index 0000000..a81750a
--- /dev/null
+++ b/kernel/checkpoint/sys.c
@@ -0,0 +1,45 @@
+/*
+ * Generic container checkpoint-restart
+ *
+ * Copyright (C) 2008-2009 Oren Laadan
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of the Linux
+ * distribution for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+
+/**
+ * sys_checkpoint - checkpoint a container
+ * @pid: pid of the container init(1) process
+ * @fd: file to which dump the checkpoint image
+ * @flags: checkpoint operation flags
+ * @logfd: fd to which to dump debug and error messages
+ *
+ * Returns positive identifier on success, 0 when returning from restart
+ * or negative value on error
+ */
+SYSCALL_DEFINE4(checkpoint, pid_t, pid, int, fd,
+ unsigned long, flags, int, logfd)
+{
+ return -ENOSYS;
+}
+
+/**
+ * sys_restart - restart a container
+ * @pid: pid of task root (in coordinator's namespace), or 0
+ * @fd: file from which read the checkpoint image
+ * @flags: restart operation flags
+ * @logfd: fd to which to dump debug and error messages
+ *
+ * Returns negative value on error, or otherwise returns in the realm
+ * of the original checkpoint
+ */
+SYSCALL_DEFINE4(restart, pid_t, pid, int, fd,
+ unsigned long, flags, int, logfd)
+{
+ return -ENOSYS;
+}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 70f2ea7..0206aca 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -181,3 +181,7 @@ cond_syscall(sys_eventfd2);
/* performance counters: */
cond_syscall(sys_perf_event_open);
+
+/* checkpoint/restart */
+cond_syscall(sys_checkpoint);
+cond_syscall(sys_restart);
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 001/100] eclone (1/11): Factor out code to allocate pidmap page
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Sukadev Bhattiprolu,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
To simplify alloc_pidmap(), move code to allocate a pid map page to a
separate function.
Changelog[v4]:
- [Oren Laadan] Adapt to kernel 2.6.33-rc5
Changelog[v3]:
- Earlier version of patchset called alloc_pidmap_page() from two
places. But now its called from only one place. Even so, moving
this code out into a separate function simplifies alloc_pidmap().
Changelog[v2]:
- (Matt Helsley, Dave Hansen) Have alloc_pidmap_page() return
-ENOMEM on error instead of -1.
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
kernel/pid.c | 41 ++++++++++++++++++++++++++---------------
1 files changed, 26 insertions(+), 15 deletions(-)
diff --git a/kernel/pid.c b/kernel/pid.c
index aebb30d..52a371a 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -122,6 +122,30 @@ static void free_pidmap(struct upid *upid)
atomic_inc(&map->nr_free);
}
+static int alloc_pidmap_page(struct pidmap *map)
+{
+ void *page;
+
+ if (likely(map->page))
+ return 0;
+
+ page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ /*
+ * Free the page if someone raced with us installing it:
+ */
+ spin_lock_irq(&pidmap_lock);
+ if (!map->page) {
+ map->page = page;
+ page = NULL;
+ }
+ spin_unlock_irq(&pidmap_lock);
+ kfree(page);
+ if (unlikely(!map->page))
+ return -1;
+
+ return 0;
+}
+
static int alloc_pidmap(struct pid_namespace *pid_ns)
{
int i, offset, max_scan, pid, last = pid_ns->last_pid;
@@ -134,22 +158,9 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
for (i = 0; i <= max_scan; ++i) {
- if (unlikely(!map->page)) {
- void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- /*
- * Free the page if someone raced with us
- * installing it:
- */
- spin_lock_irq(&pidmap_lock);
- if (!map->page) {
- map->page = page;
- page = NULL;
- }
- spin_unlock_irq(&pidmap_lock);
- kfree(page);
- if (unlikely(!map->page))
+ if (unlikely(!map->page))
+ if (alloc_pidmap_page(map) < 0)
break;
- }
if (likely(atomic_read(&map->nr_free))) {
do {
if (!test_and_set_bit(offset, map->page)) {
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 003/100] eclone (3/11): Define set_pidmap() function
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
Sukadev Bhattiprolu, linuxppc-dev, Matt Helsley, Serge Hallyn,
Sukadev Bhattiprolu, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Define a set_pidmap() interface which is like alloc_pidmap() only that
caller specifies the pid number to be assigned.
Changelog[v13]:
- Don't let do_alloc_pidmap return 0 if it failed to find a pid.
Changelog[v9]:
- Completely rewrote this patch based on Eric Biederman's code.
Changelog[v7]:
- [Eric Biederman] Generalize alloc_pidmap() to take a range of pids.
Changelog[v6]:
- Separate target_pid > 0 case to minimize the number of checks needed.
Changelog[v3]:
- (Eric Biederman): Avoid set_pidmap() function. Added couple of
checks for target_pid in alloc_pidmap() itself.
Changelog[v2]:
- (Serge Hallyn) Check for 'pid < 0' in set_pidmap().(Code
actually checks for 'pid <= 0' for completeness).
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
kernel/pid.c | 41 +++++++++++++++++++++++++++++++++--------
1 files changed, 33 insertions(+), 8 deletions(-)
diff --git a/kernel/pid.c b/kernel/pid.c
index 8330488..4eaf975 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -146,17 +146,18 @@ static int alloc_pidmap_page(struct pidmap *map)
return 0;
}
-static int alloc_pidmap(struct pid_namespace *pid_ns)
+static int do_alloc_pidmap(struct pid_namespace *pid_ns, int last, int min,
+ int max)
{
- int i, offset, max_scan, pid, last = pid_ns->last_pid;
+ int i, offset, max_scan, pid;
struct pidmap *map;
pid = last + 1;
if (pid >= pid_max)
- pid = RESERVED_PIDS;
+ pid = min;
offset = pid & BITS_PER_PAGE_MASK;
map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
- max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
+ max_scan = (max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
for (i = 0; i <= max_scan; ++i) {
if (unlikely(!map->page))
if (alloc_pidmap_page(map) < 0)
@@ -165,7 +166,6 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
do {
if (!test_and_set_bit(offset, map->page)) {
atomic_dec(&map->nr_free);
- pid_ns->last_pid = pid;
return pid;
}
offset = find_next_offset(map, offset);
@@ -176,16 +176,16 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
* bitmap block and the final block was the same
* as the starting point, pid is before last_pid.
*/
- } while (offset < BITS_PER_PAGE && pid < pid_max &&
+ } while (offset < BITS_PER_PAGE && pid < max &&
(i != max_scan || pid < last ||
!((last+1) & BITS_PER_PAGE_MASK)));
}
- if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
+ if (map < &pid_ns->pidmap[(max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
map = &pid_ns->pidmap[0];
- offset = RESERVED_PIDS;
+ offset = min;
if (unlikely(last == offset))
break;
}
@@ -194,6 +194,31 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
return -EBUSY;
}
+static int alloc_pidmap(struct pid_namespace *pid_ns)
+{
+ int nr;
+
+ nr = do_alloc_pidmap(pid_ns, pid_ns->last_pid, RESERVED_PIDS, pid_max);
+ if (nr >= 0)
+ pid_ns->last_pid = nr;
+ return nr;
+}
+
+static int set_pidmap(struct pid_namespace *pid_ns, int target)
+{
+ if (!target)
+ return alloc_pidmap(pid_ns);
+
+ if (target >= pid_max)
+ return -EINVAL;
+
+ if ((target < 0) || (target < RESERVED_PIDS &&
+ pid_ns->last_pid >= RESERVED_PIDS))
+ return -EINVAL;
+
+ return do_alloc_pidmap(pid_ns, target - 1, target, target + 1);
+}
+
int next_pidmap(struct pid_namespace *pid_ns, int last)
{
int offset;
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 007/100] eclone (7/11): Define do_fork_with_pids()
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
Oleg Nesterov, linuxppc-dev, Matt Helsley, Serge Hallyn,
Sukadev Bhattiprolu, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
do_fork_with_pids() is same as do_fork(), except that it takes an
additional, 'pid_set', parameter. This parameter, currently unused,
specifies the set of target pids of the process in each of its pid
namespaces.
Changelog[v7]:
- Drop 'struct pid_set' object and pass in 'pid_t *target_pids'
instead of 'struct pid_set *'.
Changelog[v6]:
- (Nathan Lynch, Arnd Bergmann, H. Peter Anvin, Linus Torvalds)
Change 'pid_set.pids' to a 'pid_t pids[]' so size of 'struct pid_set'
is constant across architectures.
- (Nathan Lynch) Change 'pid_set.num_pids' to 'unsigned int'.
Changelog[v4]:
- Rename 'struct target_pid_set' to 'struct pid_set' since it may
be useful in other contexts.
Changelog[v3]:
- Fix "long-line" warning from checkpatch.pl
Changelog[v2]:
- To facilitate moving architecture-inpdendent code to kernel/fork.c
pass in 'struct target_pid_set __user *' to do_fork_with_pids()
rather than 'pid_t *' (next patch moves the arch-independent
code to kernel/fork.c)
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
include/linux/sched.h | 3 +++
kernel/fork.c | 17 +++++++++++++++--
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5de3ce5..f4ae3e3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2129,6 +2129,9 @@ extern int disallow_signal(int);
extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
+extern long do_fork_with_pids(unsigned long, unsigned long, struct pt_regs *,
+ unsigned long, int __user *, int __user *,
+ unsigned int, pid_t __user *);
struct task_struct *fork_idle(int);
extern void set_task_comm(struct task_struct *tsk, char *from);
diff --git a/kernel/fork.c b/kernel/fork.c
index e41b3d1..2559d7a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1355,12 +1355,14 @@ struct task_struct * __cpuinit fork_idle(int cpu)
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
-long do_fork(unsigned long clone_flags,
+long do_fork_with_pids(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
- int __user *child_tidptr)
+ int __user *child_tidptr,
+ unsigned int num_pids,
+ pid_t __user *upids)
{
struct task_struct *p;
int trace = 0;
@@ -1463,6 +1465,17 @@ long do_fork(unsigned long clone_flags,
return nr;
}
+long do_fork(unsigned long clone_flags,
+ unsigned long stack_start,
+ struct pt_regs *regs,
+ unsigned long stack_size,
+ int __user *parent_tidptr,
+ int __user *child_tidptr)
+{
+ return do_fork_with_pids(clone_flags, stack_start, regs, stack_size,
+ parent_tidptr, child_tidptr, 0, NULL);
+}
+
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 006/100] eclone (6/11): Check invalid clone flags
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
Oleg Nesterov, linuxppc-dev, Matt Helsley, Serge Hallyn,
Sukadev Bhattiprolu, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
As pointed out by Oren Laadan, we want to ensure that unused bits in the
clone-flags remain unused and available for future. To ensure this, define
a mask of clone-flags and check the flags in the clone() system calls.
Changelog[v9]:
- Include the unused clone-flag (CLONE_UNUSED) to VALID_CLONE_FLAGS
to avoid breaking any applications that may have set it. IOW, this
patch/check only applies to clone-flags bits 33 and higher.
Changelog[v8]:
- New patch in set
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: Oren Laadan <orenl.cs.columbia.edu>
---
include/linux/sched.h | 12 ++++++++++++
kernel/fork.c | 3 +++
2 files changed, 15 insertions(+), 0 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dad7f66..5de3ce5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -29,6 +29,18 @@
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
+#define CLONE_UNUSED 0x00001000 /* Can be reused ? */
+
+#define VALID_CLONE_FLAGS (CSIGNAL | CLONE_VM | CLONE_FS | CLONE_FILES |\
+ CLONE_SIGHAND | CLONE_UNUSED | CLONE_PTRACE |\
+ CLONE_VFORK | CLONE_PARENT | CLONE_THREAD |\
+ CLONE_NEWNS | CLONE_SYSVSEM | CLONE_SETTLS |\
+ CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID |\
+ CLONE_DETACHED | CLONE_UNTRACED |\
+ CLONE_CHILD_SETTID | CLONE_STOPPED |\
+ CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWUSER |\
+ CLONE_NEWPID | CLONE_NEWNET | CLONE_IO)
+
/*
* Scheduling policies
*/
diff --git a/kernel/fork.c b/kernel/fork.c
index 9d2b57e..e41b3d1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -964,6 +964,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
struct task_struct *p;
int cgroup_callbacks_done = 0;
+ if (clone_flags & ~VALID_CLONE_FLAGS)
+ return ERR_PTR(-EINVAL);
+
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 005/100] eclone (5/11): Add target_pids parameter to copy_process()
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
Oleg Nesterov, linuxppc-dev, Matt Helsley, Serge Hallyn,
Sukadev Bhattiprolu, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Add a 'target_pids' parameter to copy_process(). The new parameter will be
used in a follow-on patch when eclone() is implemented.
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
kernel/fork.c | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/kernel/fork.c b/kernel/fork.c
index 62018c8..9d2b57e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -957,12 +957,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
+ pid_t *target_pids,
int trace)
{
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
- pid_t *target_pids = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
@@ -1339,7 +1339,7 @@ struct task_struct * __cpuinit fork_idle(int cpu)
struct pt_regs regs;
task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL,
- &init_struct_pid, 0);
+ &init_struct_pid, NULL, 0);
if (!IS_ERR(task))
init_idle(task, cpu);
@@ -1362,6 +1362,7 @@ long do_fork(unsigned long clone_flags,
struct task_struct *p;
int trace = 0;
long nr;
+ pid_t *target_pids = NULL;
/*
* Do some preliminary argument and permissions checking before we
@@ -1402,7 +1403,7 @@ long do_fork(unsigned long clone_flags,
trace = tracehook_prepare_clone(clone_flags);
p = copy_process(clone_flags, stack_start, regs, stack_size,
- child_tidptr, NULL, trace);
+ child_tidptr, NULL, target_pids, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 011/100] eclone (11/11): Document sys_eclone
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Sukadev Bhattiprolu,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
This gives a brief overview of the eclone() system call. We should
eventually describe more details in existing clone(2) man page or in
a new man page.
Changelog[v13]:
- [Nathan Lynch, Serge Hallyn] Rename ->child_stack_base to
->child_stack and ensure ->child_stack_size is 0 on architectures
that don't need it.
- [Arnd Bergmann] Remove ->reserved1 field
- [Louis Rilling, Dave Hansen] Combine the two asm statements in the
example into one and use memory constraint to avoid unncessary copies.
Changelog[v12]:
- [Serge Hallyn] Fix/simplify stack-setup in the example code
- [Serge Hallyn, Oren Laadan] Rename syscall to eclone()
Changelog[v11]:
- [Dave Hansen] Move clone_args validation checks to arch-indpendent
code.
- [Oren Laadan] Make args_size a parameter to system call and remove
it from 'struct clone_args'
- [Oren Laadan] Fix some typos and clarify the order of pids in the
@pids parameter.
Changelog[v10]:
- Rename clone3() to clone_with_pids() and fix some typos.
- Modify example to show usage with the ptregs implementation.
Changelog[v9]:
- [Pavel Machek]: Fix an inconsistency and rename new file to
Documentation/clone3.
- [Roland McGrath, H. Peter Anvin] Updates to description and
example to reflect new prototype of clone3() and the updated/
renamed 'struct clone_args'.
Changelog[v8]:
- clone2() is already in use in IA64. Rename syscall to clone3()
- Add notes to say that we return -EINVAL if invalid clone flags
are specified or if the reserved fields are not 0.
Changelog[v7]:
- Rename clone_with_pids() to clone2()
- Changes to reflect new prototype of clone2() (using clone_struct).
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: Oren Laadan <orenl@cs.columbia.edu>
---
Documentation/eclone | 348 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 348 insertions(+), 0 deletions(-)
create mode 100644 Documentation/eclone
diff --git a/Documentation/eclone b/Documentation/eclone
new file mode 100644
index 0000000..c2f1b4b
--- /dev/null
+++ b/Documentation/eclone
@@ -0,0 +1,348 @@
+
+struct clone_args {
+ u64 clone_flags_high;
+ u64 child_stack;
+ u64 child_stack_size;
+ u64 parent_tid_ptr;
+ u64 child_tid_ptr;
+ u32 nr_pids;
+ u32 reserved0;
+};
+
+
+sys_eclone(u32 flags_low, struct clone_args * __user cargs, int cargs_size,
+ pid_t * __user pids)
+
+ In addition to doing everything that clone() system call does, the
+ eclone() system call:
+
+ - allows additional clone flags (31 of 32 bits in the flags
+ parameter to clone() are in use)
+
+ - allows user to specify a pid for the child process in its
+ active and ancestor pid namespaces.
+
+ This system call is meant to be used when restarting an application
+ from a checkpoint. Such restart requires that the processes in the
+ application have the same pids they had when the application was
+ checkpointed. When containers are nested, the processes within the
+ containers exist in multiple pid namespaces and hence have multiple
+ pids to specify during restart.
+
+ The @flags_low parameter is identical to the 'clone_flags' parameter
+ in existing clone() system call.
+
+ The fields in 'struct clone_args' are meant to be used as follows:
+
+ u64 clone_flags_high:
+
+ When eclone() supports more than 32 flags, the additional bits
+ in the clone_flags should be specified in this field. This
+ field is currently unused and must be set to 0.
+
+ u64 child_stack;
+ u64 child_stack_size;
+
+ These two fields correspond to the 'child_stack' fields in
+ clone() and clone2() (on IA64) system calls. The usage of
+ these two fields depends on the processor architecture.
+
+ Most architectures use ->child_stack to pass-in a stack-pointer
+ itself and don't need the ->child_stack_size field. On these
+ architectures the ->child_stack_size field must be 0.
+
+ Some architectures, eg IA64, use ->child_stack to pass-in the
+ base of the region allocated for stack. These architectures
+ must pass in the size of the stack-region in ->child_stack_size.
+
+ u64 parent_tid_ptr;
+ u64 child_tid_ptr;
+
+ These two fields correspond to the 'parent_tid_ptr' and
+ 'child_tid_ptr' fields in the clone() system call
+
+ u32 nr_pids;
+
+ nr_pids specifies the number of pids in the @pids array
+ parameter to eclone() (see below). nr_pids should not exceed
+ the current nesting level of the calling process (i.e if the
+ process is in init_pid_ns, nr_pids must be 1, if process is
+ in a pid namespace that is a child of init-pid-ns, nr_pids
+ cannot exceed 2, and so on).
+
+ u32 reserved0;
+ u64 reserved1;
+
+ These fields are intended to extend the functionality of the
+ eclone() in the future, while preserving backward compatibility.
+ They must be set to 0 for now.
+
+ The @cargs_size parameter specifes the sizeof(struct clone_args) and
+ is intended to enable extending this structure in the future, while
+ preserving backward compatibility. For now, this field must be set
+ to the sizeof(struct clone_args) and this size must match the kernel's
+ view of the structure.
+
+ The @pids parameter defines the set of pids that should be assigned to
+ the child process in its active and ancestor pid namespaces. The
+ descendant pid namespaces do not matter since a process does not have a
+ pid in descendant namespaces, unless the process is in a new pid
+ namespace in which case the process is a container-init (and must have
+ the pid 1 in that namespace).
+
+ See CLONE_NEWPID section of clone(2) man page for details about pid
+ namespaces.
+
+ If a pid in the @pids list is 0, the kernel will assign the next
+ available pid in the pid namespace.
+
+ If a pid in the @pids list is non-zero, the kernel tries to assign
+ the specified pid in that namespace. If that pid is already in use
+ by another process, the system call fails (see EBUSY below).
+
+ The order of pids in @pids is oldest in pids[0] to youngest pid
+ namespace in pids[nr_pids-1]. If the number of pids specified in the
+ @pids list is fewer than the nesting level of the process, the pids
+ are applied from youngest namespace. i.e if the process is nested in
+ a level-6 pid namespace and @pids only specifies 3 pids, the 3 pids
+ are applied to levels 6, 5 and 4. Levels 0 through 3 are assumed to
+ have a pid of '0' (the kernel will assign a pid in those namespaces).
+
+ On success, the system call returns the pid of the child process in
+ the parent's active pid namespace.
+
+ On failure, eclone() returns -1 and sets 'errno' to one of following
+ values (the child process is not created).
+
+ EPERM Caller does not have the CAP_SYS_ADMIN privilege needed to
+ specify the pids in this call (if pids are not specifed
+ CAP_SYS_ADMIN is not required).
+
+ EINVAL The number of pids specified in 'clone_args.nr_pids' exceeds
+ the current nesting level of parent process
+
+ EINVAL Not all specified clone-flags are valid.
+
+ EINVAL The reserved fields in the clone_args argument are not 0.
+
+ EINVAL The child_stack_size field is not 0 (on architectures that
+ pass in a stack pointer in ->child_stack field)
+
+ EBUSY A requested pid is in use by another process in that namespace.
+
+---
+/*
+ * Example eclone() usage - Create a child process with pid CHILD_TID1 in
+ * the current pid namespace. The child gets the usual "random" pid in any
+ * ancestor pid namespaces.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <errno.h>
+#include <unistd.h>
+#include <wait.h>
+#include <sys/syscall.h>
+
+#define __NR_eclone 337
+#define CLONE_NEWPID 0x20000000
+#define CLONE_CHILD_SETTID 0x01000000
+#define CLONE_PARENT_SETTID 0x00100000
+#define CLONE_UNUSED 0x00001000
+
+#define STACKSIZE 8192
+
+typedef unsigned long long u64;
+typedef unsigned int u32;
+typedef int pid_t;
+struct clone_args {
+ u64 clone_flags_high;
+ u64 child_stack;
+ u64 child_stack_size;
+
+ u64 parent_tid_ptr;
+ u64 child_tid_ptr;
+
+ u32 nr_pids;
+
+ u32 reserved0;
+};
+
+#define exit _exit
+
+/*
+ * Following eclone() is based on code posted by Oren Laadan at:
+ * https://lists.linux-foundation.org/pipermail/containers/2009-June/018463.html
+ */
+#if defined(__i386__) && defined(__NR_eclone)
+
+int eclone(u32 flags_low, struct clone_args *clone_args, int args_size,
+ int *pids)
+{
+ long retval;
+
+ __asm__ __volatile__(
+ "movl %3, %%ebx\n\t" /* flags_low -> 1st (ebx) */
+ "movl %4, %%ecx\n\t" /* clone_args -> 2nd (ecx)*/
+ "movl %5, %%edx\n\t" /* args_size -> 3rd (edx) */
+ "movl %6, %%edi\n\t" /* pids -> 4th (edi)*/
+
+ "pushl %%ebp\n\t" /* save value of ebp */
+ "int $0x80\n\t" /* Linux/i386 system call */
+ "testl %0,%0\n\t" /* check return value */
+ "jne 1f\n\t" /* jump if parent */
+
+ "popl %%esi\n\t" /* get subthread function */
+ "call *%%esi\n\t" /* start subthread function */
+ "movl %2,%0\n\t"
+ "int $0x80\n" /* exit system call: exit subthread */
+ "1:\n\t"
+ "popl %%ebp\t" /* restore parent's ebp */
+
+ :"=a" (retval)
+
+ :"0" (__NR_eclone),
+ "i" (__NR_exit),
+ "m" (flags_low),
+ "m" (clone_args),
+ "m" (args_size),
+ "m" (pids)
+ );
+
+ if (retval < 0) {
+ errno = -retval;
+ retval = -1;
+ }
+ return retval;
+}
+
+/*
+ * Allocate a stack for the clone-child and arrange to have the child
+ * execute @child_fn with @child_arg as the argument.
+ */
+void *setup_stack(int (*child_fn)(void *), void *child_arg, int size)
+{
+ void *stack_base;
+ void **stack_top;
+
+ stack_base = malloc(size + size);
+ if (!stack_base) {
+ perror("malloc()");
+ exit(1);
+ }
+
+ stack_top = (void **)((char *)stack_base + (size - 4));
+ *--stack_top = child_arg;
+ *--stack_top = child_fn;
+
+ return stack_top;
+}
+#endif
+
+/* gettid() is a bit more useful than getpid() when messing with clone() */
+int gettid()
+{
+ int rc;
+
+ rc = syscall(__NR_gettid, 0, 0, 0);
+ if (rc < 0) {
+ printf("rc %d, errno %d\n", rc, errno);
+ exit(1);
+ }
+ return rc;
+}
+
+#define CHILD_TID1 377
+#define CHILD_TID2 1177
+#define CHILD_TID3 2799
+
+struct clone_args clone_args;
+void *child_arg = &clone_args;
+int child_tid;
+
+int do_child(void *arg)
+{
+ struct clone_args *cs = (struct clone_args *)arg;
+ int ctid;
+
+ /* Verify we pushed the arguments correctly on the stack... */
+ if (arg != child_arg) {
+ printf("Child: Incorrect child arg pointer, expected %p,"
+ "actual %p\n", child_arg, arg);
+ exit(1);
+ }
+
+ /* ... and that we got the thread-id we expected */
+ ctid = *((int *)(unsigned long)cs->child_tid_ptr);
+ if (ctid != CHILD_TID1) {
+ printf("Child: Incorrect child tid, expected %d, actual %d\n",
+ CHILD_TID1, ctid);
+ exit(1);
+ } else {
+ printf("Child got the expected tid, %d\n", gettid());
+ }
+ sleep(2);
+
+ printf("[%d, %d]: Child exiting\n", getpid(), ctid);
+ exit(0);
+}
+
+static int do_clone(int (*child_fn)(void *), void *child_arg,
+ unsigned int flags_low, int nr_pids, pid_t *pids_list)
+{
+ int rc;
+ void *stack;
+ struct clone_args *ca = &clone_args;
+ int args_size;
+
+ stack = setup_stack(child_fn, child_arg, STACKSIZE);
+
+ memset(ca, 0, sizeof(*ca));
+
+ ca->child_stack = (u64)(unsigned long)stack;
+ ca->child_stack_size = (u64)0;
+ ca->child_tid_ptr = (u64)(unsigned long)&child_tid;
+ ca->nr_pids = nr_pids;
+
+ args_size = sizeof(struct clone_args);
+ rc = eclone(flags_low, ca, args_size, pids_list);
+
+ printf("[%d, %d]: eclone() returned %d, error %d\n", getpid(), gettid(),
+ rc, errno);
+ return rc;
+}
+
+/*
+ * Multiple pid_t pid_t values in pids_list[] here are just for illustration.
+ * The test case creates a child in the current pid namespace and uses only
+ * the first value, CHILD_TID1.
+ */
+pid_t pids_list[] = { CHILD_TID1, CHILD_TID2, CHILD_TID3 };
+int main()
+{
+ int rc, pid, status;
+ unsigned long flags;
+ int nr_pids = 1;
+
+ flags = SIGCHLD|CLONE_CHILD_SETTID;
+
+ pid = do_clone(do_child, &clone_args, flags, nr_pids, pids_list);
+
+ printf("[%d, %d]: Parent waiting for %d\n", getpid(), gettid(), pid);
+
+ rc = waitpid(pid, &status, __WALL);
+ if (rc < 0) {
+ printf("waitpid(): rc %d, error %d\n", rc, errno);
+ } else {
+ printf("[%d, %d]: child %d:\n\t wait-status 0x%x\n", getpid(),
+ gettid(), rc, status);
+
+ if (WIFEXITED(status)) {
+ printf("\t EXITED, %d\n", WEXITSTATUS(status));
+ } else if (WIFSIGNALED(status)) {
+ printf("\t SIGNALED, %d\n", WTERMSIG(status));
+ }
+ }
+ return 0;
+}
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 012/100] c/r: extend arch_setup_additional_pages()
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, Oren Laadan, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Alexey Dobriyan,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Alexey Dobriyan <adobriyan@gmail.com>
Add "start" argument, to request to map vDSO to a specific place,
and fail the operation if not.
This is useful for restart(2) to ensure that memory layout is restore
exactly as needed.
Changelog[v19]:
- [serge hallyn] Fix potential use-before-set ret
Changelog[v2]:
- [ntl] powerpc: vdso build fix (ckpt-v17)
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Oren Laadan <orenl@cs.columbia.edu>
---
arch/powerpc/include/asm/elf.h | 1 +
arch/powerpc/kernel/vdso.c | 13 ++++++++++++-
arch/s390/include/asm/elf.h | 2 +-
arch/s390/kernel/vdso.c | 13 ++++++++++++-
arch/sh/include/asm/elf.h | 1 +
arch/sh/kernel/vsyscall/vsyscall.c | 2 +-
arch/x86/include/asm/elf.h | 3 ++-
arch/x86/vdso/vdso32-setup.c | 9 +++++++--
arch/x86/vdso/vma.c | 11 ++++++++---
fs/binfmt_elf.c | 2 +-
10 files changed, 46 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index c376eda..0b06255 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -266,6 +266,7 @@ extern int ucache_bsize;
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start,
int uses_interp);
#define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b);
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d84d192..74210ab 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -188,7 +188,8 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
*/
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start, int uses_interp)
{
struct mm_struct *mm = current->mm;
struct page **vdso_pagelist;
@@ -220,6 +221,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
vdso_base = VDSO32_MBASE;
#endif
+ /* in case restart(2) mandates a specific location */
+ if (start)
+ vdso_base = start;
+
current->mm->context.vdso_base = 0;
/* vDSO has a problem and was disabled, just don't "enable" it for the
@@ -249,6 +254,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
/* Add required alignment. */
vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
+ /* for restart(2), double check that we got we asked for */
+ if (start && vdso_base != start) {
+ rc = -EBUSY;
+ goto fail_mmapsem;
+ }
+
/*
* Put vDSO base into mm struct. We need to do this before calling
* install_special_mapping or the perf counter mmap tracking code
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 354d426..5081938 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -216,6 +216,6 @@ do { \
struct linux_binprm;
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-int arch_setup_additional_pages(struct linux_binprm *, int);
+int arch_setup_additional_pages(struct linux_binprm *, unsigned long, int);
#endif
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 6bc9c19..54dad2f 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -195,7 +195,8 @@ static void vdso_init_cr5(void)
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
*/
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start, int uses_interp)
{
struct mm_struct *mm = current->mm;
struct page **vdso_pagelist;
@@ -226,6 +227,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
vdso_pages = vdso32_pages;
#endif
+ /* in case restart(2) mandates a specific location */
+ if (start)
+ vdso_base = start;
+
/*
* vDSO has a problem and was disabled, just don't "enable" it for
* the process
@@ -248,6 +253,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
goto out_up;
}
+ /* for restart(2), double check that we got we asked for */
+ if (start && vdso_base != start) {
+ rc = -EINVAL;
+ goto out_up;
+ }
+
/*
* Put vDSO base into mm struct. We need to do this before calling
* install_special_mapping or the perf counter mmap tracking code
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index ce830fa..4128c30 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -201,6 +201,7 @@ do { \
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start,
int uses_interp);
extern unsigned int vdso_enabled;
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index 242117c..6dbdfe1 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -58,7 +58,7 @@ int __init vsyscall_init(void)
}
/* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm, unsigned long start, int uses_interp)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f2ad216..3761be8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -312,9 +312,10 @@ struct linux_binprm;
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start,
int uses_interp);
-extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
+extern int syscall32_setup_pages(struct linux_binprm *, unsigned long start, int exstack);
#define compat_arch_setup_additional_pages syscall32_setup_pages
extern unsigned long arch_randomize_brk(struct mm_struct *mm);
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 02b442e..62043c1 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -310,7 +310,8 @@ int __init sysenter_setup(void)
}
/* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start, int uses_interp)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
@@ -331,13 +332,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (compat)
addr = VDSO_HIGH_BASE;
else {
- addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+ addr = get_unmapped_area(NULL, start, PAGE_SIZE, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
}
+ /* for restart(2), double check that we got we asked for */
+ if (start && addr != start)
+ goto up_fail;
+
current->mm->context.vdso = (void *)addr;
if (compat_uses_vma || !compat) {
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index ac74869..b813286 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -100,23 +100,28 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
/* Setup a VMA at program startup for the vsyscall page.
Not called for compat tasks */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm,
+ unsigned long start, int uses_interp)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
- int ret;
+ int ret = -EINVAL;
if (!vdso_enabled)
return 0;
down_write(&mm->mmap_sem);
- addr = vdso_addr(mm->start_stack, vdso_size);
+ addr = start ? : vdso_addr(mm->start_stack, vdso_size);
addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
+ /* for restart(2), double check that we got we asked for */
+ if (start && addr != start)
+ goto up_fail;
+
current->mm->context.vdso = (void *)addr;
ret = install_special_mapping(mm, addr, vdso_size,
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 535e763..6434003 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -923,7 +923,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
set_binfmt(&elf_format);
#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
- retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
+ retval = arch_setup_additional_pages(bprm, 0, !!elf_interpreter);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 004/100] eclone (4/11): Add target_pids parameter to alloc_pid()
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Sukadev Bhattiprolu,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
This parameter is currently NULL, but will be used in a follow-on patch.
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
include/linux/pid.h | 2 +-
kernel/fork.c | 3 ++-
kernel/pid.c | 9 +++++++--
3 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 49f1c2f..914185d 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -119,7 +119,7 @@ extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
int next_pidmap(struct pid_namespace *pid_ns, int last);
-extern struct pid *alloc_pid(struct pid_namespace *ns);
+extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *target_pids);
extern void free_pid(struct pid *pid);
/*
diff --git a/kernel/fork.c b/kernel/fork.c
index afdfb08..62018c8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -962,6 +962,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
int retval;
struct task_struct *p;
int cgroup_callbacks_done = 0;
+ pid_t *target_pids = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
@@ -1147,7 +1148,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
- pid = alloc_pid(p->nsproxy->pid_ns);
+ pid = alloc_pid(p->nsproxy->pid_ns, target_pids);
if (IS_ERR(pid)) {
retval = PTR_ERR(pid);
goto bad_fork_cleanup_io;
diff --git a/kernel/pid.c b/kernel/pid.c
index 4eaf975..57f1344 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -276,13 +276,14 @@ void free_pid(struct pid *pid)
call_rcu(&pid->rcu, delayed_put_pid);
}
-struct pid *alloc_pid(struct pid_namespace *ns)
+struct pid *alloc_pid(struct pid_namespace *ns, pid_t *target_pids)
{
struct pid *pid;
enum pid_type type;
int i, nr;
struct pid_namespace *tmp;
struct upid *upid;
+ pid_t tpid;
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid) {
@@ -292,7 +293,11 @@ struct pid *alloc_pid(struct pid_namespace *ns)
tmp = ns;
for (i = ns->level; i >= 0; i--) {
- nr = alloc_pidmap(tmp);
+ tpid = 0;
+ if (target_pids)
+ tpid = target_pids[i];
+
+ nr = set_pidmap(tmp, tpid);
if (nr < 0)
goto out_free;
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 010/100] eclone (10/11): Implement sys_eclone for powerpc
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Nathan Lynch, Matt Helsley, Serge Hallyn,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Nathan Lynch <ntl@pobox.com>
Wired up for both ppc32 and ppc64, but tested only with the latter.
Changelog:
- Jan 20: (ntl) fix 32-bit build
- Nov 17: (serge) remove redundant flags_high check, and
don't fold it into flags.
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
---
arch/powerpc/include/asm/syscalls.h | 6 ++++
arch/powerpc/include/asm/systbl.h | 1 +
arch/powerpc/include/asm/unistd.h | 3 +-
arch/powerpc/kernel/entry_32.S | 8 +++++
arch/powerpc/kernel/entry_64.S | 5 +++
arch/powerpc/kernel/process.c | 54 ++++++++++++++++++++++++++++++++++-
6 files changed, 75 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h
index 4084e56..920cefd 100644
--- a/arch/powerpc/include/asm/syscalls.h
+++ b/arch/powerpc/include/asm/syscalls.h
@@ -23,6 +23,12 @@ asmlinkage int sys_execve(unsigned long a0, unsigned long a1,
asmlinkage int sys_clone(unsigned long clone_flags, unsigned long usp,
int __user *parent_tidp, void __user *child_threadptr,
int __user *child_tidp, int p6, struct pt_regs *regs);
+asmlinkage int sys_eclone(unsigned long flags_low,
+ struct clone_args __user *args,
+ size_t args_size,
+ pid_t __user *pids,
+ unsigned long p5, unsigned long p6,
+ struct pt_regs *regs);
asmlinkage int sys_fork(unsigned long p1, unsigned long p2,
unsigned long p3, unsigned long p4, unsigned long p5,
unsigned long p6, struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index a5ee345..f94fc43 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -326,3 +326,4 @@ SYSCALL_SPU(perf_event_open)
COMPAT_SYS_SPU(preadv)
COMPAT_SYS_SPU(pwritev)
COMPAT_SYS(rt_tgsigqueueinfo)
+PPC_SYS(eclone)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index f0a1026..4cdbd5c 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -345,10 +345,11 @@
#define __NR_preadv 320
#define __NR_pwritev 321
#define __NR_rt_tgsigqueueinfo 322
+#define __NR_eclone 323
#ifdef __KERNEL__
-#define __NR_syscalls 323
+#define __NR_syscalls 324
#define __NR__exit __NR_exit
#define NR_syscalls __NR_syscalls
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 1175a85..579f1da 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -586,6 +586,14 @@ ppc_clone:
stw r0,_TRAP(r1) /* register set saved */
b sys_clone
+ .globl ppc_eclone
+ppc_eclone:
+ SAVE_NVGPRS(r1)
+ lwz r0,_TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,_TRAP(r1) /* register set saved */
+ b sys_eclone
+
.globl ppc_swapcontext
ppc_swapcontext:
SAVE_NVGPRS(r1)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 07109d8..b763340 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -344,6 +344,11 @@ _GLOBAL(ppc_clone)
bl .sys_clone
b syscall_exit
+_GLOBAL(ppc_eclone)
+ bl .save_nvgprs
+ bl .sys_eclone
+ b syscall_exit
+
_GLOBAL(ppc32_swapcontext)
bl .save_nvgprs
bl .compat_sys_swapcontext
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e4d71ce..b183287 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -961,7 +961,59 @@ int sys_clone(unsigned long clone_flags, unsigned long usp,
child_tidp = TRUNC_PTR(child_tidp);
}
#endif
- return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp);
+ return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp);
+}
+
+int sys_eclone(unsigned long clone_flags_low,
+ struct clone_args __user *uclone_args,
+ size_t size,
+ pid_t __user *upids,
+ unsigned long p5, unsigned long p6,
+ struct pt_regs *regs)
+{
+ struct clone_args kclone_args;
+ unsigned long stack_base;
+ int __user *parent_tidp;
+ int __user *child_tidp;
+ unsigned long stack_sz;
+ unsigned int nr_pids;
+ unsigned long flags;
+ unsigned long usp;
+ int rc;
+
+ CHECK_FULL_REGS(regs);
+
+ rc = fetch_clone_args_from_user(uclone_args, size, &kclone_args);
+ if (rc)
+ return rc;
+
+ stack_sz = kclone_args.child_stack_size;
+ stack_base = kclone_args.child_stack;
+
+ /* powerpc doesn't do anything useful with the stack size */
+ if (stack_sz)
+ return -EINVAL;
+
+ /* Interpret stack_base as the child sp if it is set. */
+ usp = regs->gpr[1];
+ if (stack_base)
+ usp = stack_base;
+
+ flags = clone_flags_low;
+
+ nr_pids = kclone_args.nr_pids;
+
+ parent_tidp = (int __user *)(unsigned long)kclone_args.parent_tid_ptr;
+ child_tidp = (int __user *)(unsigned long)kclone_args.child_tid_ptr;
+
+#ifdef CONFIG_PPC64
+ if (test_thread_flag(TIF_32BIT)) {
+ parent_tidp = TRUNC_PTR(parent_tidp);
+ child_tidp = TRUNC_PTR(child_tidp);
+ }
+#endif
+ return do_fork_with_pids(flags, stack_base, regs, stack_sz,
+ parent_tidp, child_tidp, nr_pids, upids);
}
int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3,
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 009/100] eclone (9/11): Implement sys_eclone for s390
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Serge E. Hallyn <serue@us.ibm.com>
Implement the s390 hook for sys_eclone().
Changelog:
Nov 24: Removed user-space code from commit log. See user-cr git tree.
Nov 17: remove redundant flags_high check
Nov 13: As suggested by Heiko, convert eclone to take its
parameters via registers.
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
---
arch/s390/include/asm/unistd.h | 3 ++-
arch/s390/kernel/compat_linux.c | 17 +++++++++++++++++
arch/s390/kernel/compat_wrapper.S | 8 ++++++++
arch/s390/kernel/process.c | 37 +++++++++++++++++++++++++++++++++++++
arch/s390/kernel/syscalls.S | 1 +
5 files changed, 65 insertions(+), 1 deletions(-)
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 5f00751..ff13be1 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -269,7 +269,8 @@
#define __NR_pwritev 329
#define __NR_rt_tgsigqueueinfo 330
#define __NR_perf_event_open 331
-#define NR_syscalls 332
+#define __NR_eclone 332
+#define NR_syscalls 333
/*
* There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 73b624e..1f70d6f 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -663,6 +663,23 @@ asmlinkage long sys32_write(unsigned int fd, char __user * buf, size_t count)
return sys_write(fd, buf, count);
}
+asmlinkage long sys32_clone(void)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ unsigned long clone_flags;
+ unsigned long newsp;
+ int __user *parent_tidptr, *child_tidptr;
+
+ clone_flags = regs->gprs[3] & 0xffffffffUL;
+ newsp = regs->orig_gpr2 & 0x7fffffffUL;
+ parent_tidptr = compat_ptr(regs->gprs[4]);
+ child_tidptr = compat_ptr(regs->gprs[5]);
+ if (!newsp)
+ newsp = regs->gprs[15];
+ return do_fork(clone_flags, newsp, regs, 0,
+ parent_tidptr, child_tidptr);
+}
+
/*
* 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64.
* These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE}
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 672ce52..b7bedfa 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1847,6 +1847,14 @@ sys_clone_wrapper:
llgtr %r5,%r5 # int *
jg sys_clone # branch to system call
+ .globl sys_eclone_wrapper
+sys_eclone_wrapper:
+ llgfr %r2,%r2 # unsigned int
+ llgtr %r3,%r3 # struct clone_args *
+ lgfr %r4,%r4 # int
+ llgtr %r5,%r5 # pid_t *
+ jg sys_eclone # branch to system call
+
.globl sys32_execve_wrapper
sys32_execve_wrapper:
llgtr %r2,%r2 # char *
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 1039fde..799cbb0 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -240,6 +240,43 @@ SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags,
parent_tidptr, child_tidptr);
}
+SYSCALL_DEFINE4(eclone, unsigned int, flags_low, struct clone_args __user *,
+ uca, int, args_size, pid_t __user *, pids)
+{
+ int rc;
+ struct pt_regs *regs = task_pt_regs(current);
+ struct clone_args kca;
+ int __user *parent_tid_ptr;
+ int __user *child_tid_ptr;
+ unsigned long flags;
+ unsigned long __user child_stack;
+ unsigned long stack_size;
+
+ rc = fetch_clone_args_from_user(uca, args_size, &kca);
+ if (rc)
+ return rc;
+
+ flags = flags_low;
+ parent_tid_ptr = (int __user *) kca.parent_tid_ptr;
+ child_tid_ptr = (int __user *) kca.child_tid_ptr;
+
+ stack_size = (unsigned long) kca.child_stack_size;
+ if (stack_size)
+ return -EINVAL;
+
+ child_stack = (unsigned long) kca.child_stack;
+ if (!child_stack)
+ child_stack = regs->gprs[15];
+
+ /*
+ * TODO: On 32-bit systems, clone_flags is passed in as 32-bit value
+ * to several functions. Need to convert clone_flags to 64-bit.
+ */
+ return do_fork_with_pids(flags, child_stack, regs, stack_size,
+ parent_tid_ptr, child_tid_ptr, kca.nr_pids,
+ pids);
+}
+
/*
* This is trivial, and on the face of it looks like it
* could equally well be done in user mode.
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 201ce6b..08eab1d 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -340,3 +340,4 @@ SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv_wrapper)
SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper)
SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo_wrapper) /* 330 */
SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper)
+SYSCALL(sys_eclone,sys_eclone,sys_eclone_wrapper)
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 002/100] eclone (2/11): Have alloc_pidmap() return actual error code
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Sukadev Bhattiprolu,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
alloc_pidmap() can fail either because all pid numbers are in use or
because memory allocation failed. With support for setting a specific
pid number, alloc_pidmap() would also fail if either the given pid
number is invalid or in use.
Rather than have callers assume -ENOMEM, have alloc_pidmap() return
the actual error.
Changelog[v1]:
- [Oren Laadan] Rebase to kernel 2.6.33
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Reviewed-by: Oren Laadan <orenl@cs.columbia.edu>
---
kernel/fork.c | 5 +++--
kernel/pid.c | 10 ++++++----
2 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/kernel/fork.c b/kernel/fork.c
index 44b0791..afdfb08 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1147,10 +1147,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
- retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns);
- if (!pid)
+ if (IS_ERR(pid)) {
+ retval = PTR_ERR(pid);
goto bad_fork_cleanup_io;
+ }
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
diff --git a/kernel/pid.c b/kernel/pid.c
index 52a371a..8330488 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -160,7 +160,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
for (i = 0; i <= max_scan; ++i) {
if (unlikely(!map->page))
if (alloc_pidmap_page(map) < 0)
- break;
+ return -ENOMEM;
if (likely(atomic_read(&map->nr_free))) {
do {
if (!test_and_set_bit(offset, map->page)) {
@@ -191,7 +191,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
}
pid = mk_pid(pid_ns, map, offset);
}
- return -1;
+ return -EBUSY;
}
int next_pidmap(struct pid_namespace *pid_ns, int last)
@@ -260,8 +260,10 @@ struct pid *alloc_pid(struct pid_namespace *ns)
struct upid *upid;
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
- if (!pid)
+ if (!pid) {
+ pid = ERR_PTR(-ENOMEM);
goto out;
+ }
tmp = ns;
for (i = ns->level; i >= 0; i--) {
@@ -295,7 +297,7 @@ out_free:
free_pidmap(pid->numbers + i);
kmem_cache_free(ns->pid_cachep, pid);
- pid = NULL;
+ pid = ERR_PTR(nr);
goto out;
}
--
1.6.3.3
^ permalink raw reply related
* [PATCH v21 008/100] eclone (8/11): Implement sys_eclone for x86 (32, 64)
From: Oren Laadan @ 2010-05-01 14:14 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-s390, linux-api, containers, x86, linux-kernel,
linuxppc-dev, Matt Helsley, Serge Hallyn, Sukadev Bhattiprolu,
Pavel Emelyanov
In-Reply-To: <1272723382-19470-1-git-send-email-orenl@cs.columbia.edu>
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Container restart requires that a task have the same pid it had when it was
checkpointed. When containers are nested the tasks within the containers
exist in multiple pid namespaces and hence have multiple pids to specify
during restart.
eclone(), intended for use during restart, is the same as
clone(), except that it takes a 'pids' paramter. This parameter lets
caller choose specific pid numbers for the child process, in the
process's active and ancestor pid namespaces. (Descendant pid namespaces
in general don't matter since processes don't have pids in them anyway,
but see comments in copy_target_pids() regarding CLONE_NEWPID).
eclone() also attempts to address a second limitation of the
clone() system call. clone() is restricted to 32 clone flags and all but
one of these are in use. If more new clone flags are needed, we will be
forced to define a new variant of the clone() system call. To address
this, eclone() allows at least 64 clone flags with some room
for more if necessary.
To prevent unprivileged processes from misusing this interface,
eclone() currently needs CAP_SYS_ADMIN, when the 'pids' parameter
is non-NULL.
See Documentation/eclone in next patch for more details and an
example of its usage.
NOTE:
- System calls are restricted to 6 parameters and the number and sizes
of parameters needed for eclone() exceed 6 integers. The new
prototype works around this restriction while providing some
flexibility if eclone() needs to be further extended in the
future.
TODO:
- We should convert clone-flags to 64-bit value in all architectures.
Its probably best to do that as a separate patchset since clone_flags
touches several functions and that patchset seems independent of this
new system call.
Changelog[v14]:
- [Oren Laadan] Rebase to kernel 2.6.33
* introduce PTREGSCALL4 for sys_eclone
* consolidate syscall definitions for 32/64 bit
- [Oren Laadan] Merge x86_64 (trivial patch) with current
- [Serge Hallyn] Add eclone stub for ia32 eclone
Changelog[v13]:
- [Dave Hansen]: Reorg to enable sharing code between x86 and x86-64.
- [Arnd Bergmann]: With args_size parameter, ->reserved1 is redundant
and can be removed.
- [Nathan Lynch]: stop warnings about assigning u64 to a (32-bit) int*.
- [Nathan Lynch, Serge Hallyn] Rename ->child_stack_base to
->child_stack and ensure ->child_stack_size is 0 on architectures
that don't need it (see comments in types.h for details).
Changelog[v12]:
- [Serge Hallyn] Ignore ->child_stack_size if ->child_stack_base
is NULL.
- [Oren Laadan, Serge Hallyn] Rename clone_with_pids() to eclone()
Changelog[v11]:
- [Dave Hansen] Move clone_args validation checks to arch-indpeendent
code.
- [Oren Laadan] Make args_size a parameter to system call and remove
it from 'struct clone_args'
Changelog[v10]:
- Rename clone3() to clone_with_pids()
- [Linus Torvalds] Use PTREGSCALL() rather than the generic syscall
implementation
Changelog[v9]:
- [Roland McGrath, H. Peter Anvin] To avoid confusion on 64-bit
architectures split the new clone-flags into 'low' and 'high'
words and pass in the 'lower' flags as the first argument.
This would maintain similarity of the clone3() with clone()/
clone2(). Also has the side-effect of the name matching the
number of parameters :-)
- [Roland McGrath] Rename structure to 'clone_args' and add a
'child_stack_size' field
Changelog[v8]
- [Oren Laadan] parent_tid and child_tid fields in 'struct clone_arg'
must be 64-bit.
- clone2() is in use in IA64. Rename system call to clone3().
Changelog[v7]:
- [Peter Zijlstra, Arnd Bergmann] Rename system call to clone2()
and group parameters into a new 'struct clone_struct' object.
Changelog[v6]:
- (Nathan Lynch, Arnd Bergmann, H. Peter Anvin, Linus Torvalds)
Change 'pid_set.pids' to a 'pid_t pids[]' so size of 'struct pid_set'
is constant across architectures.
- (Nathan Lynch) Change pid_set.num_pids to unsigned and remove
'unum_pids < 0' check.
Changelog[v4]:
- (Oren Laadan) rename 'struct target_pid_set' to 'struct pid_set'
Changelog[v3]:
- (Oren Laadan) Allow CLONE_NEWPID flag (by allocating an extra pid
in the target_pids[] list and setting it 0. See copy_target_pids()).
- (Oren Laadan) Specified target pids should apply only to youngest
pid-namespaces (see copy_target_pids())
- (Matt Helsley) Update patch description.
Changelog[v2]:
- Remove unnecessary printk and add a note to callers of
copy_target_pids() to free target_pids.
- (Serge Hallyn) Mention CAP_SYS_ADMIN restriction in patch description.
- (Oren Laadan) Add checks for 'num_pids < 0' (return -EINVAL) and
'num_pids == 0' (fall back to normal clone()).
- Move arch-independent code (sanity checks and copy-in of target-pids)
into kernel/fork.c and simplify sys_clone_with_pids()
Changelog[v1]:
- Fixed some compile errors (had fixed these errors earlier in my
git tree but had not refreshed patches before emailing them)
Cc: linux-api@vger.kernel.org
Cc: x86@kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: Oren Laadan <orenl.cs.columbia.edu>
---
arch/x86/ia32/ia32entry.S | 2 +
arch/x86/include/asm/syscalls.h | 2 +
arch/x86/include/asm/unistd_32.h | 3 +-
arch/x86/include/asm/unistd_64.h | 2 +
arch/x86/kernel/entry_32.S | 14 ++++
arch/x86/kernel/entry_64.S | 1 +
arch/x86/kernel/process.c | 40 +++++++++++-
arch/x86/kernel/syscall_table_32.S | 1 +
include/linux/sched.h | 2 +
include/linux/types.h | 16 +++++
kernel/fork.c | 124 +++++++++++++++++++++++++++++++++++-
11 files changed, 204 insertions(+), 3 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 59b4556..b7f3f34 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -477,6 +477,7 @@ quiet_ni_syscall:
PTREGSCALL stub32_clone, sys32_clone, %rdx
PTREGSCALL stub32_vfork, sys_vfork, %rdi
PTREGSCALL stub32_iopl, sys_iopl, %rsi
+ PTREGSCALL stub32_eclone, sys_eclone, %r8
ENTRY(ia32_ptregs_common)
popq %r11
@@ -842,4 +843,5 @@ ia32_sys_call_table:
.quad compat_sys_rt_tgsigqueueinfo /* 335 */
.quad sys_perf_event_open
.quad compat_sys_recvmmsg
+ .quad stub32_eclone
ia32_syscall_end:
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 5c044b4..d525677 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -27,6 +27,8 @@ long sys_execve(char __user *, char __user * __user *,
char __user * __user *, struct pt_regs *);
long sys_clone(unsigned long, unsigned long, void __user *,
void __user *, struct pt_regs *);
+long sys_eclone(unsigned flags_low, struct clone_args __user *uca,
+ int args_size, pid_t __user *pids, struct pt_regs *regs);
/* kernel/ldt.c */
asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index beb9b5f..e543b0e 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -343,10 +343,11 @@
#define __NR_rt_tgsigqueueinfo 335
#define __NR_perf_event_open 336
#define __NR_recvmmsg 337
+#define __NR_eclone 338
#ifdef __KERNEL__
-#define NR_syscalls 338
+#define NR_syscalls 339
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index ff4307b..1cd16af 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -663,6 +663,8 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
#define __NR_recvmmsg 299
__SYSCALL(__NR_recvmmsg, sys_recvmmsg)
+#define __NR_eclone 300
+__SYSCALL(__NR_eclone, stub_eclone)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 44a8e0d..65e1735 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -758,6 +758,19 @@ ptregs_##name: \
addl $4,%esp; \
ret
+#define PTREGSCALL4(name) \
+ ALIGN; \
+ptregs_##name: \
+ leal 4(%esp),%eax; \
+ pushl %eax; \
+ pushl PT_ESI(%eax); \
+ movl PT_EDX(%eax),%ecx; \
+ movl PT_ECX(%eax),%edx; \
+ movl PT_EBX(%eax),%eax; \
+ call sys_##name; \
+ addl $8,%esp; \
+ ret
+
PTREGSCALL1(iopl)
PTREGSCALL0(fork)
PTREGSCALL0(vfork)
@@ -767,6 +780,7 @@ PTREGSCALL0(sigreturn)
PTREGSCALL0(rt_sigreturn)
PTREGSCALL2(vm86)
PTREGSCALL1(vm86old)
+PTREGSCALL4(eclone)
/* Clone is an oddball. The 4th arg is in %edi */
ALIGN;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0697ff1..216681e 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -698,6 +698,7 @@ END(\label)
PTREGSCALL stub_vfork, sys_vfork, %rdi
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
PTREGSCALL stub_iopl, sys_iopl, %rsi
+ PTREGSCALL stub_eclone, sys_eclone, %r8
ENTRY(ptregscall_common)
DEFAULT_FRAME 1 8 /* offset 8: return address */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 28ad9f4..5abad20 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -259,6 +259,45 @@ sys_clone(unsigned long clone_flags, unsigned long newsp,
return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}
+long
+sys_eclone(unsigned flags_low, struct clone_args __user *uca,
+ int args_size, pid_t __user *pids, struct pt_regs *regs)
+{
+ int rc;
+ struct clone_args kca;
+ unsigned long flags;
+ int __user *parent_tidp;
+ int __user *child_tidp;
+ unsigned long __user stack;
+ unsigned long stack_size;
+
+ rc = fetch_clone_args_from_user(uca, args_size, &kca);
+ if (rc)
+ return rc;
+
+ /*
+ * TODO: Convert 'clone-flags' to 64-bits on all architectures.
+ * TODO: When ->clone_flags_high is non-zero, copy it in to the
+ * higher word(s) of 'flags':
+ *
+ * flags = (kca.clone_flags_high << 32) | flags_low;
+ */
+ flags = flags_low;
+ parent_tidp = (int *)(unsigned long)kca.parent_tid_ptr;
+ child_tidp = (int *)(unsigned long)kca.child_tid_ptr;
+
+ stack_size = (unsigned long)kca.child_stack_size;
+ if (stack_size)
+ return -EINVAL;
+
+ stack = (unsigned long)kca.child_stack;
+ if (!stack)
+ stack = regs->sp;
+
+ return do_fork_with_pids(flags, stack, regs, stack_size, parent_tidp,
+ child_tidp, kca.nr_pids, pids);
+}
+
/*
* This gets run with %si containing the
* function to call, and %di containing
@@ -700,4 +739,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
unsigned long range_end = mm->brk + 0x02000000;
return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
}
-
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 8b37293..0c92570 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -337,3 +337,4 @@ ENTRY(sys_call_table)
.long sys_rt_tgsigqueueinfo /* 335 */
.long sys_perf_event_open
.long sys_recvmmsg
+ .long ptregs_eclone
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f4ae3e3..8593051 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2129,6 +2129,8 @@ extern int disallow_signal(int);
extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
+extern int fetch_clone_args_from_user(struct clone_args __user *, int,
+ struct clone_args *);
extern long do_fork_with_pids(unsigned long, unsigned long, struct pt_regs *,
unsigned long, int __user *, int __user *,
unsigned int, pid_t __user *);
diff --git a/include/linux/types.h b/include/linux/types.h
index c42724f..d8bfd6b 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -204,6 +204,22 @@ struct ustat {
char f_fpack[6];
};
+struct clone_args {
+ u64 clone_flags_high;
+ /*
+ * Architectures can use child_stack for either the stack pointer or
+ * the base of of stack. If child_stack is used as the stack pointer,
+ * child_stack_size must be 0. Otherwise child_stack_size must be
+ * set to size of allocated stack.
+ */
+ u64 child_stack;
+ u64 child_stack_size;
+ u64 parent_tid_ptr;
+ u64 child_tid_ptr;
+ u32 nr_pids;
+ u32 reserved0;
+};
+
#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
#endif /* _LINUX_TYPES_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 2559d7a..9d5be5c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1350,6 +1350,114 @@ struct task_struct * __cpuinit fork_idle(int cpu)
}
/*
+ * If user specified any 'target-pids' in @upid_setp, copy them from
+ * user and return a pointer to a local copy of the list of pids. The
+ * caller must free the list, when they are done using it.
+ *
+ * If user did not specify any target pids, return NULL (caller should
+ * treat this like normal clone).
+ *
+ * On any errors, return the error code
+ */
+static pid_t *copy_target_pids(int unum_pids, pid_t __user *upids)
+{
+ int j;
+ int rc;
+ int size;
+ int knum_pids; /* # of pids needed in kernel */
+ pid_t *target_pids;
+
+ if (!unum_pids)
+ return NULL;
+
+ knum_pids = task_pid(current)->level + 1;
+ if (unum_pids > knum_pids)
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * To keep alloc_pid() simple, allocate an extra pid_t in target_pids[]
+ * and set it to 0. This last entry in target_pids[] corresponds to the
+ * (yet-to-be-created) descendant pid-namespace if CLONE_NEWPID was
+ * specified. If CLONE_NEWPID was not specified, this last entry will
+ * simply be ignored.
+ */
+ target_pids = kzalloc((knum_pids + 1) * sizeof(pid_t), GFP_KERNEL);
+ if (!target_pids)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * A process running in a level 2 pid namespace has three pid namespaces
+ * and hence three pid numbers. If this process is checkpointed,
+ * information about these three namespaces are saved. We refer to these
+ * namespaces as 'known namespaces'.
+ *
+ * If this checkpointed process is however restarted in a level 3 pid
+ * namespace, the restarted process has an extra ancestor pid namespace
+ * (i.e 'unknown namespace') and 'knum_pids' exceeds 'unum_pids'.
+ *
+ * During restart, the process requests specific pids for its 'known
+ * namespaces' and lets kernel assign pids to its 'unknown namespaces'.
+ *
+ * Since the requested-pids correspond to 'known namespaces' and since
+ * 'known-namespaces' are younger than (i.e descendants of) 'unknown-
+ * namespaces', copy requested pids to the back-end of target_pids[]
+ * (i.e before the last entry for CLONE_NEWPID mentioned above).
+ * Any entries in target_pids[] not corresponding to a requested pid
+ * will be set to zero and kernel assigns a pid in those namespaces.
+ *
+ * NOTE: The order of pids in target_pids[] is oldest pid namespace
+ * to youngest (target_pids[0] corresponds to init_pid_ns). i.e. the
+ * the order is:
+ *
+ * - pids for 'unknown-namespaces' (if any)
+ * - pids for 'known-namespaces' (requested pids)
+ * - 0 in the last entry (for CLONE_NEWPID).
+ */
+ j = knum_pids - unum_pids;
+ size = unum_pids * sizeof(pid_t);
+
+ rc = copy_from_user(&target_pids[j], upids, size);
+ if (rc) {
+ rc = -EFAULT;
+ goto out_free;
+ }
+
+ return target_pids;
+
+out_free:
+ kfree(target_pids);
+ return ERR_PTR(rc);
+}
+
+int
+fetch_clone_args_from_user(struct clone_args __user *uca, int args_size,
+ struct clone_args *kca)
+{
+ int rc;
+
+ /*
+ * TODO: If size of clone_args is not what the kernel expects, it
+ * could be that kernel is newer and has an extended structure.
+ * When that happens, this check needs to be smarter. For now,
+ * assume exact match.
+ */
+ if (args_size != sizeof(struct clone_args))
+ return -EINVAL;
+
+ rc = copy_from_user(kca, uca, args_size);
+ if (rc)
+ return -EFAULT;
+
+ /*
+ * To avoid future compatibility issues, ensure unused fields are 0.
+ */
+ if (kca->reserved0 || kca->clone_flags_high)
+ return -EINVAL;
+
+ return 0;
+}
+
+/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
@@ -1367,7 +1475,7 @@ long do_fork_with_pids(unsigned long clone_flags,
struct task_struct *p;
int trace = 0;
long nr;
- pid_t *target_pids = NULL;
+ pid_t *target_pids;
/*
* Do some preliminary argument and permissions checking before we
@@ -1401,6 +1509,16 @@ long do_fork_with_pids(unsigned long clone_flags,
}
}
+ target_pids = copy_target_pids(num_pids, upids);
+ if (target_pids) {
+ if (IS_ERR(target_pids))
+ return PTR_ERR(target_pids);
+
+ nr = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_free;
+ }
+
/*
* When called from kernel_thread, don't do user tracing stuff.
*/
@@ -1462,6 +1580,10 @@ long do_fork_with_pids(unsigned long clone_flags,
} else {
nr = PTR_ERR(p);
}
+
+out_free:
+ kfree(target_pids);
+
return nr;
}
--
1.6.3.3
^ permalink raw reply related
* Re: -next Apr 30: OOPS during eHEA driver initialization
From: Sachin Sant @ 2010-05-01 9:54 UTC (permalink / raw)
To: Grant Likely
Cc: Linux/PPC Development, linux-next@vger.kernel.org,
Greg Kroah-Hartman, linux-kernel
In-Reply-To: <g2mfa686aa41004301043i138ffb2dmac5b641fa3d512c4@mail.gmail.com>
Grant Likely wrote:
> On Fri, Apr 30, 2010 at 11:35 AM, Grant Likely
> <grant.likely@secretlab.ca> wrote:
>
>> On Fri, Apr 30, 2010 at 11:27 AM, Sachin Sant <sachinp@in.ibm.com> wrote:
>>
>>> Sachin Sant wrote:
>>>
>>>> With today's next eHEA drivers fails to initialize.
>>>>
>>> If i revert the following patch eHEA network interface is initialized
>>> properly.
>>>
>>> commit cebfe0b6709abdab997c1a00499d67efa32ee1f0
>>> drivercore: Add of_match_table to the common device drivers
>>>
>> That is an easy one to fix. I'll get it updated today and send you the result.
>>
>
> Let me know if this patch fixes it:
>
Works for me. Thanks Grant.
Tested-by : Sachin Sant <sachinp@in.ibm.com>
Regards
-Sachin
> Cheers,
> g.
>
> diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
> index ce957a4..693b0e6 100644
> --- a/arch/powerpc/kernel/ibmebus.c
> +++ b/arch/powerpc/kernel/ibmebus.c
> @@ -201,6 +201,9 @@ static int ibmebus_create_devices(const struct
> of_device_id *matches)
>
> int ibmebus_register_driver(struct of_platform_driver *drv)
> {
> + if (!drv->driver.of_match_table)
> + drv->driver.of_match_table = drv->match_table;
> +
> /* If the driver uses devices that ibmebus doesn't know, add them */
> ibmebus_create_devices(drv->driver.of_match_table);
>
>
>
>
--
---------------------------------
Sachin Sant
IBM Linux Technology Center
India Systems and Technology Labs
Bangalore, India
---------------------------------
^ permalink raw reply
* Re: [alsa-devel] [PATCH 1/2] powerpc: add platform registration for ALSA SoC drivers
From: Timur Tabi @ 2010-04-30 22:04 UTC (permalink / raw)
To: Liam Girdwood; +Cc: alsa-devel, kumar.gala, broonie, linuxppc-dev
In-Reply-To: <t2ged82fe3e1004301446mfbe63ddele99ad22ae331dd57@mail.gmail.com>
On Fri, Apr 30, 2010 at 4:46 PM, Timur Tabi <timur@freescale.com> wrote:
> When I boot Linux, I get this:
>
> asoc: cs4270 <-> /soc@e0000000/ssi@16000 mapping ok
> sysfs: cannot create duplicate filename '/devices/platform/soc-audio/cs4270'
*sigh* never mind. The problem was that the stream_name was the same
for both DAIs.
What exactly should the stream names be set to, anyway? I did this:
machine_data->dai[0].stream_name = "playback";
machine_data->dai[1].stream_name = "capture";
but I have a suspicion that this is too simplistic.
--
Timur Tabi
Linux kernel developer at Freescale
^ permalink raw reply
* Re: [alsa-devel] [PATCH 1/2] powerpc: add platform registration for ALSA SoC drivers
From: Timur Tabi @ 2010-04-30 21:46 UTC (permalink / raw)
To: Liam Girdwood; +Cc: alsa-devel, kumar.gala, broonie, linuxppc-dev
In-Reply-To: <1272381611.11000.39.camel@odin>
On Tue, Apr 27, 2010 at 10:20 AM, Liam Girdwood <lrg@slimlogic.co.uk> wrote=
:
>> Another problem is that ASoC won't let me probe the DMA channels
>> independently. =A0That is, I cannot tell ASoC that I have a playback DMA
>> and a capture DMA. =A0ASoC does not recognize two DMA devices for a
>> single SSI. =A0If you can fix that, then I can turn the DMA driver into
>> an OF driver.
>>
>
> Iirc, the SSI and DMA controllers on your SoC mean that each DMA device
> can only do one direction (either Playback or Capture). So I'm thinking
> we create two DAI link entries for your sound card (one for playback and
> the other for capture) and they both use the same SSI device but each
> would have it's own DMA device.
>
> This would result in two separate pcm devices being exported to
> userspace i.e one for playback only and the other for capture only. I
> think this is also a more accurate representation of your hardware too
> (since we have different DMA devices for each pcm stream direction).
Ok, I'm trying to do this now, and I'm running into problems.
So here's the device list:
One machine
One SSI
Two DMA channels
One codec
So I create two dai_links in the machine driver. Each dai_link has
two DAIs in it. The DAIs are identical, except for the platform_drv
field. The platform_drv in the first DAI points to the first DMA
channel, and the platform_drv of the second DAI points to the second
DMA channel.
When I boot Linux, I get this:
asoc: cs4270 <-> /soc@e0000000/ssi@16000 mapping ok
sysfs: cannot create duplicate filename '/devices/platform/soc-audio/cs4270=
'
so it looks like when asoc is processing the dai_link, it tries to
create a sysfs device for the codec twice.
How do I avoid this?
--=20
Timur Tabi
Linux kernel developer at Freescale
^ permalink raw reply
* Re: [PATCH 3/5] powerpc/mpc5121: shared DIU framebuffer support
From: Scott Wood @ 2010-04-30 20:40 UTC (permalink / raw)
To: Timur Tabi
Cc: linux-fbdev, wd, dzu, John Rigby, devicetree-discuss,
linuxppc-dev, Anatolij Gustschin, yorksun
In-Reply-To: <r2sed82fe3e1004301118xc52b46cfi879de534283fd51@mail.gmail.com>
Timur Tabi wrote:
> On Fri, Apr 30, 2010 at 11:22 AM, Scott Wood <scottwood@freescale.com> wrote:
>
>>> That's what I meant. Actually, I think it's ULL. Regardless, I think
>>> the compiler will see the "1000000000 ... * 1000" and just combine
>>> them together. You're not actually outsmarting the compiler.
>> The compiler will do no such thing. That's a valid transformation when
>> doing pure math, but not when working with integers.
>
> I ran some tests, and it appears you're right. I doesn't make a lot
> of sense to me, but whatever.
>
> However, "(1000000000 / pixclock) * 1000" produces a result that's
> less accurate than "1000000000000ULL / pixclock".
Precisely, that's what makes it a distinct computation -- as far as the
compiler knows, it could be intentional. Plus, turning it into 64-bit
math would invoke a library call for 64-bit division, which wouldn't be
much of an optimization anyway.
The question is whether the loss of accuracy matters in this case.
>>> err = -1;
>>>
>>> because he wanted it to be the largest possible integer.
>> -1 is not the largest possible integer. LONG_MAX, perhaps?
>
> What, you don't like implicit casting of -1 to an unsigned? :-)
I like it even less when the variable is signed and it's still supposed
to be larger than positive numbers. :-)
-Scott
^ permalink raw reply
* [PATCH 2/2] powerpc/mpc5121: add initial support for PDM360NG board
From: Anatolij Gustschin @ 2010-04-30 20:30 UTC (permalink / raw)
To: linuxppc-dev
Cc: Detlev Zundel, Markus Fischer, devicetree-discuss, Michael Weiss,
Anatolij Gustschin, Wolfgang Grandegger
In-Reply-To: <1272659448-23302-1-git-send-email-agust@denx.de>
Adds IFM PDM360NG device tree, and platform code.
Currently following is supported:
- Spansion S29GL512P 256 MB NOR flash
- ST Micro NAND 1 GiB flash
- DIU, please use "fbcon=map:5 video=fslfb:800x480-32@60"
at the kernel command line to enable PrimeView PM070WL3
Display support.
- FEC
- I2C
- RTC, EEPROM
- MSCAN
- PSC UART, please pass "console=tty0 console=ttyPSC5,115200"
on the kernel command line.
- USB0/1 Host
- USB0 OTG Host/Device
- VIU, Overlay support
Signed-off-by: Markus Fischer <markus.fischer.ec@ifm.com>
Signed-off-by: Wolfgang Grandegger <wg@denx.de>
Signed-off-by: Michael Weiss <michael.weiss@ifm.com>
Signed-off-by: Detlev Zundel <dzu@denx.de>
Signed-off-by: Anatolij Gustschin <agust@denx.de>
Cc: devicetree-discuss@lists.ozlabs.org
Cc: Grant Likely <grant.likely@secretlab.ca>
---
This patch is intended to be used on top of MPC5121 DIU
support patch series:
http://thread.gmane.org/gmane.linux.ports.ppc.embedded/34806
I post it for review now, too.
arch/powerpc/boot/dts/pdm360ng.dts | 430 ++++++++++++++++++++++++++++++++
arch/powerpc/platforms/512x/Kconfig | 7 +
arch/powerpc/platforms/512x/Makefile | 1 +
arch/powerpc/platforms/512x/pdm360ng.c | 158 ++++++++++++
4 files changed, 596 insertions(+), 0 deletions(-)
create mode 100644 arch/powerpc/boot/dts/pdm360ng.dts
create mode 100644 arch/powerpc/platforms/512x/pdm360ng.c
diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts
new file mode 100644
index 0000000..23bce6e
--- /dev/null
+++ b/arch/powerpc/boot/dts/pdm360ng.dts
@@ -0,0 +1,430 @@
+/*
+ * Device Tree Source for IFM PDM360NG.
+ *
+ * Copyright 2009 - 2010 DENX Software Engineering.
+ * Anatolij Gustschin <agust@denx.de>
+ *
+ * Based on MPC5121E ADS dts.
+ * Copyright 2008 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+/dts-v1/;
+
+/ {
+ model = "pdm360ng";
+ compatible = "ifm,pdm360ng";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ PowerPC,5121@0 {
+ device_type = "cpu";
+ reg = <0>;
+ d-cache-line-size = <0x20>; // 32 bytes
+ i-cache-line-size = <0x20>; // 32 bytes
+ d-cache-size = <0x8000>; // L1, 32K
+ i-cache-size = <0x8000>; // L1, 32K
+ timebase-frequency = <49500000>;// 49.5 MHz (csb/4)
+ bus-frequency = <198000000>; // 198 MHz csb bus
+ clock-frequency = <396000000>; // 396 MHz ppc core
+ };
+ };
+
+ memory {
+ device_type = "memory";
+ reg = <0x00000000 0x20000000>; // 512MB at 0
+ };
+
+ nfc@40000000 {
+ compatible = "fsl,mpc5121-nfc";
+ reg = <0x40000000 0x100000>;
+ interrupts = <0x6 0x8>;
+ interrupt-parent = <0x1>;
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ bank-width = <0x1>;
+ chips = <0x1>;
+
+ partition@0 {
+ label = "nand0";
+ reg = <0x0 0x40000000>;
+ };
+ };
+
+ sram@50000000 {
+ compatible = "fsl,mpc5121-sram";
+ reg = <0x50000000 0x20000>; // 128K at 0x50000000
+ };
+
+ localbus@80000020 {
+ compatible = "fsl,mpc5121-localbus";
+ #address-cells = <2>;
+ #size-cells = <1>;
+ reg = <0x80000020 0x40>;
+
+ ranges = <0x0 0x0 0xf0000000 0x10000000 /* Flash */
+ 0x2 0x0 0x50040000 0x00020000>; /* CS2: MRAM */
+
+ flash@0,0 {
+ compatible = "amd,s29gl01gp", "cfi-flash";
+ reg = <0 0x00000000 0x08000000
+ 0 0x08000000 0x08000000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ bank-width = <4>;
+ device-width = <2>;
+
+ partition@0 {
+ label = "u-boot";
+ reg = <0x00000000 0x00080000>;
+ read-only;
+ };
+ partition@80000 {
+ label = "environment";
+ reg = <0x00080000 0x00080000>;
+ read-only;
+ };
+ partition@100000 {
+ label = "splash-image";
+ reg = <0x00100000 0x00080000>;
+ read-only;
+ };
+ partition@180000 {
+ label = "device-tree";
+ reg = <0x00180000 0x00040000>;
+ };
+ partition@1c0000 {
+ label = "kernel";
+ reg = <0x001c0000 0x00500000>;
+ };
+ partition@6c0000 {
+ label = "filesystem";
+ reg = <0x006c0000 0x07940000>;
+ };
+ };
+
+ mram0@2,0 {
+ compatible = "mtd-ram";
+ reg = <2 0x00000 0x10000>;
+ bank-width = <2>;
+ };
+
+ mram1@2,10000 {
+ compatible = "mtd-ram";
+ reg = <2 0x010000 0x10000>;
+ bank-width = <2>;
+ };
+ };
+
+ soc@80000000 {
+ compatible = "fsl,mpc5121-immr";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ #interrupt-cells = <2>;
+ ranges = <0x0 0x80000000 0x400000>;
+ reg = <0x80000000 0x400000>;
+ bus-frequency = <66000000>; // 66 MHz ips bus
+
+ // IPIC
+ // interrupts cell = <intr #, sense>
+ // sense values match linux IORESOURCE_IRQ_* defines:
+ // sense == 8: Level, low assertion
+ // sense == 2: Edge, high-to-low change
+ //
+ ipic: interrupt-controller@c00 {
+ compatible = "fsl,mpc5121-ipic", "fsl,ipic";
+ interrupt-controller;
+ #address-cells = <0>;
+ #interrupt-cells = <2>;
+ reg = <0xc00 0x100>;
+ };
+
+ rtc@a00 { // Real time clock
+ compatible = "fsl,mpc5121-rtc";
+ reg = <0xa00 0x100>;
+ interrupts = <79 0x8 80 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ reset@e00 { // Reset module
+ compatible = "fsl,mpc5121-reset";
+ reg = <0xe00 0x100>;
+ };
+
+ clock@f00 { // Clock control
+ compatible = "fsl,mpc5121-clock";
+ reg = <0xf00 0x100>;
+ };
+
+ pmc@1000{ //Power Management Controller
+ compatible = "fsl,mpc5121-pmc";
+ reg = <0x1000 0x100>;
+ interrupts = <83 0x2>;
+ interrupt-parent = < &ipic >;
+ };
+
+ gpio@1100 {
+ compatible = "fsl,mpc5121-gpio";
+ reg = <0x1100 0x100>;
+ interrupts = <78 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ can@1300 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <12 0x8>;
+ interrupt-parent = < &ipic >;
+ reg = <0x1300 0x80>;
+ };
+
+ can@1380 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <13 0x8>;
+ interrupt-parent = < &ipic >;
+ reg = <0x1380 0x80>;
+ };
+
+ i2c@1700 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc5121-i2c";
+ reg = <0x1700 0x20>;
+ interrupts = <0x9 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,preserve-clocking;
+
+ eeprom@50 {
+ compatible = "at,24c01";
+ reg = <0x50>;
+ };
+
+ rtc@68 {
+ compatible = "stm,m41t00";
+ reg = <0x68>;
+ };
+ };
+
+ i2c@1740 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc5121-i2c";
+ reg = <0x1740 0x20>;
+ interrupts = <0xb 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,preserve-clocking;
+ };
+
+ i2ccontrol@1760 {
+ compatible = "fsl,mpc5121-i2c-ctrl";
+ reg = <0x1760 0x8>;
+ };
+
+ axe@2000 {
+ compatible = "fsl,mpc5121-axe";
+ reg = <0x2000 0x100>;
+ interrupts = <42 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ display@2100 {
+ compatible = "fsl,mpc5121-diu";
+ reg = <0x2100 0x100>;
+ interrupts = <64 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ can@2300 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <90 0x8>;
+ interrupt-parent = < &ipic >;
+ reg = <0x2300 0x80>;
+ };
+
+ can@2380 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <91 0x8>;
+ interrupt-parent = < &ipic >;
+ reg = <0x2380 0x80>;
+ };
+
+ viu@2400 {
+ compatible = "fsl,mpc5121-viu";
+ reg = <0x2400 0x400>;
+ interrupts = <67 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ mdio@2800 {
+ compatible = "fsl,mpc5121-fec-mdio";
+ reg = <0x2800 0x200>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy: ethernet-phy@0 {
+ reg = <0x1f>;
+ device_type = "ethernet-phy";
+ };
+ };
+
+ ethernet@2800 {
+ device_type = "network";
+ compatible = "fsl,mpc5121-fec";
+ reg = <0x2800 0x200>;
+ local-mac-address = [ 00 00 00 00 00 00 ];
+ interrupts = <4 0x8>;
+ interrupt-parent = < &ipic >;
+ phy-handle = < &phy >;
+ };
+
+ // USB1 using external ULPI PHY
+ usb@3000 {
+ compatible = "fsl,mpc5121-usb2-dr";
+ reg = <0x3000 0x600>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = < &ipic >;
+ interrupts = <43 0x8>;
+ dr_mode = "host";
+ phy_type = "ulpi";
+ };
+
+ // USB0 using internal UTMI PHY
+ usb@4000 {
+ compatible = "fsl,mpc5121-usb2-dr";
+ reg = <0x4000 0x600>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = < &ipic >;
+ interrupts = <44 0x8>;
+ dr_mode = "otg";
+ phy_type = "utmi_wide";
+ fsl,invert-pwr-fault;
+ };
+
+ // IO control
+ ioctl@a000 {
+ compatible = "fsl,mpc5121-ioctl";
+ reg = <0xA000 0x1000>;
+ };
+
+ // 512x PSCs are not 52xx PSCs compatible
+ serial@11000 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <0>;
+ reg = <0x11000 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11100 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <1>;
+ reg = <0x11100 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11200 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <2>;
+ reg = <0x11200 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11300 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <3>;
+ reg = <0x11300 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11400 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <4>;
+ reg = <0x11400 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11600 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <6>;
+ reg = <0x11600 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11800 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <8>;
+ reg = <0x11800 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ serial@11B00 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <11>;
+ reg = <0x11B00 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+ };
+
+ pscfifo@11f00 {
+ compatible = "fsl,mpc5121-psc-fifo";
+ reg = <0x11f00 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+
+ spi@11900 {
+ compatible = "fsl,mpc5121-psc-spi", "fsl,mpc5121-psc";
+ cell-index = <9>;
+ reg = <0x11900 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+
+ // 7845 touch screen controller
+ ts@0 {
+ compatible = "ti,ads7845";
+ interrupt-parent = < &ipic >;
+ // pen irq is GPIO25
+ interrupts = <78 0x8>;
+ };
+ };
+
+ dma@14000 {
+ compatible = "fsl,mpc5121-dma";
+ reg = <0x14000 0x1800>;
+ interrupts = <65 0x8>;
+ interrupt-parent = < &ipic >;
+ };
+ };
+};
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index e9dca28..27b0651 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -25,3 +25,10 @@ config MPC5121_GENERIC
Compatible boards include: Protonic LVT base boards (ZANMCU
and VICVT2).
+
+config PDM360NG
+ bool "ifm PDM360NG board"
+ depends on PPC_MPC512x
+ select DEFAULT_UIMAGE
+ help
+ This option enables support for the PDM360NG board.
diff --git a/arch/powerpc/platforms/512x/Makefile b/arch/powerpc/platforms/512x/Makefile
index 90be2f5..4efc1c4 100644
--- a/arch/powerpc/platforms/512x/Makefile
+++ b/arch/powerpc/platforms/512x/Makefile
@@ -4,3 +4,4 @@
obj-y += clock.o mpc512x_shared.o
obj-$(CONFIG_MPC5121_ADS) += mpc5121_ads.o mpc5121_ads_cpld.o
obj-$(CONFIG_MPC5121_GENERIC) += mpc5121_generic.o
+obj-$(CONFIG_PDM360NG) += pdm360ng.o
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
new file mode 100644
index 0000000..dc8f860
--- /dev/null
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2010 DENX Software Engineering
+ *
+ * Anatolij Gustschin, <agust@denx.de>
+ *
+ * PDM360NG board setup
+ *
+ * This is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/of_platform.h>
+
+#include <asm/machdep.h>
+#include <asm/ipic.h>
+#include <asm/prom.h>
+
+#include "mpc512x.h"
+
+#if defined(CONFIG_TOUCHSCREEN_ADS7846) || \
+ defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
+#include <linux/fsl_devices.h>
+#include <linux/interrupt.h>
+#include <linux/spi/ads7846.h>
+#include <linux/spi/spi.h>
+
+static void *pdm360ng_gpio_base;
+
+static int pdm360ng_get_pendown_state(void)
+{
+ u32 reg;
+
+ reg = in_be32((u32 *)(pdm360ng_gpio_base + 0xc));
+ if (reg & 0x40)
+ setbits32((u32 *)(pdm360ng_gpio_base + 0xc), 0x40);
+
+ reg = in_be32((u32 *)(pdm360ng_gpio_base + 0x8));
+
+ /* return 1 if pen is down */
+ return reg & 0x40 ? 0 : 1;
+}
+
+static struct ads7846_platform_data pdm360ng_ads7846_pdata __initdata = {
+ .model = 7845,
+ .get_pendown_state = pdm360ng_get_pendown_state,
+ /*.irq_trigger = IRQF_TRIGGER_LOW,*/
+};
+
+static int __init pdm360ng_penirq_init(void)
+{
+ struct device_node *np;
+ struct resource r;
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-gpio");
+ if (!np) {
+ pr_err("%s: Can't find 'mpc5121-gpio' node\n", __func__);
+ return -1;
+ }
+
+ if (of_address_to_resource(np, 0, &r)) {
+ pr_err("%s: Invalid gpio address.\n", __func__);
+ of_node_put(np);
+ return -1;
+ }
+ of_node_put(np);
+
+ pdm360ng_gpio_base = ioremap(r.start, resource_size(&r));
+ if (!pdm360ng_gpio_base) {
+ pr_err("%s: Can't map gpio regs.\n", __func__);
+ return -1;
+ }
+ out_be32((u32 *)pdm360ng_gpio_base + 0xc, 0xffffffff);
+ setbits32((u32 *)(pdm360ng_gpio_base + 0x18), 0x2000);
+ setbits32((u32 *)(pdm360ng_gpio_base + 0x10), 0x40);
+
+ return 0;
+}
+
+static int __init pdm360ng_touchscreen_init(void)
+{
+ struct device_node *np;
+ struct of_device *of_dev;
+ struct spi_board_info info;
+ const u32 *prop;
+ int bus_num = -1;
+ int len;
+
+ np = of_find_compatible_node(NULL, NULL, "ti,ads7845");
+ if (!np)
+ return -ENODEV;
+
+ memset(&info, 0, sizeof(info));
+ info.irq = irq_of_parse_and_map(np, 0);
+ if (info.irq == NO_IRQ)
+ return -ENODEV;
+
+ info.platform_data = &pdm360ng_ads7846_pdata;
+ if (strlcpy(info.modalias, "ads7846",
+ SPI_NAME_SIZE) >= SPI_NAME_SIZE)
+ return -ENOMEM;
+
+ np = of_get_next_parent(np);
+ if (!np)
+ return -ENODEV;
+
+ prop = of_get_property(np, "cell-index", &len);
+ if (prop && len == 4)
+ bus_num = *prop;
+
+ if (bus_num < 0 || bus_num > 11)
+ return -ENODEV;
+
+ info.bus_num = bus_num;
+
+ of_dev = of_find_device_by_node(np);
+ of_node_put(np);
+ if (of_dev) {
+ struct fsl_spi_platform_data *pdata;
+
+ pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+ if (pdata) {
+ pdata->bus_num = bus_num;
+ pdata->max_chipselect = 1;
+ of_dev->dev.platform_data = pdata;
+ }
+ }
+
+ if (pdm360ng_penirq_init())
+ return -ENODEV;
+
+ return spi_register_board_info(&info, 1);
+}
+machine_device_initcall(pdm360ng, pdm360ng_touchscreen_init);
+#endif
+
+static int __init pdm360ng_probe(void)
+{
+ unsigned long root = of_get_flat_dt_root();
+
+ return of_flat_dt_is_compatible(root, "ifm,pdm360ng");
+}
+
+define_machine(pdm360ng) {
+ .name = "PDM360NG",
+ .probe = pdm360ng_probe,
+ .setup_arch = mpc512x_setup_diu,
+ .init = mpc512x_init,
+ .init_early = mpc512x_init_diu,
+ .init_IRQ = mpc512x_init_IRQ,
+ .get_irq = ipic_get_irq,
+ .calibrate_decr = generic_calibrate_decr,
+ .restart = mpc512x_restart,
+};
--
1.6.3.3
^ permalink raw reply related
* [PATCH 1/2] powerpc/mpc512x: Group mpc512x board's selection menu
From: Anatolij Gustschin @ 2010-04-30 20:30 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Anatolij Gustschin, Detlev Zundel
Allow board selection in a drop-down board sub-menu
like many other platforms do.
Before the patch:
...
[ ] Freescale MPC5121E ADS
[ ] Generic support for simple MPC5121 based boards
[ ] 52xx-based boards
...
Patched:
...
[*] 512x-based boards
[ ] Freescale MPC5121E ADS
[ ] Generic support for simple MPC5121 based boards
[ ] 52xx-based boards
...
This is a cleanup before adding new board selection entry.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
Cc: Grant Likely <grant.likely@secretlab.ca>
---
arch/powerpc/platforms/512x/Kconfig | 13 ++++---------
1 files changed, 4 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index 4dac9b0..e9dca28 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -1,29 +1,24 @@
config PPC_MPC512x
- bool
+ bool "512x-based boards"
+ depends on 6xx
select FSL_SOC
select IPIC
select PPC_CLOCK
select PPC_PCI_CHOICE
select FSL_PCI if PCI
-config PPC_MPC5121
- bool
- select PPC_MPC512x
-
config MPC5121_ADS
bool "Freescale MPC5121E ADS"
- depends on 6xx
+ depends on PPC_MPC512x
select DEFAULT_UIMAGE
- select PPC_MPC5121
select MPC5121_ADS_CPLD
help
This option enables support for the MPC5121E ADS board.
config MPC5121_GENERIC
bool "Generic support for simple MPC5121 based boards"
- depends on 6xx
+ depends on PPC_MPC512x
select DEFAULT_UIMAGE
- select PPC_MPC5121
help
This option enables support for simple MPC5121 based boards
which do not need custom platform specific setup.
--
1.6.3.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox