Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node: BUG: unable to handle kernel paging request at ffffc90008963690 IP: __wake_up_bit+0x20/0x70 Oops: 0000 [#1] SMP CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80 Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015 task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000 RIP: 0010:[<ffffffff810dff80>] [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP: 0018:ffff880017b97be8 EFLAGS: 00010246 RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9 RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648 RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800 R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000 FS: 00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0 Call Trace: unlock_page+0x6d/0x70 generic_write_end+0x53/0xb0 xfs_vm_write_end+0x29/0x80 [xfs] generic_perform_write+0x10a/0x1e0 xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs] xfs_file_write_iter+0x79/0x120 [xfs] __vfs_write+0xd4/0x110 vfs_write+0xac/0x1c0 SyS_write+0x58/0xd0 system_call_fastpath+0x12/0x76 Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48 RIP [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP <ffff880017b97be8> CR2: ffffc90008963690 Reproduce method (re-add a node):: Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic) This seems an use-after-free problem, and the root cause is zone->wait_table was not set to *NULL* after free it in try_offline_node. When hot re-add a node, we will reuse the pgdat of it, so does the zone struct, and when add pages to the target zone, it will init the zone first (including the wait_table) if the zone is not initialized. The judgement of zone initialized is based on zone->wait_table: static inline bool zone_is_initialized(struct zone *zone) { return !!zone->wait_table; } so if we do not set the zone->wait_table to *NULL* after free it, the memory hotplug routine will skip the init of new zone when hot re-add the node, and the wait_table still points to the freed memory, then we will access the invalid address when trying to wake up the waiting people after the i/o operation with the page is done, such as mentioned above. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com> Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5879ae5
clk-pll-out.c
/*
* Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/kernel.h>
#include <linux/io.h>
#include <linux/err.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/clk-provider.h>
#include <linux/clk.h>
#include "clk.h"
#define pll_out_enb(p) (BIT(p->enb_bit_idx))
#define pll_out_rst(p) (BIT(p->rst_bit_idx))
static int clk_pll_out_is_enabled(struct clk_hw *hw)
{
struct tegra_clk_pll_out *pll_out = to_clk_pll_out(hw);
u32 val = readl_relaxed(pll_out->reg);
int state;
state = (val & pll_out_enb(pll_out)) ? 1 : 0;
if (!(val & (pll_out_rst(pll_out))))
state = 0;
return state;
}
static int clk_pll_out_enable(struct clk_hw *hw)
{
struct tegra_clk_pll_out *pll_out = to_clk_pll_out(hw);
unsigned long flags = 0;
u32 val;
if (pll_out->lock)
spin_lock_irqsave(pll_out->lock, flags);
val = readl_relaxed(pll_out->reg);
val |= (pll_out_enb(pll_out) | pll_out_rst(pll_out));
writel_relaxed(val, pll_out->reg);
udelay(2);
if (pll_out->lock)
spin_unlock_irqrestore(pll_out->lock, flags);
return 0;
}
static void clk_pll_out_disable(struct clk_hw *hw)
{
struct tegra_clk_pll_out *pll_out = to_clk_pll_out(hw);
unsigned long flags = 0;
u32 val;
if (pll_out->lock)
spin_lock_irqsave(pll_out->lock, flags);
val = readl_relaxed(pll_out->reg);
val &= ~(pll_out_enb(pll_out) | pll_out_rst(pll_out));
writel_relaxed(val, pll_out->reg);
udelay(2);
if (pll_out->lock)
spin_unlock_irqrestore(pll_out->lock, flags);
}
const struct clk_ops tegra_clk_pll_out_ops = {
.is_enabled = clk_pll_out_is_enabled,
.enable = clk_pll_out_enable,
.disable = clk_pll_out_disable,
};
struct clk *tegra_clk_register_pll_out(const char *name,
const char *parent_name, void __iomem *reg, u8 enb_bit_idx,
u8 rst_bit_idx, unsigned long flags, u8 pll_out_flags,
spinlock_t *lock)
{
struct tegra_clk_pll_out *pll_out;
struct clk *clk;
struct clk_init_data init;
pll_out = kzalloc(sizeof(*pll_out), GFP_KERNEL);
if (!pll_out)
return ERR_PTR(-ENOMEM);
init.name = name;
init.ops = &tegra_clk_pll_out_ops;
init.parent_names = (parent_name ? &parent_name : NULL);
init.num_parents = (parent_name ? 1 : 0);
init.flags = flags;
pll_out->reg = reg;
pll_out->enb_bit_idx = enb_bit_idx;
pll_out->rst_bit_idx = rst_bit_idx;
pll_out->flags = pll_out_flags;
pll_out->lock = lock;
/* Data in .init is copied by clk_register(), so stack variable OK */
pll_out->hw.init = &init;
clk = clk_register(NULL, &pll_out->hw);
if (IS_ERR(clk))
kfree(pll_out);
return clk;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...