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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 23 Aug 2017 10:22:46 -0400
From:   kan.liang@...el.com
To:     peterz@...radead.org, mingo@...hat.com,
        linux-kernel@...r.kernel.org
Cc:     acme@...nel.org, jolsa@...hat.com, tglx@...utronix.de,
        eranian@...gle.com, ak@...ux.intel.com,
        Kan Liang <kan.liang@...el.com>
Subject: [PATCH V6] perf: Add PERF_SAMPLE_PHYS_ADDR

From: Kan Liang <kan.liang@...el.com>

For understanding how the workload maps to memory channels and hardware
behavior, it's very important to collect address maps with physical
addresses. For example, 3D XPoint access can only be found by filtering
the physical address.
However, perf doesn't collect physical address information in sampling.

The virtual address which stored in data->addr can be used to calculate
the physical address.
For kernel direct mapping addresses, virt_to_phys is used to convert the
virtual addresses to physical address.
For user virtual addresses, __get_user_pages_fast is used to walk the
pages tables for user physical address.
This does not work for vmalloc addresses. Right now these are not
resolved, but code to do that could be added.
For security, the physical address can only be exposed to root or
privileged user.
A new sample type PERF_SAMPLE_PHYS_ADDR is introduced to expose the
physical addresses.

Signed-off-by: Kan Liang <kan.liang@...el.com>
---

This patch is kernel patch.
The user space patch can be found here.
https://www.spinics.net/lists/kernel/msg2587093.html

Changes since V5
 - Move virt_to_phys to generic code (PeterZ)

 arch/x86/events/perf_event.h    |  2 +-
 include/linux/perf_event.h      |  2 ++
 include/uapi/linux/perf_event.h |  4 +++-
 kernel/events/core.c            | 47 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 476aec3..65bb91e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -91,7 +91,7 @@ struct amd_nb {
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
-	PERF_SAMPLE_TRANSACTION)
+	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR)
 
 /*
  * A debug store configuration.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b14095b..74fb87e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -944,6 +944,8 @@ struct perf_sample_data {
 
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
+
+	u64				phys_addr;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 642db5f..cbea02f 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
-	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 };
 
 /*
@@ -814,6 +815,7 @@ enum perf_event_type {
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 *	{ u64			abi; # enum perf_sample_regs_abi
 	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d704e23..b991af3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1570,6 +1570,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		size += sizeof(data->txn);
 
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		size += sizeof(data->phys_addr);
+
 	event->header_size = size;
 }
 
@@ -6012,6 +6015,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		perf_output_put(handle, data->phys_addr);
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -6027,6 +6033,38 @@ void perf_output_sample(struct perf_output_handle *handle,
 	}
 }
 
+static u64 perf_virt_to_phys(u64 virt)
+{
+	u64 phys_addr = 0;
+	struct page *p = NULL;
+
+	if (!virt)
+		return 0;
+
+	if (virt >= TASK_SIZE) {
+		/* If it's vmalloc()d memory, leave phys_addr as 0 */
+		if (virt_addr_valid(virt) &&
+		    !(virt >= VMALLOC_START && virt < VMALLOC_END))
+			phys_addr = (u64)virt_to_phys((void *)(uintptr_t)virt);
+	} else {
+		/*
+		 * Walking the pages tables for user address.
+		 * Interrupts are disabled, so it prevents any tear down
+		 * of the page tables.
+		 * Try IRQ-safe __get_user_pages_fast first.
+		 * If failed, leave phys_addr as 0.
+		 */
+		if ((current->mm != NULL) &&
+		    (__get_user_pages_fast(virt, 1, 0, &p) == 1))
+			phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+
+		if (p)
+			put_page(p);
+	}
+
+	return phys_addr;
+}
+
 void perf_prepare_sample(struct perf_event_header *header,
 			 struct perf_sample_data *data,
 			 struct perf_event *event,
@@ -6145,6 +6183,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
 static void __always_inline
@@ -9892,6 +9933,12 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	/* Only privileged users can get kernel addresses */
+	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) &&
+	    perf_paranoid_kernel() &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	if (!attr.sample_max_stack)
 		attr.sample_max_stack = sysctl_perf_event_max_stack;
 
-- 
2.4.3

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ