All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Thomas Gleixner <tglx@linutronix.de>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 32/43] x86/mm/kaiser: Map virtually-addressed performance monitoring buffers
Date: Fri, 24 Nov 2017 18:24:00 +0100	[thread overview]
Message-ID: <20171124172411.19476-33-mingo@kernel.org> (raw)
In-Reply-To: <20171124172411.19476-1-mingo@kernel.org>

From: Hugh Dickins <hughd@google.com>

[Dave] Add explicit _PAGE_GLOBAL
[Dave] remove KAISER #ifdefs by moving kmalloc() to plain page allocator
[Dave] reword the commit message a bit to be consistent with other patches

The BTS and PEBS buffers both have their virtual addresses
programmed into the hardware.  This means that any access to them
is performed via the page tables.  The times that the hardware
accesses these are entirely dependent on how the performance
monitoring hardware events are set up.  In other words, there is
no way for the kernel to tell when the hardware might access
these buffers.

To avoid perf crashes, place 'debug_store' in the user-mapped
per-cpu area instead of dynamically allocating.  Also use the
page allocator plus kaiser_add_mapping() to keep the BTS and PEBS
buffers user-mapped (that is, present in the user mapping, though
visible only to kernel and hardware).  The PEBS fixup buffer does
not need this treatment.

The need for a user-mapped struct debug_store showed up before doing
any conscious perf testing: in a couple of kernel paging oopses on
Westmere, implicating the debug_store offset of the per-cpu area.

Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: daniel.gruss@iaik.tugraz.at
Cc: keescook@google.com
Cc: linux-mm@kvack.org
Cc: luto@kernel.org
Cc: michael.schwarz@iaik.tugraz.at
Cc: moritz.lipp@iaik.tugraz.at
Cc: richard.fellner@student.tugraz.at
Link: https://lkml.kernel.org/r/20171123003500.7EC0DB4E@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/ds.c | 49 ++++++++++++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 12 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..b5cf473e443a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bitops.h>
 #include <linux/types.h>
+#include <linux/kaiser.h>
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
@@ -8,6 +9,9 @@
 
 #include "../perf_event.h"
 
+static
+DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
@@ -279,6 +283,31 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
+static void *dsalloc(size_t size, gfp_t flags, int node)
+{
+	unsigned int order = get_order(size);
+	struct page *page;
+	unsigned long addr;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	if (!page)
+		return NULL;
+	addr = (unsigned long)page_address(page);
+	if (kaiser_add_mapping(addr, size, __PAGE_KERNEL | _PAGE_GLOBAL) < 0) {
+		__free_pages(page, order);
+		addr = 0;
+	}
+	return (void *)addr;
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+	if (!buffer)
+		return;
+	kaiser_remove_mapping((unsigned long)buffer, size);
+	free_pages((unsigned long)buffer, get_order(size));
+}
+
 static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -289,7 +318,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -300,7 +329,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree(buffer, x86_pmu.pebs_buffer_size);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
@@ -326,7 +355,8 @@ static void release_pebs_buffer(int cpu)
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	dsfree((void *)(unsigned long)ds->pebs_buffer_base,
+			x86_pmu.pebs_buffer_size);
 	ds->pebs_buffer_base = 0;
 }
 
@@ -340,7 +370,7 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
@@ -366,19 +396,15 @@ static void release_bts_buffer(int cpu)
 	if (!ds || !x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE);
 	ds->bts_buffer_base = 0;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu);
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
 
 	return 0;
@@ -392,7 +418,6 @@ static void release_ds_buffer(int cpu)
 		return;
 
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)
-- 
2.14.1

  parent reply	other threads:[~2017-11-24 17:25 UTC|newest]

Thread overview: 112+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-24 17:23 [PATCH 00/43] x86 entry-stack and Kaiser series, 2017/11/24, v2 version Ingo Molnar
2017-11-24 17:23 ` [PATCH 01/43] x86/decoder: Add new TEST instruction pattern Ingo Molnar
2017-11-24 17:23 ` [PATCH 02/43] x86/asm/64: Allocate and enable the SYSENTER stack Ingo Molnar
2017-11-24 17:23 ` [PATCH 03/43] x86/dumpstack: Add get_stack_info() support for " Ingo Molnar
2017-11-24 17:23 ` [PATCH 04/43] x86/gdt: Put per-cpu GDT remaps in ascending order Ingo Molnar
2017-11-24 17:23 ` [PATCH 05/43] x86/fixmap: Generalize the GDT fixmap mechanism Ingo Molnar
2017-11-24 17:23 ` [PATCH 06/43] x86/kasan/64: Teach KASAN about the cpu_entry_area Ingo Molnar
2017-11-24 17:23 ` [PATCH 07/43] x86/asm: Fix assumptions that the HW TSS is at the beginning of cpu_tss Ingo Molnar
2017-11-24 17:23 ` [PATCH 08/43] x86/dumpstack: Handle stack overflow on all stacks Ingo Molnar
2017-11-24 17:23 ` [PATCH 09/43] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct Ingo Molnar
2017-11-24 17:23 ` [PATCH 10/43] x86/asm: Remap the TSS into the cpu entry area Ingo Molnar
2017-11-24 17:23 ` [PATCH 11/43] x86/asm/64: Separate cpu_current_top_of_stack from TSS.sp0 Ingo Molnar
2017-11-24 17:23 ` [PATCH 12/43] x86/espfix/64: Stop assuming that pt_regs is on the entry stack Ingo Molnar
2017-11-24 18:25   ` Borislav Petkov
2017-11-24 19:12     ` Andy Lutomirski
2017-11-26 14:05       ` Ingo Molnar
2017-11-26 17:28         ` Borislav Petkov
2017-11-27  9:19           ` Ingo Molnar
2017-11-24 17:23 ` [PATCH 13/43] x86/asm/64: Use a percpu trampoline stack for IDT entries Ingo Molnar
2017-11-24 19:02   ` Borislav Petkov
2017-11-26 14:16     ` Ingo Molnar
2017-11-24 17:23 ` [PATCH 14/43] x86/asm/64: Return to userspace from the trampoline stack Ingo Molnar
2017-11-24 19:10   ` Borislav Petkov
2017-11-26 14:18     ` Ingo Molnar
2017-11-26 17:33       ` Borislav Petkov
2017-11-24 17:23 ` [PATCH 15/43] x86/entry/64: Create a percpu SYSCALL entry trampoline Ingo Molnar
2017-11-25 11:40   ` Borislav Petkov
2017-11-25 15:00     ` Andy Lutomirski
2017-11-26 14:26       ` [PATCH] " Ingo Molnar
2017-11-24 17:23 ` [PATCH 16/43] x86/irq: Remove an old outdated comment about context tracking races Ingo Molnar
2017-11-25 12:05   ` Borislav Petkov
2017-11-24 17:23 ` [PATCH 17/43] x86/irq/64: In the stack overflow warning, print the offending IP Ingo Molnar
2017-11-25 12:07   ` Borislav Petkov
2017-11-24 17:23 ` [PATCH 18/43] x86/entry/64: Move the IST stacks into cpu_entry_area Ingo Molnar
2017-11-25 12:34   ` Borislav Petkov
2017-11-24 17:23 ` [PATCH 19/43] x86/entry/64: Remove the SYSENTER stack canary Ingo Molnar
2017-11-25 15:29   ` Borislav Petkov
2017-11-24 17:23 ` [PATCH 20/43] x86/entry: Clean up SYSENTER_stack code Ingo Molnar
2017-11-25 16:39   ` Borislav Petkov
2017-11-25 16:50     ` Thomas Gleixner
2017-11-25 16:55       ` Andy Lutomirski
2017-11-25 17:03         ` Thomas Gleixner
2017-11-25 17:10           ` Borislav Petkov
2017-11-25 17:26             ` Andy Lutomirski
2017-11-27  9:27               ` Peter Zijlstra
2017-11-24 17:23 ` [PATCH 21/43] x86/mm/kaiser: Disable global pages by default with KAISER Ingo Molnar
2017-11-24 17:23 ` [PATCH 22/43] x86/mm/kaiser: Prepare assembly for entry/exit CR3 switching Ingo Molnar
2017-11-25  0:02   ` Thomas Gleixner
2017-11-25 12:41     ` Thomas Gleixner
2017-11-26 11:50   ` Borislav Petkov
2017-11-26 14:55     ` [PATCH v2] x86/mm/kaiser: Prepare the x86/entry assembly code " Ingo Molnar
2017-11-27 13:29       ` Josh Poimboeuf
2017-11-27 13:36         ` Thomas Gleixner
2017-11-24 17:23 ` [PATCH 23/43] x86/mm/kaiser: Introduce user-mapped per-cpu areas Ingo Molnar
2017-11-26 17:41   ` Borislav Petkov
2017-11-27  9:26     ` Ingo Molnar
2017-11-27 21:14     ` Dave Hansen
2017-11-24 17:23 ` [PATCH 24/43] x86/mm/kaiser: Mark per-cpu data structures required for entry/exit Ingo Molnar
2017-11-25 17:17   ` Thomas Gleixner
2017-11-26 15:54     ` Ingo Molnar
2017-11-24 17:23 ` [PATCH 25/43] x86/mm/kaiser: Unmap kernel from userspace page tables (core patch) Ingo Molnar
2017-11-26 18:51   ` Borislav Petkov
2017-11-27  9:30     ` Ingo Molnar
2017-11-26 20:49   ` Borislav Petkov
2017-11-27 10:38     ` Ingo Molnar
2017-11-26 22:25   ` [PATCH 25/43] x86/mm/kaiser: Unmap kernel from userspace page tables (core patch), noexec=off Borislav Petkov
2017-11-26 22:41     ` Thomas Gleixner
2017-11-24 17:23 ` [PATCH 26/43] x86/mm/kaiser: Allow NX poison to be set in p4d/pgd Ingo Molnar
2017-11-24 17:23 ` [PATCH 27/43] x86/mm/kaiser: Make sure static PGDs are 8k in size Ingo Molnar
2017-11-24 17:23 ` [PATCH 28/43] x86/mm/kaiser: Map cpu entry area Ingo Molnar
2017-11-25 21:40   ` Thomas Gleixner
2017-11-26 15:19     ` Ingo Molnar
2017-11-24 17:23 ` [PATCH 29/43] x86/mm/kaiser: Map dynamically-allocated LDTs Ingo Molnar
2017-11-24 17:23 ` [PATCH 30/43] x86/mm/kaiser: Map espfix structures Ingo Molnar
2017-11-24 17:23 ` [PATCH 31/43] x86/mm/kaiser: Map entry stack variable Ingo Molnar
2017-11-24 17:24 ` Ingo Molnar [this message]
2017-11-24 17:24 ` [PATCH 33/43] x86/mm: Move CR3 construction functions Ingo Molnar
2017-11-24 17:24 ` [PATCH 34/43] x86/mm: Remove hard-coded ASID limit checks Ingo Molnar
2017-11-24 17:24 ` [PATCH 35/43] x86/mm: Put mmu-to-h/w ASID translation in one place Ingo Molnar
2017-11-24 17:24 ` [PATCH 36/43] x86/mm/kaiser: Allow flushing for future ASID switches Ingo Molnar
2017-11-24 17:24 ` [PATCH 37/43] x86/mm/kaiser: Use PCID feature to make user and kernel switches faster Ingo Molnar
2017-11-24 17:24 ` [PATCH 38/43] x86/mm/kaiser: Disable native VSYSCALL Ingo Molnar
2017-11-24 17:24 ` [PATCH 39/43] x86/mm/kaiser: Add debugfs file to turn KAISER on/off at runtime Ingo Molnar
2017-11-24 17:24 ` [PATCH 40/43] x86/mm/kaiser: Add a function to check for KAISER being enabled Ingo Molnar
2017-11-24 17:24 ` [PATCH 41/43] x86/mm/kaiser: Un-poison PGDs at runtime Ingo Molnar
2017-11-24 17:24 ` [PATCH 42/43] x86/mm/kaiser: Allow KAISER to be enabled/disabled " Ingo Molnar
2017-11-25 19:18   ` Thomas Gleixner
2017-11-25 19:53     ` Andy Lutomirski
2017-11-25 20:05       ` Thomas Gleixner
2017-11-25 22:10         ` Andy Lutomirski
2017-11-25 22:48           ` Thomas Gleixner
2017-11-26  0:21             ` Andy Lutomirski
2017-11-26  8:11               ` Thomas Gleixner
2017-11-24 17:24 ` [PATCH 43/43] x86/mm/kaiser: Add Kconfig Ingo Molnar
2017-11-24 20:22 ` [crash] PANIC: double fault, error_code: 0x0 Ingo Molnar
2017-11-24 20:59   ` Andy Lutomirski
2017-11-24 21:49     ` Ingo Molnar
2017-11-24 21:52       ` Ingo Molnar
2017-11-24 22:09   ` Ingo Molnar
2017-11-24 22:35     ` Andy Lutomirski
2017-11-24 22:53       ` Ingo Molnar
2017-11-25  9:21         ` Ingo Molnar
2017-11-25  9:32           ` Ingo Molnar
2017-11-25  9:39             ` Ingo Molnar
2017-11-25 11:17               ` [PATCH] x86/mm/kaiser: Fix IRQ entries text section mapping Ingo Molnar
2017-11-25 16:08                 ` Thomas Gleixner
2017-11-25 20:06                   ` Steven Rostedt
2017-11-27  8:14                   ` Peter Zijlstra
2017-11-27  8:21                     ` Peter Zijlstra
2017-11-25  4:09   ` [crash] PANIC: double fault, error_code: 0x0 Dave Hansen
2017-11-25  4:15     ` Dave Hansen
  -- strict thread matches above, loose matches on Subject: below --
2017-11-24  9:14 [PATCH 00/43] x86 entry-stack and Kaiser series, 2017/11/24 version Ingo Molnar
2017-11-24  9:14 ` [PATCH 32/43] x86/mm/kaiser: Map virtually-addressed performance monitoring buffers Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171124172411.19476-33-mingo@kernel.org \
    --to=mingo@kernel.org \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.