| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1509728692-10460-12-git-send-email-cmetcalf@mellanox.com>
Date: Fri, 3 Nov 2017 13:04:50 -0400
From: Chris Metcalf <cmetcalf@...lanox.com>
To: Steven Rostedt <rostedt@...dmis.org>,
Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Rik van Riel <riel@...hat.com>, Tejun Heo <tj@...nel.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Thomas Gleixner <tglx@...utronix.de>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Christoph Lameter <cl@...ux.com>,
Viresh Kumar <viresh.kumar@...aro.org>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will.deacon@....com>,
Andy Lutomirski <luto@...capital.net>,
linux-kernel@...r.kernel.org
Cc: Chris Metcalf <cmetcalf@...lanox.com>
Subject: [PATCH v16 11/13] arch/tile: enable task isolation functionality
We add the necessary call to task_isolation_start() in the
prepare_exit_to_usermode() routine. We already unconditionally
call into this routine if TIF_NOHZ is set, since that's where
we do the user_enter() call.
We add calls to task_isolation_interrupt() in places where exceptions
may not generate signals to the application.
Signed-off-by: Chris Metcalf <cmetcalf@...lanox.com>
---
arch/tile/Kconfig | 1 +
arch/tile/include/asm/thread_info.h | 2 ++
arch/tile/kernel/hardwall.c | 2 ++
arch/tile/kernel/irq.c | 3 +++
arch/tile/kernel/messaging.c | 4 ++++
arch/tile/kernel/process.c | 4 ++++
arch/tile/kernel/ptrace.c | 10 ++++++++++
arch/tile/kernel/single_step.c | 7 +++++++
arch/tile/kernel/smp.c | 21 +++++++++++----------
arch/tile/kernel/time.c | 2 ++
arch/tile/kernel/unaligned.c | 4 ++++
arch/tile/mm/fault.c | 13 ++++++++++++-
arch/tile/mm/homecache.c | 11 +++++++++++
13 files changed, 73 insertions(+), 11 deletions(-)
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 4583c0320059..2d644138f2eb 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -16,6 +16,7 @@ config TILE
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_TASK_ISOLATION
select HAVE_ARCH_TRACEHOOK
select HAVE_CONTEXT_TRACKING
select HAVE_DEBUG_BUGVERBOSE
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index b7659b8f1117..3e298bd43d11 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -126,6 +126,7 @@ extern void _cpu_idle(void);
#define TIF_SYSCALL_TRACEPOINT 9 /* syscall tracepoint instrumentation */
#define TIF_POLLING_NRFLAG 10 /* idle is polling for TIF_NEED_RESCHED */
#define TIF_NOHZ 11 /* in adaptive nohz mode */
+#define TIF_TASK_ISOLATION 12 /* in task isolation mode */
#define _TIF_SIGPENDING (1<<TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED)
@@ -139,6 +140,7 @@ extern void _cpu_idle(void);
#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG)
#define _TIF_NOHZ (1<<TIF_NOHZ)
+#define _TIF_TASK_ISOLATION (1<<TIF_TASK_ISOLATION)
/* Work to do as we loop to exit to user space. */
#define _TIF_WORK_MASK \
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 2fd1694ac1d0..9559f04d1c2a 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -23,6 +23,7 @@
#include <linux/smp.h>
#include <linux/cdev.h>
#include <linux/compat.h>
+#include <linux/isolation.h>
#include <asm/hardwall.h>
#include <asm/traps.h>
#include <asm/siginfo.h>
@@ -328,6 +329,7 @@ void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
int found_processes;
struct pt_regs *old_regs = set_irq_regs(regs);
+ task_isolation_interrupt("hardwall trap");
irq_enter();
/* Figure out which network trapped. */
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 22044fc691ef..0b1b24b9c496 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -18,6 +18,7 @@
#include <linux/irq.h>
#include <linux/kernel_stat.h>
#include <linux/uaccess.h>
+#include <linux/isolation.h>
#include <hv/drv_pcie_rc_intf.h>
#include <arch/spr_def.h>
#include <asm/traps.h>
@@ -100,6 +101,8 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
/* Track time spent here in an interrupt context. */
old_regs = set_irq_regs(regs);
+
+ task_isolation_interrupt("IPI: IRQ mask %#lx", remaining_irqs);
irq_enter();
#ifdef CONFIG_DEBUG_STACKOVERFLOW
diff --git a/arch/tile/kernel/messaging.c b/arch/tile/kernel/messaging.c
index 7475af3aacec..1cf1630215f0 100644
--- a/arch/tile/kernel/messaging.c
+++ b/arch/tile/kernel/messaging.c
@@ -16,6 +16,7 @@
#include <linux/smp.h>
#include <linux/hardirq.h>
#include <linux/ptrace.h>
+#include <linux/isolation.h>
#include <asm/hv_driver.h>
#include <asm/irq_regs.h>
#include <asm/traps.h>
@@ -86,6 +87,7 @@ void hv_message_intr(struct pt_regs *regs, int intnum)
tag = message[0];
#ifdef CONFIG_SMP
+ task_isolation_interrupt("SMP message %d", tag);
evaluate_message(message[0]);
#else
panic("Received IPI message %d in UP mode", tag);
@@ -94,6 +96,8 @@ void hv_message_intr(struct pt_regs *regs, int intnum)
HV_IntrMsg *him = (HV_IntrMsg *)message;
struct hv_driver_cb *cb =
(struct hv_driver_cb *)him->intarg;
+ task_isolation_interrupt("interrupt message %#lx(%#lx)",
+ him->intarg, him->intdata);
cb->callback(cb, him->intdata);
__this_cpu_inc(irq_stat.irq_hv_msg_count);
}
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index f0a0e18e4dfb..ac22e971dc1d 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -32,6 +32,7 @@
#include <linux/signal.h>
#include <linux/delay.h>
#include <linux/context_tracking.h>
+#include <linux/isolation.h>
#include <asm/stack.h>
#include <asm/switch_to.h>
#include <asm/homecache.h>
@@ -516,6 +517,9 @@ void prepare_exit_to_usermode(struct pt_regs *regs, u32 thread_info_flags)
#endif
}
+ if (thread_info_flags & _TIF_TASK_ISOLATION)
+ task_isolation_start();
+
user_enter();
}
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index e1a078e6828e..908d57d3d2cf 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -24,6 +24,7 @@
#include <linux/tracehook.h>
#include <linux/context_tracking.h>
#include <linux/sched/task_stack.h>
+#include <linux/isolation.h>
#include <asm/traps.h>
#include <arch/chip.h>
@@ -263,6 +264,15 @@ int do_syscall_trace_enter(struct pt_regs *regs)
return -1;
}
+ /*
+ * In task isolation mode, we may prevent the syscall from
+ * running, and if so we also deliver a signal to the process.
+ */
+ if (work & _TIF_TASK_ISOLATION) {
+ if (task_isolation_syscall(regs->regs[TREG_SYSCALL_NR]) == -1)
+ return -1;
+ }
+
if (secure_computing(NULL) == -1)
return -1;
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de3eae813e52..4d5d4897e70c 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include <linux/err.h>
#include <linux/prctl.h>
+#include <linux/isolation.h>
#include <asm/cacheflush.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
@@ -320,6 +321,9 @@ void single_step_once(struct pt_regs *regs)
int size = 0, sign_ext = 0; /* happy compiler */
int align_ctl;
+ /* No signal was generated, but notify task-isolation tasks. */
+ task_isolation_interrupt("single step at %#lx", regs->pc);
+
align_ctl = unaligned_fixup;
switch (task_thread_info(current)->align_ctl) {
case PR_UNALIGN_NOPRINT:
@@ -767,6 +771,9 @@ void single_step_once(struct pt_regs *regs)
unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
+ /* No signal was generated, but notify task-isolation tasks. */
+ task_isolation_interrupt("single step at %#lx", regs->pc);
+
*ss_pc = regs->pc;
control |= SPR_SINGLE_STEP_CONTROL_1__CANCELED_MASK;
control |= SPR_SINGLE_STEP_CONTROL_1__INHIBIT_MASK;
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index 94a62e1197ce..6b100faa33ef 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -20,6 +20,7 @@
#include <linux/irq.h>
#include <linux/irq_work.h>
#include <linux/module.h>
+#include <linux/isolation.h>
#include <asm/cacheflush.h>
#include <asm/homecache.h>
@@ -258,10 +259,8 @@ void __init ipi_init(void)
#if CHIP_HAS_IPI()
-void smp_send_reschedule(int cpu)
+static void __smp_send_reschedule(int cpu)
{
- WARN_ON(cpu_is_offline(cpu));
-
/*
* We just want to do an MMIO store. The traditional writeq()
* functions aren't really correct here, since they're always
@@ -273,15 +272,17 @@ void smp_send_reschedule(int cpu)
#else
-void smp_send_reschedule(int cpu)
+static void __smp_send_reschedule(int cpu)
{
- HV_Coord coord;
-
- WARN_ON(cpu_is_offline(cpu));
-
- coord.y = cpu_y(cpu);
- coord.x = cpu_x(cpu);
+ HV_Coord coord = { .y = cpu_y(cpu), .x = cpu_x(cpu) };
hv_trigger_ipi(coord, IRQ_RESCHEDULE);
}
#endif /* CHIP_HAS_IPI() */
+
+void smp_send_reschedule(int cpu)
+{
+ WARN_ON(cpu_is_offline(cpu));
+ task_isolation_remote(cpu, "reschedule IPI");
+ __smp_send_reschedule(cpu);
+}
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 6643ffbc0615..f74f10d827fa 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -25,6 +25,7 @@
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/timekeeper_internal.h>
+#include <linux/isolation.h>
#include <asm/irq_regs.h>
#include <asm/traps.h>
#include <asm/vdso.h>
@@ -196,6 +197,7 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
arch_local_irq_mask(INT_TILE_TIMER);
/* Track time spent here in an interrupt context */
+ task_isolation_interrupt("timer");
irq_enter();
/* Track interrupt count. */
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 8149c38f67b6..ee14a61d0eee 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -27,6 +27,7 @@
#include <linux/extable.h>
#include <linux/compat.h>
#include <linux/prctl.h>
+#include <linux/isolation.h>
#include <asm/cacheflush.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
@@ -1547,6 +1548,9 @@ void do_unaligned(struct pt_regs *regs, int vecnum)
return;
}
+ /* No signal was generated, but notify task-isolation tasks. */
+ task_isolation_interrupt("unaligned access at %#lx", regs->pc);
+
if (!info->unalign_jit_base) {
void __user *user_page;
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index f58fa06a2214..0a7a731d7413 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -38,6 +38,7 @@
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
+#include <linux/isolation.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
@@ -311,8 +312,13 @@ static int handle_page_fault(struct pt_regs *regs,
*/
pgd = get_current_pgd();
if (handle_migrating_pte(pgd, fault_num, address, regs->pc,
- is_kernel_mode, write))
+ is_kernel_mode, write)) {
+ /* No signal was generated, but notify task-isolation tasks. */
+ if (!is_kernel_mode)
+ task_isolation_interrupt("migration fault at %#lx",
+ address);
return 1;
+ }
si_code = SEGV_MAPERR;
@@ -482,6 +488,11 @@ static int handle_page_fault(struct pt_regs *regs,
#endif
up_read(&mm->mmap_sem);
+
+ /* No signal was generated, but notify task-isolation tasks. */
+ if (flags & FAULT_FLAG_USER)
+ task_isolation_interrupt("page fault at %#lx", address);
+
return 1;
/*
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index b51cc28acd0a..82bcffb26ec4 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -31,6 +31,7 @@
#include <linux/smp.h>
#include <linux/module.h>
#include <linux/hugetlb.h>
+#include <linux/isolation.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -85,6 +86,16 @@ static void hv_flush_update(const struct cpumask *cache_cpumask,
*/
for_each_cpu(cpu, &mask)
++per_cpu(irq_stat, cpu).irq_hv_flush_count;
+
+ /*
+ * Send an extra Linux-level interrupt here to task isolation tasks
+ * so that they can generate the appropriate signal to kill
+ * themselves. If we didn't send a Linux interrupt, we would
+ * interrupt the task into the hypervisor but it wouldn't get a
+ * signal to advise it of the loss of the cpu.
+ */
+ task_isolation_remote_cpumask_interrupt(&mask,
+ "remote cache/TLB flush");
}
/*
--
2.1.2
Powered by blists - more mailing lists